{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:53:06Z","timestamp":1775645586121,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pharmaceuticals"],"abstract":"<jats:p>Introduction: Drug side effects are a relevant problem for patient safety and public health, and traditional methods have limitations in capturing complex patterns between clinical and pharmacological variables. Objective: To evaluate machine learning models to probabilistically predict multiple side effects associated with drug use. Materials and methods: A cross-sectional computational study was carried out with data from 1000 medications that included clinical condition, dosage and duration of treatment. Random Forest, Decision Tree, Support Vector Classifier and KNN were trained and optimized using Grid Search and an 80:20 split for training and testing. Chi-square tests and Principal Component Analysis were applied to explore associations and overlap between categories. Results: Significant associations were found between side effects and clinical condition (p &lt; 0.05) and the drug administered (p &lt; 0.05). The PCA showed a high overlap between categories, which justified a probabilistic approach. Tree-based models showed better performance (accuracy \u2248 0.35). Conclusions: Prediction of side effects is a multifactorial and non-deterministic problem; probabilistic machine learning models allow for estimating several plausible adverse events and can support clinical decision-making and pharmacovigilance.<\/jats:p>","DOI":"10.3390\/ph19040595","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T09:49:44Z","timestamp":1775641784000},"page":"595","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Output Probabilistic Prediction of Drug Side Effects Using Classical Machine Learning Algorithms"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2523-6687","authenticated-orcid":false,"given":"Diego","family":"Quiguango Farias","sequence":"first","affiliation":[{"name":"Carrera Ciencias de la Salud, Universidad de Las Americas (UDLA), Quito 170516, Ecuador"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2915-2422","authenticated-orcid":false,"given":"Juan","family":"Sarasti Espejo","sequence":"additional","affiliation":[{"name":"Carrera Ciencias de la Salud, Universidad de Las Americas (UDLA), Quito 170516, Ecuador"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4091-2763","authenticated-orcid":false,"given":"Marlene","family":"Arce Salcedo","sequence":"additional","affiliation":[{"name":"Carrera Ciencias de la Salud, Universidad de Las Americas (UDLA), Quito 170516, Ecuador"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5660-3941","authenticated-orcid":false,"given":"Byron","family":"Velasquez Ron","sequence":"additional","affiliation":[{"name":"Carrera de Odontolog\u00eda, Universidad de Las Americas (UDLA), Quito 170516, Ecuador"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.mpaic.2025.11.012","article-title":"Adverse drug reactions","volume":"27","author":"Evans","year":"2026","journal-title":"Anaesth. Intensive Care Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1136\/bmjqs-2022-015275","article-title":"Adverse drug events leading to medical emergency team activation in hospitals: What can we learn?","volume":"32","author":"Schepel","year":"2023","journal-title":"BMJ Qual. Saf."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Khouri, C., Nguyen, T., Revol, B., Lepelley, M., Pariente, A., Roustit, M., and Cracowski, J.-L. (2021). Leveraging the variability of pharmacovigilance disproportionality analyses to improve signal detection performances. Front. Pharmacol., 12.","DOI":"10.3389\/fphar.2021.668765"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.jbi.2015.02.004","article-title":"Utilizing social media data for pharmacovigilance","volume":"54","author":"Sarker","year":"2015","journal-title":"J. Biomed. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N. Engl. J. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s42452-025-06991-6","article-title":"Deep learning and artificial intelligence for drug discovery: Application, challenge, and future perspectives","volume":"7","author":"Ali","year":"2025","journal-title":"Discov. Appl. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","article-title":"The rise of deep learning in drug discovery","volume":"23","author":"Chen","year":"2018","journal-title":"Drug Discov. Today"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.procs.2023.09.087","article-title":"Machine learning methods for predicting adverse drug reactions in hospitalized patients","volume":"225","author":"Wolff","year":"2023","journal-title":"Procedia Comput. Sci."},{"key":"ref_9","first-page":"1238","article-title":"Pharmacogenomics in drug development: From discovery to clinical trials","volume":"54","author":"Rani","year":"2025","journal-title":"Pharmacogenomics J."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gupta, D., and Ramsundar, B. (2024, January 19\u201321). Ensemble methods for ADR prediction. Proceedings of the IEEE\/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Wilmington, DE, USA.","DOI":"10.1109\/CHASE60773.2024.00043"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1093\/bib\/bbx099","article-title":"Facilitating prediction of adverse drug reactions by using knowledge graphs and multi-label learning models","volume":"20","author":"Vandenbussche","year":"2019","journal-title":"Brief. Bioinform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1007\/s10462-024-10811-5","article-title":"Big data and predictive analytics: A systematic review of applications","volume":"57","author":"Jamarani","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med."},{"key":"ref_14","unstructured":"Amran, M. (2021). Adverse drug reactions and pharmacovigilance. Pharmacovigilance, IntechOpen."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Oei, S., Bakkes, T., Mischi, M., Bouwman, R., Sloun, R., and Turco, S. (2025). Artificial intelligence in clinical decision support and the prediction of adverse events. Front. Digit. Health, 7.","DOI":"10.3389\/fdgth.2025.1403047"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"Beam","year":"2018","journal-title":"JAMA"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: The convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Roshandel, G., Ghasemi-Kebria, F., and Malekzadeh, R. (2024). Colorectal cancer: Epidemiology, risk factors, and prevention. Cancers, 16.","DOI":"10.3390\/cancers16081530"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1016\/j.dcan.2021.12.001","article-title":"Entropy-based redundancy analysis and information screening","volume":"9","author":"Li","year":"2023","journal-title":"Digit. Commun. Netw."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1002\/bimj.201300068","article-title":"Probability estimation with machine learning methods for dichotomous and multicategory outcome: Theory","volume":"56","author":"Kruppa","year":"2014","journal-title":"Biom. J."},{"key":"ref_21","unstructured":"Tyralis, H., and Papacharalampous, G. (2022). A review of probabilistic forecasting and prediction with machine learning. arXiv."},{"key":"ref_22","unstructured":"Bent\u00e9jac, C., Cs\u00f6rg\u0151, A., and Mart\u00ednez-Mu\u00f1oz, G. (2019). A comparative analysis of XGBoost. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Jagadeesha, N., and Bhandari, N. (2021). Computational complexity of gradient descent algorithm. TechRxiv.","DOI":"10.36227\/techrxiv.14544000.v1"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"012031","DOI":"10.1088\/1742-6596\/1994\/1\/012031","article-title":"Multi-label classification of research papers using multi-label k-nearest neighbour algorithm","volume":"1994","author":"Li","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"102837","DOI":"10.1016\/j.ebiom.2020.102837","article-title":"Machine learning guided association of adverse drug reactions with in vitro target-based pharmacology","volume":"57","author":"Ietswaart","year":"2020","journal-title":"EBioMedicine"},{"key":"ref_26","first-page":"313","article-title":"Predicting adverse drug reactions on distributed health data using federated learning","volume":"2019","author":"Choudhury","year":"2020","journal-title":"AMIA Annu. Symp. Proc."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"39","DOI":"10.12691\/ajams-8-2-1","article-title":"Detecting multicollinearity in regression analysis","volume":"8","author":"Shrestha","year":"2020","journal-title":"Am. J. Appl. Math. Stat."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1038\/s41467-019-09186-x","article-title":"Network-based prediction of drug combinations","volume":"10","author":"Cheng","year":"2019","journal-title":"Nat. Commun."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/s13278-024-01239-4","article-title":"EADR: An ensemble learning method for detecting adverse drug reactions from Twitter","volume":"14","author":"Keyvanpour","year":"2024","journal-title":"Soc. Netw. Anal. Min."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"ehdi019","DOI":"10.63946\/ehdi\/17369","article-title":"Developing and validating predictive models for adverse drug reactions using electronic health records: A narrative review","volume":"1","author":"Nwokedi","year":"2025","journal-title":"Epidemiol. Health Data Insights"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Afdhal, D., Ananta, K.W., and Hartono, W.S. (2020, January 17\u201318). Adverse drug reactions prediction using multi-label linear discriminant analysis and multi-label learning. Proceedings of the International Conference on Advanced Computer Science and Information Systems (ICACSIS), Depok, Indonesia.","DOI":"10.1109\/ICACSIS51025.2020.9263166"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1038\/s43586-022-00184-w","article-title":"Principal component analysis","volume":"2","author":"Greenacre","year":"2022","journal-title":"Nat. Rev. Methods Primers"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1038\/s41698-024-00691-x","article-title":"Multi-output prediction of dose-response curves enables drug repositioning and biomarker discovery","volume":"8","author":"Gutierrez","year":"2024","journal-title":"NPJ Precis. Oncol."},{"key":"ref_34","first-page":"100158","article-title":"A multioutput classifier model for breast cancer treatment prediction","volume":"10","author":"Ruhaiyem","year":"2024","journal-title":"Intell.-Based Med."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1007\/s40264-022-01190-3","article-title":"Quantitative prediction of adverse event probability due to pharmacokinetic interactions","volume":"45","author":"Tod","year":"2022","journal-title":"Drug Saf."},{"key":"ref_36","first-page":"51","article-title":"The importance of early detection in disease management","volume":"2","author":"Setyati","year":"2024","journal-title":"J. World Future Med. Health Nurs."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Gheorghita, F.-I., Bocanet, V.-I., and Iantovics, L.B. (2025). Machine learning-based drug\u2013drug interaction prediction: A critical review of models, limitations, and data challenges. Front. Pharmacol., 16.","DOI":"10.3389\/fphar.2025.1632775"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Foody, G.M. (2023). Challenges in the real world use of classification accuracy metrics: From recall and precision to the Matthews correlation coefficient. PLoS ONE, 18.","DOI":"10.1371\/journal.pone.0291908"},{"key":"ref_39","unstructured":"Grandini, M., Bagli, E., and Visani, G. (2020). Metrics for multi-class classification: An overview. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"103725","DOI":"10.1016\/j.jbi.2021.103725","article-title":"Predicting opioid overdose risk of patients with opioid prescriptions using electronic health records based on temporal deep learning","volume":"116","author":"Dong","year":"2021","journal-title":"J. Biomed. Inform."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1007\/s40264-022-01176-1","article-title":"Artificial intelligence based on machine learning in pharmacovigilance: A scoping review","volume":"45","author":"Kompa","year":"2022","journal-title":"Drug Saf."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1016\/j.procs.2025.09.235","article-title":"Machine learning-based adverse drug reaction prediction: Model comparisons, feature optimization and generative AI challenges","volume":"270","author":"Cucos","year":"2025","journal-title":"Procedia Comput. Sci."},{"key":"ref_43","first-page":"6","article-title":"Comparison of multiclass classification techniques using dry bean dataset","volume":"4","author":"Khan","year":"2023","journal-title":"Int. J. Cogn. Comput. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1007\/s11096-025-01975-3","article-title":"Artificial intelligence in pharmacovigilance: A narrative review and practical experience with an expert-defined Bayesian network tool","volume":"47","author":"Algarvio","year":"2025","journal-title":"Int. J. Clin. Pharm."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10543406.2024.2365976","article-title":"Drug safety assessment by machine learning models","volume":"18","author":"Xi","year":"2024","journal-title":"J. Biopharm. Stat."}],"container-title":["Pharmaceuticals"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/4\/595\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:03:24Z","timestamp":1775642604000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8247\/19\/4\/595"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["ph19040595"],"URL":"https:\/\/doi.org\/10.3390\/ph19040595","relation":{},"ISSN":["1424-8247"],"issn-type":[{"value":"1424-8247","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,8]]}}}