{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:09:27Z","timestamp":1783098567832,"version":"3.54.6"},"reference-count":67,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T00:00:00Z","timestamp":1636675200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006544","name":"Ministry of Health, State of Israel","doi-asserted-by":"publisher","award":["3-000015730"],"award-info":[{"award-number":["3-000015730"]}],"id":[{"id":"10.13039\/501100006544","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. In this article, we propose a novel deep learning-based treatment selection approach that is shown to strike a balance between the two paradigms using latent-space prototyping. Our approach is specifically tailored for domains in which effective prototypes and sub-groups of patients are assumed to exist, but groupings relevant to the training objective are not observable in the non-latent space. In an extensive evaluation, using both synthetic and Major Depressive Disorder (MDD) real-world clinical data describing 4754 MDD patients from clinical trials for depression treatment, we show that our approach favorably compares with state-of-the-art approaches. Specifically, the model produced an 8% absolute and 23% relative improvement over random treatment allocation. This is potentially clinically significant, given the large number of patients with MDD. Therefore, the model can bring about a much desired leap forward in the way depression is treated today.<\/jats:p>","DOI":"10.1371\/journal.pone.0258400","type":"journal-article","created":{"date-parts":[[2021,11,12]],"date-time":"2021-11-12T18:33:05Z","timestamp":1636741985000},"page":"e0258400","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":14,"title":["Treatment selection using prototyping in latent-space with application to depression treatment"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2056-9694","authenticated-orcid":true,"given":"Akiva","family":"Kleinerman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ariel","family":"Rosenfeld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Benrimoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3292-6233","authenticated-orcid":true,"given":"Robert","family":"Fratila","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caitrin","family":"Armstrong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Mehltretter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eliyahu","family":"Shneider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amit","family":"Yaniv-Rosenfeld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordan","family":"Karp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles F.","family":"Reynolds","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo","family":"Turecki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5985-6792","authenticated-orcid":true,"given":"Adam","family":"Kapelner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"pone.0258400.ref001","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1001\/jama.2016.12260","article-title":"Will precision medicine improve population health?","volume":"316","author":"M Khoury","year":"2016","journal-title":"Jama"},{"key":"pone.0258400.ref002","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1377\/hlthaff.2017.1624","article-title":"Precision medicine: from science to value","volume":"37","author":"G Ginsburg","year":"2018","journal-title":"Health Affairs"},{"key":"pone.0258400.ref003","first-page":"215","article-title":"Deep learning opens new horizons in personalized medicine","volume":"10","author":"G. Papadakis","year":"2019","journal-title":"Biomedical Reports"},{"key":"pone.0258400.ref004","doi-asserted-by":"crossref","DOI":"10.1016\/j.brat.2019.103505","article-title":"Latent variable mixture modelling and individual treatment prediction","volume":"124","author":"R. Saunders","year":"2020","journal-title":"Behaviour Research And Therapy"},{"key":"pone.0258400.ref005","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.tics.2019.03.009","article-title":"The heterogeneity problem: approaches to identify psychiatric subtypes","volume":"23","author":"E. Feczko","year":"2019","journal-title":"Trends In Cognitive Sciences"},{"key":"pone.0258400.ref006","first-page":"433","article-title":"Beyond lumping and splitting: a review of computational approaches for stratifying psychiatric disorders","volume":"1","author":"A. Marquand","year":"2016","journal-title":"Biological Psychiatry: Cognitive Neuroscience And Neuroimaging"},{"key":"pone.0258400.ref007","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1513\/AnnalsATS.201702-101OC","article-title":"Discovering pediatric asthma phenotypes on the basis of response to controller medication using machine learning","volume":"15","author":"M. Ross","year":"2018","journal-title":"Annals Of The American Thoracic Society"},{"key":"pone.0258400.ref008","doi-asserted-by":"crossref","first-page":"926","DOI":"10.6004\/jnccn.2017.0116","article-title":"Acute myeloid leukemia, version 3.2017, NCCN clinical practice guidelines in oncology","volume":"15","author":"M. O\u2019donnell","year":"2017","journal-title":"Journal Of The National Comprehensive Cancer Network"},{"key":"pone.0258400.ref009","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1176\/appi.ajp.2015.14020181","article-title":"Depression subtypes in predicting antidepressant response: a report from the iSPOT-D trial","volume":"172","author":"B. Arnow","year":"2015","journal-title":"American Journal Of Psychiatry"},{"key":"pone.0258400.ref010","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1038\/s41380-019-0385-5","article-title":"Data-driven biological subtypes of depression: systematic review of biological approaches to depression subtyping","volume":"24","author":"L. Beijers","year":"2019","journal-title":"Molecular Psychiatry"},{"key":"pone.0258400.ref011","unstructured":"World Health Organization, Depression, https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/depression, 2020."},{"key":"pone.0258400.ref012","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1001\/jamapsychiatry.2019.0633","article-title":"Trends in treatment and spending for patients receiving outpatient treatment of depression in the United States, 1998-2015","volume":"76","author":"J. Hockenberry","year":"2019","journal-title":"Jama Psychiatry"},{"key":"pone.0258400.ref013","doi-asserted-by":"crossref","first-page":"155","DOI":"10.4088\/JCP.14m09298","article-title":"The economic burden of adults with major depressive disorder in the United States (2005 and 2010)","volume":"76","author":"P. Greenberg","year":"2015","journal-title":"The Journal Of Clinical Psychiatry"},{"key":"pone.0258400.ref014","author":"American psychiatric association D","year":"2013"},{"key":"pone.0258400.ref015","doi-asserted-by":"crossref","first-page":"233","DOI":"10.3390\/ijms19010233","article-title":"Personalized antidepressant selection and pathway to novel treatments: clinical utility of targeting inflammation","volume":"19","author":"M Jha","year":"2018","journal-title":"International Journal Of Molecular Sciences"},{"key":"pone.0258400.ref016","unstructured":"Winerman L. By the numbers: Antidepressant use on the rise. https:\/\/www.apa.org\/monitor\/2017\/11\/numbers, 2017."},{"key":"pone.0258400.ref017","doi-asserted-by":"crossref","first-page":"435","DOI":"10.31887\/DCNS.2009.11.4\/afleuchter","article-title":"A new paradigm for the prediction of antidepressant treatment response","volume":"11","author":"A. Leuchter","year":"2009","journal-title":"Dialogues In Clinical Neuroscience"},{"key":"pone.0258400.ref018","doi-asserted-by":"crossref","first-page":"670","DOI":"10.4088\/JCP.v66n0601","article-title":"Remission rates with 3 consecutive antidepressant trials: effectiveness for depressed outpatients","volume":"66","author":"F. Quitkin","year":"2005","journal-title":"The Journal Of Clinical Psychiatry"},{"key":"pone.0258400.ref019","doi-asserted-by":"crossref","first-page":"101753","DOI":"10.1016\/j.artmed.2019.101753","article-title":"Artificial intelligence and the future of psychiatry: Insights from a global physician survey","volume":"102","author":"P. Doraiswamy","year":"2020","journal-title":"Artificial Intelligence In Medicine"},{"key":"pone.0258400.ref020","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/B978-0-12-820203-6.00001-1","article-title":"Big data analytics and ai in mental healthcare","author":"A. Rosenfeld","year":"2021","journal-title":"Applications of Big Data in Healthcare"},{"key":"pone.0258400.ref021","article-title":"The advantages of paroxetine in different subgroups of depression","author":"S Montgomery","year":"1992","journal-title":"International Clinical Psychopharmacology"},{"key":"pone.0258400.ref022","doi-asserted-by":"crossref","first-page":"2623","DOI":"10.1038\/npp.2017.97","article-title":"Data-driven subgroups in depression derived from directed functional connectivity paths at rest","volume":"42","author":"R. Price","year":"2017","journal-title":"Neuropsychopharmacology"},{"key":"pone.0258400.ref023","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.jad.2016.03.011","article-title":"Predicting treatment outcome in psychological treatment services by identifying latent profiles of patients","volume":"197","author":"R. Saunders","year":"2016","journal-title":"Journal Of Affective Disorders"},{"key":"pone.0258400.ref024","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1136\/ebmental-2019-300118","article-title":"Personalise antidepressant treatment for unipolar depression combining individual choices, risks and big data (PETRUSHKA): rationale and protocol","volume":"23","author":"A. Tomlinson","year":"2020","journal-title":"Evidence-based Mental Health"},{"key":"pone.0258400.ref025","unstructured":"Metz C. A.I. Shows Promise Assisting Physicians, https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/depression, 2020."},{"key":"pone.0258400.ref026","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.copbio.2020.05.002","article-title":"Organoid technology and applications in cancer immunotherapy and precision medicine","volume":"65","author":"K Homicsko","year":"2020","journal-title":"Current Opinion In Biotechnology"},{"key":"pone.0258400.ref027","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1080\/10673220902724565","article-title":"A prototype approach toward antipsychotic medication adherence in schizophrenia","volume":"17","author":"O Freudenreich","year":"2009","journal-title":"Harvard Review Of Psychiatry"},{"key":"pone.0258400.ref028","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.psychres.2012.03.033","article-title":"Adherence styles of schizophrenia patients identified by a latent class analysis of the Medication Adherence Rating Scale (MARS): a six-month follow-up study","volume":"200","author":"S. Jaeger","year":"2012","journal-title":"Psychiatry Research"},{"key":"pone.0258400.ref029","doi-asserted-by":"crossref","unstructured":"Li, O., Liu, H., Chen, C. Rudin, C. Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions. Proceedings of the AAAI Conference on Artificial Intelligence: vol. 32, no. 1. 2018.","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"pone.0258400.ref030","first-page":"8930","article-title":"This looks like that: deep learning for interpretable image recognition","author":"C. Chen","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0258400.ref031","first-page":"3076","article-title":"Estimating individual treatment effect: generalization bounds and algorithms","author":"U. Shalit","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"pone.0258400.ref032","doi-asserted-by":"crossref","unstructured":"Mehltretter, J., Fratila, R., Benrimoh, D., Kapelner, A., Perlman, K., et al. Differential treatment benefit prediction for treatment selection in depression: a deep learning analysis of STAR* D and CO-MED data. Available At Ssrn 3309427: 2018.","DOI":"10.2139\/ssrn.3309427"},{"key":"pone.0258400.ref033","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/j.eswa.2018.12.036","article-title":"Case-base maintenance of a personalised and adaptive CBR bolus insulin recommender system for type 1 diabetes","volume":"121","author":"F. Torrent-fontbona","year":"2019","journal-title":"Expert Systems With Applications"},{"key":"pone.0258400.ref034","unstructured":"Yao, L., Li, S., Li, Y., Huai, M., Gao, J. Zhang, A. Representation learning for treatment effect estimation from observational data."},{"key":"pone.0258400.ref035","article-title":"From real-world patient data to individualized treatment effects using machine learning: Current and future methods to address underlying challenges","author":"I. Bica","year":"2020","journal-title":"Clinical Pharmacology & Therapeutics"},{"key":"pone.0258400.ref036","doi-asserted-by":"crossref","first-page":"4156","DOI":"10.1073\/pnas.1804597116","article-title":"Metalearners for estimating heterogeneous treatment effects using machine learning","volume":"116","author":"S. K\u00fcnzel","year":"2019","journal-title":"Proceedings Of The National Academy Of Sciences"},{"key":"pone.0258400.ref037","article-title":"Aifred health, a deep learning powered clinical decision support system for mental health","author":"D. Benrimoh","year":"2018","journal-title":"The NIPS\u201917 Competition: Building Intelligent Systems"},{"key":"pone.0258400.ref038","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1017\/S0269888906000567","article-title":"Case-based recommender systems","volume":"20","author":"D. Bridge","year":"2005","journal-title":"The Knowledge Engineering Review"},{"key":"pone.0258400.ref039","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-85820-3","volume-title":"Introduction to recommender systems handbook","author":"F. Ricci","year":"2011"},{"key":"pone.0258400.ref040","volume-title":"International Journal Of Advanced Computer Science And Applications","author":"T. Lim","year":"2013"},{"key":"pone.0258400.ref041","first-page":"91","article-title":"Refining initial points for k-means clustering","volume":"vol. 98","author":"P Bradley","year":"1998","journal-title":"ICML"},{"key":"pone.0258400.ref042","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0210314","article-title":"Classification of patients with bipolar disorder using k-means clustering","volume":"14","author":"L. Fuente-tomas","year":"2019","journal-title":"Plos One"},{"key":"pone.0258400.ref043","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-26633-6_12","article-title":"Mixture models: Latent profile and latent class analysis","volume-title":"Modern statistical methods for HCI","author":"D Oberski","year":"2016"},{"key":"pone.0258400.ref044","unstructured":"Shi, C., Blei, D. Veitch, V. Adapting neural networks for the estimation of treatment effects. Proceedings of the 33rd International Conference on Neural Information Processing Systems: 2019, 2507-2517."},{"key":"pone.0258400.ref045","doi-asserted-by":"crossref","unstructured":"Shi, Y., Karatzoglou, A., Baltrunas, L., Larson, M., Oliver, N. Hanjalic, A. CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering. Proceedings of the sixth ACM conference on Recommender systems: 2012, pp. 139-146.","DOI":"10.1145\/2365952.2365981"},{"key":"pone.0258400.ref046","article-title":"Metric learning to rank","author":"B Mcfee","year":"2010","journal-title":"ICML"},{"key":"pone.0258400.ref047","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2009.187","article-title":"Sensitivity analysis of k-fold cross validation in prediction error estimation","volume":"32","author":"J. Rodriguez","year":"2009","journal-title":"Ieee Transactions On Pattern Analysis And Machine Intelligence"},{"key":"pone.0258400.ref048","first-page":"21","article-title":"Power comparisons of shapiro-wilk, kolmogorov-smirnov, lilliefors and anderson-darling tests","volume":"2","author":"N Razali","year":"2011","journal-title":"Journal Of Statistical Modeling And Analytics"},{"key":"pone.0258400.ref049","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"J Dem\u0161ar","year":"2006","journal-title":"Journal Of Machine Learning Research"},{"key":"pone.0258400.ref050","doi-asserted-by":"crossref","first-page":"2636","DOI":"10.1080\/03610918.2014.931971","article-title":"Overview of Friedman\u2019s test and post-hoc analysis","volume":"44","author":"D. Pereira","year":"2015","journal-title":"Communications In Statistics-simulation And Computation"},{"key":"pone.0258400.ref051","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1007\/s00362-012-0443-4","article-title":"A generalization of the Wilcoxon signed-rank test and its applications","volume":"54","author":"S Taheri","year":"2013","journal-title":"Statistical Papers"},{"key":"pone.0258400.ref052","first-page":"40","article-title":"What is the Bonferroni correction","volume":"6","author":"M Napierala","year":"2012","journal-title":"Aaos Now"},{"key":"pone.0258400.ref053","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1093\/bjaceaccp\/mkn041","article-title":"Clinical tests: sensitivity and specificity","volume":"8","author":"A. Lalkhen","year":"2008","journal-title":"Continuing Education In Anaesthesia Critical Care & Pain"},{"key":"pone.0258400.ref054","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1176\/appi.ajp.2011.10111645","article-title":"Combining medications to enhance depression outcomes (CO-MED): acute and long-term outcomes of a single-blind randomized study","volume":"168","author":"A. Rush","year":"2011","journal-title":"American Journal Of Psychiatry"},{"key":"pone.0258400.ref055","doi-asserted-by":"crossref","first-page":"1905","DOI":"10.1176\/ajp.2006.163.11.1905","article-title":"Acute and longer-term outcomes in depressed outpatients requiring one or several treatment steps: a STAR* D report","volume":"163","author":"A. Rush","year":"2006","journal-title":"American Journal Of Psychiatry"},{"key":"pone.0258400.ref056","first-page":"5","article-title":"REVAMP-Research Evaluating the Value of Augmenting Medication with Psychotherapy: rationale and design","volume":"41","author":"M. Trivedi","year":"2008","journal-title":"Psychopharmacol Bull"},{"key":"pone.0258400.ref057","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.jpsychires.2016.03.001","article-title":"Establishing moderators and biosignatures of antidepressant response in clinical care (EMBARC): rationale and design","volume":"78","author":"M. Trivedi","year":"2016","journal-title":"Journal Of Psychiatric Research"},{"key":"pone.0258400.ref058","doi-asserted-by":"crossref","first-page":"2404","DOI":"10.1016\/S0140-6736(15)00308-6","article-title":"Efficacy, safety, and tolerability of augmentation pharmacotherapy with aripiprazole for treatment-resistant depression in late life: a randomised, double-blind, placebo-controlled trial","volume":"386","author":"E. Lenze","year":"2015","journal-title":"The Lancet"},{"key":"pone.0258400.ref059","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/S0006-3223(02)01866-8","article-title":"The 16-Item Quick Inventory of Depressive Symptomatology (QIDS), clinician rating (QIDS-C), and self-report (QIDS-SR): a psychometric evaluation in patients with chronic major depression","volume":"54","author":"A. Rush","year":"2003","journal-title":"Biological Psychiatry"},{"key":"pone.0258400.ref060","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1111\/j.2044-8260.1967.tb00530.x","article-title":"Development of a rating scale for primary depressive illness","volume":"6","author":"M Hamilton","year":"1967","journal-title":"British Journal Of Social And Clinical Psychology"},{"key":"pone.0258400.ref061","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00820ED1V01Y201712AIM036","article-title":"Predicting human decision-making: From prediction to action","volume":"12","author":"A Rosenfeld","year":"2018","journal-title":"Synthesis Lectures On Artificial Intelligence And Machine Learning"},{"key":"pone.0258400.ref062","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/BF02294245","article-title":"An examination of procedures for determining the number of clusters in a data set","volume":"50","author":"G Milligan","year":"1985","journal-title":"Psychometrika"},{"key":"pone.0258400.ref063","article-title":"Using a Simulation Centre to Evaluate the Effect of an Artificial Intelligence-Powered Clinical Decision Support System for Depression Treatment on the Physician-Patient Interaction","author":"D. Benrimoh","year":"2020","journal-title":"Medrxiv"},{"key":"pone.0258400.ref064","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"T Miller","year":"2019","journal-title":"Artificial Intelligence"},{"key":"pone.0258400.ref065","first-page":"540","article-title":"Clinical guidelines for the management of adults with major depressive disorder: section 3. Pharmacological treatments","volume":"61","author":"S. Kennedy","year":"2016","journal-title":"Can J Psychiatry"},{"key":"pone.0258400.ref066","volume-title":"Stahl\u2019s essential psychopharmacology: neuroscientific basis and practical applications","author":"S Stahl","year":"2013"},{"key":"pone.0258400.ref067","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1017\/S0033291718001708","article-title":"Personalized prediction of antidepressant v. placebo response: evidence from the EMBARC study","volume":"49","author":"C. Webb","year":"2019","journal-title":"Psychological Medicine"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0258400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T03:06:49Z","timestamp":1673752009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0258400"}},"subtitle":[],"editor":[{"given":"Luca","family":"Citi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":67,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,11,12]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0258400","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,12]]}}}