{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:33:44Z","timestamp":1785411224272,"version":"3.56.0"},"posted":{"date-parts":[[2026,5,22]]},"group-title":"Ophthalmology","reference-count":46,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["R00EY033027"],"award-info":[{"award-number":["R00EY033027"]}],"id":[{"id":"https:\/\/ror.org\/03wkg3b53","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R01EY029885"],"award-info":[{"award-number":["R01EY029885"]}],"id":[{"id":"https:\/\/ror.org\/03wkg3b53","id-type":"ROR","asserted-by":"publisher"}]},{"award":["R01EY036593"],"award-info":[{"award-number":["R01EY036593"]}],"id":[{"id":"https:\/\/ror.org\/03wkg3b53","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,5,22]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>Psychological distress is highly prevalent in glaucoma and is associated with worse adherence, reduced quality of life, and faster disease progression. However, distress is rarely assessed in ophthalmology settings due to time, workflow, and staffing constraints. We evaluated two artificial intelligence (AI)-based screening strategies, designed to efficiently identify distressed primary open angle glaucoma (POAG) patients during routine care, aiming to achieve effective, resource conscious, low burden clinical screening.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Design<\/jats:title>\n                  <jats:p>Hybrid retrospective cohort and prospective cross-sectional study.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Participants<\/jats:title>\n                  <jats:p>The retrospective cohort included &gt;3,000 POAG patients from the Duke Ophthalmic Registry. Prospective validation was conducted in a separate 300 POAG patient cohort who completed patient-reported distress screening.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Using retrospective data, a neural network model was trained to predict an electronic health record (EHR)-derived computable phenotype of distress (\u201csilver standard\u201d). Prospective validation used the 8-item Patient Health Questionnaire (PHQ-8) as the \u201cgold standard.\u201d Three screening strategies were compared against PHQ-8: (1) universal PHQ-2 screening (two-item screener administered to all patients), (2) AI-only screening (fully automated EHR-based screener), and (3) sequential screening, (only patients flagged as high risk by AI screener completed the PHQ-2). Performance metrics included sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and screening burden.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Main Outcome Measures<\/jats:title>\n                  <jats:p>Sensitivity; specificity; PPV; NPV; accuracy; proportion of patients requiring secondary screening (screening burden).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Distress prevalence was 17% (PHQ-8 &gt; 6). Universal PHQ-2 screening (&gt; 0) achieved high sensitivity (0.96) but lower specificity (0.73) and PPV (0.41), while requiring screening of all patients. The AI-assisted sequential approach substantially reduced screening burden while maintaining strong diagnostic performance. By administering PHQ-2 to \u223c25% of patients, sequential screening achieved sensitivity 0.64, specificity 0.93, PPV 0.64, NPV 0.93, and accuracy 0.88, representing a \u223c50% increase in PPV compared to PHQ-2 alone. AI-only screening reduced burden further but did not achieve comparable sensitivity or predictive performance.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>AI-assisted sequential screening enables scalable, resource efficient identification of psychological distress in glaucoma care, substantially reducing screening burden while preserving clinically meaningful performance. This framework offers a practical pathway for integrating distress screening into routine ophthalmology workflows and improving the identification and referral of at-risk patients.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.05.20.26353679","type":"posted-content","created":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T02:10:26Z","timestamp":1779502226000},"source":"Crossref","is-referenced-by-count":0,"title":["Design and Validation of an AI-Assisted Sequential Screening Framework for Psychological Distress in Glaucoma"],"prefix":"10.64898","author":[{"given":"Natalie A.","family":"Chou","sequence":"first","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youngsoo","family":"Baek","sequence":"additional","affiliation":[{"name":"Department of Biostatistics & Bioinformatics, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feilin","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Statistical Science, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics & Bioinformatics, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eun Young","family":"Choi","sequence":"additional","affiliation":[{"name":"Kaiser Permanente, Santa Clara Homestead Medical Center, Santa Clara, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah M.","family":"Fisher","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davina","family":"Malek","sequence":"additional","affiliation":[{"name":"Bascom Palmer Eye Institute, University of Miami, Miami, Florida, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Jammal","sequence":"additional","affiliation":[{"name":"Massachusetts Eye and Ear, Harvard University, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamara J.","family":"Somers","sequence":"additional","affiliation":[{"name":"Department of Psychiatry and Behavioral Sciences, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelly W.","family":"Muir","sequence":"additional","affiliation":[{"name":"Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe","family":"Medeiros","sequence":"additional","affiliation":[{"name":"Bascom Palmer Eye Institute, University of Miami, Miami, Florida, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel I.","family":"Berchuck","sequence":"additional","affiliation":[{"name":"Department of Biostatistics & Bioinformatics, Duke University, Durham, North Carolina, USA"},{"name":"Department of Statistical Science, Duke University, Durham, North Carolina, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026052610351277000_2026.05.20.26353679v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2014.05.013"},{"key":"2026052610351277000_2026.05.20.26353679v1.2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2014.3192"},{"key":"2026052610351277000_2026.05.20.26353679v1.3","doi-asserted-by":"publisher","DOI":"10.1097\/00061198-200304000-00009"},{"key":"2026052610351277000_2026.05.20.26353679v1.4","doi-asserted-by":"publisher","DOI":"10.1080\/08870449708407413"},{"key":"2026052610351277000_2026.05.20.26353679v1.5","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2020-316617"},{"key":"2026052610351277000_2026.05.20.26353679v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2017.07.021"},{"key":"2026052610351277000_2026.05.20.26353679v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2015.10.046"},{"key":"2026052610351277000_2026.05.20.26353679v1.8","doi-asserted-by":"publisher","DOI":"10.1097\/IJG.0b013e318163bdd1"},{"issue":"4","key":"2026052610351277000_2026.05.20.26353679v1.9","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1016\/j.ophtha.2015.12.014","article-title":"Fast visual field progression is associated with depressive symptoms in patients with glaucoma","volume":"123","year":"2016","journal-title":"Ophthalmology"},{"key":"2026052610351277000_2026.05.20.26353679v1.10","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2013-004632"},{"key":"2026052610351277000_2026.05.20.26353679v1.11","doi-asserted-by":"publisher","DOI":"10.2147\/PPA.S89336"},{"key":"2026052610351277000_2026.05.20.26353679v1.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2020.02.009"},{"key":"2026052610351277000_2026.05.20.26353679v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ogla.2019.03.010"},{"key":"2026052610351277000_2026.05.20.26353679v1.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ogla.2020.06.011"},{"key":"2026052610351277000_2026.05.20.26353679v1.15","doi-asserted-by":"publisher","DOI":"10.1080\/00981389.2018.1437499"},{"key":"2026052610351277000_2026.05.20.26353679v1.16","doi-asserted-by":"publisher","DOI":"10.1002\/pon.1228"},{"key":"2026052610351277000_2026.05.20.26353679v1.17","doi-asserted-by":"publisher","DOI":"10.6004\/jnccn.2013.0029"},{"key":"2026052610351277000_2026.05.20.26353679v1.18","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.108.190769"},{"key":"2026052610351277000_2026.05.20.26353679v1.19","doi-asserted-by":"publisher","DOI":"10.1054\/bjoc.2001.2182"},{"key":"2026052610351277000_2026.05.20.26353679v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/pon.1368"},{"key":"2026052610351277000_2026.05.20.26353679v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ogla.2026.02.006"},{"key":"2026052610351277000_2026.05.20.26353679v1.22","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000000038"},{"issue":"2","key":"2026052610351277000_2026.05.20.26353679v1.23","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/s11886-013-0451-6","article-title":"Improving cardiovascular outcomes using electronic health records","volume":"16","year":"2014","journal-title":"Current cardiology reports"},{"issue":"2","key":"2026052610351277000_2026.05.20.26353679v1.24","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/MIS.2013.51","article-title":"Using artificial intelligence to improve hospital inpatient care","volume":"28","year":"2013","journal-title":"IEEE Intelligent Systems"},{"key":"2026052610351277000_2026.05.20.26353679v1.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.03.009"},{"issue":"10","key":"2026052610351277000_2026.05.20.26353679v1.26","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1176\/appi.ajp.2018.17101167","article-title":"Predicting suicide attempts and suicide deaths following outpatient visits using electronic health records","volume":"175","year":"2018","journal-title":"American Journal of Psychiatry"},{"key":"2026052610351277000_2026.05.20.26353679v1.27","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.11.10.6"},{"key":"2026052610351277000_2026.05.20.26353679v1.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ogla.2025.09.004"},{"key":"2026052610351277000_2026.05.20.26353679v1.29","unstructured":"Kingma DP , Ba J. Adam: A Method for Stochastic Optimization. 2014\/12\/\/ 2014;"},{"issue":"1","key":"2026052610351277000_2026.05.20.26353679v1.30","first-page":"335","article-title":"Early stopping and non-parametric regression: an optimal data-dependent stopping rule","volume":"15","year":"2014","journal-title":"J Mach Learn Res"},{"key":"2026052610351277000_2026.05.20.26353679v1.31","doi-asserted-by":"crossref","unstructured":"Kroenke K , Spitzer RL . The PHQ-9: a new depression diagnostic and severity measure. Slack Incorporated Thorofare, NJ; 2002. p. 509\u2013515.","DOI":"10.3928\/0048-5713-20020901-06"},{"key":"2026052610351277000_2026.05.20.26353679v1.32","doi-asserted-by":"publisher","DOI":"10.1017\/s0033291719001314"},{"key":"2026052610351277000_2026.05.20.26353679v1.33","doi-asserted-by":"publisher","DOI":"10.1017\/s0033291722002835"},{"key":"2026052610351277000_2026.05.20.26353679v1.34","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2023-076193"},{"key":"2026052610351277000_2026.05.20.26353679v1.35","doi-asserted-by":"publisher","DOI":"10.1002\/lary.30000"},{"key":"2026052610351277000_2026.05.20.26353679v1.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.01.041"},{"key":"2026052610351277000_2026.05.20.26353679v1.37","doi-asserted-by":"publisher","DOI":"10.1002\/bimj.200410135"},{"key":"2026052610351277000_2026.05.20.26353679v1.38","doi-asserted-by":"publisher","DOI":"10.3389\/fmolb.2016.00035"},{"key":"2026052610351277000_2026.05.20.26353679v1.39","doi-asserted-by":"crossref","unstructured":"Shapley LS . 17. A Value for n-Person Games. In: Harold William K , Albert William T , eds. Contributions to the Theory of Games, Volume II. Princeton University Press; 1953:307\u2013318.","DOI":"10.1515\/9781400881970-018"},{"key":"2026052610351277000_2026.05.20.26353679v1.40","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"key":"2026052610351277000_2026.05.20.26353679v1.41","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v077.i01"},{"key":"2026052610351277000_2026.05.20.26353679v1.42","unstructured":"Dorogush AV , Ershov V , Gulin A. CatBoost: gradient boosting with categorical features support. 2018\/10\/\/ 2018;"},{"key":"2026052610351277000_2026.05.20.26353679v1.43","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21672"},{"key":"2026052610351277000_2026.05.20.26353679v1.44","doi-asserted-by":"publisher","DOI":"10.1007\/s10900-016-0162-1"},{"key":"2026052610351277000_2026.05.20.26353679v1.45","doi-asserted-by":"publisher","DOI":"10.1017\/s2045796019000799"},{"key":"2026052610351277000_2026.05.20.26353679v1.46","doi-asserted-by":"publisher","DOI":"10.2147\/opth.S258783"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.05.20.26353679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T17:35:20Z","timestamp":1779816920000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.05.20.26353679"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":46,"URL":"https:\/\/doi.org\/10.64898\/2026.05.20.26353679","relation":{},"subject":[],"published":{"date-parts":[[2026,5,22]]},"subtype":"preprint"}}