{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:51:20Z","timestamp":1753890680539,"version":"3.41.2"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T00:00:00Z","timestamp":1706832000000},"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. Digit. Health"],"abstract":"Introduction<\/jats:title>Individuals in the midst of a mental health crisis frequently exhibit instability and face an elevated risk of recurring crises in the subsequent weeks, which underscores the importance of timely intervention in mental healthcare. This work presents a data-driven method to infer the mental state of a patient during the weeks following a mental health crisis by leveraging their historical data. Additionally, we propose a policy that determines the necessary duration for closely monitoring a patient after a mental health crisis before considering them stable.<\/jats:p><\/jats:sec>Methods<\/jats:title>We model the patient\u2019s mental state as a Hidden Markov Process, partially observed through mental health crisis events. We introduce a closed-form solution that leverages the model parameters to optimally estimate the risk of future mental health crises. Our policy determines a patient should be closely monitored when their estimated risk of crisis exceeds a predefined threshold. The method\u2019s performance is evaluated using both simulated data and a real-world dataset comprising 162 anonymized psychiatric patients.<\/jats:p><\/jats:sec>Results<\/jats:title>In the simulations, 96.2<\/mml:mn>%<\/mml:mi><\/mml:math><\/jats:inline-formula> of the patients identified by the policy were in an unstable state, achieving a F1 score of 0.74<\/mml:mn><\/mml:math><\/jats:inline-formula>. In the real-world dataset, the policy yielded an F1 score of 0.79, with a sensitivity of 79.8<\/mml:mn>%<\/mml:mi><\/mml:math><\/jats:inline-formula> and specificity of 88.9<\/mml:mn>%<\/mml:mi><\/mml:math><\/jats:inline-formula>. Under this policy, 67.3<\/mml:mn>%<\/mml:mi><\/mml:math><\/jats:inline-formula> of the patients should undergo close monitoring for one week, 21.6<\/mml:mn>%<\/mml:mi><\/mml:math><\/jats:inline-formula> during 2 weeks or more, while 11.1<\/mml:mn>%<\/mml:mi><\/mml:math><\/jats:inline-formula> do not need close monitoring.<\/jats:p><\/jats:sec>Discussion<\/jats:title>The simulation results provide compelling evidence that the method is effective under the specified assumptions. When applied to actual psychiatric patients, the proposed policy showed significant potential for providing an individualized assessment of the required duration for close and automatic monitoring after a mental health crisis to reduce the relapse risks.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdgth.2024.1322555","type":"journal-article","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T04:54:33Z","timestamp":1706849673000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Individualized post-crisis monitoring of psychiatric patients via Hidden Markov models"],"prefix":"10.3389","volume":"6","author":[{"given":"Roger","family":"Garriga","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vicen\u00e7","family":"G\u00f3mez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G\u00e1bor","family":"Lugosi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,2,2]]},"reference":[{"volume-title":"Navigating a Mental Health Crises","year":"2018","key":"B1"},{"volume-title":"Principles of Preventive Psychiatry","year":"1964","author":"Caplan","key":"B2"},{"key":"B3","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1080\/01612840.2017.1300841","article-title":"Evaluating an alternative to the emergency department for adults in mental health crisis","volume":"38","author":"Heyland","year":"2017","journal-title":"Issues Ment Health Nurs"},{"key":"B4","first-page":"35","article-title":"Treatment of psychiatric patients in emergency settings","volume":"17","author":"Zeller","year":"2010","journal-title":"Prim Psychiatry"},{"key":"B5","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1111\/j.1440-1630.1991.tb01710.x","article-title":"A role for occupational therapy in crisis intervention, prevention","volume":"38","author":"Miller","year":"1991","journal-title":"Aust Occup Ther J"},{"volume-title":"Crisis Intervention: Studies in Community Care","year":"1976","author":"Morrice","key":"B6"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.1214\/aoms\/1177699147","article-title":"Statistical inference for probabilistic functions of finite state Markov chains","volume":"37","author":"Baum","year":"1966","journal-title":"Ann Math Stat"},{"key":"B8","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1146\/annurev-biodatasci-092820-033938","article-title":"Probabilistic machine learning for healthcare","volume":"4","author":"Chen","year":"2021","journal-title":"Annu Rev Biomed Data Sci"},{"year":"","author":"Ansari","key":"B9"},{"key":"B10","doi-asserted-by":"publisher","first-page":"14411","DOI":"10.3390\/ijerph192114411","article-title":"A depression-risk mental pattern identified by hidden Markov model in undergraduates","volume":"19","author":"Jiang","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1770","DOI":"10.1109\/JBHI.2020.3031263","article-title":"Adaptive symptom monitoring using hidden Markov models\u2014an application in ecological momentary assessment","volume":"25","author":"Hulme","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"year":"","author":"Chen","key":"B12"},{"key":"B13","doi-asserted-by":"publisher","first-page":"5619","DOI":"10.1007\/s00521-022-07845-7","article-title":"Prediction of schizophrenia from activity data using hidden Markov model parameters","volume":"35","author":"Boeker","year":"2023","journal-title":"Neural Comput Appl"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TII.2016.2610191","article-title":"Em-psychiatry: An ambient intelligent system for psychiatric emergency","volume":"12","author":"Alam","year":"2016","journal-title":"IEEE Trans Ind Inform"},{"key":"B15","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1038\/s41591-022-01811-5","article-title":"Machine learning model to predict mental health crises from electronic health records","volume":"28","author":"Garriga","year":"2022","journal-title":"Nat Med"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2023.101260","article-title":"Combining clinical notes with structured electronic health records enhances the prediction of mental health crisis","volume":"4","author":"Garriga","year":"2023","journal-title":"Cell Rep Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"100861","DOI":"10.1016\/j.xcrm.2022.100861","article-title":"Ai in medicine: Where are we now, where are we going?","volume":"3","author":"Shandhi","year":"2022","journal-title":"Cell Rep Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"127","DOI":"10.2147\/PGPM.S198225","article-title":"Challenges, future prospects of precision medicine in psychiatry","author":"Manchia","year":"2020","journal-title":"Pharmgenomics Pers Med"},{"key":"B19","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1214\/aoms\/1177697196","article-title":"A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains","volume":"41","author":"Baum","year":"1970","journal-title":"Ann Math Stat"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447067","article-title":"Statistical and computational guarantees for the Baum\u2013Welch algorithm","author":"Yang","year":"2015","journal-title":"2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804779","volume-title":"Bayesian Reasoning and Machine Learning","author":"Barber","year":"2012"},{"year":"","author":"Chinchor","key":"B22"},{"key":"B23","first-page":"111","article-title":"Higher-order Markov chains","volume-title":"Markov Chains: Models, Algorithms and Applications. International Series in Operations Research & Management Science","author":"Ching","year":"2006"},{"year":"","author":"Seifert","key":"B24"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2024.1322555\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T04:54:48Z","timestamp":1706849688000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2024.1322555\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,2]]},"references-count":24,"alternative-id":["10.3389\/fdgth.2024.1322555"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2024.1322555","relation":{},"ISSN":["2673-253X"],"issn-type":[{"type":"electronic","value":"2673-253X"}],"subject":[],"published":{"date-parts":[[2024,2,2]]},"article-number":"1322555"}}