{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T21:49:49Z","timestamp":1791236989448,"version":"4.1.0"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pharmacol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To construct a risk prediction model for potentially inappropriate medications (PIM) in elderly stroke patients based on multiple machine-learning algorithms, providing decision support to identify high-risk patients and ensure rational clinical medication use.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 1,252 discharged stroke patients from a tertiary hospital in Anhui Province, China, were included from January 2023 to December 2024. PIM was assessed using the American Geriatrics Society 2023 Updated Beers Criteria<jats:sup>\u00ae<\/jats:sup>. Univariate analysis identified factors potentially associated with PIM, and the least absolute shrinkage and selection operator regression analysis was applied to select variables. The dataset was randomly split into training and internal validations sets in a 7:3 ratio. Additionally, a dataset independent of the training set in terms of time was selected, consisting of 240 stroke patients diagnosed at the same hospital from January to February 2025, to serve as an external validation cohort. Four machine-learning models, Random Forest, Elastic Net (Enet), Support Vector Machine Classifier, and Extreme Gradient Boosting were built using the meaningful variables identified after selection. The evaluation of machine-learning models was carried out through the discrimination, calibration, and clinical utility. SHapley Additive exPlanation (SHAP) values were utilized to rank the importance of features and to interpret the best-performing model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Among 1,252 patients, 675 (53.91%) had PIM, with 107 types and 1,140 occurrences of PIM. Both in internal and external validation cohort, Enet performed the best. The area under the curve (AUC) of Receiver Operating Characteristic (ROC) curve of Enet in external validation set was 0.894 (0.854, 0.933). The model\u2019s calibration curve closely followed the ideal curve, and the clinical decision curve showed high net benefit within a threshold probability range of 15%\u201397%. The results indicate that the Enet prediction model exhibits good accuracy and generalizability, offering a basis for guiding clinical treatment.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The PIM risk prediction model developed using machine-learning can effectively identify PIM, aiding in the implementation of targeted interventions to prevent and reduce the risk of PIM in elderly stroke patients.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fphar.2025.1565420","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T04:10:45Z","timestamp":1747973445000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Development and validation of a machine-learning model for the risk of potentially inappropriate medications in elderly stroke patients"],"prefix":"10.3389","volume":"16","author":[{"given":"Xiaodan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianqian","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuewei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manqin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jad.2012.11.053","article-title":"Antidepressants in elderly: metaregression of double-blind, randomized clinical trials","volume":"147","author":"Calati","year":"2013","journal-title":"J. Affect Disord."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1405838","DOI":"10.3389\/fphar.2024.1405838","article-title":"Dispensing of zolpidem and benzodiazepines in Brazilian private pharmacies: a retrospective cohort study from 2014 to 2021","volume":"15","author":"Carvalho","year":"2024","journal-title":"Front. Pharmacol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1186\/s12877-023-04487-9","article-title":"Polypharmacy, potentially inappropriate medications, and drug-drug interactions in older COVID-19 inpatients","volume":"23","author":"Chen","year":"2023","journal-title":"BMC Geriatr."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.1016\/j.jval.2024.06.005","article-title":"Traditional methods hold their ground against machine learning in predicting potentially inappropriate medication use in older adults","volume":"27","author":"Chiu","year":"2024","journal-title":"Value Health"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1016\/j.eururo.2014.11.025","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement","volume":"67","author":"Collins","year":"2015","journal-title":"Eur. Urol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1159\/000529445","article-title":"Cognitive behavioral therapy for late-life depression (CBTlate): results of a multicenter, randomized, observer-blinded, controlled trial","volume":"92","author":"Dafsari","year":"2023","journal-title":"Psychother. Psychosom."},{"key":"B7","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/j.neurol.2023.08.008","article-title":"Insomnia in neurological disorders: prevalence, mechanisms, impact and treatment approaches","volume":"179","author":"de Bergeyck","year":"2023","journal-title":"Rev. Neurol. Paris."},{"key":"B8","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/S0140-6736(22)00878-9","article-title":"Comparative effects of pharmacological interventions for the acute and long-term management of insomnia disorder in adults: a systematic review and network meta-analysis","volume":"400","author":"De Crescenzo","year":"2022","journal-title":"Lancet"},{"key":"B9","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1136\/svn-2020-000691","article-title":"Patterns of antidepressant therapy and clinical outcomes among ischaemic stroke survivors","volume":"6","author":"Etherton","year":"2021","journal-title":"Stroke Vasc. Neurol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1001\/jamapsychiatry.2023.5060","article-title":"Components and delivery formats of cognitive behavioral therapy for chronic insomnia in adults: a systematic review and component network meta-analysis","volume":"81","author":"Furukawa","year":"2024","journal-title":"JAMA Psychiatry"},{"key":"B11","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1016\/j.arthro.2021.08.009","article-title":"A machine-learning algorithm to predict the likelihood of prolonged opioid use following arthroscopic hip surgery","volume":"38","author":"Grazal","year":"2022","journal-title":"J. Arthrosc. Relat. Surg."},{"key":"B12","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Crit. Care"},{"key":"B13","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1017\/S1352465818000061","article-title":"Development and evaluation of a cognitive behavioural intervention for chronic post-stroke insomnia","volume":"46","author":"Herron","year":"2018","journal-title":"Behav. Cognitive Psychotherapy"},{"key":"B14","doi-asserted-by":"publisher","first-page":"915","DOI":"10.6004\/jnccn.2022.7033","article-title":"Association of polypharmacy and potentially inappropriate medications with frailty among older adults with blood cancers","volume":"20","author":"Hshieh","year":"2022","journal-title":"J. Natl. Compr. Cancer Netw."},{"key":"B15","doi-asserted-by":"publisher","first-page":"201","DOI":"10.12114\/j.issn.1007-9572.2023.0459","article-title":"Analysis of the current status of ischemic stroke Co-morbidity and Co-morbidity patterns in middle-aged based on data from tertiary hospitals in henan Province","volume":"27","author":"Hu","year":"","journal-title":"Chin. General Pract."},{"key":"B16","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1007\/s11096-024-01730-0","article-title":"Amodel for identifying potentially inappropriate medication used in older people with dementia: a machine learning study","volume":"46","author":"Hu","year":"","journal-title":"Int. J. Clin. Pharm."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1672-3384.2023.08.014","article-title":"Analysis of potentially inappropriate drug use in elderly tumor inpatients and construction of early warning model","volume":"7","author":"Jiang","year":"2023","journal-title":"Clin. Medicat. J."},{"key":"B18","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1001\/jama.2017.5706","article-title":"Management of depression in older adults: a review","volume":"317","author":"Kok","year":"2017","journal-title":"J. Am. Med. Assoc."},{"key":"B19","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1161\/HYPERTENSIONAHA.119.14223","article-title":"Risk of developing hypokalemia in patients with hypertension treated with combination antihypertensive therapy","volume":"75","author":"Krogager","year":"2020","journal-title":"Hypertension"},{"key":"B20","doi-asserted-by":"publisher","first-page":"2357232","DOI":"10.1080\/07853890.2024.2357232","article-title":"Polypharmacy and potentially inappropriate prescribing of benzodiazepines in older nursing home residents","volume":"56","author":"Kummer","year":"2024","journal-title":"Ann. Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"984750","DOI":"10.3389\/fpubh.2022.984750","article-title":"Predictive models based on machine learning for bone metastasis in patients with diagnosed colorectal cancer","volume":"10","author":"Li","year":"2022","journal-title":"Front. Public Health"},{"key":"B22","doi-asserted-by":"publisher","first-page":"107116","DOI":"10.1016\/j.ypmed.2022.107116","article-title":"Characteristics of statewide prescription drug monitoring programs and potentially inappropriate opioid prescribing to patients with non-cancer chronic pain: a machine learning application","volume":"161","author":"Lin","year":"2022","journal-title":"Prev. Med. Balt."},{"key":"B23","doi-asserted-by":"publisher","first-page":"00755","DOI":"10.3389\/fpsyt.2020.00755","article-title":"The effects of benzodiazepine use and abuse on cognition in the elders: a systematic review and meta-analysis of comparative studies","volume":"11","author":"Liu","year":"2020","journal-title":"Front. Psychiatry"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2495","DOI":"10.1111\/jgs.18353","article-title":"Potentially inappropriate medication use is associated with increased risk of incident disability in healthy older adults","volume":"71","author":"Lockery","year":"2023","journal-title":"J. Am. Geriatr. Soc."},{"key":"B25","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s11096-022-01416-5","article-title":"Polypharmacy and potentially inappropriate medications in stroke rehabilitation: prevalence and association with outcomes","volume":"44","author":"Matsumoto","year":"2022","journal-title":"Int. J. Clin. Pharm."},{"key":"B26","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1080\/09602011.2017.1326945","article-title":"Cognitive behavioural therapy for post-stroke fatigue and sleep disturbance: a pilot randomised controlled trial with blind assessment","volume":"29","author":"Nguyen","year":"2019","journal-title":"Neuropsychol. Rehabil."},{"key":"B27","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1007\/s41999-023-00777-y","article-title":"STOPP\/START criteria for potentially inappropriate prescribing in older people: version 3","volume":"14","author":"O\u2019Mahony","year":"2023","journal-title":"Eur. Geriatr. Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1111\/ene.15137","article-title":"Antidepressant use and stroke or mortality risk in the elderly","volume":"29","author":"\u00d6n","year":"2022","journal-title":"Eur. J. Neurol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"136353","DOI":"10.1016\/j.chemosphere.2022.136353","article-title":"Machine learning and deep learning modeling and simulation for predicting PM2.5 concentrations","volume":"308","author":"Peng","year":"2022","journal-title":"Chemosphere"},{"key":"B30","doi-asserted-by":"publisher","first-page":"2148","DOI":"10.1111\/jgs.13057","article-title":"Electronic surveillance and pharmacist intervention for vulnerable older inpatients on high-risk medication regimens","volume":"62","author":"Peterson","year":"2014","journal-title":"J. Am. Geriatr. Soc."},{"key":"B31","doi-asserted-by":"publisher","first-page":"104142","DOI":"10.1016\/j.ajp.2024.104142","article-title":"Clinical High-Risk for Psychosis (CHR-P) circa 2024: synoptic analysis and synthesis of contemporary treatment guidelines","volume":"100","author":"Poletti","year":"2024","journal-title":"Asian J. Psychiatr."},{"key":"B32","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1186\/s12916-023-03021-3","article-title":"Healthcare fragmentation, multimorbidity, potentially inappropriate medication, and mortality: a Danish nationwide cohort study","volume":"21","author":"Prior","year":"2023","journal-title":"BMC Med."},{"key":"B33","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1186\/s12877-022-02757-6","article-title":"Efficacy and safety of Z-substances in the management of insomnia in older adults: a systematic review for the development of recommendations to reduce potentially inappropriate prescribing","volume":"22","author":"Scharner","year":"2022","journal-title":"BMC Geriatr."},{"key":"B34","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1002\/gps.4999","article-title":"Prescription opioid and benzodiazepine misuse is associated with suicidal ideation in older adults","volume":"34","author":"Schepis","year":"2019","journal-title":"Int. J. Geriatr. Psychiatry"},{"key":"B35","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1111\/ajag.13046","article-title":"A comprehensive look at explicit screening tools for potentially inappropriate medication: a systematic scoping review","volume":"41","author":"Schiavo","year":"2022","journal-title":"Australas. J. Ageing"},{"key":"B36","doi-asserted-by":"publisher","first-page":"e2417988","DOI":"10.1001\/jamanetworkopen.2024.17988","article-title":"Potentially inappropriate medication use in primary care in Switzerland","volume":"7","author":"Schietzel","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e2248559","DOI":"10.1001\/jamanetworkopen.2022.48559","article-title":"Development and validation of a machine learning model to estimate risk of adverse outcomes within 30 Days of opioid dispensation","volume":"5","author":"Sharma","year":"2022","journal-title":"JAMA Netw. Open"},{"key":"B38","doi-asserted-by":"publisher","first-page":"5085","DOI":"10.12307\/2022.891","article-title":"Construction of a nomogram model for predicting bone mass loss in middle-aged men","volume":"26","author":"Shen","year":"2022","journal-title":"Chin. J. Tissue Eng. Res."},{"key":"B39","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1002\/acn3.50817","article-title":"Comparison of machine learning models for seizure prediction in hospitalized patients","volume":"6","author":"Struck","year":"2019","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"B40","doi-asserted-by":"publisher","first-page":"104733","DOI":"10.1016\/j.archger.2022.104733","article-title":"Potentially inappropriate medications increase while prevalence of polypharmacy\/hyperpolypharmacy decreases in Japan: a comparison of nationwide prescribing data","volume":"102","author":"Suzuki","year":"2022","journal-title":"Arch. Gerontol. Geriatr."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.3969\/j.issn.1004-2407.2021.06.028","article-title":"Analysis of potentially inappropriate medication in elderly stroke in patients","volume":"6","author":"Wang","year":"2021","journal-title":"Northwest Pharm. J."},{"key":"B42","doi-asserted-by":"publisher","first-page":"101145","DOI":"10.1016\/j.lanepe.2024.101145","article-title":"Benefits and harms associated with the use of AI-related algorithmic decision-making systems by healthcare professionals: a systematic review","volume":"48","author":"Wilhelm","year":"2025","journal-title":"Lancet Regional Health Eur."},{"key":"B43","doi-asserted-by":"publisher","first-page":"1092721","DOI":"10.3389\/fonc.2023.1092721","article-title":"Risk factors and a new nomogram for predicting brain metastasis from lung cancer: a retrospective study","volume":"13","author":"Wu","year":"2023","journal-title":"Front. Oncol."},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.14109\/j.cnki.xyylc.2024.07.09","article-title":"Potential medication safety risks and Lasso-Logistic regression analysis in hypertension complicated with cerebral infarction patients","author":"Ye","year":"2024"},{"key":"B45","doi-asserted-by":"publisher","first-page":"107876","DOI":"10.1016\/j.compbiomed.2023.107876","article-title":"A machine learning-based universal outbreak risk prediction tool","volume":"169","author":"Zhang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1097\/CM9.0000000000003426","article-title":"Prescribing rate, healthcare utilization, and expenditure of older adults using potentially inappropriate medications in China: a nationwide cross-sectional study","author":"Zhao","year":"2025","journal-title":"Chin. Med. J. Engl."},{"key":"B47","doi-asserted-by":"publisher","first-page":"105394","DOI":"10.1016\/j.jamda.2024.105394","article-title":"Association between potentially inappropriate medication and mortality risk in older adults: a systematic review and meta-analysis","volume":"26","author":"Zhou","year":"2025","journal-title":"J. Am. Med. Dir. Assoc."},{"key":"B48","doi-asserted-by":"publisher","first-page":"1265463","DOI":"10.3389\/fphar.2023.1265463","article-title":"Evaluation of potentially inappropriate medications for the elderly according to beers, STOPP, START, and Chinese criteria","volume":"14","author":"Zhu","year":"2023","journal-title":"Front. Pharmacol."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2025.1565420\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T04:10:52Z","timestamp":1747973452000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2025.1565420\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":48,"alternative-id":["10.3389\/fphar.2025.1565420"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2025.1565420","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"article-number":"1565420"}}