{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T18:26:12Z","timestamp":1770488772520,"version":"3.49.0"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2017,11,21]],"date-time":"2017-11-21T00:00:00Z","timestamp":1511222400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Systems for Action National Coordinating Center","award":["73485"],"award-info":[{"award-number":["73485"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Introduction<\/jats:title>\n                  <jats:p>A growing variety of diverse data sources is emerging to better inform health care delivery and health outcomes. We sought to evaluate the capacity for clinical, socioeconomic, and public health data sources to predict the need for various social service referrals among patients at a safety-net hospital.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We integrated patient clinical data and community-level data representing patients\u2019 social determinants of health (SDH) obtained from multiple sources to build random forest decision models to predict the need for any, mental health, dietitian, social work, or other SDH service referrals. To assess the impact of SDH on improving performance, we built separate decision models using clinical and SDH determinants and clinical data only.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Decision models predicting the need for any, mental health, and dietitian referrals yielded sensitivity, specificity, and accuracy measures ranging between 60% and 75%. Specificity and accuracy scores for social work and other SDH services ranged between 67% and 77%, while sensitivity scores were between 50% and 63%. Area under the receiver operating characteristic curve values for the decision models ranged between 70% and 78%. Models for predicting the need for any services reported positive predictive values between 65% and 73%. Positive predictive values for predicting individual outcomes were below 40%.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>The need for various social service referrals can be predicted with considerable accuracy using a wide range of readily available clinical and community data that measure socioeconomic and public health conditions. While the use of SDH did not result in significant performance improvements, our approach represents a novel and important application of risk predictive modeling.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocx130","type":"journal-article","created":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T19:09:43Z","timestamp":1508440183000},"page":"47-53","source":"Crossref","is-referenced-by-count":59,"title":["Assessing the capacity of social determinants of health data to augment predictive models identifying patients in need of wraparound social services"],"prefix":"10.1093","volume":"25","author":[{"given":"Suranga N","family":"Kasthurirathne","sequence":"first","affiliation":[{"name":"Indiana University School of Informatics and Computing, Indianapolis, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua R","family":"Vest","sequence":"additional","affiliation":[{"name":"Indiana University Richard M. Fairbanks School of Public Health, Indianapolis, IN, USA"},{"name":"Regenstrief Institute, Indianapolis, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nir","family":"Menachemi","sequence":"additional","affiliation":[{"name":"Indiana University Richard M. Fairbanks School of Public Health, Indianapolis, IN, USA"},{"name":"Regenstrief Institute, Indianapolis, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul K","family":"Halverson","sequence":"additional","affiliation":[{"name":"Indiana University Richard M. Fairbanks School of Public Health, Indianapolis, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaun J","family":"Grannis","sequence":"additional","affiliation":[{"name":"Regenstrief Institute, Indianapolis, IN, USA"},{"name":"Indiana University School of Medicine, Indianapolis, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,11,21]]},"reference":[{"issue":"7","key":"2020110612455004800_ocx130-B1","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1377\/hlthaff.2014.0147","article-title":"Creating value in health care through big data: opportunities and policy implications","volume":"33","author":"Roski","year":"2014","journal-title":"Health Affairs."},{"key":"2020110612455004800_ocx130-B2","volume-title":"Adoption of Electronic Health Record Systems among US Non-Federal Acute Care Hospitals: 2008\u20132014","author":"Charles","year":"2016"},{"issue":"8","key":"2020110612455004800_ocx130-B3","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1377\/hlthaff.2013.0010","article-title":"Hospital electronic health information exchange grew substantially in 2008\u201312","volume":"32","author":"Furukawa","year":"2013","journal-title":"Health Affairs."},{"key":"2020110612455004800_ocx130-B4","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1177\/00333549111260S310","article-title":"Incorporating geospatial capacity within clinical data systems to address social determinants of health","volume":"126","author":"Comer","year":"2011","journal-title":"Public Health Rep."},{"issue":"13","key":"2020110612455004800_ocx130-B5","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1001\/jama.2013.393","article-title":"The inevitable application of big data to health care","volume":"309","author":"Murdoch","year":"2013","journal-title":"JAMA."},{"issue":"23","key":"2020110612455004800_ocx130-B6","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.1056\/NEJMp1401111","article-title":"Learning from big health care data","volume":"370","author":"Schneeweiss","year":"2014","journal-title":"New Engl J Med."},{"issue":"7","key":"2020110612455004800_ocx130-B7","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1377\/hlthaff.2014.0041","article-title":"Big data in health care: using analytics to identify and manage high-risk and high-cost patients","volume":"33","author":"Bates","year":"2014","journal-title":"Health Affairs."},{"issue":"7","key":"2020110612455004800_ocx130-B8","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.1377\/hlthaff.2014.0053","article-title":"Big data and new knowledge in medicine: the thinking, training, and tools needed for a learning health system","volume":"33","author":"Krumholz","year":"2014","journal-title":"Health Affairs."},{"key":"2020110612455004800_ocx130-B9","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1001\/jama.2011.1515","article-title":"Risk prediction models for hospital readmission: a systematic review","volume":"306","author":"Kansagara","year":"2011","journal-title":"JAMA."},{"key":"2020110612455004800_ocx130-B10","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1089\/109350702760301448","article-title":"An introduction to predictive modeling for disease management risk stratification","volume":"5","author":"Cousins","year":"2002","journal-title":"Dis Manage."},{"key":"2020110612455004800_ocx130-B11","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1377\/hlthaff.2015.1311","article-title":"Patient segmentation analysis offers significant benefits for integrated care and support","volume":"35","author":"Vuik","year":"2016","journal-title":"Health Affairs."},{"issue":"12","key":"2020110612455004800_ocx130-B12","first-page":"827","article-title":"Getting from here to there: health IT needs for population health","volume":"22","author":"Vest","year":"2016","journal-title":"Am J Managed Care."},{"issue":"13","key":"2020110612455004800_ocx130-B13","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1001\/jama.2016.12260","article-title":"Will precision medicine improve population health?","volume":"316","author":"Khoury","year":"2016","journal-title":"JAMA."},{"issue":"8","key":"2020110612455004800_ocx130-B14","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1016\/j.apmr.2012.04.028","article-title":"Use of neighborhood characteristics to improve prediction of psychosocial outcomes: a traumatic brain injury model systems investigation","volume":"93","author":"Corrigan","year":"2012","journal-title":"Arch Phys Med Rehabil."},{"issue":"8","key":"2020110612455004800_ocx130-B15","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1097\/01.mlr.0000223475.70440.07","article-title":"In search of the perfect comorbidity measure for use with administrative claims data: does it exist?","volume":"44","author":"Baldwin","year":"2006","journal-title":"Med Care."},{"key":"2020110612455004800_ocx130-B16","doi-asserted-by":"crossref","DOI":"10.1109\/BigData.2013.6691760","article-title":"Big data solutions for predicting risk-of-readmission for congestive heart failure patients","volume-title":"2013 IEEE International Conference on Big Data","author":"Zolfaghar","year":"2013"},{"issue":"22","key":"2020110612455004800_ocx130-B17","doi-asserted-by":"crossref","first-page":"2666","DOI":"10.1001\/jama.2008.792","article-title":"Socioeconomic status and coronary heart disease risk prediction","volume":"300","author":"Fiscella","year":"2008","journal-title":"JAMA."},{"issue":"1","key":"2020110612455004800_ocx130-B18","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/1472-6947-11-51","article-title":"Predicting disease risks from highly imbalanced data using random forest","volume":"11","author":"Khalilia","year":"2011","journal-title":"BMC Med Inform Dec Mak."},{"issue":"5","key":"2020110612455004800_ocx130-B19","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1370\/afm.1167","article-title":"Including socioeconomic status in coronary heart disease risk estimation","volume":"8","author":"Franks","year":"2010","journal-title":"Ann Fam Med."},{"key":"2020110612455004800_ocx130-B20","volume-title":"Capturing Social and Behavioral Domains in Electronic Health Records, Phase 1","author":"Institute of Medicine, Board on Population Health and Public Health Practice, Committee on the Recommended Social and Behavioral Domains and Measures for Electronic Health Records","year":"2014"},{"issue":"9","key":"2020110612455004800_ocx130-B21","first-page":"725","article-title":"Risk-stratification methods for identifying patients for care coordination","volume":"19","author":"Haas","year":"2013","journal-title":"Am J Managed Care."},{"issue":"4","key":"2020110612455004800_ocx130-B22","first-page":"206","article-title":"The Regenstrief Medical Record System: 20 years of experience in hospitals, clinics, and neighborhood health centers","volume":"9","author":"McDonald","year":"1991","journal-title":"MD Comput."},{"issue":"5","key":"2020110612455004800_ocx130-B23","doi-asserted-by":"crossref","first-page":"1214","DOI":"10.1377\/hlthaff.24.5.1214","article-title":"The Indiana network for patient care: a working local health information infrastructure","volume":"24","author":"McDonald","year":"2005","journal-title":"Health Affairs."},{"key":"2020110612455004800_ocx130-B24","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/B978-0-12-803135-3.00027-X","article-title":"The Indiana health information exchange","volume-title":"Health Information Exchange: Navigating and Managing a Network of Health Information Systems","author":"Overhage","year":"2016","edition":"1st ed."},{"key":"2020110612455004800_ocx130-B25","doi-asserted-by":"crossref","DOI":"10.5888\/pcd10.120239","article-title":"Peer reviewed: defining and measuring chronic conditions: imperatives for research, policy, program, and practice","volume":"10","author":"Goodman","year":"2013","journal-title":"Prev Chronic Dis."},{"issue":"4","key":"2020110612455004800_ocx130-B26","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1136\/amiajnl-2012-001557","article-title":"ICD-9 tobacco use codes are effective identifiers of smoking status","volume":"20","author":"Wiley","year":"2013","journal-title":"J Am Med Inform Assoc."},{"issue":"12","key":"2020110612455004800_ocx130-B27","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.jclinepi.2008.01.006","article-title":"The Charlson comorbidity index is adapted to predict costs of chronic disease in primary care patients","volume":"61","author":"Charlson","year":"2008","journal-title":"J Clin Epidemiol."},{"issue":"10","key":"2020110612455004800_ocx130-B28","article-title":"Beyond health care: the role of social determinants in promoting health and health equity","volume":"20","author":"Heiman","year":"2015","journal-title":"Health."},{"issue":"3","key":"2020110612455004800_ocx130-B29","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1002\/wics.35","article-title":"Sturges\u2019 rule","volume":"1","author":"Scott","year":"2009","journal-title":"Wiley Interdiscip Rev Comput Stat."},{"key":"2020110612455004800_ocx130-B30","article-title":"Class imbalance problem in data mining review","author":"Longadge","year":"2013","journal-title":"arXiv preprint arXiv:13051707."},{"key":"2020110612455004800_ocx130-B31","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res."},{"issue":"2","key":"2020110612455004800_ocx130-B32","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach Learn."},{"issue":"3","key":"2020110612455004800_ocx130-B33","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News."},{"key":"2020110612455004800_ocx130-B34","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res."},{"key":"2020110612455004800_ocx130-B35","doi-asserted-by":"crossref","first-page":"2023","DOI":"10.1007\/978-1-4419-9863-7_1184","article-title":"Student\u2019s t-test","volume-title":"Encyclopedia of Systems Biology","author":"Haynes","year":"2013"},{"issue":"1","key":"2020110612455004800_ocx130-B36","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer."},{"issue":"4857","key":"2020110612455004800_ocx130-B37","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1126\/science.3287615","article-title":"Measuring the accuracy of diagnostic systems","volume":"240","author":"Swets","year":"1988","journal-title":"Science."},{"issue":"5","key":"2020110612455004800_ocx130-B38","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1161\/CIRCHEARTFAILURE.112.000043","article-title":"Risk prediction models for mortality in ambulatory heart failure patients: a systematic review","volume":"6","author":"Alba","year":"2013","journal-title":"Circ Heart Fail."},{"issue":"15","key":"2020110612455004800_ocx130-B39","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1001\/jama.2011.1515","article-title":"Risk prediction models for hospital readmission: a systematic review","volume":"306","author":"Kansagara","year":"2011","journal-title":"JAMA."},{"issue":"7","key":"2020110612455004800_ocx130-B40","doi-asserted-by":"crossref","first-page":"e67370","DOI":"10.1371\/journal.pone.0067370","article-title":"Risk models to predict hypertension: a systematic review","volume":"8","author":"Echouffo-Tcheugui","year":"2013","journal-title":"PLoS ONE."},{"key":"2020110612455004800_ocx130-B41","article-title":"Patients as customers: applying service industry lessons to health care","volume-title":"Healthcare","author":"Powers","year":"2013"},{"issue":"5","key":"2020110612455004800_ocx130-B42","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1080\/00981389.2015.1025122","article-title":"Moving toward integrated health: an opportunity for social work","volume":"54","author":"Stanhope","year":"2015","journal-title":"Soc Work Health Care."},{"issue":"9","key":"2020110612455004800_ocx130-B43","doi-asserted-by":"crossref","first-page":"1697","DOI":"10.1377\/hlthaff.2010.0038","article-title":"Medical-legal partnerships: transforming primary care by addressing the legal needs of vulnerable populations","volume":"29","author":"Sandel","year":"2010","journal-title":"Health Affairs."},{"issue":"5","key":"2020110612455004800_ocx130-B44","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1370\/afm.1840","article-title":"Primary care physician insights into a typology of the complex patient in primary care","volume":"13","author":"Loeb","year":"2015","journal-title":"Ann Fam Med."},{"issue":"3","key":"2020110612455004800_ocx130-B45","doi-asserted-by":"crossref","first-page":"169","DOI":"10.7326\/0003-4819-158-3-201302050-00579","article-title":"The patient-centered medical home: a systematic review","volume":"158","author":"Jackson","year":"2013","journal-title":"Ann Int Med."},{"issue":"2","key":"2020110612455004800_ocx130-B46","doi-asserted-by":"crossref","first-page":"2","DOI":"10.13063\/2327-9214.1282","article-title":"Integrating social determinants of health into primary care clinical and informational workflow during care transitions","volume":"5","author":"Hewner","year":"2017","journal-title":"eGEMS."},{"issue":"3","key":"2020110612455004800_ocx130-B47","doi-asserted-by":"crossref","first-page":"350","DOI":"10.4300\/JGME-D-10-00199.1","article-title":"Missed appointments in resident continuity clinic: patient characteristics and health care outcomes","volume":"3","author":"Nguyen","year":"2011","journal-title":"J Grad Med Educ."},{"issue":"8","key":"2020110612455004800_ocx130-B48","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1089\/apc.2013.0073","article-title":"Missed office visits and risk of mortality among HIV-infected subjects in a large healthcare system in the United States","volume":"27","author":"Horberg","year":"2013","journal-title":"AIDS Patient Care STDs."},{"key":"2020110612455004800_ocx130-B49","first-page":"230","article-title":"Development and performance of text-mining algorithms to extract socioeconomic status from de-identified electronic health records","volume":"22","author":"Hollister","year":"2017","journal-title":"Pac Symp Biocomput."}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/1\/47\/34149726\/ocx130.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/25\/1\/47\/34149726\/ocx130.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T18:32:05Z","timestamp":1604687525000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/25\/1\/47\/4645255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,21]]},"references-count":49,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2017,11,21]]},"published-print":{"date-parts":[[2018,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocx130","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,1]]},"published":{"date-parts":[[2017,11,21]]}}}