{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:43:35Z","timestamp":1785545015165,"version":"3.56.0"},"reference-count":40,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Unlike one-snap data collection methods that only identify high-risk patients, machine learning models using time-series data can predict adverse events and aid in the timely management of cancer.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and validate machine learning models for sunitinib- and sorafenib-associated thyroid dysfunction using a time-series data collection approach.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Time series data of patients first prescribed sunitinib or sorafenib were collected from a deidentified clinical research database. Logistic regression, random forest, adaptive Boosting, Light Gradient-Boosting Machine, and Gradient Boosting Decision Tree were used to develop the models. Prediction performances were compared using the accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve, and area under the precision-recall curve. The optimal threshold for the best-performing model was selected based on the maximum F1-score. SHapley Additive exPlanations analysis was conducted to assess feature importance and contributions at both the cohort and patient levels.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The training cohort included 609 patients, while the temporal validation cohort had 198 patients. The Gradient Boosting Decision Tree model without resampling outperformed other models, with area under the precision-recall curve of 0.600, area under the receiver operating characteristic curve of 0.876, and F1-score of 0.583 after adjusting the threshold. The SHapley Additive exPlanations analysis identified higher cholesterol levels, longer summed days of medication use, and clear cell adenocarcinoma histology as the most important features. The final model was further integrated into a web-based application.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This model can serve as an explainable adverse drug reaction surveillance system for predicting sunitinib- and sorafenib-associated thyroid dysfunction.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/67767","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T16:31:56Z","timestamp":1744302716000},"page":"e67767-e67767","source":"Crossref","is-referenced-by-count":3,"title":["Web-Based Explainable Machine Learning-Based Drug Surveillance for Predicting Sunitinib- and Sorafenib-Associated Thyroid Dysfunction: Model Development and Validation Study"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5525-6651","authenticated-orcid":false,"given":"Fan-Ying","family":"Chan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7387-1136","authenticated-orcid":false,"given":"Yi-En","family":"Ku","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8166-2844","authenticated-orcid":false,"given":"Wen-Nung","family":"Lie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5535-7152","authenticated-orcid":false,"given":"Hsiang-Yin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,4,10]]},"reference":[{"issue":"4","key":"R1","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1038\/nrclinonc.2009.4","article-title":"Hypothyroidism related to tyrosine kinase inhibitors: an emerging toxic effect of targeted therapy","volume":"6","author":"Torino","journal-title":"Nat Rev Clin Oncol"},{"issue":"9","key":"R2","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1586\/14737140.2014.929501","article-title":"Risk of thyroid dysfunction in patients with solid tumors treated with VEGF receptor tyrosine kinase inhibitors: a critical literature review and meta analysis","volume":"14","author":"Abdel-Rahman","journal-title":"Expert Rev Anticancer Ther"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1634\/theoncologist.2016-0233","article-title":"Pharmacoepidemiology of clinically relevant hypothyroidism and hypertension from sunitinib and sorafenib","volume":"22","author":"Walko","journal-title":"Oncologist"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-019-5610-8","article-title":"\u0399mpact of sunitinib-induced hypothyroidism on survival of patients with metastatic renal cancer","volume":"19","author":"Vasileiadis","journal-title":"BMC Cancer"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/S1470-2045(08)70003-2","article-title":"Incidence and risk of hypertension with sorafenib in patients with cancer: a systematic review and meta-analysis","volume":"9","author":"Wu","journal-title":"Lancet Oncol"},{"issue":"3","key":"R6","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1093\/annonc\/mdr275","article-title":"Could thyroid dysfunction influence outcome in sunitinib-treated metastatic renal cell carcinoma?","volume":"23","author":"Sabatier","journal-title":"Ann Oncol"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.clgc.2012.08.002","article-title":"Thyroid dysfunction in patients treated with sunitinib or sorafenib","volume":"10","author":"Clemons","journal-title":"Clin Genitourin Cancer"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.critrevonc.2019.05.015","article-title":"Tyrosine kinase inhibitors and immune checkpoint inhibitors-induced thyroid disorders","volume":"141","author":"Jannin","journal-title":"Crit Rev Oncol Hematol"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.2196\/43734","article-title":"Explainable machine learning techniques to predict amiodarone-induced thyroid dysfunction risk: multicenter, retrospective study with external validation","volume":"25","author":"Lu","journal-title":"J Med Internet Res"},{"issue":"21","key":"R10","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3390\/cancers13215465","article-title":"Factors associated with thyroid-related adverse events in patients receiving PD-1 or PD-L1 inhibitors using machine learning models","volume":"13","author":"Kim","journal-title":"Cancers (Basel)"},{"issue":"10","key":"R11","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1016\/j.eprac.2024.07.006","article-title":"Development and validation of a prediction model for thyroid dysfunction in patients during immunotherapy","volume":"30","author":"Wang","journal-title":"Endocr Pract"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.12930","article-title":"Development and validation of an explainable machine learning model for major complications after cytoreductive surgery","volume":"5","author":"Deng","journal-title":"JAMA Netw Open"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.102409","article-title":"Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study","volume":"68","author":"Hu","journal-title":"EClinicalMedicine"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107772","article-title":"Interpretable machine-learning model for real-time, clustered risk factor analysis of sepsis and septic death in critical care","volume":"241","author":"Jiang","journal-title":"Comput Methods Programs Biomed"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375830","article-title":"Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods","author":"Slack","journal-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-023-04387-x","article-title":"A novel explainable online calculator for contrast-induced AKI in diabetics: A multi-centre validation and prospective evaluation study","volume":"21","author":"Ma","journal-title":"J Transl Med"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106670","article-title":"Modeling risk of hypoglycemia during and following physical activity in people with type 1 diabetes using explainable mixed-effects machine learning","volume":"155","author":"Mosquera-Lopez","journal-title":"Comput Biol Med"},{"issue":"2","key":"R18","doi-asserted-by":"publisher","first-page":"e137","DOI":"10.1016\/S2589-7500(21)00229-6","article-title":"Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review","volume":"4","author":"Syrowatka","journal-title":"Lancet Digit Health"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","journal-title":"BMJ"},{"key":"R20","unstructured":"van Buuren S Oudshoorn CG . Multivariate Imputation by Chained Equations. Leiden: TNO; 2000. URL: https:\/\/stefvanbuuren.name\/publications\/MICE%20V1.0%20Manual%20TNO00038%202000.pdfISBN: 90-6743-677-1"},{"issue":"9","key":"R21","doi-asserted-by":"publisher","first-page":"3372","DOI":"10.1210\/JC.2015-2329","article-title":"Iodinated contrast media increased the risk of thyroid dysfunction: a 6-year retrospective cohort study","volume":"100","author":"Kornelius","journal-title":"J Clin Endocrinol Metab"},{"issue":"7","key":"R22","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1016\/j.ejca.2012.01.036","article-title":"Incidence of thyroid hormone therapy in patients treated with sunitinib or sorafenib: a cohort study","volume":"48","author":"Feldt","journal-title":"Eur J Cancer"},{"key":"R23","author":"Freund","journal-title":"ICML\u201996: Proceedings of the Thirteenth International Conference on International Conference on Machine Learning"},{"key":"R24","unstructured":"Ke G Meng Q Finley T et al. Lightgbm: A highly efficient gradient boosting decision tree [abstract]. Presented at: 31st Conference on Neural Information Processing Systems (NIPS 2017); Dec 4-9, 2017. 2017.URL: https:\/\/papers.nips.cc\/paper_files\/paper\/2017\/hash\/6449f44a102fde848669bdd9eb6b76fa-Abstract.html [Accessed 31-03-2025]"},{"issue":"5","key":"R25","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","journal-title":"Ann Statist"},{"key":"R26","unstructured":"Snoek J Larochelle H Adams RP . Practical bayesian optimization of machine learning algorithms [abstract]. Presented at: Advances in neural information processing systems; Dec 3-6, 2012; Lake Tahoe, Nevada. 2012.URL: https:\/\/papers.nips.cc\/paper_files\/paper\/2012\/hash\/05311655a15b75fab86956663e1819cd-Abstract.html"},{"key":"R27","unstructured":"Lundberg SM Lee SI . A unified approach to interpreting model predictions. Presented at: 31st Conference on Neural Information Processing Systems (NIPS 2017); Dec 4-9, 2017; Long Beach, CA. 2017.URL: https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf [Accessed 31-03-2025]"},{"issue":"2","key":"R28","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1177\/1740774515602688","article-title":"Fallacies of last observation carried forward analyses","volume":"13","author":"Lachin","journal-title":"Clin Trials"},{"issue":"2","key":"R29","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1056\/NEJMoa060655","article-title":"Sorafenib in advanced clear-cell renal-cell carcinoma","volume":"356","author":"Escudier","journal-title":"N Engl J Med"},{"issue":"22","key":"R30","doi-asserted-by":"publisher","first-page":"3584","DOI":"10.1200\/JCO.2008.20.1293","article-title":"Overall survival and updated results for sunitinib compared with interferon alfa in patients with metastatic renal cell carcinoma","volume":"27","author":"Motzer","journal-title":"J Clin Oncol"},{"issue":"3","key":"R31","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1002\/cncr.25422","article-title":"Hypothyroidism in patients with renal cell carcinoma: blessing or curse?","volume":"117","author":"Schmidinger","journal-title":"Cancer"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107980","article-title":"Machine learning for hospital readmission prediction in pediatric population","volume":"244","author":"Silva","journal-title":"Comput Methods Programs Biomed"},{"key":"R33","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107943","article-title":"Machine learning-based prediction model for distant metastasis of breast cancer","volume":"169","author":"Duan","journal-title":"Comput Biol Med"},{"issue":"3","key":"R34","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1093\/jamia\/ocad217","article-title":"Generalizable pipeline for constructing HIV risk prediction models across electronic health record systems","volume":"31","author":"May","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"R35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","journal-title":"PLoS ONE"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44851-9_15","article-title":"Optimal thresholding of classifiers to maximize F1 measure","volume":"8725","author":"Lipton","journal-title":"Mach Learn Knowl Discov Databases"},{"key":"R37","doi-asserted-by":"publisher","DOI":"10.2174\/1874192401105010076","article-title":"Effects of thyroid dysfunction on lipid profile","volume":"5","author":"Rizos","journal-title":"Open Cardiovasc Med J"},{"issue":"2","key":"R38","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.eururo.2015.07.006","article-title":"Long-term safety of sunitinib in metastatic renal cell carcinoma","volume":"69","author":"Porta","journal-title":"Eur Urol"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0221-y","article-title":"An overview of clinical decision support systems: benefits, risks, and strategies for success","volume":"3","author":"Sutton","journal-title":"NPJ Digit Med"},{"issue":"9","key":"R40","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1093\/ajhp\/zxz018","article-title":"Using artificial intelligence in health-system pharmacy practice: finding new patterns that matter","volume":"76","author":"Flynn","journal-title":"Am J Health Syst Pharm"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e67767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:27:43Z","timestamp":1785536863000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e67767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.2196\/67767","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,10]]},"article-number":"v9i4e67767"}}