Hadi Kharrazi1,2, Hsien-Yen Chang1, Sara E Heins1,3, Jonathan P Weiner1, Kimberly A Gudzune4,5. 1. Department of Health Policy and Management, Center for Population Health IT, Johns Hopkins Bloomberg School of Public Health. 2. Division of Health Sciences and Informatics, Johns Hopkins School of Medicine, Baltimore, MD. 3. RAND Corporation, Pittsburgh, PA. 4. Department of Medicine, Division of General Internal Medicine, Johns Hopkins University School of Medicine. 5. Welch Center for Prevention, Epidemiology, and Clinical Research, Johns Hopkins Medical Institution, Baltimore, MD.
Abstract
BACKGROUND: Using electronic health records (EHRs) for population risk stratification has gained attention in recent years. Compared with insurance claims, EHRs offer novel data types (eg, vital signs) that can potentially improve population-based predictive models of cost and utilization. OBJECTIVE: To evaluate whether EHR-extracted body mass index (BMI) improves the performance of diagnosis-based models to predict concurrent and prospective health care costs and utilization. METHODS: We used claims and EHR data over a 2-year period from a cohort of continuously insured patients (aged 20-64 y) within an integrated health system. We examined the addition of BMI to 3 diagnosis-based models of increasing comprehensiveness (ie, demographics, Charlson, and Dx-PM model of the Adjusted Clinical Group system) to predict concurrent and prospective costs and utilization, and compared the performance of models with and without BMI. RESULTS: The study population included 59,849 patients, 57% female, with BMI class I, II, and III comprising 19%, 9%, and 6% of the population. Among demographic models, R improvement from adding BMI ranged from 61% (ie, R increased from 0.56 to 0.90) for prospective pharmacy cost to 29% (1.24-1.60) for concurrent medical cost. Adding BMI to demographic models improved the prediction of all binary service-linked outcomes (ie, hospitalization, emergency department admission, and being in top 5% total costs) with area under the curve increasing from 2% (0.602-0.617) to 7% (0.516-0.554). Adding BMI to Charlson models only improved total and medical cost predictions prospectively (13% and 15%; 4.23-4.79 and 3.30-3.79), and also improved predicting all prospective outcomes with area under the curve increasing from 3% (0.649-0.668) to 4% (0.639-0.665; and, 0.556-0.576). No improvements in prediction were seen in the most comprehensive model (ie, Dx-PM). DISCUSSION: EHR-extracted BMI levels can be used to enhance predictive models of utilization especially if comprehensive diagnostic data are missing.
BACKGROUND: Using electronic health records (EHRs) for population risk stratification has gained attention in recent years. Compared with insurance claims, EHRs offer novel data types (eg, vital signs) that can potentially improve population-based predictive models of cost and utilization. OBJECTIVE: To evaluate whether EHR-extracted body mass index (BMI) improves the performance of diagnosis-based models to predict concurrent and prospective health care costs and utilization. METHODS: We used claims and EHR data over a 2-year period from a cohort of continuously insured patients (aged 20-64 y) within an integrated health system. We examined the addition of BMI to 3 diagnosis-based models of increasing comprehensiveness (ie, demographics, Charlson, and Dx-PM model of the Adjusted Clinical Group system) to predict concurrent and prospective costs and utilization, and compared the performance of models with and without BMI. RESULTS: The study population included 59,849 patients, 57% female, with BMI class I, II, and III comprising 19%, 9%, and 6% of the population. Among demographic models, R improvement from adding BMI ranged from 61% (ie, R increased from 0.56 to 0.90) for prospective pharmacy cost to 29% (1.24-1.60) for concurrent medical cost. Adding BMI to demographic models improved the prediction of all binary service-linked outcomes (ie, hospitalization, emergency department admission, and being in top 5% total costs) with area under the curve increasing from 2% (0.602-0.617) to 7% (0.516-0.554). Adding BMI to Charlson models only improved total and medical cost predictions prospectively (13% and 15%; 4.23-4.79 and 3.30-3.79), and also improved predicting all prospective outcomes with area under the curve increasing from 3% (0.649-0.668) to 4% (0.639-0.665; and, 0.556-0.576). No improvements in prediction were seen in the most comprehensive model (ie, Dx-PM). DISCUSSION: EHR-extracted BMI levels can be used to enhance predictive models of utilization especially if comprehensive diagnostic data are missing.
Authors: Julia Adler-Milstein; Peter J Embi; Blackford Middleton; Indra Neil Sarkar; Jeff Smith Journal: J Am Med Inform Assoc Date: 2017-09-01 Impact factor: 4.497
Authors: Hsien-Yen Chang; Thomas M Richards; Kenneth M Shermock; Stacy Elder Dalpoas; Hong J Kan; G Caleb Alexander; Jonathan P Weiner; Hadi Kharrazi Journal: Med Care Date: 2017-12 Impact factor: 2.983
Authors: Hong J Kan; Hadi Kharrazi; Bruce Leff; Cynthia Boyd; Ashwini Davison; Hsien-Yen Chang; Joe Kimura; Shannon Wu; Laura Anzaldi; Tom Richards; Elyse C Lasser; Jonathan P Weiner Journal: Med Care Date: 2018-03 Impact factor: 2.983
Authors: Ahmed Mattar; David Carlston; Glen Sariol; Tongle Yu; Ahmad Almustafa; Genevieve B Melton; Adil Ahmed Journal: Appl Clin Inform Date: 2017-01-25 Impact factor: 2.342
Authors: Hude Quan; Vijaya Sundararajan; Patricia Halfon; Andrew Fong; Bernard Burnand; Jean-Christophe Luthi; L Duncan Saunders; Cynthia A Beck; Thomas E Feasby; William A Ghali Journal: Med Care Date: 2005-11 Impact factor: 2.983
Authors: Wendy L Bennett; Renee F Wilson; Allen Zhang; Eva Tseng; Emily A Knapp; Hadi Kharrazi; Elizabeth A Stuart; Oluwaseun Shogbesan; Eric B Bass; Lawrence J Cheskin Journal: Ann Intern Med Date: 2018-05-01 Impact factor: 25.391
Authors: Hsien-Yen Chang; Noa Krawczyk; Kristin E Schneider; Lindsey Ferris; Matthew Eisenberg; Tom M Richards; B Casey Lyons; Kate Jackson; Jonathan P Weiner; Brendan Saloner Journal: Drug Alcohol Depend Date: 2019-06-07 Impact factor: 4.492
Authors: Thomas R Radomski; Xinhua Zhao; Joseph T Hanlon; Joshua M Thorpe; Carolyn T Thorpe; Jennifer G Naples; Florentina E Sileanu; John P Cashy; Jennifer A Hale; Maria K Mor; Leslie R M Hausmann; Julie M Donohue; Katie J Suda; Kevin T Stroupe; Chester B Good; Michael J Fine; Walid F Gellad Journal: Healthc (Amst) Date: 2019-04-26
Authors: Brian D Nicholson; Paul Aveyard; Willie Hamilton; Clare R Bankhead; Constantinos Koshiaris; Sarah Stevens; Frederick Dr Hobbs; Rafael Perera Journal: Clin Epidemiol Date: 2019-01-25 Impact factor: 4.790
Authors: Hong J Kan; Hadi Kharrazi; Hsien-Yen Chang; Dave Bodycombe; Klaus Lemke; Jonathan P Weiner Journal: PLoS One Date: 2019-03-06 Impact factor: 3.240
Authors: Stephanie N Howson; Michael J McShea; Raghav Ramachandran; Howard S Burkom; Hsien-Yen Chang; Jonathan P Weiner; Hadi Kharrazi Journal: JMIR Med Inform Date: 2022-03-24