{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T08:52:48Z","timestamp":1784883168000,"version":"3.55.0"},"reference-count":31,"publisher":"American Medical Association (AMA)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"Importance<\/jats:title>There is an absence of mortality risk assessment tools in first-episode psychosis (FEP) that could enable personalized interventions.<\/jats:p><\/jats:sec>Objective<\/jats:title>To examine the feasibility of machine learning (ML) in discerning mortality risk in FEP and to assess whether such risk predictions can inform pharmacotherapy choices.<\/jats:p><\/jats:sec>Design, Setting, and Participants<\/jats:title>In this prognostic study, Swedish nationwide cohort data (from July 1, 2006, to December 31, 2021) were harnessed for model development and validation. Finnish cohort data (from January 1, 1998, to December 31, 2017) were used for external validation. Data analyses were completed between December 2022 and December 2023.<\/jats:p><\/jats:sec>Main Outcomes and Measures<\/jats:title>Fifty-one nationwide register variables, encompassing demographics and clinical and work-related histories, were subjected to ML to predict future mortality risk. The ML model\u2019s performance was evaluated by calculating the area under the receiver operating characteristic curve (AUROC). The comparative effectiveness of pharmacotherapies in patients was assessed and was stratified by the ML model to those with predicted high mortality risk (vs low risk), using the between-individual hazard ratio (HR). The 5 most important variables were then identified and a model was retrained using these variables in the discovery sample.<\/jats:p><\/jats:sec>Results<\/jats:title>This study included 24\u202f052 Swedish participants (20\u202f000 in the discovery sample and 4052 in the validation sample) and 1490 Finnish participants (in the validation sample). Swedish participants had a mean (SD) age of 29.1 (8.1) years, 62.1% were men, and 418 died with 2 years. Finnish participants had a mean (SD) age of 29.7 (8.0) years, 61.7% were men, and 31 died within 2 years. The discovery sample achieved an AUROC of 0.71 (95% CI,\u20090.68-0.74) for 2-year mortality prediction. Using the 5 most important variables (ie, the top 10% [substance use comorbidities, first hospitalization duration due to FEP, male sex, prior somatic hospitalizations, and age]), the final model resulted in an AUROC of 0.70 (95% CI,\u20090.63-0.76) in the Swedish sample and 0.67 (95% CI,\u20090.56-0.78) in the Finnish sample. Individuals with predicted high mortality risk had an elevated 15-year risk in the Swedish sample (HR, 3.77 [95% CI,\u20092.92-4.88]) and an elevated 20-year risk in the Finnish sample (HR, 3.72 [95% CI,\u20092.67-5.18]). For those with predicted high mortality risk, long-acting injectable antipsychotics (HR, 0.45 [95% CI,\u20090.23-0.88]) and mood stabilizers (HR, 0.64 [95% CI,\u20090.46-0.90]) were associated with decreased mortality risk. Conversely, for those predicted to survive, only oral aripiprazole (HR, 0.38 [95% CI,\u20090.20-0.69]) and risperidone (HR, 0.38 [95% CI,\u20090.18-0.82]) were associated with decreased mortality risk.<\/jats:p><\/jats:sec>Conclusions and Relevance<\/jats:title>In this prognostic study, an ML-based model was developed and validated to predict mortality risk in FEP. These findings may help to develop personalized interventions to mitigate mortality risk in FEP.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2024.0640","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T15:35:07Z","timestamp":1710776107000},"page":"e240640","source":"Crossref","is-referenced-by-count":15,"title":["Development and Validation of a Machine Learning\u2013Based Model of Mortality Risk in First-Episode Psychosis"],"prefix":"10.1001","volume":"7","author":[{"given":"Johannes","family":"Lieslehto","sequence":"first","affiliation":[{"name":"Department of Forensic Psychiatry, Niuvanniemi Hospital, University of Eastern Finland, Kuopio"},{"name":"Division of Insurance Medicine, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jari","family":"Tiihonen","sequence":"additional","affiliation":[{"name":"Department of Forensic Psychiatry, Niuvanniemi Hospital, University of Eastern Finland, Kuopio"},{"name":"Center for Psychiatry Research, Stockholm City Council, Stockholm, Sweden"},{"name":"Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markku","family":"L\u00e4hteenvuo","sequence":"additional","affiliation":[{"name":"Department of Forensic Psychiatry, Niuvanniemi Hospital, University of Eastern Finland, Kuopio"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Leucht","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Psychotherapy, School of Medicine, Technical University of Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph U.","family":"Correll","sequence":"additional","affiliation":[{"name":"The Zucker Hillside Hospital, Department of Psychiatry, Northwell Health, Glen Oaks, New York"},{"name":"Department of Psychiatry and Molecular Medicine, Donald and Barbara Zucker School of Medicine at Hofstra\/Northwell, Hempstead, New York"},{"name":"Department of Child and Adolescent Psychiatry, Charit\u00e9\u2013Universit\u00e4tsmedizin Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ellenor","family":"Mittendorfer-Rutz","sequence":"additional","affiliation":[{"name":"Division of Insurance Medicine, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antti","family":"Tanskanen","sequence":"additional","affiliation":[{"name":"Department of Forensic Psychiatry, Niuvanniemi Hospital, University of Eastern Finland, Kuopio"},{"name":"Division of Insurance Medicine, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden"},{"name":"Center for Psychiatry Research, Stockholm City Council, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heidi","family":"Taipale","sequence":"additional","affiliation":[{"name":"Department of Forensic Psychiatry, Niuvanniemi Hospital, University of Eastern Finland, Kuopio"},{"name":"Division of Insurance Medicine, Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden"},{"name":"Center for Psychiatry Research, Stockholm City Council, Stockholm, Sweden"},{"name":"School of Pharmacy, University of Eastern Finland, Kuopio"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2024,3,18]]},"reference":[{"issue":"2","key":"zoi240049r1","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1002\/wps.v21.2","article-title":"Mortality in people with schizophrenia: a systematic review and meta-analysis of relative risk and aggravating or attenuating factors.","volume":"21","author":"Correll","year":"2022","journal-title":"World Psychiatry"},{"issue":"3","key":"zoi240049r2","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1001\/jamapsychiatry.2017.4437","article-title":"Mortality rates after the first diagnosis of psychotic disorder in adolescents and young adults.","volume":"75","author":"Simon","year":"2018","journal-title":"JAMA Psychiatry"},{"issue":"3","key":"zoi240049r3","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1093\/schbul\/sbaa180","article-title":"Mortality after the first diagnosis of schizophrenia-spectrum disorders: a population-based retrospective cohort study.","volume":"47","author":"Kurdyak","year":"2021","journal-title":"Schizophr Bull"},{"issue":"6","key":"zoi240049r4","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1111\/acps.2018.138.issue-6","article-title":"Mortality in schizophrenia: 30-year nationwide follow-up study.","volume":"138","author":"Tanskanen","year":"2018","journal-title":"Acta Psychiatr Scand"},{"issue":"1","key":"zoi240049r5","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1111\/acps.v144.1","article-title":"Morbidity and mortality in schizophrenia with comorbid substance use disorders.","volume":"144","author":"L\u00e4hteenvuo","year":"2021","journal-title":"Acta Psychiatr Scand"},{"issue":"S51","key":"zoi240049r6","doi-asserted-by":"publisher","first-page":"s140","DOI":"10.1192\/bjp.191.51.s140","article-title":"Suicidal behaviour and mortality in first-episode psychosis: the OPUS trial.","volume":"51","author":"Bertelsen","year":"2007","journal-title":"Br J Psychiatry Suppl"},{"issue":"1","key":"zoi240049r7","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1038\/s41398-022-02256-7","article-title":"Heterogeneity in treatment outcomes and incomplete recovery in first episode psychosis: does one size fit all?","volume":"12","author":"Griffiths","year":"2022","journal-title":"Transl Psychiatry"},{"issue":"4","key":"zoi240049r8","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1176\/appi.ajp.2021.20111658","article-title":"20-year prospective, sequential follow-up study of heterogeneity in associations of duration of untreated psychosis with symptoms, functioning, and quality of life following first-episode psychosis.","volume":"179","author":"O\u2019Keeffe","year":"2022","journal-title":"Am J Psychiatry"},{"key":"zoi240049r9","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1146\/clinpsy.2018.14.issue-1","article-title":"Machine learning approaches for clinical psychology and psychiatry.","volume":"14","author":"Dwyer","year":"2018","journal-title":"Annu Rev Clin Psychol"},{"issue":"1","key":"zoi240049r10","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2020-040387","article-title":"Prescribing pattern of antipsychotic medication for first-episode psychosis: a retrospective cohort study.","volume":"11","author":"Keating","year":"2021","journal-title":"BMJ Open"},{"key":"zoi240049r11","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.schres.2017.12.010","article-title":"Antipsychotics and mortality in a nationwide cohort of 29,823 patients with schizophrenia.","volume":"197","author":"Taipale","year":"2018","journal-title":"Schizophr Res"},{"issue":"1","key":"zoi240049r14","doi-asserted-by":"publisher","DOI":"10.2196\/cancer.6750","article-title":"Rotterdam Prostate Cancer Risk Calculator: development and usability testing of the mobile phone app.","volume":"3","author":"Pereira-Azevedo","year":"2017","journal-title":"JMIR Cancer"},{"issue":"2","key":"zoi240049r15","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1001\/jama.286.2.180","article-title":"Validation of the Framingham coronary heart disease prediction scores: results of a multiple ethnic groups investigation.","volume":"286","author":"D\u2019Agostino","year":"2001","journal-title":"JAMA"},{"issue":"12","key":"zoi240049r16","doi-asserted-by":"publisher","first-page":"E655","DOI":"10.1097\/BRS.0000000000003893","article-title":"Does the ACS NSQIP Surgical Risk Calculator accurately predict complications rates after anterior lumbar interbody fusion procedures?","volume":"46","author":"Narain","year":"2021","journal-title":"Spine (Phila Pa 1976)"},{"key":"zoi240049r18","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: deep learning is not all you need.","volume":"81","author":"Shwartz-Ziv","year":"2022","journal-title":"Inf Fusion"},{"issue":"1","key":"zoi240049r19","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees.","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat Mach Intell"},{"key":"zoi240049r20","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s12911-015-0140-z","article-title":"From prescription drug purchases to drug use periods\u2014a second generation method (PRE2DUP).","volume":"15","author":"Tanskanen","year":"2015","journal-title":"BMC Med Inform Decis Mak"},{"key":"zoi240049r22","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.jclinepi.2015.04.005","article-title":"Prediction models need appropriate internal, internal-external, and external validation.","volume":"69","author":"Steyerberg","year":"2016","journal-title":"J Clin Epidemiol"},{"issue":"1-3","key":"zoi240049r23","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.schres.2012.05.007","article-title":"Risk factors for relapse following treatment for first episode psychosis: a systematic review and meta-analysis of longitudinal studies.","volume":"139","author":"Alvarez-Jimenez","year":"2012","journal-title":"Schizophr Res"},{"issue":"6","key":"zoi240049r24","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1093\/schbul\/sbad103","article-title":"Effects of substance use and antisocial personality on neuroimaging-based machine learning prediction of schizophrenia.","volume":"49","author":"Taipale","year":"2023","journal-title":"Schizophr Bull"},{"issue":"2","key":"zoi240049r25","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1001\/jamapsychiatry.2020.3604","article-title":"Multimodal machine learning workflows for prediction of psychosis in patients with clinical high-risk syndromes and recent-onset depression.","volume":"78","author":"Koutsouleris","year":"2021","journal-title":"JAMA Psychiatry"},{"issue":"26","key":"zoi240049r26","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abi7293","article-title":"Deep learning-based integration of genetics with registry data for stratification of schizophrenia and depression.","volume":"8","author":"Alles\u00f8e","year":"2022","journal-title":"Sci Adv"},{"issue":"3","key":"zoi240049r27","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1001\/jama.2018.19323","article-title":"Breast cancer treatment: a review.","volume":"321","author":"Waks","year":"2019","journal-title":"JAMA"},{"issue":"3","key":"zoi240049r28","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1093\/schbul\/sbac014","article-title":"Primary nonadherence to antipsychotic treatment among persons with schizophrenia.","volume":"48","author":"Lieslehto","year":"2022","journal-title":"Schizophr Bull"},{"issue":"6","key":"zoi240049r29","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1001\/jamapsychiatry.2016.0432","article-title":"Self-harm, unintentional injury, and suicide in bipolar disorder during maintenance mood stabilizer treatment: a UK population-based electronic health records study.","volume":"73","author":"Hayes","year":"2016","journal-title":"JAMA Psychiatry"},{"issue":"11","key":"zoi240049r30","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1017\/S0033291717000435","article-title":"Antipsychotic treatment resistance in first-episode psychosis: prevalence, subtypes and predictors.","volume":"47","author":"Demjaha","year":"2017","journal-title":"Psychol Med"},{"issue":"15","key":"zoi240049r31","doi-asserted-by":"publisher","first-page":"3231","DOI":"10.1017\/S0033291716002014","article-title":"Two distinct patterns of treatment resistance: clinical predictors of treatment resistance in first-episode schizophrenia spectrum psychoses.","volume":"46","author":"Lally","year":"2016","journal-title":"Psychol Med"},{"key":"zoi240049r12","doi-asserted-by":"crossref","DOI":"10.1176\/appi.books.9780890424841","volume-title":"The American Psychiatric Association Practice Guideline for the Treatment of Patients With Schizophrenia","author":"American Psychiatric Association","year":"2020"},{"key":"zoi240049r13","volume-title":"Psychosis and Schizophrenia in Adults: Treatment and Management: Updated Edition","author":"National Collaborating Centre for Mental Health","year":"2014"},{"key":"zoi240049r17","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"zoi240049r21","unstructured":"MIRACLE-FEP. Mortality risk assessment calculator for early first episode psychosis. Accessed December 23, 2023. https:\/\/johannes-lieslehto.shinyapps.io\/miracle-fep\/"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2816411\/lieslehto_2024_oi_240049_1710514375.04825.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T15:35:12Z","timestamp":1710776112000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2816411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3,4]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.0640","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,18]]}}}