[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123686-en":3,"doc-seo-123686-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123686,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Predicting Undesired Treatment Outcome with Machine Learning in Multi-Site Mental Healthcare","Mental healthcare faces a persistent challenge in predicting which treatments will work for which patients. This multi-site study aimed to forecast patient treatment response during care using routinely collected, commonly available data in Dutch basic mental healthcare, and to compare model performance across three Netherlands mental healthcare organizations. Anonymized datasets from three organizations (n=6,452) supported three LASSO regression runs, with internal cross-validation per site and external validation across sites. AUC values for internal and external validation ranged from 0.77 to 0.80, supporting robust, generalizable automated risk signaling for poor outcomes.","JMIR Preprints  \nPredicting Undesired Treatment Outcome with  \nMachine Learning in multi-site Mental Healthcare  \nKasper Van Mens, Joran Lokkerbol, Ben Wijnen, Richard Janssen, Robert deLange, Bea Tiemens  \nSubmitted to: JMIR Medical Informatics  \non: November 15, 2022  \nDisclaimer: © The authors. All rights reserved. This is a privileged document currently under peer-review/communityreview. Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website forreview purposes only. While the final peer-reviewed paper may be licensed under a CC BY license on publication, at thisstage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.  \nhttps://preprints.jmir.org/preprint/44322 [unpublished, peer-reviewed preprint]  \nJMIR Preprints Van Mens et al  \nTable of Contents  \nOriginal Manuscript....................................................................................................................................................................... 4  \nSupplementary Files..................................................................................................................................................................... 24  \nFigures ......................................................................................................................................................................................... 25  \nFigure 0...................................................................................................................................................................................... 26  \nhttps://preprints.jmir.org/preprint/44322 [unpublished, peer-reviewed preprint]  \nPredicting Undesired Treatment Outcome with Machine Learning in multi -site Mental Healthcare  \n\n|  |\n| --- |\n| Kasper Van Mens 1 MSc; Joran Lokkerbol2 PhD; Ben Wijnen3 PhD; Richard Janssen4 PhD; Robert de Lange5 PhD;Bea Tiemens 1 PhD   |\n| 1Radboud University Nijmegen NL  \u003Cbr>2Centre of Economic Evaluation & Machine Learning, Trimbos Institute (Netherlands Institute of Mental Health) Utrecht NL3Department of Clinical Epidemiology and Medical Technology Assessment, Maastricht University Medical Centre Maastricht NL4Erasmus University Rotterdam, Erasmus School of Health Policy & Management / Health Care Governance Rotterdam NL5Alan Turing Institute Almere NL  \u003Cbr>Corresponding Author:  \u003Cbr>Kasper Van Mens MScRadboud University  \u003Cbr>Houtlaan 4NijmegenNL  \u003Cbr>Abstract   |\n\nBackground: It remains a challenge to predict which treatment will work for which patient in mental healthcare.  \nObjective: The aims ofthis multi-site study were two-fold: 1) to predict patient’s response to treatment, during treatment, inDutch basic mental healthcare using commonly available data from routine care; and 2) to compare the performance of thesemachine learning models across three different mental healthcare organizations in the Netherlands by using clinicallyinterpretable models.  \nMethods: Using anonymized datasets from three different mental healthcare organizations in the Netherlands (n = 6,452), weapplied three times a lasso regression to predict treatment outcome. The algorithms were internally validated with cross -validation within each site and externally validated on the data from the other sites.  \nResults: The performance of the algorithms, measured by the AUC of the internal validations as well as the correspondingexternal validations, were in the range of 0.77 to 0.80.  \nConclusions: Machine learning models provide a robust and generalizable approach in automated risk signaling technology toidentify cases at risk of poor treatment outcome. Results of this study hold substantial implications for clinical practice bydemonstrating that model performance of a model derived from one site is similar when applied to another site (i.e. good externalvalidation) .  \n(JMIR Preprints 15/11/2022:44322)  \nDOI: https://doi.org/10.2196/preprints.44","cbCaiduYPIMRkadL","https://ap.wps.com/l/cbCaiduYPIMRkadL","pdf",629795,1,26,"English","en",105,"# Original Manuscript\n## Abstract\n## Methods\n## Results\n## Conclusions\n# Supplementary Files\n# Figures\n## Figure 0","[{\"question\":\"What was the primary objective of this multi-site study?\",\"answer\":\"To predict patients’ treatment response during Dutch basic mental healthcare using routine care data, and to compare machine learning performance across three mental healthcare organizations in the Netherlands.\"},{\"question\":\"How were the machine learning models developed and validated?\",\"answer\":\"Models used anonymized datasets from three organizations and applied three LASSO regression runs. Performance was assessed with internal cross-validation within each site and external validation on data from the other sites.\"},{\"question\":\"What performance did the models achieve and what does it imply?\",\"answer\":\"The AUC for internal and external validations ranged from 0.77 to 0.80, indicating robust and generalizable risk signaling and similar performance when applied across sites.\"}]","Predicting Undesired Treatment Outcome with Machine Learning in Multi-Site Mental Healthcare | PDF",1785817998,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-undesired-treatment-outcome-with-machine-learning-in-multi-site-mental-healthcare","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-undesired-treatment-outcome-with-machine-learning-in-multi-site-mental-healthcare/123686/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What was the primary objective of this multi-site study?","Question",{"text":75,"@type":76},"To predict patients’ treatment response during Dutch basic mental healthcare using routine care data, and to compare machine learning performance across three mental healthcare organizations in the Netherlands.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the machine learning models developed and validated?",{"text":80,"@type":76},"Models used anonymized datasets from three organizations and applied three LASSO regression runs. Performance was assessed with internal cross-validation within each site and external validation on data from the other sites.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance did the models achieve and what does it imply?",{"text":84,"@type":76},"The AUC for internal and external validations ranged from 0.77 to 0.80, indicating robust and generalizable risk signaling and similar performance when applied across sites.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]