{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"submitter":["Hurwitz E"],"funding":["NHGRI NIH HHS"],"pubmed_abstract":["<h4>Introduction</h4>Perinatal depression affects up to 30% of pregnant and postpartum women, which has increased since the COVID-19 pandemic, making rapidly identifying affected women a high clinical priority. While screening tools like the Edinburgh Postnatal Depression Scale (EPDS) are widely used, brevity is important for busy clinical practice to reduce administration time and patient burden. Current methods to shorten assessments rely on traditional psychometric approaches, rather than machine learning (ML) methods that could optimize predictive accuracy.<h4>Methods</h4>We developed a ML framework using National Clinical Cohort Collaborative (N3C) data to predict full 10-item EPDS scores from shortened question subsets (n=22,924). We evaluated all 2-5 item combinations using linear r"],"journal":["medRxiv : the preprint server for health sciences"],"pagination":["2025.10.13.25337771"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12633091"],"repository":["biostudies-literature"],"pubmed_title":["Machine learning-optimized perinatal depression screening: Maximum impact, minimal burden."],"pmcid":["PMC12633091"],"funding_grant_id":["U24 HG011449","RM1 HG010860"],"pubmed_authors":["Bergink V","Haendel MA","Chugh K","Patel RC","Shell C","Schiller C","Hurwitz E"],"additional_accession":[]},"is_claimable":false,"name":"Machine learning-optimized perinatal depression screening: Maximum impact, minimal burden.","description":"<h4>Introduction</h4>Perinatal depression affects up to 30% of pregnant and postpartum women, which has increased since the COVID-19 pandemic, making rapidly identifying affected women a high clinical priority. While screening tools like the Edinburgh Postnatal Depression Scale (EPDS) are widely used, brevity is important for busy clinical practice to reduce administration time and patient burden. Current methods to shorten assessments rely on traditional psychometric approaches, rather than machine learning (ML) methods that could optimize predictive accuracy.<h4>Methods</h4>We developed a ML framework using National Clinical Cohort Collaborative (N3C) data to predict full 10-item EPDS scores from shortened question subsets (n=22,924). We evaluated all 2-5 item combinations using linear r","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Dec","modification":"2026-06-04T03:18:01.098Z","creation":"2026-06-04T03:12:02.078Z"},"accession":"S-EPMC12633091","cross_references":{"pubmed":["41282910"],"doi":["10.1101/2025.10.13.25337771"]}}