{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:45:49Z","timestamp":1768571149694,"version":"3.49.0"},"posted":{"date-parts":[[2025,7,14]]},"group-title":"Health Informatics","reference-count":60,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T00:00:00Z","timestamp":1752451200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,7,14]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:p>\n                  Eviction is a significant yet understudied social determinants of health (SDoH), linked to housing instability, unemployment, and mental health. While eviction appears in unstructured electronic health records (EHRs), it is rarely coded in structured fields, limiting downstream applications. We introduce\n                  <jats:italic>SynthEHR-Eviction<\/jats:italic>\n                  , a scalable pipeline combining LLMs, human-in-the-loop annotation, and automated prompt optimization (APO) to extract eviction statuses from clinical notes. Using this pipeline, we created the largest public eviction-related SDoH dataset to date, comprising 14 fine-grained categories. Fine-tuned LLMs (e.g., Qwen2.5, LLaMA3) trained on SynthEHR-Eviction achieved Macro-F1 scores of 88.8% (eviction) and 90.3% (other SDoH) on human validated data, outperforming GPT-4o-APO (87.8%, 87.3%), GPT-4o-mini-APO (69.1%, 78.1%), and BioBERT (60.7%, 68.3%), while enabling cost-effective deployment across various model sizes. The pipeline reduces annotation effort by over 80%, accelerates dataset creation, enables scalable eviction detection, and generalizes to other information extraction tasks.\n                <\/jats:p>","DOI":"10.1101\/2025.07.10.25331237","type":"posted-content","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:11Z","timestamp":1752537611000},"source":"Crossref","is-referenced-by-count":0,"title":["SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5707-8410","authenticated-orcid":false,"given":"Zonghai","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youxia","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avijit","family":"Mitra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David A.","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily","family":"Druhl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025071607500632000_2025.07.10.25331237v1.1","unstructured":"National Center for Complementary and Integrative Health. Whole person health: What it is and why it\u2019s important. https:\/\/www.nccih.nih.gov\/health\/whole-person-health-what-it-is-and-why-its-important (n.d.). Accessed: 2025-03-17."},{"key":"2025071607500632000_2025.07.10.25331237v1.2","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1097\/MLR.0000000000001316","article-title":"Transforming the veterans affairs to a whole health system of care: time for action and research","volume":"58","year":"2020","journal-title":"Med. Care"},{"key":"2025071607500632000_2025.07.10.25331237v1.3","unstructured":"Organization, W. H. Social determinants of health. http:\/\/www.who.int\/social determinants\/sdh definition\/en\/ (n.d.). Accessed: 2025-03-17."},{"key":"2025071607500632000_2025.07.10.25331237v1.4","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.amepre.2015.08.024","article-title":"County health rankings: relationships between determinant factors and health outcomes","volume":"50","year":"2016","journal-title":"Am. journal preventive medicine"},{"key":"2025071607500632000_2025.07.10.25331237v1.5","first-page":"E14","article-title":"Leveraging data and digital health technologies to assess and impact social determinants of health (sdoh): a state-of-the-art literature review. Online J","volume":"13","year":"2021","journal-title":"Public Heal. Informatics"},{"key":"2025071607500632000_2025.07.10.25331237v1.6","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1186\/s12913-025-12494-2","article-title":"Impact of hospital and health system initiatives to address social determinants of health (sdoh) in the united states: a scoping review of the peer-reviewed literature","volume":"25","year":"2025","journal-title":"BMC Heal. Serv. Res"},{"key":"2025071607500632000_2025.07.10.25331237v1.7","doi-asserted-by":"crossref","first-page":"1679","DOI":"10.1007\/s00127-020-01953-2","article-title":"Longitudinal study of the housing and mental health outcomes of tenants appearing in eviction court","volume":"56","year":"2021","journal-title":"Soc. psychiatry psychiatric epidemiology"},{"key":"2025071607500632000_2025.07.10.25331237v1.8","doi-asserted-by":"crossref","first-page":"e2239860","DOI":"10.1001\/jamanetworkopen.2022.39860","article-title":"Association of promoting housing affordability and stability with improved health outcomes: a systematic review","volume":"5","year":"2022","journal-title":"JAMA Netw. Open"},{"key":"2025071607500632000_2025.07.10.25331237v1.9","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1377\/hlthaff.2023.01332","article-title":"Transportation as a determinant of health: Evaluating the veterans affairs rideshare program for homeless patients: Article examines the veterans affairs rideshare program for homeless patients","volume":"43","year":"2024","journal-title":"Heal. Aff"},{"key":"2025071607500632000_2025.07.10.25331237v1.10","doi-asserted-by":"crossref","first-page":"101887","DOI":"10.1016\/j.jth.2024.101887","article-title":"Understanding transportation-related health determinants and their interrelationships in rural us","volume":"38","year":"2024","journal-title":"J. Transp. & Heal"},{"key":"2025071607500632000_2025.07.10.25331237v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00970-0"},{"key":"2025071607500632000_2025.07.10.25331237v1.12","unstructured":"Wikipedia contributors. Eviction in the united states. https:\/\/en.wikipedia.org\/wiki\/Eviction in the United States (n.d.). Accessed: 2025-03-17."},{"key":"2025071607500632000_2025.07.10.25331237v1.13","doi-asserted-by":"publisher","DOI":"10.1093\/sf\/sov044"},{"key":"2025071607500632000_2025.07.10.25331237v1.14","unstructured":"Desmond, M. Evicted: Poverty and Profit in the American City (Crown, New York City, USA, 2016)."},{"key":"2025071607500632000_2025.07.10.25331237v1.15","first-page":"e1","article-title":"Systematic review of psychosocial factors associated with evictions","volume":"27","year":"2019","journal-title":"Heal. Soc. Care Community"},{"key":"2025071607500632000_2025.07.10.25331237v1.16","doi-asserted-by":"crossref","first-page":"649","DOI":"10.15195\/v7.a27","article-title":"Racial and gender disparities among evicted americans","volume":"7","year":"2020","journal-title":"Sociol. Sci"},{"key":"2025071607500632000_2025.07.10.25331237v1.17","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.27978"},{"key":"2025071607500632000_2025.07.10.25331237v1.18","first-page":"1","article-title":"Mimic-iii, a freely accessible critical care database","volume":"3","year":"2016","journal-title":"Sci. data"},{"key":"2025071607500632000_2025.07.10.25331237v1.19","unstructured":"Johnson, A. et al. Mimic-iv. PhysioNet. Available online at: https:\/\/physionet.org\/content\/mimiciv\/1.0\/(accessed August 23, 2021) p49\u201355 (2020)."},{"key":"2025071607500632000_2025.07.10.25331237v1.20","unstructured":"for Medicare & Medicaid Services (CMS), C. Improving the collection of social determinants of health (sdoh) data with icd-10-cm z codes (2023). Retrieved from https:\/\/go.cms.gov\/OMH."},{"key":"2025071607500632000_2025.07.10.25331237v1.21","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/s41666-024-00159-4","article-title":"Clinical information retrieval: a literature review","volume":"8","year":"2024","journal-title":"J. healthcare informatics research"},{"key":"2025071607500632000_2025.07.10.25331237v1.22","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560"},{"key":"2025071607500632000_2025.07.10.25331237v1.23","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1055\/s-0040-1702001","article-title":"Medical information extraction in the age of deep learning","volume":"29","year":"2020","journal-title":"Yearb. medical informatics"},{"key":"2025071607500632000_2025.07.10.25331237v1.24","unstructured":"Hu, Y. et al. Information extraction from clinical notes: Are we ready to switch to large language models? arXiv preprint arXiv:2411.10020 (2024)."},{"key":"2025071607500632000_2025.07.10.25331237v1.25","first-page":"1","article-title":"Social determinants of health extraction from clinical notes across institutions using large language models. npj Digit","volume":"8","year":"2025","journal-title":"Medicine"},{"key":"2025071607500632000_2025.07.10.25331237v1.26","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocab170"},{"key":"2025071607500632000_2025.07.10.25331237v1.27","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad081"},{"key":"2025071607500632000_2025.07.10.25331237v1.28","unstructured":"Ramnath, K. et al. A systematic survey of automatic prompt optimization techniques. arXiv preprint arXiv:2502.16923 (2025)."},{"key":"2025071607500632000_2025.07.10.25331237v1.29","unstructured":"Khattab, O. et al. Dspy: Compiling declarative language model calls into self-improving pipelines. arXiv preprint arXiv:2310.03714 (2023)."},{"key":"2025071607500632000_2025.07.10.25331237v1.30","doi-asserted-by":"crossref","unstructured":"Magister, L. C. , Mallinson, J. , Adamek, J. , Malmi, E. & Severyn, A. Teaching small language models to reason. arXiv preprint arXiv:2212.08410 (2022).","DOI":"10.18653\/v1\/2023.acl-short.151"},{"key":"2025071607500632000_2025.07.10.25331237v1.31","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1038\/s41597-023-02814-8","article-title":"A large-scale dataset of patient summaries for retrieval-based clinical decision support systems","volume":"10","year":"2023","journal-title":"Sci. data"},{"key":"2025071607500632000_2025.07.10.25331237v1.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssresearch.2016.08.017"},{"key":"2025071607500632000_2025.07.10.25331237v1.33","first-page":"8241","article-title":"Leveraging large language models for knowledge-free weak supervision in clinical natural language processing","volume":"15","year":"2025","journal-title":"Sci. reports"},{"key":"2025071607500632000_2025.07.10.25331237v1.34","unstructured":"Zhang, J. , Hsieh, C.-Y. , Yu, Y. , Zhang, C. & Ratner, A. A survey on programmatic weak supervision. arXiv preprint arXiv:2202.05433 (2022)."},{"key":"2025071607500632000_2025.07.10.25331237v1.35","first-page":"1","article-title":"Data-centric artificial intelligence: A survey","volume":"57","year":"2025","journal-title":"ACM Comput. Surv"},{"key":"2025071607500632000_2025.07.10.25331237v1.36","doi-asserted-by":"crossref","unstructured":"Wang, Y. et al. Promda: Prompt-based data augmentation for low-resource nlu tasks. arXiv preprint arXiv:2202.12499 (2022).","DOI":"10.18653\/v1\/2022.acl-long.292"},{"key":"2025071607500632000_2025.07.10.25331237v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103984"},{"key":"2025071607500632000_2025.07.10.25331237v1.38","doi-asserted-by":"crossref","first-page":"e233079","DOI":"10.1001\/jamanetworkopen.2023.3079","article-title":"Associations between natural language processing\u2013enriched social determinants of health and suicide death among us veterans","volume":"6","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"2025071607500632000_2025.07.10.25331237v1.39","unstructured":"Majid, I. , Mishra, V. , Ravindranath, R. & Wang, S. Y. Evaluating the performance of large language models for named entity recognition in ophthalmology clinical free-text notes. In AMIA Annual Symposium Proceedings, vol. 2024, 778 (2025)."},{"key":"2025071607500632000_2025.07.10.25331237v1.40","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1038\/s41746-025-01476-7","article-title":"Implementing large language models in healthcare while balancing control, collaboration, costs and security","volume":"8","year":"2025","journal-title":"npj Digit. Medicine"},{"key":"2025071607500632000_2025.07.10.25331237v1.41","doi-asserted-by":"crossref","unstructured":"Kougia, V. , Sedova, A. , Stephan, A. , Zaporojets, K. & Roth, B. Analysing zero-shot temporal relation extraction on clinical notes using temporal consistency. arXiv preprint arXiv:2406.11486 (2024).","DOI":"10.18653\/v1\/2024.bionlp-1.6"},{"key":"2025071607500632000_2025.07.10.25331237v1.42","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1162\/tacl_a_00172","article-title":"Temporal annotation in the clinical domain","volume":"2","year":"2014","journal-title":"Transactions association for computational linguistics"},{"key":"2025071607500632000_2025.07.10.25331237v1.43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S16-1165"},{"key":"2025071607500632000_2025.07.10.25331237v1.44","unstructured":"Liu, Z. , Han, P. , Yu, H. , Li, H. & You, J. Time-r1: Towards comprehensive temporal reasoning in llms. arXiv preprint arXiv:2505.13508 (2025)."},{"key":"2025071607500632000_2025.07.10.25331237v1.45","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","year":"2022","journal-title":"Adv. neural information processing systems"},{"key":"2025071607500632000_2025.07.10.25331237v1.46","unstructured":"Mitra, A. et al. Orca 2: Teaching small language models how to reason. arXiv preprint arXiv:2311.11045 (2023)."},{"key":"2025071607500632000_2025.07.10.25331237v1.47","unstructured":"Yeo, W. J. , Satapathy, R. , Goh, R. S. M. & Cambria, E. How interpretable are reasoning explanations from prompting large language models? arXiv preprint arXiv:2402.11863 (2024)."},{"key":"2025071607500632000_2025.07.10.25331237v1.48","unstructured":"Bilal, A. , Ebert, D. & Lin, B. Llms for explainable ai: A comprehensive survey. arXiv preprint arXiv:2504.00125 (2025)."},{"key":"2025071607500632000_2025.07.10.25331237v1.49","unstructured":"Agarwal, C. , Tanneru, S. H. & Lakkaraju, H. Faithfulness vs. plausibility: On the (un) reliability of explanations from large language models. arXiv preprint arXiv:2402.04614 (2024)."},{"key":"2025071607500632000_2025.07.10.25331237v1.50","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1038\/s41746-024-01185-7","article-title":"Hidden flaws behind expert-level accuracy of multimodal gpt-4 vision in medicine","volume":"7","year":"2024","journal-title":"npj Digit. Medicine"},{"key":"2025071607500632000_2025.07.10.25331237v1.51","doi-asserted-by":"crossref","first-page":"e65146","DOI":"10.2196\/65146","article-title":"Unveiling gpt-4v\u2019s hidden challenges behind high accuracy on usmle questions: Observational study","volume":"27","year":"2025","journal-title":"J. Med. Internet Res"},{"key":"2025071607500632000_2025.07.10.25331237v1.52","doi-asserted-by":"crossref","unstructured":"Paul, D. , West, R. , Bosselut, A. & Faltings, B. Making reasoning matter: Measuring and improving faithfulness of chain-of-thought reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2024, 15012\u201315032 (2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.882"},{"key":"2025071607500632000_2025.07.10.25331237v1.53","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-024-05005-y"},{"key":"2025071607500632000_2025.07.10.25331237v1.54","unstructured":"Kim, Y. et al. Medical hallucinations in foundation models and their impact on healthcare. arXiv preprint arXiv:2503.05777 (2025)."},{"key":"2025071607500632000_2025.07.10.25331237v1.55","doi-asserted-by":"publisher","DOI":"10.1145\/3561048"},{"key":"2025071607500632000_2025.07.10.25331237v1.56","doi-asserted-by":"crossref","unstructured":"Mishra, P. et al. Synfac-edit: Synthetic imitation edit feedback for factual alignment in clinical summarization. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 20061\u201320083 (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.1120"},{"key":"2025071607500632000_2025.07.10.25331237v1.57","doi-asserted-by":"crossref","unstructured":"Yao, Z. , Schloss, B. & Selvaraj, S. Improving summarization with human edits. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2604\u20132620 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.158"},{"key":"2025071607500632000_2025.07.10.25331237v1.58","doi-asserted-by":"crossref","unstructured":"Yao, Z. & Yu, H. A survey on llm-based multi-agent ai hospital. OSF (2025).","DOI":"10.31219\/osf.io\/bv5sg_v1"},{"key":"2025071607500632000_2025.07.10.25331237v1.59","doi-asserted-by":"crossref","unstructured":"Tsai, J. et al. Development of a surveillance system to identify incidence of evictions among patients in veterans affairs medical centers across the united states. J. Community Heal. 1\u201310 (2025).","DOI":"10.1007\/s10900-025-01491-5"},{"key":"2025071607500632000_2025.07.10.25331237v1.60","doi-asserted-by":"crossref","unstructured":"Yao, Z. , Jaafar, A. , Wang, B. , Yang, Z. & Yu, H. Do clinicians know how to prompt? the need for automatic prompt optimization help in clinical note generation. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, 182\u2013201 (2024).","DOI":"10.18653\/v1\/2024.bionlp-1.15"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.10.25331237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:40:28Z","timestamp":1768509628000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.07.10.25331237"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,14]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1101\/2025.07.10.25331237","relation":{},"subject":[],"published":{"date-parts":[[2025,7,14]]},"subtype":"preprint"}}