{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:22:51Z","timestamp":1787570571903,"version":"build-2736575974"},"posted":{"date-parts":[[2025,10,17]]},"group-title":"Psychiatry and Clinical Psychology","reference-count":66,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["R01131542"],"award-info":[{"award-number":["R01131542"]}],"id":[{"id":"https:\/\/ror.org\/04xeg9z08","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"crossref","award":["U24HG011449"],"award-info":[{"award-number":["U24HG011449"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"crossref","award":["RM1HG010860"],"award-info":[{"award-number":["RM1HG010860"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,8,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Perinatal depression affects up to 30% of pregnant and postpartum women and represents a leading cause of maternal morbidity and mortality. Despite clinical guidelines recommending routine screening with tools like the Edinburgh Postnatal Depression Scale (EPDS), implementation rates remain less than 20% in clinical practice. Assessment burden and administration time are key barriers to widespread screening adoption. Current methods to abbreviate screening instruments rely on traditional psychometric approaches that may not optimize predictive accuracy. Machine learning methods offer potential to develop briefer screening tools while maintaining clinical performance.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To develop and validate a machine learning framework for abbreviating the EPDS from 10 to 2 questions and evaluate its clinical utility compared to traditional additive scoring methods.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Study Design<\/jats:title>\n                  <jats:p>\n                    Cross-sectional, retrospective, observational study using electronic health record data (01\/2018-10\/2024) with external validation in an independent prospective cohort (01\/2017-01\/2020). We evaluated all possible 2-question through 5-question EPDS combinations using linear regression to predict remaining scores from question subsets, which combined with the known subset scores reconstructed full 10-item EPDS total scores. Binary classification models assessed screening accuracy for positive depression screens using the clinical threshold of 13. Decision curve analysis evaluated net benefit across threshold probabilities. For methodological validation, we applied the framework to PHQ-9 data. Study setting included the National Clinical Cohort Collaborative (N3C), a multi-site electronic health record database of clinical sites across the United States, and Washington University in St. Louis longitudinal prospective pregnancy cohort. Participants included women with complete item-level EPDS assessments in N3C (n=22,924 total; 7,750 postpartum-specific subset), external validation cohort of pregnant women (n=1,217), and individuals with PHQ-9 data for methodological validation (n=398,606). Statistical analyses included coefficient of determination (R\n                    <jats:sup>2<\/jats:sup>\n                    ), root mean square error, mean absolute error, sensitivity, specificity, F1 score, and decision curve analysis.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    Among 22,924 women (median age 32 years, 48.8% White non-Hispanic [n=11,190], 11.5% positive screens [n=2,626]), optimal 2-question combinations were Q4:anxious plus Q8:sad and Q5:scared plus Q8:sad, both achieving R\n                    <jats:sup>2<\/jats:sup>\n                    =0.70 (root mean square error=2.17-2.23). Binary classification demonstrated sensitivity 68-72% and specificity 98-99% for identifying positive screens. Performance remained consistent in postpartum subset (R\n                    <jats:sup>2<\/jats:sup>\n                    =0.70) and external pregnancy cohort (R\n                    <jats:sup>2<\/jats:sup>\n                    =0.64). Decision curve analysis showed machine learning approaches provided superior net benefit (0.01-0.03) compared to traditional additive scoring across clinically relevant threshold probabilities. Methodological validation using PHQ-9 confirmed framework generalizability (R\n                    <jats:sup>2<\/jats:sup>\n                    =0.63). Adding demographic or clinical covariates did not improve predictive performance.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>A machine learning framework identified 2-question EPDS subsets that maintain predictive accuracy while reducing assessment burden by 80%. This approach demonstrates superior net benefit compared to traditional abbreviated scoring methods and could enhance perinatal depression screening implementation in resource-constrained settings, obstetric telehealth, and routine clinical workflows. With \u223c3.6 million annual births in the United States, widespread adoption could substantially improve identification of women with perinatal depression.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec id=\"s11\">\n                  <jats:title>Condensation page<\/jats:title>\n                  <jats:sec id=\"s11a\">\n                    <jats:title>Tweetable statement<\/jats:title>\n                    <jats:p>Machine learning identifies two EPDS questions that maintain screening accuracy while reducing assessment burden by 80%, potentially improving perinatal depression detection across diverse clinical settings.<\/jats:p>\n                  <\/jats:sec>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>AJOG at a glance<\/jats:title>\n                  <jats:list list-type=\"alpha-lower\">\n                    <jats:list-item>\n                      <jats:p>\n                        Why was this study conducted?\n                        <jats:list list-type=\"bullet\">\n                          <jats:list-item>\n                            <jats:p>Perinatal depression affects up to 30% of women but screening implementation remains below 20% despite clinical guidelines<\/jats:p>\n                          <\/jats:list-item>\n                          <jats:list-item>\n                            <jats:p>Assessment burden is a key barrier to widespread screening adoption<\/jats:p>\n                          <\/jats:list-item>\n                          <jats:list-item>\n                            <jats:p>Current abbreviation methods rely on traditional psychometric approaches rather than machine learning<\/jats:p>\n                          <\/jats:list-item>\n                        <\/jats:list>\n                      <\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>\n                        What are the key findings?\n                        <jats:list list-type=\"bullet\">\n                          <jats:list-item>\n                            <jats:p>\n                              Machine learning identified two-question Edinburgh Postnatal Depression Scale combinations that maintained predictive accuracy (R\n                              <jats:sup>2<\/jats:sup>\n                              =0.70) while reducing assessment burden by 80%\n                            <\/jats:p>\n                          <\/jats:list-item>\n                          <jats:list-item>\n                            <jats:p>Decision curve analysis showed superior net benefit versus traditional additive scoring<\/jats:p>\n                          <\/jats:list-item>\n                          <jats:list-item>\n                            <jats:p>Model performance remained strong across validation cohorts<\/jats:p>\n                          <\/jats:list-item>\n                        <\/jats:list>\n                      <\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>\n                        What does this study add to what is already known?\n                        <jats:list list-type=\"bullet\">\n                          <jats:list-item>\n                            <jats:p>First application of machine learning to Edinburgh Postnatal Depression Scale abbreviation, with the largest sample size to date<\/jats:p>\n                          <\/jats:list-item>\n                          <jats:list-item>\n                            <jats:p>Machine learning-weighted scoring outperforms traditional scoring for shortened screening tools<\/jats:p>\n                          <\/jats:list-item>\n                          <jats:list-item>\n                            <jats:p>Provides a generalizable machine learning framework to shorten other mental health assessments<\/jats:p>\n                          <\/jats:list-item>\n                        <\/jats:list>\n                      <\/jats:p>\n                    <\/jats:list-item>\n                  <\/jats:list>\n                <\/jats:sec>","DOI":"10.1101\/2025.10.13.25337771","type":"posted-content","created":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T01:45:11Z","timestamp":1760751911000},"source":"Crossref","is-referenced-by-count":1,"title":["Machine learning-optimized perinatal depression screening: Maximum impact, minimal burden"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6581-7754","authenticated-orcid":false,"given":"Eric G.","family":"Hurwitz","sequence":"first","affiliation":[{"name":"Department of Genetics, University of North Carolina at Chapel Hill, 120 Mason Farm Road, Chapel Hill, NC, 27599, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5403-5474","authenticated-orcid":false,"given":"Caroline","family":"Shell","sequence":"additional","affiliation":[{"name":"Department of OBGYN, Sinai Hospital of Baltimore, 2435 W. Belvedere Ave. Suite 33 Baltimore, MD, 21215, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5642-7054","authenticated-orcid":false,"given":"Kritika","family":"Chugh","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, University of North Carolina at Chapel Hill, 101 Manning Dr #1, Chapel Hill, NC, 27514, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4495-4762","authenticated-orcid":false,"given":"Veerle","family":"Bergink","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Icahn School of Medicine at Mount Sinai, One Gustave L. Levy Place, New York, NY, 10029, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9893-5856","authenticated-orcid":false,"given":"Rena C.","family":"Patel","sequence":"additional","affiliation":[{"name":"Department of Medicine, University of Alabama at Birmingham, 510 20th Street South Birmingham, AL, 35294, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9114-8737","authenticated-orcid":false,"given":"Melissa A.","family":"Haendel","sequence":"additional","affiliation":[{"name":"Department of Genetics, University of North Carolina at Chapel Hill, 120 Mason Farm Road, Chapel Hill, NC, 27599, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026082403450616000_2025.10.13.25337771v3.1","doi-asserted-by":"publisher","DOI":"10.1046\/j.1525-1497.2001.016009606.x"},{"key":"2026082403450616000_2025.10.13.25337771v3.2","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-199102000-00008"},{"key":"2026082403450616000_2025.10.13.25337771v3.3","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1080\/00273171.2020.1781585","article-title":"Psychometric and machine learning approaches to reduce the length of scales","volume":"56","year":"2021","journal-title":"Multivariate Behav. Res"},{"key":"2026082403450616000_2025.10.13.25337771v3.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychores.2004.09.006"},{"key":"2026082403450616000_2025.10.13.25337771v3.5","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605269"},{"key":"2026082403450616000_2025.10.13.25337771v3.6","unstructured":"The Theory and Practice of Item Response Theory. Google Books https:\/\/books.google.com\/books\/about\/The_Theory_and_Practice_of_Item_Response.html?id=NchXAQAAQBAJ."},{"key":"2026082403450616000_2025.10.13.25337771v3.7","doi-asserted-by":"crossref","unstructured":"Wainer, H. , Dorans, N. J. , Flaugher, R. , Green, B. F. & Mislevy, R. J . Computerized Adaptive Testing: A Primer. (Routledge, 2000).","DOI":"10.4324\/9781410605931"},{"key":"2026082403450616000_2025.10.13.25337771v3.8","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1111\/j.1745-3992.1993.tb00543.x","article-title":"Comparison of classical test theory and item response theory and their applications to test development","volume":"12","year":"1993","journal-title":"Educational measurement: issues and practice"},{"key":"2026082403450616000_2025.10.13.25337771v3.9","first-page":"236","article-title":"Psychometric and machine learning approaches for diagnostic assessment and tests of individual classification","volume":"26","year":"2020","journal-title":"Psychol. Methods"},{"key":"2026082403450616000_2025.10.13.25337771v3.10","first-page":"e2446486","article-title":"Trends in postpartum depression by race, ethnicity, and prepregnancy body mass index. JAMA Netw","volume":"7","year":"2024","journal-title":"Open"},{"key":"2026082403450616000_2025.10.13.25337771v3.11","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.150.6.782"},{"key":"2026082403450616000_2025.10.13.25337771v3.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2008.11.033"},{"key":"2026082403450616000_2025.10.13.25337771v3.13","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1111\/aogs.14740","article-title":"Global prevalence of perinatal depression and anxiety during the COVID-19 pandemic: An umbrella review and meta-analytic synthesis","volume":"103","year":"2024","journal-title":"Acta Obstet. Gynecol. Scand"},{"key":"2026082403450616000_2025.10.13.25337771v3.14","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.1860"},{"key":"2026082403450616000_2025.10.13.25337771v3.15","unstructured":"Implementing Perinatal Mental Health Screening. https:\/\/www.acog.org\/programs\/perinatal-mental-health\/implementing-perinatal-mental-health-screening."},{"key":"2026082403450616000_2025.10.13.25337771v3.16","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2018-3259"},{"key":"2026082403450616000_2025.10.13.25337771v3.17","unstructured":"Britt, R. U.S. Maternal Depression Screening Rates Released for the First Time Through HEDIS. Policy Center for Maternal Mental Health https:\/\/policycentermmh.org\/u-s-maternal-depression-screening-rates-released-for-the-first-time-through-hedis\/ (2022)."},{"key":"2026082403450616000_2025.10.13.25337771v3.18","doi-asserted-by":"crossref","first-page":"40","DOI":"10.7150\/ijms.9.40","article-title":"The simplified Edinburgh Postnatal Depression Scale (EPDS) for antenatal depression: is it a valid measure for pre-screening?","volume":"9","year":"2012","journal-title":"Int. J. Med. Sci"},{"key":"2026082403450616000_2025.10.13.25337771v3.19","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1111\/j.1600-0447.2006.00934.x","article-title":"A short matrix-version of the Edinburgh Depression Scale","volume":"116","year":"2007","journal-title":"Acta Psychiatr. Scand"},{"key":"2026082403450616000_2025.10.13.25337771v3.20","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/j.jad.2016.10.013","article-title":"Generating an efficient version of the Edinburgh Postnatal Depression Scale in an urban obstetrical population","volume":"208","year":"2017","journal-title":"J. Affect. Disord"},{"key":"2026082403450616000_2025.10.13.25337771v3.21","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1002\/jclp.23041","article-title":"Development and validation of a three-item version of the Edinburgh Postnatal Depression Scale","volume":"76","year":"2020","journal-title":"J. Clin. Psychol"},{"key":"2026082403450616000_2025.10.13.25337771v3.22","doi-asserted-by":"crossref","unstructured":"Pallant, J. F. , Miller, R. L. & Tennant, A . Evaluation of the Edinburgh Post Natal Depression Scale using Rasch analysis. BMC Psychiatry 6, 28 (2006).","DOI":"10.1186\/1471-244X-6-28"},{"key":"2026082403450616000_2025.10.13.25337771v3.23","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2013-1628"},{"key":"2026082403450616000_2025.10.13.25337771v3.24","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1111\/acps.13272","article-title":"Shortening the Edinburgh postnatal depression scale using optimal test assembly methods: Development of the EPDS-Dep-5","volume":"143","year":"2021","journal-title":"Acta Psychiatr. Scand"},{"key":"2026082403450616000_2025.10.13.25337771v3.25","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1093\/jamia\/ocaa196","article-title":"The National COVID Cohort Collaborative (N3C): Rationale, design, infrastructure, and deployment","volume":"28","year":"2021","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2026082403450616000_2025.10.13.25337771v3.26","doi-asserted-by":"crossref","unstructured":"Davenport, M. H. , Meyer, S. , Meah, V. L. , Strynadka, M. C. & Khurana, R . Moms are not OK: COVID-19 and maternal mental health. Front. Glob. Womens Health 1, 1 (2020).","DOI":"10.3389\/fgwh.2020.00001"},{"key":"2026082403450616000_2025.10.13.25337771v3.27","doi-asserted-by":"crossref","unstructured":"Tomfohr-Madsen, L. M. , Racine, N. , Giesbrecht, G. F. , Lebel, C. & Madigan, S . Depression and anxiety in pregnancy during COVID-19: A rapid review and meta-analysis. Psychiatry Res. 300, 113912 (2021).","DOI":"10.1016\/j.psychres.2021.113912"},{"key":"2026082403450616000_2025.10.13.25337771v3.28","doi-asserted-by":"crossref","unstructured":"Farewell, C. V. , Jewell, J. , Walls, J. & Leiferman, J. A . A mixed-methods pilot study of perinatal risk and resilience during COVID-19. J. Prim. Care Community Health 11, 2150132720944074 (2020).","DOI":"10.1177\/2150132720944074"},{"key":"2026082403450616000_2025.10.13.25337771v3.29","unstructured":"Abuse, S. Bookshelf. Substance Abuse and Mental Health Services Administration (US) https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK519712\/table\/ch3.t5\/ (2016)."},{"key":"2026082403450616000_2025.10.13.25337771v3.30","unstructured":"Tatachar, A. V . Comparative assessment of regression models based on model evaluation metrics. Impact Factor value: 7, 529 (2008)."},{"key":"2026082403450616000_2025.10.13.25337771v3.31","doi-asserted-by":"publisher","DOI":"10.1080\/02646838.2016.1141346"},{"key":"2026082403450616000_2025.10.13.25337771v3.32","doi-asserted-by":"crossref","first-page":"e200126","DOI":"10.1148\/ryai.2021200126","article-title":"Magician\u2019s corner: 9. Performance metrics for machine learning models","volume":"3","year":"2021","journal-title":"Radiol. Artif. Intell"},{"key":"2026082403450616000_2025.10.13.25337771v3.33","doi-asserted-by":"crossref","unstructured":"Jones, S. E. et al. Who is pregnant? Defining real-world data-based pregnancy episodes in the National COVID Cohort Collaborative (N3C). JAMIA Open 6, ooad067 (2023).","DOI":"10.1101\/2022.08.04.22278439"},{"key":"2026082403450616000_2025.10.13.25337771v3.34","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1097\/01.NME.0000531872.48283.ab","article-title":"Postpartum depression: Beyond the \u2018baby blues\u2019","volume":"16","year":"2018","journal-title":"Nurs. Made Incred. Easy!"},{"key":"2026082403450616000_2025.10.13.25337771v3.35","doi-asserted-by":"crossref","unstructured":"Ravindra, N. G. et al. Deep representation learning identifies associations between physical activity and sleep patterns during pregnancy and prematurity. NPJ Digit. Med. 6, 171 (2023).","DOI":"10.1038\/s41746-023-00911-x"},{"key":"2026082403450616000_2025.10.13.25337771v3.36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0272155"},{"key":"2026082403450616000_2025.10.13.25337771v3.37","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X06295361"},{"key":"2026082403450616000_2025.10.13.25337771v3.38","doi-asserted-by":"crossref","unstructured":"Vickers, A. J. , Cronin, A. M. , Elkin, E. B. & Gonen, M . Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers. BMC Med. Inform. Decis. Mak. 8, 53 (2008).","DOI":"10.1186\/1472-6947-8-53"},{"key":"2026082403450616000_2025.10.13.25337771v3.39","first-page":"61","article-title":"The Chi square test: an introduction","volume":"4","year":"1995","journal-title":"COMSIG Rev"},{"key":"2026082403450616000_2025.10.13.25337771v3.40","doi-asserted-by":"crossref","unstructured":"Bland, J. M. & Altman, D. G . Multiple significance tests: the Bonferroni method. BMJ 310, 170 (1995).","DOI":"10.1136\/bmj.310.6973.170"},{"key":"2026082403450616000_2025.10.13.25337771v3.41","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v028.i05"},{"key":"2026082403450616000_2025.10.13.25337771v3.42","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/S2213-2600(21)00068-0","article-title":"COVID-19: a heavy toll on health-care workers","volume":"9","year":"2021","journal-title":"Lancet Respir. Med"},{"key":"2026082403450616000_2025.10.13.25337771v3.43","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1016\/S2215-0366(20)30307-2","article-title":"How mental health care should change as a consequence of the COVID-19 pandemic","volume":"7","year":"2020","journal-title":"Lancet Psychiatry"},{"key":"2026082403450616000_2025.10.13.25337771v3.44","doi-asserted-by":"publisher","DOI":"10.1101\/2024.10.07.24315026"},{"key":"2026082403450616000_2025.10.13.25337771v3.45","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-79061-9_5723"},{"key":"2026082403450616000_2025.10.13.25337771v3.46","first-page":"2970","article-title":"Machine Learning in psychometrics and psychological research","volume":"10","year":"2019","journal-title":"Front. Psychol"},{"key":"2026082403450616000_2025.10.13.25337771v3.47","doi-asserted-by":"crossref","first-page":"512","DOI":"10.1093\/postmj\/qgae027","article-title":"Understanding decision curve analysis in clinical prediction model research","volume":"100","year":"2024","journal-title":"Postgrad. Med. J"},{"key":"2026082403450616000_2025.10.13.25337771v3.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbi.2020.05.026"},{"key":"2026082403450616000_2025.10.13.25337771v3.49","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01381-y"},{"key":"2026082403450616000_2025.10.13.25337771v3.50","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)60755-3"},{"key":"2026082403450616000_2025.10.13.25337771v3.51","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.1097\/AOG.0000000000005200","article-title":"Screening and diagnosis of Mental Health Conditions During Pregnancy and postpartum: ACOG Clinical Practice Guideline no. 4: ACOG Clinical Practice Guideline no. 4: Obstet","volume":"141","year":"2023","journal-title":"Gynecol"},{"key":"2026082403450616000_2025.10.13.25337771v3.52","unstructured":"Births and Natality. https:\/\/www.cdc.gov\/nchs\/fastats\/births.htm (2025)."},{"key":"2026082403450616000_2025.10.13.25337771v3.53","doi-asserted-by":"publisher","DOI":"10.2105\/AJPH.2020.305663"},{"key":"2026082403450616000_2025.10.13.25337771v3.54","unstructured":"National Academies of Sciences, Engineering, and Medicine, Health and Medicine Division, Board on Health Care Services & Committee on Implementing High-Quality Primary Care. Implementing High-Quality Primary Care: Rebuilding the Foundation of Health Care. (National Academies Press, Washington, D.C., DC, 2021)."},{"key":"2026082403450616000_2025.10.13.25337771v3.55","doi-asserted-by":"crossref","first-page":"100284","DOI":"10.1016\/j.ijnsa.2024.100284","article-title":"Proposing a two-stage screening approach to distinguish between transient and enduring postnatal depressive symptoms: A prospective cohort study","volume":"8","year":"2025","journal-title":"Int. J. Nurs. Stud. Adv"},{"key":"2026082403450616000_2025.10.13.25337771v3.56","doi-asserted-by":"crossref","first-page":"133","DOI":"10.5498\/wjp.v11.i4.133","article-title":"Effectiveness of digital psychotherapeutic intervention among perinatal women: A systematic review and meta-analysis of randomized controlled trials","volume":"11","year":"2021","journal-title":"World J. Psychiatry"},{"key":"2026082403450616000_2025.10.13.25337771v3.57","doi-asserted-by":"crossref","first-page":"499","DOI":"10.3934\/publichealth.2024025","article-title":"An evaluation of digital intervention for perinatal depression and anxiety: A systematic review","volume":"11","year":"2024","journal-title":"AIMS Public Health"},{"key":"2026082403450616000_2025.10.13.25337771v3.58","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2016.02.057"},{"key":"2026082403450616000_2025.10.13.25337771v3.59","doi-asserted-by":"crossref","unstructured":"Suharwardy, S. et al. Feasibility and impact of a mental health chatbot on postpartum mental health: a randomized controlled trial. AJOG Glob. Rep. 3, 100165 (2023).","DOI":"10.1016\/j.xagr.2023.100165"},{"key":"2026082403450616000_2025.10.13.25337771v3.60","doi-asserted-by":"publisher","DOI":"10.1016\/j.pop.2022.04.002"},{"key":"2026082403450616000_2025.10.13.25337771v3.61","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026082403450616000_2025.10.13.25337771v3.62","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"2026082403450616000_2025.10.13.25337771v3.63","unstructured":"N3C Data Access Forms and Resources. https:\/\/ncats.nih.gov\/research\/research-activities\/n3c\/resources\/data-access."},{"key":"2026082403450616000_2025.10.13.25337771v3.64","unstructured":"N3C - For Researchers. https:\/\/covid.cd2h.org\/for-researchers\/."},{"key":"2026082403450616000_2025.10.13.25337771v3.65","unstructured":"ChatGPT. https:\/\/chatgpt.com\/?utm_source=google&utm_medium=paidsearch_brand&utm_campaign=DEPT_SEM_Google_Brand_Acquisition_NAMER_US_Consumer_CPA_BAU_Mix&utm_term=chatgpt&gad_source=1&gad_campaignid=21714513245&gbraid=0AAAAA-IW-UVFk-hpJoMk5cXUoRwk50Tkb&gclid=Cj0KCQjw5ubABhDIARIsAHMighZT7_afTK4rSWfz34gPuX87_uWooKyn06qmNvMBGD8VeQZhbmDdZ0IaApi3EALw_wcB."},{"key":"2026082403450616000_2025.10.13.25337771v3.66","unstructured":"Claude. https:\/\/claude.ai\/login?returnTo=%2F%3F."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.10.13.25337771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T10:45:19Z","timestamp":1787568319000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.10.13.25337771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1101\/2025.10.13.25337771","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"subtype":"preprint"}}