Getty Images/iStockphoto The Internet Archive, the non-profit digital library and operator of the popular Wayback Machine that holds a repository of billions of captures of web pages as they appeared in the past, has come under sustained cyber attack in the form of a significant distributed denial of service (DDoS) attack on its infrastructure, and a major breach that may have seen the data of 31 million users stolen. Visitors to the organisation’s website were greeted by a JavaScript pop-up created by the attackers on the afternoon and evening of Wednesday 9 October. In their message, the hackers behind the attack said: “Have you ever felt like the Internet Archive runs on sticks and is constantly on the verge of suffering a catastrophic security breach? It just happened. See 31 million of you on HIBP! [HaveIBeenPwned]” According to Bleeping Computer, HaveIBeenPwned owner Troy Hunt has confirmed the attackers have passed a 6.4GB database to him, which is in the process of being added to the HaveIBeenPwned service. As of 2am BST on Thursday 10 October, Internet Archive founder Brewster Kahle said the DDoS attack had been “fended off for now” and revealed the organisation had its website defaced. He also confirmed there had been a breach of usernames, email addresses, and salted and hashed passwords. However, at the time of writing, the US-based organisation’s website remains inaccessible on a public internet connection, and at approximately 12pm BST, Kahle said: “Sorry, but DDoS folks are back and knocked archive.org and openlibrary.org offline. “@Internetarchive is being cautious and prioritising keeping data safe at the expense of service availability,” he said via his X account. “Will share more as we know it.” Meanwhile, the group responsible for the attack has identified itself as SN_BlackMeta, a hacktivist operation that supports pro-Palestinian causes. In statements posted to X, the collective said: “The Internet Archive has and is [sic] suffering from a devastating attack. We have been launching several highly successful attacks for five long hours and to this moment, all their systems are completely down.” Responding to questions online, they added: “They are under attack because the archive belongs to the USA, and as we all know, this horrendous and hypocritical government supports the genocide that is being carried out by the terrorist state of Israel.” This is disinformation. Although the Internet Archive is US-based, it is a non-profit organisation and has no connection to the US government, regardless of Washington’s stance on the wars in Gaza and Lebanon. “Hacking the past is usually technically impossible but this data breach is the closest we may ever come to it,” said Jake Moore, ESET global cyber security advisor. “The stolen dataset includes personal information but at least the stolen passwords are encrypted. However, it’s a good reminder to make sure all your passwords are unique as even encrypted passwords can be cross references against previous uses of it. “HaveIBeenPwned is a fantastic free service that can be used after a breach. It securely contains millions of breached usernames and passwords for people to safely check their credentials against the database to check if they have ever been caught up in a breach. If you find your data in any known breaches, it would be a good idea to change those passwords and implement multi-factor authentication.” Donny Chony, director at Nexusguard, a supplier of anti-DDoS protection, said it was not unusual for DDoS attacks to have political motives, but that the landscape surrounding them was evolving rapidly. “We’re witnessing a concerning shift where it’s not just businesses or traditional critical national infrastructure at risk of DDoS attacks,” he said. “Hacktivists are launching more powerful and destructive attacks that affect a broader range of people.” He cited a recent report compiled by Nexusguard that reveals that while DDoS attack frequency is well down this year on 2023, average attack sizes have more than trebled in the same timeframe. “As geopolitical tensions continue to escalate, especially with the ongoing conflict in the Middle East, we are likely to see even more DDoS attacks on critical infrastructure and disrupt the lives of everyday people,” said Chong, who also argued for better industry regulation to set improved standards for DDoS prevention. The metaverse is evolving, beginning with its rebranding as spatial computing and its expanding impact in the workplace. Here are… Looking back on the last four years shows how aggressive the FTC and DOJ were on M&A activity. That might be a hallmark of the … Digital transformation is crucial for businesses wanting to keep up with technological growth. Start your digital transformation … What does 2025 have in store for network security? Analyst John Grady from Informa TechTarget’s Enterprise Strategy Group shares … Ransomware made major headlines in 2024, from the massive Change Healthcare attack to the creative takedown of the notorious … Some of the biggest stories of the year include a massive IT outage, a record-setting ransom payment and devastating breaches at … Network automation tools automate repetitive tasks, provision devices and manage configurations. Evaluate seven tools to discover… It’s important for network architects to consider several factors for an effective network design. Top principles include … Organizations that are considering AI-driven network orchestration will find it has many business cases — chief among them are … After a year of lawsuits, customer confusion and a restructuring of the core business, VMware by Broadcom has much to prove in … DCIM tools can improve data center management and operation. Learn how six prominent products can help organizations control … High GPU costs and scarcity drive users to GPUaaS for AI workloads. But businesses should assess needs before investing. Automating data governance makes tedious, time-consuming tasks more efficient. The human element remains critical to keeping … Organizations pursuing generative AI tools in 2025 will focus on making sure their data is AI-ready. The tools must work … Without proper training, models and applications will fail. As a result, enterprises will pay increased attention to the … All Rights Reserved, Copyright 2000 – 2024, TechTarget
‘This is a moral and scientific imperative,’ World Health Organization says in statement marking five years since Chinese authorities first alerted to ‘viral pneumonia’ in Wuhan The World Health Organization on Monday implored China to share data and access to help understand the origins of Covid-19, five years on from the start of the pandemic that upended the planet. “We continue to call on China to share data and access so we can understand the origins of Covid-19. This is a moral and scientific imperative,” the WHO said in a statement. Covid-19 killed more than seven million people, shredded economies and crippled health systems. “Without transparency, sharing, and cooperation among countries, the world cannot adequately prevent and prepare for future epidemics and pandemics,” the WHO said. The WHO recounted how on 31 December 2019, its country office in China picked up a media statement from health authorities in Wuhan concerning cases of “viral pneumonia” in the city. “In the weeks, months and years that unfolded after that, Covid-19 came to shape our lives and our world,” the UN health agency said. “As we mark this milestone, let’s take a moment to honour the lives changed and lost, recognise those who are suffering from Covid-19 and Long Covid, express gratitude to the health workers who sacrificed so much to care for us, and commit to learning from Covid-19 to build a healthier tomorrow.” Earlier this month, the WHO’s director general Tedros Adhanom Ghebreyesus addressed the issue of whether the world was better prepared for the next pandemic than it was for Covid-19. “The answer is yes, and no,” he told a press conference. “If the next pandemic arrived today, the world would still face some of the same weaknesses and vulnerabilities that gave Covid-19 a foothold five years ago. “But the world has also learned many of the painful lessons the pandemic taught us, and has taken significant steps to strengthen its defences against future epidemics and pandemics.” In December 2021, spooked by the devastation caused by Covid, countries decided to start drafting an accord on pandemic prevention, preparedness and response. The WHO’s 194 member states negotiating the treaty have agreed on most of what it should include, but are stuck on the practicalities. A key fault-line lies between western nations with major pharmaceutical industry sectors and poorer countries wary of being sidelined when the next pandemic strikes. While the outstanding issues are few, they include the heart of the agreement: the obligation to quickly share emerging pathogens, and then the pandemic-fighting benefits derived from them such as vaccines. The deadline for the negotiations is May 2025.
The final Powerball drawing of 2024 sees an estimated $163 million jackpot up for grabs after no one won the prize Saturday. The game has seen nine winners this year, the largest of which came in April when three players in Oregon − including a cancer survivor − split a $1.3 billion jackpot. The most recent win came earlier this month when a ticket sold in New York had the winning numbers for a $256 million jackpot. The first drawing of 2025 will occur on New Year’s Day. The holiday was lucky last New Year’s Day, with a Michigan lottery club winning an $842 million jackpot to start the year. The last Powerball draw of 2024 is set to take place shortly after 11 p.m. ET and we will have the results below. Check here shortly after 11 p.m. ET to see the winning numbers for the Powerball drawing on Dec. 30, 2024. Winning lottery numbers are sponsored by Jackpocket, the official digital lottery courier of the USA TODAY network. Check back Tuesday to see if anyone won in the final Powerball drawing of the year. To find the full list of previous Powerball winners, click the link to the lottery’s website. In order to purchase a $2 Powerball ticket, you’ll have to visit your local convenience store, gas station or grocery store − and in a handful of states, you can purchase tickets online. To play, you will need to pick six numbers in total to mark on your ticket. Five numbers will be white balls ranging from numbers 1 to 69. The Powerball is red and one number which is between 1 and 26. If you want to increase your chances of winning, you can add a “Power Play” for $1 which increases the winnings for all non-jackpot prizes. This addition can multiply winnings by 2X, 3X, 4X, 5X, or 10X. Players can also ask a cashier for a “Quick Pick” where a cashier will give you computer-generated numbers on a printed Powerball ticket. Drawings are held on Monday, Wednesday and Saturday nights. If there’s no jackpot winner, the cash prize will increase by millions. Tickets can be purchased in person at gas stations, convenience stores and grocery stores. Some airport terminals may also sell lottery tickets. You can also order tickets online through Jackpocket, the official digital lottery courier of the USA TODAY Network, in these U.S. states and territories: Arizona, Arkansas, Colorado, Idaho, Maine, Massachusetts, Minnesota, Montana, Nebraska, New Hampshire, New Jersey, New Mexico, New York, Ohio, Oregon, Puerto Rico, Texas, Washington D.C. and West Virginia. The Jackpocket app allows you to pick your lottery game and numbers, place your order, see your ticket and collect your winnings all using your phone or home computer. Jackpocket is the official digital lottery courier of the USA TODAY Network. Gannett may earn revenue for audience referrals to Jackpocket services. Must be 18+, 21+ in AZ and 19+ in NE. Not affiliated with any State Lottery. Gambling Problem? Call 1-877-8-HOPE-NY or text HOPENY (467369) (NY); 1-800-327-5050(MA); 1-877-MYLIMIT (OR); 1-800-981-0023 (PR); 1-800-GAMBLER (all others). Visit jackpocket.com/tos for full terms.
The quarterfinals for the 2024-2025 College Football Playoff start Tuesday. This season is the first season with the 12-team expanded playoff field, as the Deseret News previously reported. Under the new format, the top four seeds earned a bye, while seeds 5-12 battled it out in the first round of games held Dec. 20 and 21. The new format has brought new twists to the College Football Playoff with the first round games being played at the home stadiums of seed Nos. 5-8, according to ESPN. Now, the quarterfinal games will move to more traditional playoff venues: the Fiesta Bowl, Peach Bowl, Rose Bowl and Sugar Bowl. The winners will advance to the semifinals — the Orange Bowl and Cotton Bowl — and then the national championship in Atlanta. Here’s how to watch the College Football Playoff quarterfinals. The following 12 teams qualified for the 2024-25 College Football Playoff: Four teams —Tennessee, Clemson, Indiana and SMU — were eliminated in the CFP’s first round. Texas, Ohio State, Notre Dame and Penn State advanced to the quarterfinals to play the top four seeds, which are Oregon, Georgia, Boise State and Arizona State. The CFP quarterfinals begin Tuesday with Boise State and Penn State playing in the final college football game of the calendar year. The winners of this week’s game will advance to the semifinals and play in either the Orange Bowl on Jan. 9 or the Cotton Bowl on Jan. 10. The winners of the Orange Bowl and Cotton Bowl will play in the national championship on Jan. 20. Here is the schedule — including viewing information — for the 2024-2025 College Football Playoff quarterfinals, per the NCAA.
The 2024 regular season finale of “Monday Night Football” is about as meaningless as a “MNF” matchup can get, but the Detroit Lions and San Francisco 49ers meet in a playoff rematch with revenge on the line. The 49ers are playing for pride during the last two weeks of the season after being eliminated from playoff contention, a sour end to a disappointing, injury-riddled season. The defending NFC champions downed the Lions in last year’s NFC championship game, but they won’t have an opportunity to meet them in the postseason again. Meanwhile, the pride of Detroit is the Lions, and they’re roaring en route to the playoffs. Detroit has the inside track to the No. 1 overall seed in the NFC, which they can secure in Week 18 with a win over the Minnesota Vikings, regardless of whatever happens tonight vs. the 49ers. That said, it might not be a given for a once sure thing of the Lions, who are dealing with multiple injuries at the wrong time, especially on the defensive side of the ball. That could spell trouble for the Lions in Week 17 and beyond. USA TODAY Sports will provide live updates, highlights and more from the Lions-49ers matchup on “Monday Night Football” in Week 17. NFL STATS CENTRAL:The latest NFL scores, schedules, odds, stats and more. NFL NEWSLETTER:Sign up now to get football news delivered to your inbox The Lions responded to San Francisco’s opening-drive touchdown with a score of their own, this coming on a 3-yard touchdown run by wide receiver Jameson Williams. San Francisco defensive lineman Jordan Elliott blocked the extra point attempt but linebacker Fred Warner could not run it past the 30-yard line. Detroit relied on the run game in their opening drive and got 36 yards on seven carries combined from Jahmyr Gibbs, Jermar Jefferson and Williams. San Francisco quarterback Brock Purdy fired a pass to rookie wideout Ricky Pearsall for a 3-yard touchdown. Pearsall was initially ruled down at the one-yard line but review showed he crossed the plane with the ball for the touchdown. Jake Moody’s extra point is good and the 49ers take an early lead. Purdy went 3 for 3 for 34 yards on this drive and made a key conversion with his legs on fourth-and-1 at the Detroit 5-yard line to set up the score. San Francisco went 61 yards in 11 plays for the score. The 49ers vs. Lions matchup kicks off at 8:15 p.m. (5:15 p.m. PT). ESPN again is the broadcast home of “Monday Night Football.” The longtime team of Joe Buck (play-by-play) and Troy Aikman (color) will be on the call, with Lisa Salters adding reports from the sideline. There will be no “ManningCast” for tonight’s broadcast. For cord cutters looking for a live stream for the matchup, you can turn to Fubo. Fubo carries NBC, as well as CBS, FOX, NFL Network and the ESPN family of networks, meaning you can catch NFL action through the remainder of the season. ESPN+, the proprietary streaming service of ESPN, will also carry the game. Here’s how the USA TODAY Sports staff feels the 49ers vs. Lions“MNF” matchup will go down: The Lions are favorites to defeat the 49ers, according to the BetMGM NFL odds. Not interested in this game? Check out expert picks and best bets for every NFL game this week. The Lions travel to Levi’s Stadium in Santa Clara, California, to take on the 49ers on “Monday Night Football.” Levi’s Stadium has been the 49ers’ home since 2014. The venue hosted Super Bowl 50 — the Denver Broncos’ win over the Carolina Panthers — and will host Super Bowl 60 on Feb. 8, 2026. The stadium will be a host venue for the 2026 World Cup. Levi’s Stadium also occasionally will host games for the San Jose Earthquakes of Major League Soccer. ➤ Ranking NFL’s stadiums from 1 to 30: Where does 49ers’ Levi’s Stadium rate? Game time temperatures at Levi’s Stadium in Santa Clara, California, will be in the mid-50s and there is no chance for precipitation, according to AccuWeather. Temperatures will dip below 50 degrees by the time the game ends. The Lions still have a shot to play for the division and the No. 1 seed. They’ll need a win in Week 18 to make that happen. Here’s how the division stacks up: The 49ers won’t have a chance to repeat as NFC West champs this year, as the division has been wrapped up by the Los Angeles Rams. Here’s how the division shakes out: The first round of the NFL playoffs is the wild-card round, which will take place Jan. 11-13. Seeds Nos. 2 through 7 in both conferences will face off in one of the six total matchups over the three-day opening round. This year’s playoffs will kick off with two games on Saturday, Jan. 11, continue with three more on Sunday, Jan. 12 and conclude with one game on Monday, Jan. 13. The Lions have already clinched a playoff berth and will be either the No. 1 seed in the NFC or the No. 5 seed. It all depends on whether they can stave off competition from the Vikings in the race for the NFC North. Detroit will be the NFC’s No. 1 seed if either of the following scenarios occurs: Detroit will be the NFC’s No. 5 seed in either of the scenarios below: There are only two ways for the Lions and Vikings to end up tied in the standings at season’s end. They are as follows: If the Lions are the NFC’s No. 1 seed, they will get a much-needed first-round bye after which they would play the lowest-remaining seed in the NFC bracket. If Detroit ends up as the No. 5 seed, it will go on the road to face one of the following three teams: The 49ers were eliminated from the playoff picture ahead of their Week 16 game against the Dolphins. They failed to qualify for the postseason for the first time since 2020. San Francisco faced an uphill climb all season, dealing with countless injuries and ultimately succumbing to the dreaded Super Bowl hangover. The 2024 playoff field is almost set: 12 teams have clinched a playoff spot heading into Monday of Week 17: AFC NFC Below is the playoff clinching situation heading into Week 18 of the 2024 NFL season: Baltimore Ravens clinch AFC North with: Steelers clinch AFC North with: Bengals clinch playoff berth with: Broncos clinch playoff berth with: Dolphins clinch playoff berth with: Lions clinch NFC North and NFC’s No. 1 playoff seed with: If win on MNF … If lose on MNF … Vikings clinch NFC North and NFC’s No. 1 playoff seed with: If Lions win on MNF … If Lions lose on MNF … Falcons clinch NFC South with: Buccaneers clinch NFC South with: Here’s how the top 15 picks of the first round of the 2025 NFL draft stack up entering Monday night’s game: The New England Patriots and Pittsburgh Steelers are tied for the most Super Bowl wins with six. The 49ers have made eight total Super Bowl appearances and own five rings to show for it, the most recent coming during the 1994 season in Super Bowl XXIX. Since then, the 49ers have lost three Super Bowls, twice to the Kansas City Chiefs and also against the Baltimore Ravens. The Lions are among four NFL teams that have never appeared in a Super Bowl. The Lions, however, were a powerhouse team before the advent of the Super Bowl, winning four NFL championships, including three in the 1950s. NFL franchises with most Super Bowl wins: ➤ Super Bowl winners: All-time scores, results for NFL title game Do you like football? Then you’ll enjoy getting our NFL newsletter delivered to your inbox. 📲 Get the latest news, expert analysis, game insights and the must-see moments from the NFL conveniently delivered to your email inbox. Sign up now! Check out the latest edition … ➤ Best (and worst) from NFL Week 17: Playoff picture, draft order come into further focus We occasionally recommend interesting products and services. If you make a purchase by clicking one of the links, we may earn an affiliate fee. USA TODAY operates independently, and this doesn’t influence our coverage. Gannett may earn revenue from sports betting operators for audience referrals to betting services. Sports betting operators have no influence over nor are any such revenues in any way dependent on or linked to the newsrooms or news coverage. Terms apply, see operator site for Terms and Conditions. If you or someone you know has a gambling problem, help is available. Call the National Council on Problem Gambling 24/7 at 1-800-GAMBLER (NJ, OH), 1-800-522-4700 (CO), 1-800-BETS-OFF (IA), 1-800-9-WITH-IT (IN). Must be 21 or older to gamble. Sports betting and gambling are not legal in all locations. Be sure to comply with laws applicable where you reside.
Website intended for a NZ health professional readership Welcome to Pharmacy Today‘s Summer Hiatus – our seasonal content schedule while Pharmacy Today staff take their summer break. We will resume normal transmission on 13 January 2025. In the meantime, we wish all our subscribers a Merry Christmas and a Happy New Year. This article was first published on 1 August. Pharmacist and medical herbalist Phil Rasmussen looks at the complex issue of appropriate dosing for herbal medicines 1. Zha LH, He LS, Lian FM, et al. Clinical strategy for optimal Traditional Chinese Medicine (TCM) herbal dose selection in disease therapeutics: Expert consensus on classic TCM herbal formula dose conversion. Am J Chin Med 2015;43(8):1515–524. 2. Ni Sheng-Lou, Chen Chuan-Rong, Fu Yan-Ling, et al. Chinese Herbal Medicines – Comparison of doses prescribed in clinical practice and those in China Pharmacopoeia. Trop J Pharmaceutical Research 2015; 14(1):171–77. 3. Jaiswal Y, Liang Z, Zhao Z. Botanical drugs in Ayurveda and Traditional Chinese Medicine. J Ethnopharmacol 2016;194:245–59. 4. Li X, Wu L, Wu R, et al. Comparison of medicinal preparations of Ayurveda in India and five traditional medicines in China. J Ethnopharmacol 2022;284:114775. 5. Felter, HW. 1912: John Milton Scudder, M.D, Eclectic Biographies, The Lloyd Library, Cincinnati, Ohio. Southwest School of Botanical Medicine www.swsbm.com 6. Jussofie A, Schmiz A, Hiemke C. Kavapyrone enriched extract from Piper methysticum as modulator of the GABA binding site in different regions of rat brain. Psychopharmacology (Berl) 1994;116(4):469–74. 7. Yuan CS, Dey L, Wang A, et al. Kavalactones and dihydrokavain modulate GABAergic activity in a rat gastric-brainstem preparation. Planta Med 2002;68(12):1092–96. 8. Luger D, Poli G, Wieder M, et al. Identification of the putative binding pocket of valerenic acid on GABAA receptors using docking studies and site-directed mutagenesis. Br J Pharmacol 2015;172(22):5403–13. 9. Khom S, Hintersteiner J, Luger D, et al. Analysis of β-Subunit-dependent GABAA receptor modulation and behavioral effects of valerenic acid derivatives. J Pharmacol Exp Ther 2016;357(3):580–90. 10. Liu S, Yao C, Xie J, et al. Effect of an herbal-based injection on 28-day mortality in patients with sepsis: The EXIT-SEP randomized clinical trial. JAMA Intern Med 2023;183(7):647–55. 11. Rasmussen PL. Chinese parenteral phytomedicine reduces mortality from sepsis. Pharmacy Today 2023;Oct:14–16. 12. Tauchert M. Efficacy and safety of crataegus extract WS 1442 in comparison with placebo in patients with chronic stable New York Heart Association class-III heart failure. Am Heart J 2002;143(5):910–15. 13. Barton DL, Soori GS, Bauer BA, et al. Pilot study of Panax quinquefolius (American ginseng) to improve cancer-related fatigue: a randomized, double-blind, dosefinding evaluation: NCCTG trial N03CA. Support Care Cancer 2010;18(2):179–87. 14. Kennedy DO, Little W, Scholey AB. Attenuation of laboratory-induced stress in humans after acute administration of Melissa officinalis (Lemon balm). Psychosom Med 2004;66(4):607–13. 15. Chevassus H, Molinier N, Costa F, et al. A fenugreek seed extract selectively reduces spontaneous fat consumption in healthy volunteers. Eur J Clin Pharmacol 2009;65(12):1175–78. 16. Naser B, Lund B, Henneicke-von Zepelin HH, et al. A randomized, double-blind, placebo-controlled, clinical dose-response trial of an extract of Baptisia, Echinacea and Thuja for the treatment of patients with common cold. Phytomedicine 2005;12(10):715–22. 17. Huang YH, Liu GH, Hsu TY, et al. Effective dose of Rhizoma Coptidis extract granules for type 2 diabetes treatment: A hospital-based retrospective cohort study. Front Pharmacol 2021;11:597703. 18. Huntsman RJ, Tang-Wai R, Alcorn J, et al. Dosage related efficacy and tolerability of cannabidiol in children with treatment-resistant epileptic encephalopathy: Preliminary results of the CARE-E study. Front Neurol 2019;10:716. Academic pharmacist Nataly Martini highlights the importance of understanding non-Hodgkin lymphoma and pharmacists’ roles in managing this condition Talking about butt stuff in the pharmacy can be awkward. Care Pharmaceuticals and Rectogesic® can help you get to the bottom of the issue Pharmacy Today Online is intended for a New Zealand health professional readership. Use of this site implies acceptance of our Terms of Use and Privacy Statement. Pharmacy Today Online is not a consumer medical advice service. Consumers should seek advice from a health professional and not act in reliance on any statement contained in the information provided.
Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement Scientific Reportsvolume 14, Article number: 31928 (2024) Cite this article Metrics details The increasing development of technology has led to the increase of digital data in various fields, such as medication-related texts. Sentiment Analysis (SA) in medication is essential to give clinicians insights into patients’ feedback about the treatment procedure. Therefore, this study intends to develop Artificial Intelligence (AI) models to predict patients’ sentiments. This study used a large medication review dataset to perform a SA of medications. Three scenarios were considered for classification, including two, three, and ten classes. The Word2Vec algorithm and pre-trained word embeddings, including the general and clinical domains, were utilized in model development. Seven Machine Learning (ML) and Deep Learning (DL) models were developed for various scenarios. The best hyperparameters for all models were fine-tuned. Moreover, two ensemble learning models were developed from the proposed ML and DL models. For the first time, a technique was implemented to interpret the results for explainability and interpretability. The results showed that the developed deep ensemble model (DL_ENS), using PubMed and PMC, as pre-trained word embedding representation, achieved the best results, with accuracy and F1-Score of 92.96% and 92.27% in two classes, 92.18% and 88.50 in three classes, and 90.31% and 67.07% in ten classes, respectively. Combining DL models and developing a DL_ENS with clinical domain pre-trained word embedding representation can accurately predict classes and scores of patients’ sentiments about medications compared to previous studies on the same dataset. Due to the transparency in decision-making, our DL_ENS model can be used as an auxiliary tool to help clinicians prescribe medications. In recent decades, users’ reviews on websites and social media have been increased dramatically. Users publish their reviews about various products such as medication, movies, restaurants, home appliances, clinical services, and marketing on related sites. People read the reviews before purchasing or using products or services, which enables them to make informed decisions based on previous reviews1,2,3. Medical and clinical reports, patients’ feedback, and sentiments about medical systems and services are among the most valuable and useful textual content4,5,6. Although the safety of medications after production is monitored and tested under standard clinical conditions, people still write their reviews and sentiments on medication review websites. These websites enable people to read reviews about the medications before using them. Clinicians and pharmacists can also use this information to align with patient expectations and experiences, ultimately improving adherence and treatment effectiveness. Sentiment analysis of patient feedback enables clinicians to adjust prescribing behaviors by recognizing common patient-reported side effects and satisfaction levels associated with medications. This approach enhances clinicians’ decision-making process and informs patient care strategies by highlighting areas where medication efficacy or patient experience could be improved4,5,6. Analyzing such text data using sentiment analysis (SA) is a useful step in evaluating medications’ effectiveness and side effects more accurately4,5,7,8,9,10,11. Prediction of patients’ sentiments in medicine can be used to facilitate treatment in the future because the results of different types of medical treatments and awareness of their effectiveness have been investigated. Analyzing patients’ sentiments in clinical documents, where treatment processes and results were recorded from the past to the present, can help clinicians and pharmacists identify factors affecting diseases and treatments12. SA is one of the most prominent branches of natural language processing that focuses on finding the sentiments in the texts13. In SA, reviews are divided into different levels, including aspect, entity, sentence, and document levels13. SA is known as a classification problem, and some studies used artificial intelligence (AI) techniques to solve this problem6. Machine Learning (ML) and Deep Learning (DL) algorithms are branches of AI, and their use in clinical fields, especially in the field of clinical SA and text mining, has recently increased6,8. Many studies in the past have used AI techniques to detect sentiments in non-clinical contexts1,2,3,14,15,16,17,18,19,20. However, previous studies in the clinical and medicine domain6,8,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39, which are reviewed in Sect. 2, have various shortcomings: Various scenarios for predicting sentiment have not been considered. Most studies have not considered finding the best hyperparameters for their proposed models. Most studies in this field utilized relatively small datasets. The impact of using various pre-trained word embeddings in the clinical domain has not been studied. The explainability and interpretability of AI models, which are very important in the clinical domain, have not been considered in previous studies. To address these shortcomings, this study aims to provide a new method for comprehensively identifying the sentiments of medication reviews. For this aim, seven AI techniques, including ML and DL models and two ensemble (ENS) models, were developed to predict patients’ sentiments and rate scores. In general, our main contributions in this study are as follows: Proposed ML and DL models were trained and tested on the drugs.com dataset, which is a rich dataset for medication reviews. Three scenarios have been considered to comprehensively determine patients’ sentiment classes and rate scores. Various ML, DL, and ENS algorithms and experiments are developed to compare the prediction of patients’ sentiments and rate scores. A deep ensemble (DL_ENS) model with a new architecture is designed to predict patients’ sentiments and rate scores in medication reviews. The best values of the hyperparameters of ML and DL models have been found and selected for prediction using Grid Search. Various general and clinical pre-trained word embedding models were used to improve AI models’ performance. This study is the first study using Local Interpretable Model-agnostic Explanations (LIME) to explain the decision-making process to have interpretable and explainable AI models for medication reviews. The remainder of this paper is divided into six sections: Section two presents an overview of previous studies on SA, Section three describes the materials and methods that have been used in this study, Section four presents the results, Section five is the discussion, and finally, Section six concludes the study and outlines future work. Table 1 provides an overview of previous SA studies including their methods, type of dataset, and their research gaps6,8,15,16,17,18,19,21,24,25,28,29,30,31,32,35,37,39. Various researchers have attempted to analyze the medication reviews provided by people to get insight into their conditions, needs, sentiments, and the side effects of each medication6,8,28,29,30,31,32,33,34,35,36,37,38,39. SA can play an important role in this field for extracting beneficial information for mentioned purposes. Most studies in this field are based on datasets with a limited number of samples. Moreover, most researchers have used rule-based and traditional ML models for SA31. For SA in medication reviews, datasets with a more significant number of samples by ML algorithms such as Support Vector Machine (SVM), Logistic Regression (LR), Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF), K Nearest Neighbor (KNN) were considered28,30,32,38,39. Recently, ML methods were also used for SA in medication reviews in a non-English language, and their performance was compared with medication reviews in English32. Moreover, new feature extraction methods and ML algorithms have been proposed to improve the performance of models in SA of medication reviews39. In the SA of medication reviews, DL algorithms, including Convolutional Neural Networks (CNN), have been developed to achieve better performance in sentiment classification8,35,36. With the increasing use of DL models, the performance of these models has also been compared with ML models in SA of medication reviews. Results have indicated that DL models have promising results compared to traditional ML models6,33,34. Finally, in recent studies, the combination of DL models such as CNN-Gated Recurrent Unit (GRU) or bidirectional models such as Bidirectional Gated Recurrent Unit (Bi-GRU) have been suggested to analyze sentiments in the dataset of patients’ medication reviews29,37. Ebrahimi et al.31 proposed a sentiment extraction recognition system using rule-based and SVM algorithms to recognize side effects in medication reviews. The medication reviews were hand-selected by a medical experiment for model training and testing. Their results have indicated that the SVM algorithm had significantly better performance than rule-based algorithms. Gräßer et al.28 have performed both cross-domain and in-domain SA using LR to predict the sentiments of overall satisfaction, effectiveness, and side effects of the medications. They crawled Drugs.com and Druglib.com to obtain their data. In the cross-domain SA, using Drugs.com data, they achieved 70.06% for accuracy and 26.76% for kappa. The results for the side effects were 49.75% for accuracy and 25.88% for kappa. Chen et al.30 have applied SA of the medication reviews using NB, DT, RF, and Ripper to positive, negative, and neutral labels. They collected their data by scraping the Hypertext Markup Language (HTML) file of Druglib.com. To solve the problem of many features, they employed Fuzzy-rough feature selection to reduce the data effectively. They used two techniques to determine the value of terms: the Bag of Words (BoW) and the Term Frequency-Inverse Document Frequency (TF-IDF). The best results were obtained using the BoW method. RF model, with 66.41% accuracy, was the most accurate model, and the average accuracy of the four implemented ML models was 63.85%. Jiménez-Zafra et al.32 applied lexicon-based and supervised learning SA approaches to inform patients’ sentiments for both physician and medication purposes. They have collected their dataset in Spanish from internet forums. Their results have indicated that it is much more challenging to classify medication opinions from opinions related to doctors. Liu et al.39 have proposed a new feature extraction approach using position embeddings for SA of medication reviews. They implemented different feature extraction techniques with various ML models to classify sentiments and concluded that their proposed method had superior performance. Colón-Ruiz et al.8 have used patients’ medication reviews to predict feelings about taking each medication. For this aim, they developed a CNN for classification. Their results indicated that precision, recall, and F1-Score values were better than classical classification methods such as SVM. Zhang et al.35 provided a dataset of adverse medication reactions and proposed a new DL architecture for its identification. Their results showed that their proposed model performance was slightly better than other models in detecting adverse medication reactions. Basiri et al.6 have proposed two different methods using the traditional techniques of ML and DL to distinguish sentiments from patients’ medication reviews. They compared their best proposed method with traditional and DL models. According to their reported results, they increased accuracy and F1-Measure by 4%. Jain et al.29 have developed DL models, including CNN, GRU, Multi-Instance Learning (MIL), and CNN-GRU, to identify the deceptive comments and sentiments from different datasets, including the medication review dataset. They used two MIL and Hierarchical architecture methods and claimed that they achieved better results using DL models compared to previous studies where traditional ML models were developed. In the SA of medication review dataset, CNN obtained the values of 76.8%, 0.77, and 0.77, GRU obtained the values of 76.3%, 0.76, and 0.76, MIL obtained the values of 78.2%, 0.78, and 0.78, and CNN-GRU obtained the values of 83.8%, 0.84, and 0.83 for accuracy, precision, and recall, respectively. Han et al.37 have used two Bi-GRU neural networks and the attention mechanism to produce a bidirectional semantic representation of medication review. They have stated that their proposed approach can improve performance compared to other modern architectures for classifying the sentiments of medication review. Our literature review shows that previous studies exclusively have used ML and DL models to predict patients’ sentiments in medication reviews. However, the previous studies were done without considering the interpretability and explainability issues of AI models, and different pre-trained word embeddings in the clinical domain were not considered for SA of medication reviews6,8,28,29,30,31,32,33,34,35,36,37,38,39. Furthermore, the ENS learning models have not been used in any of them. Nevertheless, previous studies have used SA widely in non-medication fields, indicating its use in shopping, tourism, and social networks14,15,16,17,18,19,20,40. In recent years, the application of SA for medicine-related information in social networks has also been considered21,22,23,24,25,26,27. Furthermore, previous studies in medication SA have attempted to provide classical ML and DL methods to predict medication review sentiments6,8,28,29,30,31,32,33,34,35,36,37,38,39. For instance, recent systematic reviews have confirmed that SA is a promising tool in unexpected events such as the COVID-19 pandemic, which can be used to inform the public’s sentiments about the disease and its vaccination40,41. According to recent systematic reviews6,8,28,29,30,31,32,33,34,35,36,37,38,39,42,43 and our literature review, existing gaps in the field of SA in medication have been identified. First, shared reviews about medications on the internet can be a beneficial source for SA that can help clinicians get insights about patients’ conditions as well as side effects42. Second, the creation of a special and comprehensive sentiment lexicon for medication reviews SA in the clinical domain, which was endorsed by clinicians and pharmacists, has not been addressed in previous studies6,8,12,28,29,30,31,32,33,34,35,36,37,38,39,43. Third, even though drugs.com is a rich dataset for SA analysis, there is no comprehensive study using this dataset6,8,28,29,30,31,32,33,34,35,36,37,38,39,42. Fourth, some studies have used meta-heuristics, optimization, and fuzzy methods19,30, but newly developed and improved meta-heuristics and optimization algorithms were not considered in the feature selection process and finding models’ optimal hyperparameters44,45,46. Fifth, no study has used various pre-trained word embeddings in the clinical domain for SA in medication reviews. Finally, no study considered explainable AI techniques to predict SA in the medication review dataset6,8,28,29,30,31,32,33,34,35,36,37,38,39,42,43. Therefore, to address these gaps, in this study, a DL_ENS model has been proposed to comprehensively predict the analysis of patients’ sentiments in medication reviews28 with different scenarios. Also, different pre-trained word embeddings in the clinical domain were integrated into the proposed model to overcome the lack of a specific lexicon for the medication SA challenge. Furthermore, an explainable method of AI was used to increase the transparency and explainability of our proposed best model (DL_ENS). Addressing this issue can help clinicians to understand the decision-making process and increase their trust in the results. The dataset of this study was extracted from drugs.com28, which is publicly available in the UCI Machine Learning “Drug Review Dataset (Drugs.com)” repository. The medication review dataset contains 215,063 patients’ sentiments (text) about the medication they used, along with a score from 1 to 10 (numerical) that patients have registered as well as the condition of the medications (text)28. The methodology diagram of this study is illustrated in Fig. 1. Workflow diagram illustrating the steps performed in this study. In this study, NumPy and NLTK libraries were used to perform preprocessing tasks on medication review texts. This stage had five steps as: (1) removing all incomplete records, (2) removing the redundant punctuation marks and characters from all texts, (3) converting uppercase letters to lowercase letters in all instances of the dataset, (4) deleting the stop words because they were frequently present in the texts and did not provide us with the helpful information in terms of performance, and (5) using Snowball Stemmer to remove the suffixes of the words in the dataset and find their roots. After fully preprocessing, 213,869 samples were remained. After preprocessing phase, a clean and consistent dataset was created. ML and DL models are not able to work directly with texts. So, texts should be converted to vectors of numbers. This study utilized BoW and word embedding techniques to extract features from texts. BoW is a simple way to count the number of repetitions of words and an easy-to-use technique for converting texts to vectors for classification models47. Word embedding is a new method to represent any word using a vector of numbers such that each number in the vector represents one latent feature of the word, and the vector represents different latent features of the word48. Word2Vec is a neural network-based word embedding technique. This method comprises three layers: input, hidden, and output. The Word2Vec method consists of two structures, Skip-Gram (SG) and Continuous BoW (CBOW)48. Furthermore, pre-trained word embedding, including Glove in the general domain, and PubMed, PMC, and combined PubMed and PMC in the clinical domain were considered in this study for DL models49,50. Three scenarios were implemented in this study. In the first scenario, the scores of the medication reviews dataset were divided into two classes: Negative (for the scores less or equal to 5) and Positive (for the scores greater than 5). In the second scenario, the scores were divided into three classes: Negative (for the scores less than 5), Neutral (for the scores 5 and 6), and Positive (for the scores greater than 6). Eventually, in the third scenario, the dataset scores of this study were considered from one to ten for each medication review. This study used Hold-Out cross-validation to split patients’ medication review dataset51. According to this method, the dataset was randomly divided into two training and testing sets, so 75% of the dataset was considered for training (160,093 samples) and 25% for testing (53,776 samples). Nine common models of ML, DL, and ENS with different theoretical backgrounds, including KNN, DT, RF, Artificial Neural Network (ANN), Bidirectional Recurrent Neural Network (Bi-RNN), Bidirectional Long Short-Term Memory (Bi-LSTM), Bi-GRU, Machine ENS learning (ML_ENS), and DL_ENS52,53,54,55,56,57, were developed to predict patients’ sentiment and rate scores. All proposed ML algorithms in this study are described in detail in Appendix A. DL algorithms depend on activation functions and loss functions during their learning process. By utilizing these functions and updating the weights, the models are trained to make predictions. Rectified Linear Unit (ReLU) is a type of activation function that is used in neural networks to introduce the property of non-linearity to them, and help them learn complex patterns and predict more accurately55. This function sets negative values of input to zero, while leaving positive values unchanged55. The mathematical equation of the ReLU activation function is as follows: Where (:x) represents the input value. Sigmoid is an activation function that takes any inputs and transforms them into output values in the range of 0 to 1 in neural networks55. The sigmoid function is commonly used in binary classification tasks55. The following equation shows how the sigmoid activation function works: Where (:sigma:) represents the sigmoid function, and (:e) represents Euler’s number. Softmax is an activation function that converts numbers or logic to probabilities. Softmax’s output is a vector of probabilities for the possible outcomes55. It is used to normalize the output of neural networks. Unlike the sigmoid activation function, it is commonly utilized for multivariate classification tasks55. The following equation shows how the softmax activation function works: Where (:S) is softmax, (:overrightarrow{z}) devotes input vector, (:{e}^{{z}_{i}}) standard exponential function for input vector, (:K) shows the number of classes in multivariate classification, and (:{e}^{{z}_{j}}) means standard exponential function for output vector. The loss function is a function that is calculated to evaluate the models’ performance in modeling the dataset55. In other words, it measures the difference between the predicted and actual target values55. The following equation represents how binary log loss is calculated: Where (:{y}_{i}) shows actual values, and (:{widehat{y}}_{i}) shows model predictions. Another loss function that is used for multivariate classification is categorical cross-entropy loss55, which is calculated as follows: Where (:{y}_{i}) shows actual values, and (:{widehat{y}}_{i}:)shows model predictions55. RNN is a type of ANN which used in text, speech, and sequential data processing54,55. Unlike feed-forward networks, RNNs have a feedback layer where the output of the network and the next input are fed back to the network55. RNNs have internal memory, so they can remember their previous input and use their memory to process sequential inputs. Long Short-Term Memory (LSTM) and GRU are among the RNN algorithms in which the output of the previous layers is used as input to the subsequent layers54. LSTM and GRU, in their architecture, solve the vanishing gradient problem that occurs in RNN54,55. Bi-RNN, Bi-LSTM, and Bi-GRU algorithms have a two-way architecture55. These three algorithms move and learn in two directions (forward and backward) in a progressive and regressive way55. The output of Bi-RNN is: Where That (:{x}_{t}) denotes the input vector at the time (:t), (:{y}_{t}) is the output vector at the time (:t),(::{h}_{t}) is the hidden layer at the time (:t), (:f) means forward, (:b) means backward, and (:{W}_{y}), (:{W}_{h}), and (:{W}_{x}) denote the weight matrices that connect the hidden layer to the output layer, the hidden layer to the hidden layer, and the input layer to the hidden layer, respectively. (:{b}_{y}) and (:{b}_{h}) are the bias vectors of the output and hidden layer, respectively55. In the following, the calculation process of Bi-LSTM is explained: . Equations (9–14) are the equations of the forgotten gate, input gate, current state of the cell, memory unit status value, output gate, and hidden gate, respectively. The (:b) and (:W) denote the bias vector and weight coefficient matrix55. (:sigma:) shows the sigmoid activation function55.(::{x}_{t}) denotes the input vector at the time (:t) and (:{h}_{t}) is the hidden layer at the time (:t)55. The output of Bi-LSTM is: Where That (:{y}_{t}) is the output vector at the time (:t),(::f) means forward, (:b) means backward, and (:V), (:W), and (:U) denote the weight matrices that connect the hidden layer to the output layer, hidden layer to hidden layer, and input layer to hidden layer, respectively54. The calculation process of Bi-GRU is: Where (:W) is the weight matrix, (:{z}_{t}) shows update gate, (:{r}_{t}:)represents the reset gate, (:{stackrel{sim}{h}}_{t}) shows reset memory, and (:{h}_{t}) shows new memory. (:{x}_{t}) denotes the input vector at the time (:t), and (:b) is the bias vector55. The output of Bi-GRU is: Where That (:GRU) is the traditional GRU computing process, (:f) and (:b) mean forward and backward, respectively, and (:{b}_{t}) is the bias vector at the time (:t). Supposing (:h) is equal to Eq. (6) for Bi-RNN, Eq. (15) for Bi-LSTM, and Eq. (22) for Bi-GRU, and the parameters are: the number of these models units is (:150), the number of units in the first fully connected layer is (:n=128), and the number of units in the second fully connected layer is (:z), given a single time step input: Where Eqs. (25, 26) are the equations of the first fully connected layer with ReLU activation and the second fully connected layer, respectively. (:{f}_{i}) could be sigmoid as Eq. (2) for the first approach, and it could be softmax as Eq. (3) for the second and third approaches. The (:{b}_{1}) and (:{b}_{2}) denote the bias vectors and (:{W}_{1}) and (:{W}_{2}) denote weight coefficient matrices. By knowing (:t=1), and (:{f}_{i}) is sigmoid, we have these proposed algorithms: Also, if (:t=1), and (:{f}_{i}) is softmax, we have these proposed algorithms: ENS learning is an AI technique to increase the model’s power in estimating data output, which uses several models in combination and simultaneously to make decisions56. One of the ENS learning methods is the voting method, in which decisions are made based on the votes of the models, and it includes two approaches, hard and soft voting52. In hard voting, the choice of target is based on the maximum number of votes the models have given to the output56. In soft voting, the target selection is based on the highest joint probability that the models had over the output52,56. In this paper, the hard voting method is used to develop two ENS models of ML_ENS and DL_ENS. The equation of hard voting is represented as follows: Where (:t=:{KNN,DT,:RF,:ANN}) in ML_ENS model and (:t={Bi-RNN,:Bi-LSTM,::Bi-GRU}) in DL_ENS model, (::j={Negative,:Positive}) in the first scenario, (::j={Negative,::Neutral:,Positive}) in the second scenario, and (::j={One,:Two,:Three,:Four,:Five,:Six,:Seven,:Eight,:Nine,:Ten}) in the third scenario. (:T)represents the number of models, and (:C) represents the number of classes. Nonetheless, the mathematical forms of the ML_ENS and DL_ENS models, according to the aforementioned sentences, determine the target class in each approach by voting from all the proposed algorithms. In this study, Sklearn and TensorFlow libraries were used for implementation. Grid Search was applied to find the best values of hyperparameters. This method searches and evaluates the grid in which hyperparameters and their values are specified and determines the best hyperparameter values for each model57. The best selected hyperparameters for proposed models are shown in Table 2. Once the best hyperparameters were identified for each model, these tuned models were chosen to create ML_ENS and DL_ENS models. The ENS approaches then combined the predictions from these optimized models. The aggregated votes of these tuned models determined the final prediction of each ENS model. This process ensured that the ensemble models benefited from the strengths of each individually optimized model to improve overall prediction performance. Furthermore, weighted loss functions were considered to address the class imbalance and ensure that the model paid more attention to the minority class during training. Specifically, a weight was assigned to each class based on its frequency in the dataset, so that underrepresented classes were given more importance in the optimization process. This approach helps mitigate the negative effects of class imbalance on model performance. We developed our algorithm on a server with 32 GB of RAM, Intel E5-2650 CPU, and 4 GB memory by GPU Nvidia GTX 1650. The following evaluation criteria were considered to evaluate the performance of the proposed models58: TP, TN, FP, and FN are True Positive, True Negative, False Positive, and False Negative. These are components of the confusion matrix59. Moreover, the Area Under Curve (AUC) metric was used to estimate the performance of the best model as it often provides a better evaluation of performance than the accuracy metric60. LIME is an interpretable and explainable method for AI black box models59,61. The LIME is a simple but powerful way to interpret and explain models’ decision-making processes59,61. This method considers the most influential features to explain how the model predicts. LIME locally approximates the prediction by forming a disturbance in the input around the class so that when a linear approximation is reached, it explains and justifies the model’s behavior and performance61. SA is a prominent component of natural language processing applications. One field that has attracted researchers’ attention is using SA to evaluate medications and their impacts on patients. The current study used the medication review dataset to predict patients’ sentiments and rate scores based on their responses to the medications in the proposed scenarios. For this purpose, four ML models, three DL models, and two ENS models with a hard voting approach were developed. The patients’ medication reviews database was preprocessed to achieve the best performance. So, redundant samples were removed, and their possible negative impact and bias on the models’ performance were avoided as much as possible. At the end of the preprocessing, 213,869 patient comments remained as the main dataset for this study. Figure 2 shows the most common patient conditions with more than two thousand samples in this dataset. According to Fig. 2, birth control, depression, pain, anxiety, and acne are the five most common conditions. Also, Fig. 3 shows the share of each score in this dataset. According to Fig. 3, the scores of 10, 9, 1, 8, and 7 have the largest share in this dataset. The most common patient conditions in the dataset. Chart showing the distribution of each score in the dataset. According to Table 3, this study has considered different scenarios for predicting sentiment classes and rate scores. The reason for these different scenarios is the imbalanced number of samples for each class. Especially in the second scenario, the number of samples of the neutral class is less than in other classes. Therefore, the third scenario has been created with ten classes to improve the performance. Based on experiments, we selected a BoW vector size of 20,000 for ML models among values (10,000–25,000). Also, the CBOW method from the gensim library in Python was selected by the dimensionality of the 15,000 words number size for DL models among values (1,000–25,000). After completing the preprocessing and selecting the best hyperparameters, our proposed models were executed and tested. Then, models were evaluated based on the evaluation criteria (Eqs. (34–37)) considered in Sect. “Evaluation of models”. As mentioned, patients’ sentiments were predicted based on three scenarios. Accuracy, precision, recall, and F1-Score were calculated for all models. Table 4 shows the results of all proposed models in the first scenario (two classes). As seen, among traditional ML and DL models, RF and Bi-GRU had the best performance, respectively. Moreover, the DL_ENS model outperforms all ML, DL, and ENS models proposed in this study. Results of all models in the second scenario (three classes) are presented in Table 5. As shown RF model had the best performance among the ML models. Among the proposed DL models, the Bi-GRU model had better performance. DL_ENS model also had the highest achievement among all proposed models. The results of the models proposed in this study in the third scenario (ten classes) are presented in Table 6. RF model performed better than other ML models. Among the proposed DL models, the Bi-GRU model had the best performance. Finally, the best proposed model (DL_ENS) showed better results than all ML, DL, and ML_ENS models. According to Tables 4, 5 and 6, the results of the DL_ENS model in all scenarios clearly show that this model (DL_ENS) has outperformed other implemented models. Therefore, the DL_ENS model was utilized and tested for further investigation using general and clinical pre-trained word embeddings. The results of these experiments for the first, second, and third scenarios are presented in Tables 7, 8 and 9. It is worth noting that clinical pre-trained word embedding (combined PubMed and PMC) had superior performance in the proposed best model and was able to increase its accuracy and F1-score values. Also, clinical pre-trained word embeddings had more positive impacts on the models’ performance than general domain pre-trained word embeddings. Furthermore, the computation time of the best model of this study on different pre-trained word embeddings for various scenarios is shown in Table 10. In addition, the proposed best model was compared with previous studies6,8,28,29,30 on the same dataset, and the comparison is presented in Table 11. This table shows that DL_ENS outperformed other previously reported models6,8,28,29,30. Figures 4 and 5 show the AUC diagram and confusion matrices for all scenarios of the proposed DL_ENS model, respectively. As shown in Figs. 6, 7 and 8, and Figs. S1-S6 in Appendix A, three reviews from the test dataset were selected randomly to interpret the decisions of the best model in all scenarios. Therefore, this study utilized LIME, which explains the decisions of these random medication reviews. The AUC diagrams illustrating the performance of the best model. Confusion matrices illustrating the classification performance of the best model. Explanation of decisions made by the best model in the first scenario. Explanation of decisions made by the best model in the second scenario. Explanation of decisions made by the best model in the third scenario. In this study, three different scenarios are presented to predict patients’ SA about medication. The first and second scenarios are the most common modes for predicting SA, as used in most studies6,8,28,29,30. In the first scenario, scores less than 5 were classified as negative, and scores 5 and above were classified as positive. In the second scenario, scores less than 5 were classified as negative, scores 5 and 6 as neutral, and scores above 6 as positive. To identify patients’ sentiments more accurately towards medications, a third scenario considered ten classes, with scores ranging from 1 to 10 based on what patients recorded for each medication. Comparing the results of the best proposed model in Tables 4, 5 and 6 with Tables 7, 8 and 9, in the first scenario, the accuracy value is increased by 1.57%, and the value of F1-Score is increased by 1.58%. Also, in the second scenario, the accuracy value is increased by 1.23%, and the F1-Score value is increased by 1.15%. Finally, in the third scenario, the accuracy value is increased by 0.36%, and the F1-Score value is increased by 0.83%. The best proposed model with pre-trained word embedding (a combination of PubMed and PMC) obtained the best result in all scenarios of this study. According to Table 10, the computing time of the best-proposed model (with PubMed and PMC pre-trained word embedding) is comparable with that of other word embeddings. It is important to note that the computational costs across different model configurations can vary, which is crucial for assessing the practicality of the models in real-world applications. While the PubMed and PMC combination achieves the highest performance, its computation time is slightly longer than other word embeddings. For instance, the runtime for the third scenario with the PubMed and PMC embedding is 18,952.50 s, while Word2Vec and GloVe require 18,055.00 and 18,495.00 s, respectively. These time differences should be considered when evaluating the trade-off between model accuracy and computational efficiency, especially in resource-constrained environments. Based on62, the results provided in Figs. 4 and 5 indicate outstanding performance in the first and second scenarios and acceptable performance in the third scenario for the proposed best model using pre-trained PubMed and PMC word embedding models. Medication SA can provide insight into the effectiveness of a medication and treatment process. Nonetheless, detecting and predicting patients’ sentiments towards medication is very complicated32, but by doing so, we can identify views about the medications, their unreliability, and their effectiveness; consequently, it can be used in clinical decision-making12. Transparency is one of the main issues for developing AI models in clinical practices, and most AI models are considered as a black box where the logic of decision-making is not easy to understand and follow, especially for clinicians61. To address this, we used the LIME technique specifically designed to interpret complex machine learning models by approximating their decision-making process locally around each prediction. LIME works by perturbing the input data (words in medication reviews) and observing how these perturbations affect the model’s predictions. This method allows us to identify each prediction’s most influential features (words). As shown in Figs. 6, 7 and 8 and Figs. S1-S6 in Appendix A, LIME was applied to explain the predictions made by the best-performing model. For each instance, LIME generated a local surrogate model that approximates the decision boundary of the black-box model in the vicinity of the specific prediction. By calculating the importance of each word for sentiment classification and rate scoring, we could identify the words that had the most significant impact on the model’s output. This step-by-step explanation of model decisions helps to uncover the rationale behind sentiment predictions, making them more transparent. The output of LIME highlights the most influential words and provides a confidence score for each class based on the sum of the weighted probabilities of these words. This transparency level enables clinicians to better understand the reasoning behind the model’s predictions, increasing the trustworthiness and potential for adopting AI-driven tools in clinical workflows. By providing clear explanations of how sentiment analysis is performed, clinicians can use these models more confidently, ultimately aiding in more informed patient-care decision-making. This research aimed to extend previous work by focusing on SA of patient medication reviews, which presented unique challenges requiring specialized models32. Compared to the models proposed in previous studies6,8,15,16,17,18,19,24,25,28,29,30,31,32,35,37,39, both for non-medication and medication reviews datasets, and as shown in Table 11, the performance of the DL_ENS model was superior to traditional DL and ML models. ENS learning mitigates errors, reduces overfitting, and increases accuracy and robustness by leveraging the strengths of different models63,64. Additionally, pre-trained word embeddings enhanced model performance and generalizability by capturing semantic and syntactic meanings from large datasets, as recommended by the study65. The absence of ENS models and the use of pre-trained word embeddings in previous studies6,8,15,16,17,18,19,24,25,28,29,30,31,32,35,37,39, as well as in other proposed models of this study, has resulted in lower performance compared to the best proposed model. In this study, the DL_ENS model, combined with pre-trained word embeddings (from PubMed and PMC), leverages the advantages of DL models, ENS learning, and pre-trained word embeddings, showing promising results in all scenarios. Several reasons caused this study’s improvement compared to previous studies: (1) comprehensive preprocessing was applied to the dataset to prevent errors and bias in the model prediction; (2) a systematic way to find the best hyperparameters was deployed; and (3) the recommended DL_ENS model in SA63 was used along with pre-trained word embedding in the clinical domain. So, in this study, PubMed and PMC were chosen as the pre-trained word embeddings due to their strong relevance to the clinical domain. These embeddings are trained on extensive biomedical corpora, allowing them to capture medical terminology and language patterns specific to healthcare. This choice enhances the model’s ability to understand and process sentiment in medication reviews, ensuring more accurate and contextually relevant predictions in the healthcare setting. The development of these models, such as the proposed DL_ENS model, can serve as an auxiliary tool for clinicians and patients in the health and pharmaceutical systems to predict the sentiment of used medications. Initially, we developed several models based on a patient sentiment dataset about medications from the drugs.com website, which is for patients in the United States. The best model proposed in this study can also be tested and retrained on datasets from other countries as an external validation to enhance its effectiveness. This model can be integrated as a plug-in tool with software systems for registering and managing patient medications. Analyzing the collected sentiments can help clinicians prescribe more suitable medications with fewer side effects. This integration means patients and clinicians do not need to understand the model in detail, as it can be seamlessly incorporated into their routine software applications. Furthermore, the findings and detailed implementation of this study can guide the development of more advanced and comprehensive models by experts in AI applications in medicine. Finally, integrating the DL_ENS model in clinical settings raises important ethical considerations, particularly regarding the use of patient-generated data for model training and deployment. It is important to note that the dataset used in this study contains no patient information, as all records have been anonymized to ensure privacy and confidentiality. Patient consent and transparency are essential principles in this approach, as no identifiable data were involved in the analysis. Furthermore, as the model is integrated into clinical decision-making, it is crucial to remain free from biases that could affect treatment outcomes, especially for underrepresented patient groups. Continuous monitoring of the model’s real-world performance will be necessary to address any ethical concerns, ensuring it serves patients’ best interests. However, our study has a few limitations. Firstly, in all scenarios proposed in this study, the number of instances of considered classes was not the same due to the dataset’s imbalanced number of reviews for different classes. Secondly, we could not develop more models due to limited resources. Additionally, there was no other suitable dataset similar to the one used, with a high number of samples, for external validation to verify the generalizability of the developed models. Finally, the DL_ENS model has its own limitations, such as higher computational costs and potential challenges in real-time deployment, which could impact its practical application in clinical settings. These factors may require further optimization to balance efficiency for practical use in healthcare environments. In this study, the proposed DL_ENS model, a deep ENS model with PubMed and PMC pre-trained word embedding in all implemented scenarios, obtained the best results. Additionally, our findings show that pre-trained word embedding in the clinical domain has a better impact on the models’ performance rather than pre-trained word embedding in the general domain. Moreover, our developed model performs better than previous studies for SA on the drugs.com dataset. Our study also considers the explainability and interpretability of results by utilizing the LIME technique. This technique can help clinicians see the logic behind the decisions and increase trust in the results. As a result, this technique can also increase the chance of using our best model as a clinical decision support system in real practice. This study’s proposed technique can enhance transparency and facilitate the integration of our DL_ENS model as a clinical decision support tool, which could be added as a plug-in to existing healthcare systems. This integration would allow clinicians to use sentiment insights from patient reviews to assist in medication selection, treatment planning, and patient counseling. The model can contribute to more personalized and effective care strategies by providing actionable insights into patient satisfaction and side effects, ultimately improving patient outcomes. In the future, we plan to develop more models to increase the accuracy of SA in predicting patients’ sentiments. In addition, we intend to explore multi-modal approaches by integrating both text and voice data for sentiment analysis, testing the performance of such models in clinical practice. This extension could provide a more comprehensive understanding of patient sentiments by incorporating different forms of communication, potentially enhancing the model’s robustness and applicability in real-world healthcare settings. The dataset analyzed during the current study is available publicly in the “Drug Review Dataset (Drugs.com)” repository, https://archive.ics.uci.edu/dataset/462. Cambria, E., Wang, H. & White, B. Guest editorial: Big social data analysis. Knowl. Based Syst.69, 1–2 (2014). Article Google Scholar Budennyy, S., Kazakov, A., Kovtun, E. & Zhukov, L. New drugs and stock market: A machine learning framework for predicting pharma market reaction to clinical trial announcements. Sci. Rep.13, 12817 (2023). ArticleADSCASPubMedPubMed Central Google Scholar Grassi, M., Cambria, E., Hussain, A. & Piazza, F. Sentic web: A new paradigm for managing social media affective information. Cognit Comput.3, 480–489 (2011). Article Google Scholar Chintalapudi, N., Battineni, G., Canio, M. D., Sagaro, G. G. & Amenta, F. Text mining with sentiment analysis on seafarers’ medical documents. Int. J. Inform. Manage. Data Insights. 1, 100005 (2021). Google Scholar Blanco, A., Casillas, A., Pérez, A. & de Diaz, A. Multi-label clinical document classification: Impact of label-density. Expert Syst. Appl.138, 112835 (2019). Article Google Scholar Basiri, M. E., Abdar, M., Cifci, M. A., Nemati, S. & Acharya, U. R. A novel method for sentiment classification of drug reviews using fusion of deep and machine learning techniques. Knowl. Based Syst.198, 105949 (2020). Article Google Scholar Hiremath, B. N. & Patil, M. M. Enhancing optimized personalized therapy in clinical decision support system using natural language processing. J King Saud Univ. – Comput Inf. Sci. 34, 2840–2848 (2022). Google Scholar Colón-Ruiz, C., Segura-Bedmar, I. & Martínez, P. Análisis de Sentimiento en el dominio salud: Analizando comentarios sobre fármacos. Procesamiento del. Lenguaje Nat.63, 15–22 (2019). Google Scholar Sutphin, C., Lee, K., Yepes, A. J., Uzuner, Ö. & McInnes, B. T. Adverse drug event detection using reason assignments in FDA drug labels. J. Biomed. Inf.110, 103552 (2020). Article Google Scholar Snyder, C. F. et al. The role of informatics in promoting patient-centered care. Cancer J.17, 211–218 (2011). ArticlePubMedPubMed Central Google Scholar Liu, Z. et al. Entity recognition from clinical texts via recurrent neural network. BMC Med. Inf. Decis. Mak17, (2017). Denecke, K. & Deng, Y. Sentiment analysis in medical settings: New opportunities and challenges. Artif. Intell. Med.64, 17–27 (2015). ArticlePubMed Google Scholar Cambria, E., Poria, S., Gelbukh, A. & Thelwall, M. Sentiment analysis is a big suitcase. IEEE Intell. Syst.32, 74–80 (2017). Article Google Scholar Chen, J. et al. A classified feature representation three-way decision model for sentiment analysis. Appl. Intell.52, 7995–8007 (2022). Article Google Scholar Wu, D. C., Zhong, S., Qiu, R. T. R. & Wu, J. Are customer reviews just reviews? Hotel forecasting using sentiment analysis. Tourism Econ.28, 795–816 (2022). Article Google Scholar Sarsam, S. M., Al-Samarraie, H., Alzahrani, A. I., Alnumay, W. & Smith A. P. A lexicon-based approach to detecting suicide-related messages on Twitter. Biomed. Signal. Process. Control. 65, 102355 (2021). Article Google Scholar Gao, Z., Li, Z., Luo, J. & Li, X. Short Text Aspect-Based Sentiment Analysis Based on CNN + BiGRU. Applied Sciences12, (2022). Yu, W., Cui, F. & Hou, Z. The evolution of consumers’ demand for hotels under the public health crisis: Opinion mining from online reviews. Curr. Issues Tourism. 26, 1974–1990 (2023). Article Google Scholar Yildirim, G. A novel grid-based many-objective swarm intelligence approach for sentiment analysis in social media. Neurocomputing503, 173–188 (2022). Article Google Scholar AL-Smadi, M., Hammad, M. M., Al-Zboon, S. A., AL-Tawalbeh, S. & Cambria, E. Gated recurrent unit with multilingual universal sentence encoder for Arabic aspect-based sentiment analysis. Knowl. Based Syst.261, 107540 (2023). Article Google Scholar Singh, C., Imam, T., Wibowo, S. & Grandhi, S. A deep learning approach for sentiment analysis of COVID-19 reviews. Appl. Sci. (Basel). 12, 3709 (2022). ArticleCAS Google Scholar Marcec, R. & Likic, R. Using Twitter for sentiment analysis towards AstraZeneca/Oxford, Pfizer/BioNTech and Moderna COVID-19 vaccines. Postgrad. Med. J.98, 544–550 (2022). ArticlePubMed Google Scholar Chinnasamy, P. et al. COVID-19 vaccine sentiment analysis using public opinions on Twitter. Mater. Today. 64, 448–451 (2022). CAS Google Scholar Tang, J. E. et al. How are patients reviewing spine surgeons online? A Sentiment Analysis of physician review website written comments. Global Spine J.13, 2107–2114 (2023). ArticlePubMed Google Scholar Chandra, R. & Krishna, A. COVID-19 sentiment analysis via deep learning during the rise of novel cases. PLoS One. 16, e0255615 (2021). ArticleCASPubMedPubMed Central Google Scholar Zulfiker, M. S., Kabir, N., Biswas, A. A., Zulfiker, S. & Uddin, M. S. Analyzing the public sentiment on COVID-19 vaccination in social media: Bangladesh context. Array (N Y). 15, 100204 (2022). ArticlePubMed Google Scholar Alam, K. N. et al. Deep learning-based sentiment analysis of COVID-19 vaccination responses from Twitter data. Comput. Math. Methods Med. 4321131 (2021). (2021). Gräßer, F., Kallumadi, S., Malberg, H. & Zaunseder, S. Aspect-based sentiment analysis of drug reviews applying cross-domain and cross-data learning. in Proceedings of the International Conference on Digital Health (ACM, New York, NY, USA, 2018). (ACM, New York, NY, USA, 2018). (2018). Jain, N., Kumar, A., Singh, S., Singh, C. & Tripathi, S. Deceptive reviews detection using deep learning techniques. in Natural Language Processing and Information Systems 79–91Springer International Publishing, Cham, (2019). Chen, T. et al. Sentiment classification of drug reviews using fuzzy-rough feature selection. in. IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (IEEE, 2019). (2019). Ebrahimi, M., Yazdavar, A. H., Salim, N. & Eltyeb, S. Recognition of side effects as implicit-opinion words in drug reviews. Online Inf. Rev.40, 1018–1032 (2016). Article Google Scholar Jiménez-Zafra, S. M., Martín-Valdivia, M. T. & Molina-González, M. D. Ureña-López, L. A. How do we talk about doctors and drugs? Sentiment analysis in forums expressing opinions for medical domain. Artif. Intell. Med.93, 50–57 (2019). ArticlePubMed Google Scholar Youbi, F. & Settouti, N. Analysis of machine learning and deep learning frameworks for opinion mining on drug reviews. Comput. J.65, 2470–2483 (2022). Article Google Scholar Ru, B., Li, D., Hu, Y. & Yao, L. Serendipity-A machine-learning application for mining serendipitous drug usage from social media. IEEE Trans. Nanobiosci.18, 324–334 (2019). Article Google Scholar Zhang, M. & Geng, G. Adverse drug event detection using a weakly supervised convolutional neural network and recurrent neural network model. Information (Basel) 10, 276 (2019). Colón-Ruiz, C. & Segura-Bedmar, I. Comparing deep learning architectures for sentiment analysis on drug reviews. J. Biomed. Inf.110, 103539 (2020). Article Google Scholar Han, Y., Liu, M. & Jing, W. Aspect-level drug reviews sentiment analysis based on double BiGRU and knowledge transfer. IEEE Access.8, 21314–21325 (2020). Article Google Scholar Hossain, M. D., Azam, M. S., Ali, M. J. & Sabit, H. Drugs rating generation and recommendation from sentiment analysis of drug reviews using machine learning. in 2020 Emerging Technology in Computing, Communication and Electronics (ETCCE) (IEEE, (2020). Liu, S. & Lee, I. Extracting features with medical sentiment lexicon and position encoding for drug reviews. Health Inf. Sci. Syst.7, 11 (2019). ArticlePubMedPubMed Central Google Scholar Xu, Q. A., Chang, V. & Jayne, C. A systematic review of social media-based sentiment analysis: Emerging trends and challenges. Decis. Analytics J.3, 100073 (2022). Article Google Scholar Cascini, F. et al. Social media and attitudes towards a COVID-19 vaccination: A systematic review of the literature. EClinicalMedicine48, 101454 (2022). ArticlePubMedPubMed Central Google Scholar Zunic, A., Corcoran, P. & Spasic, I. Sentiment analysis in health and well-being: Systematic review. JMIR Med. Inf.8, e16023 (2020). Article Google Scholar Pilipiec, P., Liwicki, M. & Bota, A. Using machine learning for pharmacovigilance: A systematic review. Pharmaceutics14, 266 (2022). ArticlePubMedPubMed Central Google Scholar El-kenawy, E. S. M. et al. Greylag Goose Optimization: Nature-inspired optimization algorithm. Expert Syst. Appl.238, 122147 (2024). Article Google Scholar El-kenawy, E. S. M. et al. Football Optimization Algorithm (FbOA): A novel metaheuristic inspired by team strategy dynamics. J. Artif. Intell. Metaheuristics. 8, 21–38 (2024). Article Google Scholar Abdollahzadeh, B. et al. Puma optimizer (PO): A novel metaheuristic optimization algorithm and its application in machine learning. Cluster Comput.27, 5235–5283 (2024). Article Google Scholar Zhang, Y., Jin, R. & Zhou, Z. H. Understanding bag-of-words model: A statistical framework. Int. J. Mach. Learn. Cybern. 1, 43–52 (2010). Article Google Scholar Serrano-Guerrero, J., Bani-Doumi, M., Romero, F. P. & Olivas, J. A. Understanding what patients think about hospitals: A deep learning approach for detecting emotions in patient opinions. Artif. Intell. Med.128, 102298 (2022). ArticlePubMed Google Scholar Pennington, J., Socher, R. & Manning, C. Glove: Global vectors for word representation. in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (Association for Computational Linguistics, Stroudsburg, PA, USA, 2014). (Association for Computational Linguistics, Stroudsburg, PA, USA, 2014). (2014). Moen, S. P. & Ananiadou, T. S. Distributional semantics resources for biomedical text processing. in Proceedings of LBM 39–44 (2013). Shortliffe, E. H. & Sepúlveda, M. J. Clinical decision support in the era of artificial intelligence. JAMA320, 2199–2200 (2018). ArticlePubMed Google Scholar Alzubi, J., Nayyar, A. & Kumar, A. Machine learning from theory to algorithms: An overview. J. Phys. Conf. Ser.1142, 012012 (2018). Article Google Scholar Alpaydin, E. Introduction to Machine Learning (MIT Press, 2020). Islam, M. S. & Ghani, N. A. A novel BiGRUBiLSTM model for multilevel sentiment analysis using deep neural network with BiGRU-BiLSTM. in Lecture Notes in Electrical Engineering 403–414Springer Singapore, Singapore, (2022). Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016). Alsulami, B., Almalawi, A. & Fahad, A. Toward an efficient automatic self-augmentation labeling tool for intrusion detection based on a semi-supervised approach. Appl. Sci. (Basel). 12, 7189 (2022). ArticleCAS Google Scholar Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res.12, 2825–2830 (2011). MathSciNet Google Scholar Hossin, M. & Sulaiman, M. N. A review on evaluation metrics for data classification evaluations. Int. J. Data Min. Knowl. Manag. Process 5, (2015). Babaei Rikan, S. et al. Survival prediction of glioblastoma patients using modern deep learning and machine learning techniques. Sci. Rep.14, 2371 (2024). ArticleADSCASPubMedPubMed Central Google Scholar Ling, C. X., Huang, J., Zhang, H. & AUC A better measure than accuracy in comparing learning algorithms. in Advances in Artificial Intelligence, 329–341 (Springer 2003). Linardatos, P., Papastefanopoulos, V., Kotsiantis, S. & Explainable, A. I. A review of machine learning interpretability methods. Entropy (Basel). 23, 18 (2020). ArticleADSPubMed Google Scholar Mandrekar, J. N. Receiver operating characteristic curve in diagnostic test assessment. J. Thorac. Oncol.5, 1315–1316 (2010). ArticlePubMed Google Scholar Kazmaier, J. & van Vuuren, J. H. The power of ensemble learning in sentiment analysis. Expert Syst. Appl.187, 115819 (2022). Article Google Scholar Baradaran, R. & Amirkhani, H. Ensemble learning-based approach for improving generalization capability of machine reading comprehension systems. Neurocomputing466, 229–242 (2021). Article Google Scholar Rezaeinia, S. M., Rahmani, R., Ghodsi, A. & Veisi, H. Sentiment analysis based on improved pre-trained word embeddings. Expert Syst. Appl.117, 139–147 (2019). Article Google Scholar Download references There is no funding attached to this study. Amir Sorayaie Azar and Samin Babaei Rikan contributed equally to this work SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark Amir Sorayaie Azar, Amin Naemi, Jamshid Bagherzadeh Mohasefi & Uffe Kock Wiil Department of Computer Engineering, Urmia University, Urmia, Iran Amir Sorayaie Azar, Samin Babaei Rikan & Jamshid Bagherzadeh Mohasefi You can also search for this author in PubMedGoogle Scholar You can also search for this author in PubMedGoogle Scholar You can also search for this author in PubMedGoogle Scholar You can also search for this author in PubMedGoogle Scholar You can also search for this author in PubMedGoogle Scholar A.S.A., S.B.R., A.N., J.B.M., and U.K.W. were involved in the conception and design of this study. A.S.A. and S.B.R. prepared the dataset and performed the analysis. A.S.A., S.B.R., A.N., J.B.M., and U.K.W. interpreted the results. A.S.A. and S.B.R. drafted the manuscript, and all authors (A.S.A., S.B.R., A.N., J.B.M., and U.K.W.) contributed to writing the final draft and prepared the final manuscript. All authors read and approved by the final manuscript. Correspondence to Jamshid Bagherzadeh Mohasefi. The authors declare no competing interests. Not applicable. Not applicable. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Below is the link to the electronic supplementary material. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/. Reprints and permissions Sorayaie Azar, A., Babaei Rikan, S., Naemi, A. et al. Predicting patients’ sentiments about medications using artificial intelligence techniques. Sci Rep14, 31928 (2024). https://doi.org/10.1038/s41598-024-83222-9 Download citation Received: Accepted: Published: DOI: https://doi.org/10.1038/s41598-024-83222-9 Anyone you share the following link with will be able to read this content: Sorry, a shareable link is not currently available for this article.
Français 
English