{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:43:34Z","timestamp":1775191414507,"version":"3.50.1"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T00:00:00Z","timestamp":1682467200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T00:00:00Z","timestamp":1682467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000025","name":"U.S. Department of Health & Human Services | NIH | National Institute of Mental Health","doi-asserted-by":"publisher","award":["R01MH118233"],"award-info":[{"award-number":["R01MH118233"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000025","name":"U.S. Department of Health & Human Services | NIH | National Institute of Mental Health","doi-asserted-by":"publisher","award":["R01MH118233"],"award-info":[{"award-number":["R01MH118233"]}],"id":[{"id":"10.13039\/100000025","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008548","name":"Harvard T.H. Chan School of Public Health","doi-asserted-by":"publisher","award":["Taiwanese Physician Scholarship"],"award-info":[{"award-number":["Taiwanese Physician Scholarship"]}],"id":[{"id":"10.13039\/100008548","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"U.S. Department of Health & Human Services | NIH | National Institute on Aging","doi-asserted-by":"publisher","award":["R01AG058063"],"award-info":[{"award-number":["R01AG058063"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"U.S. Department of Health & Human Services | NIH | National Institute on Aging","doi-asserted-by":"publisher","award":["P30AG062421"],"award-info":[{"award-number":["P30AG062421"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Health & Human Services | NIH | National Institute on Aging"},{"name":"U.S. Department of Health & Human Services | NIH | National Institute of Mental Health"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs\u2009\u2265\u20090.70, AUPRCs\u2009\u2265\u20090.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.<\/jats:p>","DOI":"10.1038\/s41746-023-00817-8","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T09:02:33Z","timestamp":1682499753000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":73,"title":["AI-assisted prediction of differential response to antidepressant classes using electronic health records"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2767-0851","authenticated-orcid":false,"given":"Yi-han","family":"Sheu","sequence":"first","affiliation":[]},{"given":"Colin","family":"Magdamo","sequence":"additional","affiliation":[]},{"given":"Matthew","family":"Miller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9486-6811","authenticated-orcid":false,"given":"Sudeshna","family":"Das","sequence":"additional","affiliation":[]},{"given":"Deborah","family":"Blacker","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0381-6334","authenticated-orcid":false,"given":"Jordan W.","family":"Smoller","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,26]]},"reference":[{"key":"817_CR1","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1001\/jamapsychiatry.2017.4602","volume":"75","author":"DS Hasin","year":"2018","unstructured":"Hasin, D. S. et al. Epidemiology of adult DSM-5 major depressive disorder and its specifiers in the United States. JAMA Psychiatry 75, 336\u2013346 (2018).","journal-title":"JAMA Psychiatry"},{"key":"817_CR2","unstructured":"Pratt, L. A., Brody, D. J. & Gu, Q. Antidepressant use among persons aged 12 and over: United States, 2011-2014. NCHS Data Brief 283, 1\u20138 (2017)."},{"key":"817_CR3","unstructured":"Gelenberg, A. J. et al. Practice guideline for the treatment of patients with major depressive disorder (American Psychiatric Association, 2010)."},{"key":"817_CR4","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1056\/NEJMcp1712493","volume":"380","author":"LT Park","year":"2019","unstructured":"Park, L. T. & Zarate, C. A. Depression in the primary care setting. N. Engl. J. Med. 380, 559\u2013568 (2019).","journal-title":"N. Engl. J. Med."},{"key":"817_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-020-01100-0","volume":"10","author":"C Su","year":"2020","unstructured":"Su, C. et al. Machine learning for suicide risk prediction in children and adolescents with electronic health records. Transl. Psychiatry 10, 413 (2020).","journal-title":"Transl. Psychiatry"},{"key":"817_CR6","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1038\/s41596-021-00513-5","volume":"16","author":"N Toma\u0161ev","year":"2021","unstructured":"Toma\u0161ev, N. et al. Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records. Nat. Protoc. 16, 2765\u20132787 (2021).","journal-title":"Nat. Protoc."},{"key":"817_CR7","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1176\/appi.ajp.2018.17101167","volume":"175","author":"GE Simon","year":"2018","unstructured":"Simon, G. E. et al. Predicting suicide attempts and suicide deaths following outpatient visits using electronic health records. Am. J. Psychiatry 175, 951\u2013960 (2018).","journal-title":"Am. J. Psychiatry"},{"key":"817_CR8","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41586-019-1390-1","volume":"572","author":"N Toma\u0161ev","year":"2019","unstructured":"Toma\u0161ev, N. et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 572, 116\u2013119 (2019).","journal-title":"Nature"},{"key":"817_CR9","doi-asserted-by":"publisher","first-page":"768","DOI":"10.3389\/fpsyt.2018.00768","volume":"9","author":"N Jaworska","year":"2018","unstructured":"Jaworska, N., de la Salle, S., Ibrahim, M.-H., Blier, P. & Knott, V. Leveraging machine learning approaches for predicting antidepressant treatment response using electroencephalography (EEG) and clinical data. Front. Psychiatry 9, 768 (2018).","journal-title":"Front. Psychiatry"},{"key":"817_CR10","doi-asserted-by":"publisher","first-page":"641","DOI":"10.3389\/fpsyt.2020.00641","volume":"11","author":"K K\u00f6hler-Forsberg","year":"2020","unstructured":"K\u00f6hler-Forsberg, K. et al. Predicting treatment outcome in major depressive disorder using serotonin 4 receptor pet brain imaging, functional MRI, cognitive-, EEG-based, and peripheral biomarkers: a NeuroPharm open label clinical trial protocol. Front. Psychiatry 11, 641 (2020).","journal-title":"Front. Psychiatry"},{"key":"817_CR11","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1038\/s41587-019-0397-3","volume":"38","author":"W Wu","year":"2020","unstructured":"Wu, W. et al. An electroencephalographic signature predicts antidepressant response in major depression. Nat. Biotechnol. 38, 439\u2013447 (2020).","journal-title":"Nat. Biotechnol."},{"key":"817_CR12","doi-asserted-by":"publisher","first-page":"290","DOI":"10.3389\/fpsyt.2018.00290","volume":"9","author":"E Lin","year":"2018","unstructured":"Lin, E. et al. A deep learning approach for predicting antidepressant response in major depression using clinical and genetic biomarkers. Front. Psychiatry 9, 290 (2018).","journal-title":"Front. Psychiatry"},{"key":"817_CR13","doi-asserted-by":"publisher","first-page":"554186","DOI":"10.3389\/fncom.2020.554186","volume":"14","author":"M Kl\u00f6bl","year":"2020","unstructured":"Kl\u00f6bl, M. et al. Predicting antidepressant citalopram treatment response via changes in brain functional connectivity after acute intravenous challenge. Front. Comput. Neurosci. 14, 554186 (2020).","journal-title":"Front. Comput. Neurosci."},{"key":"817_CR14","doi-asserted-by":"publisher","first-page":"907","DOI":"10.3390\/genes10110907","volume":"10","author":"B Chang","year":"2019","unstructured":"Chang, B. et al. Arpnet: antidepressant response prediction network for major depressive disorder. Genes 10, 907 (2019).","journal-title":"Genes"},{"key":"817_CR15","doi-asserted-by":"publisher","first-page":"e1918377","DOI":"10.1001\/jamanetworkopen.2019.18377","volume":"3","author":"A Zhdanov","year":"2020","unstructured":"Zhdanov, A. et al. Use of machine learning for predicting escitalopram treatment outcome from electroencephalography recordings in adult patients with depression. JAMA Netw. Open 3, e1918377 (2020).","journal-title":"JAMA Netw. Open"},{"key":"817_CR16","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1002\/jmri.27029","volume":"52","author":"C Pei","year":"2020","unstructured":"Pei, C. et al. Ensemble learning for early-response prediction of antidepressant treatment in major depressive disorder. J. Magn. Reson. Imaging 52, 161\u2013171 (2020).","journal-title":"J. Magn. Reson. Imaging"},{"key":"817_CR17","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1038\/s41386-020-00943-x","volume":"46","author":"AP Athreya","year":"2021","unstructured":"Athreya, A. P. et al. Prediction of short-term antidepressant response using probabilistic graphical models with replication across multiple drugs and treatment settings. Neuropsychopharmacology 46, 1272\u20131282 (2021).","journal-title":"Neuropsychopharmacology"},{"key":"817_CR18","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1093\/brain\/aww326","volume":"140","author":"NA Crane","year":"2017","unstructured":"Crane, N. A. et al. Multidimensional prediction of treatment response to antidepressants with cognitive control and functional MRI. Brain 140, 472\u2013486 (2017).","journal-title":"Brain"},{"key":"817_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-021-01286-x","volume":"11","author":"SE Cohen","year":"2021","unstructured":"Cohen, S. E., Zantvoord, J. B., Wezenberg, B. N., Bockting, C. L. H. & van Wingen, G. A. Magnetic resonance imaging for individual prediction of treatment response in major depressive disorder: a systematic review and meta-analysis. Transl. Psychiatry 11, 168 (2021).","journal-title":"Transl. Psychiatry"},{"key":"817_CR20","doi-asserted-by":"publisher","first-page":"305","DOI":"10.3390\/ph13100305","volume":"13","author":"E Lin","year":"2020","unstructured":"Lin, E. et al. Prediction of antidepressant treatment response and remission using an ensemble machine learning framework. Pharmaceuticals 13, 305 (2020).","journal-title":"Pharmaceuticals"},{"key":"817_CR21","doi-asserted-by":"publisher","first-page":"e205308","DOI":"10.1001\/jamanetworkopen.2020.5308","volume":"3","author":"MC Hughes","year":"2020","unstructured":"Hughes, M. C. et al. Assessment of a prediction model for antidepressant treatment stability using supervised topic models. JAMA Netw. Open 3, e205308 (2020).","journal-title":"JAMA Netw. Open"},{"key":"817_CR22","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.pnpbp.2018.07.001","volume":"91","author":"SA Langenecker","year":"2019","unstructured":"Langenecker, S. A. et al. Multidimensional imaging techniques for prediction of treatment response in major depressive disorder. Prog. Neuropsychopharmacol. Biol. Psychiatry 91, 38\u201348 (2019).","journal-title":"Prog. Neuropsychopharmacol. Biol. Psychiatry"},{"key":"817_CR23","doi-asserted-by":"publisher","first-page":"276","DOI":"10.3390\/diagnostics10050276","volume":"10","author":"HS Lee","year":"2020","unstructured":"Lee, H. S., Baik, S. Y., Kim, Y.-W., Kim, J.-Y. & Lee, S.-H. Prediction of antidepressant treatment outcome using event-related potential in patients with major depressive disorder. Diagnostics 10, 276 (2020).","journal-title":"Diagnostics"},{"key":"817_CR24","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1111\/acps.13250","volume":"143","author":"A Kautzky","year":"2021","unstructured":"Kautzky, A. et al. Combining machine learning algorithms for prediction of antidepressant treatment response. Acta Psychiatr. Scand. 143, 36\u201349 (2021).","journal-title":"Acta Psychiatr. Scand."},{"key":"817_CR25","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.jad.2021.05.013","volume":"291","author":"H Xiao","year":"2021","unstructured":"Xiao, H. et al. Functional connectivity of the hippocampus in predicting early antidepressant efficacy in patients with major depressive disorder. J. Affect. Disord. 291, 315\u2013321 (2021).","journal-title":"J. Affect. Disord."},{"key":"817_CR26","doi-asserted-by":"publisher","first-page":"538393","DOI":"10.3389\/fpsyt.2020.538393","volume":"11","author":"A Preuss","year":"2020","unstructured":"Preuss, A. et al. SSRI treatment response prediction in depression based on brain activation by emotional stimuli. Front. Psychiatry 11, 538393 (2020).","journal-title":"Front. Psychiatry"},{"key":"817_CR27","doi-asserted-by":"publisher","first-page":"3922","DOI":"10.1002\/hbm.25529","volume":"42","author":"Y Kong","year":"2021","unstructured":"Kong, Y. et al. Spatio-temporal graph convolutional network for diagnosis and treatment response prediction of major depressive disorder from functional connectivity. Hum. Brain Mapp. 42, 3922\u20133933 (2021).","journal-title":"Hum. Brain Mapp."},{"key":"817_CR28","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1002\/hbm.24872","volume":"41","author":"S Tian","year":"2020","unstructured":"Tian, S. et al. Predicting escitalopram monotherapy response in depression: the role of anterior cingulate cortex. Hum. Brain Mapp. 41, 1249\u20131260 (2020).","journal-title":"Hum. Brain Mapp."},{"key":"817_CR29","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.jad.2020.06.072","volume":"276","author":"Z Long","year":"2020","unstructured":"Long, Z. et al. Prediction on treatment improvement in depression with resting state connectivity: a coordinate-based meta-analysis. J. Affect. Disord. 276, 62\u201368 (2020).","journal-title":"J. Affect. Disord."},{"key":"817_CR30","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1002\/wps.20882","volume":"20","author":"AM Chekroud","year":"2021","unstructured":"Chekroud, A. M. et al. The promise of machine learning in predicting treatment outcomes in psychiatry. World Psychiatry 20, 154\u2013170 (2021).","journal-title":"World Psychiatry"},{"key":"817_CR31","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1016\/j.jad.2018.08.073","volume":"241","author":"Y Lee","year":"2018","unstructured":"Lee, Y. et al. Applications of machine learning algorithms to predict therapeutic outcomes in depression: a meta-analysis and systematic review. J. Affect. Disord. 241, 519\u2013532 (2018).","journal-title":"J. Affect. Disord."},{"key":"817_CR32","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-021-01488-3","volume":"11","author":"D Taliaz","year":"2021","unstructured":"Taliaz, D. et al. Optimizing prediction of response to antidepressant medications using machine learning and integrated genetic, clinical, and demographic data. Transl. Psychiatry 11, 381 (2021).","journal-title":"Transl. Psychiatry"},{"key":"817_CR33","doi-asserted-by":"publisher","first-page":"31","DOI":"10.3389\/frai.2019.00031","volume":"2","author":"J Mehltretter","year":"2019","unstructured":"Mehltretter, J. et al. Analysis of features selected by a deep learning model for differential treatment selection in depression. Front. Artif. Intell. 2, 31 (2019).","journal-title":"Front. Artif. Intell."},{"key":"817_CR34","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1109\/TNSRE.2022.3203073","volume":"30","author":"Y Peng","year":"2022","unstructured":"Peng, Y. et al. Electroencephalographic network topologies predict antidepressant responses in patients with major depressive disorder. IEEE Trans. Neural Syst. Rehabil. Eng. 30, 2577\u20132588 (2022).","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"817_CR35","doi-asserted-by":"publisher","first-page":"103120","DOI":"10.1016\/j.nicl.2022.103120","volume":"35","author":"JK Harris","year":"2022","unstructured":"Harris, J. K. et al. Predicting escitalopram treatment response from pre-treatment and early response resting state fMRI in a multi-site sample: A CAN-BIND-1 report. Neuroimage Clin. 35, 103120 (2022).","journal-title":"Neuroimage Clin."},{"key":"817_CR36","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/j.biopsych.2022.03.020","volume":"92","author":"RH Kaiser","year":"2022","unstructured":"Kaiser, R. H. et al. Dynamic resting-state network biomarkers of antidepressant treatment response. Biol. Psychiatry 92, 533\u2013542 (2022).","journal-title":"Biol. Psychiatry"},{"key":"817_CR37","doi-asserted-by":"publisher","first-page":"693","DOI":"10.3390\/jpm12050693","volume":"12","author":"P-L Tsai","year":"2022","unstructured":"Tsai, P.-L., Chang, H. H. & Chen, P. S. Predicting the treatment outcomes of antidepressants using a deep neural network of deep learning in drug-na\u00efve major depressive patients. J. Pers. Med. 12, 693 (2022).","journal-title":"J. Pers. Med."},{"key":"817_CR38","doi-asserted-by":"publisher","first-page":"102858","DOI":"10.1016\/j.nicl.2021.102858","volume":"32","author":"KR Hill","year":"2021","unstructured":"Hill, K. R. et al. Measuring brain glucose metabolism in order to predict response to antidepressant or placebo: A randomized clinical trial. Neuroimage Clin. 32, 102858 (2021).","journal-title":"Neuroimage Clin."},{"key":"817_CR39","doi-asserted-by":"publisher","first-page":"e0253023","DOI":"10.1371\/journal.pone.0253023","volume":"16","author":"J-J Nunez","year":"2021","unstructured":"Nunez, J.-J. et al. Replication of machine learning methods to predict treatment outcome with antidepressant medications in patients with major depressive disorder from STAR*D and CAN-BIND-1. PLoS One 16, e0253023 (2021).","journal-title":"PLoS One"},{"key":"817_CR40","doi-asserted-by":"publisher","unstructured":"Puac-Polanco, V. et al. Development of a model to predict antidepressant treatment response for depression among Veterans. Psychol. Med. 1\u201311 https:\/\/doi.org\/10.1017\/S0033291722001982 (2022).","DOI":"10.1017\/S0033291722001982"},{"key":"817_CR41","doi-asserted-by":"publisher","unstructured":"Mehltretter, J. et al. Differential treatment benefit prediction for treatment selection in depression: a deep learning analysis of STAR*D and CO-MED Data. BioRxiv https:\/\/doi.org\/10.1101\/679779 (2019).","DOI":"10.1101\/679779"},{"key":"817_CR42","doi-asserted-by":"publisher","first-page":"e0258400","DOI":"10.1371\/journal.pone.0258400","volume":"16","author":"A Kleinerman","year":"2021","unstructured":"Kleinerman, A. et al. Treatment selection using prototyping in latent-space with application to depression treatment. PLoS One 16, e0258400 (2021).","journal-title":"PLoS One"},{"key":"817_CR43","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep learning (The MIT Press, 2016)."},{"key":"817_CR44","doi-asserted-by":"publisher","first-page":"1422","DOI":"10.1002\/pds.4685","volume":"27","author":"GA Bushnell","year":"2018","unstructured":"Bushnell, G. A., St\u00fcrmer, T., Mack, C., Pate, V. & Miller, M. Who diagnosed and prescribed what? Using provider details to inform observational research. Pharmacoepidemiol. Drug Saf. 27, 1422\u20131426 (2018).","journal-title":"Pharmacoepidemiol. Drug Saf."},{"key":"817_CR45","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1037\/bul0000102","volume":"143","author":"RH Salk","year":"2017","unstructured":"Salk, R. H., Hyde, J. S. & Abramson, L. Y. Gender differences in depression in representative national samples: Meta-analyses of diagnoses and symptoms. Psychol. Bull. 143, 783\u2013822 (2017).","journal-title":"Psychol. Bull."},{"key":"817_CR46","unstructured":"Lundberg, S. M. & Lee, S.-I. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems (eds. Guyon, I. et al.) vol. 30 (Curran Associates, Inc., 2017)."},{"key":"817_CR47","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","volume":"2","author":"SM Lundberg","year":"2018","unstructured":"Lundberg, S. M. et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat. Biomed. Eng. 2, 749\u2013760 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"817_CR48","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.genhosppsych.2022.12.004","volume":"81","author":"Y-H Sheu","year":"2023","unstructured":"Sheu, Y.-H., Magdamo, C., Miller, M., Smoller, J. W. & Blacker, D. Initial antidepressant choice by non-psychiatrists: Learning from large-scale electronic health records. Gen. Hosp. Psychiatry 81, 22\u201331 (2023).","journal-title":"Gen. Hosp. Psychiatry"},{"key":"817_CR49","unstructured":"MassGeneralBrigham Healthcare System. Research Patient Data Registry (RPDR). https:\/\/rc.partners.org\/about\/who-we-are-risc\/research-patient-data-registry (2018)."},{"key":"817_CR50","unstructured":"Beltagy, I., Peters, M. E. & Cohan, A. Longformer: The Long-Document Transformer. Preprint at https:\/\/arxiv.org\/abs\/2004.05150 (2020)."},{"key":"817_CR51","doi-asserted-by":"crossref","unstructured":"Sheu, Y. et al. Phenotyping Antidepressant Treatment Response with Deep Learning in Electronic Health Records. Preprint at https:\/\/www.medrxiv.org\/content\/10.1101\/2021.08.04.21261512v1.full (2021).","DOI":"10.1101\/2021.08.04.21261512"},{"key":"817_CR52","unstructured":"Sadock, B. J., Sadock, V. A. & Ruiz, P. Kaplan & Sadock\u2019s synopsis of psychiatry: behavioral sciences\/clinical psychiatry (Lippincott Williams, 2015)."},{"key":"817_CR53","unstructured":"Stahl, S. S. Stahl\u2019s essential psychopharmacology: neuroscientific basis and practical applications (Cambridge University Press, 2013)."},{"key":"817_CR54","doi-asserted-by":"publisher","unstructured":"Breiman, L. Random forests. Springer Science and Business Media LLC. https:\/\/doi.org\/10.1023\/a:1010933404324 (2001).","DOI":"10.1023\/a:1010933404324"},{"key":"817_CR55","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"JH Friedman","year":"2001","unstructured":"Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189\u20131232 (2001).","journal-title":"Ann. Stat."},{"key":"817_CR56","unstructured":"Vaswani, A. et al. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems 6000\u20136010 (Curran Associates Inc., 2017)."},{"key":"817_CR57","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou, H. & Hastie, T. Regularization and variable selection via the elastic net. J. R. Stat. Soc. B 67, 301\u2013320 (2005).","journal-title":"J. R. Stat. Soc. B"},{"key":"817_CR58","unstructured":"H2O.ai. R Interface for H2O. https:\/\/github.com\/h2oai\/h2o-3 (2021)."},{"key":"817_CR59","unstructured":"Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems (eds. Wallach, H. et al.) vol. 32 (Curran Associates, Inc., 2019)."},{"key":"817_CR60","unstructured":"Falcon, W. A. PyTorch Lightning. PyTorch Lightning. https:\/\/github.com\/PyTorchLightning\/pytorch-lightning (2019)."},{"key":"817_CR61","doi-asserted-by":"publisher","unstructured":"Wolf, T. et al. Transformers: state-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 38\u201345 (Association for Computational Linguistics, 2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-demos.6.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"817_CR62","unstructured":"Rajapakse, T. C. Simple transformers. https:\/\/github.com\/ThilinaRajapakse\/simpletransformers (2019)."},{"key":"817_CR63","unstructured":"GitHub - slundberg\/shap: a game theoretic approach to explain the output of any machine learning model. https:\/\/github.com\/slundberg\/shap (2017)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00817-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00817-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00817-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T10:09:14Z","timestamp":1682503754000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00817-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,26]]},"references-count":63,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["817"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00817-8","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,26]]},"assertion":[{"value":"17 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"J.W.S. is a member of Scientific Advisory Board of Sensorium Therapeutics (with equity) and has received grant support from Biogen, Inc. He is PI of a collaborative study of the genetics of depression and bipolar disorder sponsored by 23andMe for which 23andMe provides analysis time as in-kind support but no payments. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"73"}}