Alvin D Jeffery1, Sharon Hewner2, Lisiane Pruinelli3, Deborah Lekan4, Mikyoung Lee5, Grace Gao6, Laura Holbrook7, Martha Sylvia8. 1. Department of Veterans Affairs and Vanderbilt University Department of Biomedical Informatics, Nashville, Tennessee, USA. 2. Family, Community and Health Systems Science Department, University at Buffalo School of Nursing, Buffalo, New York, USA. 3. School of Nursing, University of Minnesota, Minneapolis, Minnesota, USA. 4. School of Nursing, University of North Carolina, Greensboro, North Carolina, USA. 5. College of Nursing, Texas Woman's University, Denton, Texas, USA. 6. Department of Nursing, St. Catherine University, St. Paul, Minnesota, USA. 7. American Sentinel University, Aurora, California, USA. 8. College of Nursing, Medical University of South Carolina, Charleston, South Carolina, USA.
Abstract
OBJECTIVE: We sought to assess the current state of risk prediction and segmentation models (RPSM) that focus on whole populations. MATERIALS: Academic literature databases (ie MEDLINE, Embase, Cochrane Library, PROSPERO, and CINAHL), environmental scan, and Google search engine. METHODS: We conducted a critical review of the literature focused on RPSMs predicting hospitalizations, emergency department visits, or health care costs. RESULTS: We identified 35 distinct RPSMs among 37 different journal articles (n = 31), websites (n = 4), and abstracts (n = 2). Most RPSMs (57%) defined their population as health plan enrollees while fewer RPSMs (26%) included an age-defined population (26%) and/or geographic boundary (26%). Most RPSMs (51%) focused on predicting hospital admissions, followed by costs (43%) and emergency department visits (31%), with some models predicting more than one outcome. The most common predictors were age, gender, and diagnostic codes included in 82%, 77%, and 69% of models, respectively. DISCUSSION: Our critical review of existing RPSMs has identified a lack of comprehensive models that integrate data from multiple sources for application to whole populations. Highly depending on diagnostic codes to define high-risk populations overlooks the functional, social, and behavioral factors that are of great significance to health. CONCLUSION: More emphasis on including nonbilling data and providing holistic perspectives of individuals is needed in RPSMs. Nursing-generated data could be beneficial in addressing this gap, as they are structured, frequently generated, and tend to focus on key health status elements like functional status and social/behavioral determinants of health. Published by Oxford University Press on behalf of the American Medical Informatics Association 2019.
OBJECTIVE: We sought to assess the current state of risk prediction and segmentation models (RPSM) that focus on whole populations. MATERIALS: Academic literature databases (ie MEDLINE, Embase, Cochrane Library, PROSPERO, and CINAHL), environmental scan, and Google search engine. METHODS: We conducted a critical review of the literature focused on RPSMs predicting hospitalizations, emergency department visits, or health care costs. RESULTS: We identified 35 distinct RPSMs among 37 different journal articles (n = 31), websites (n = 4), and abstracts (n = 2). Most RPSMs (57%) defined their population as health plan enrollees while fewer RPSMs (26%) included an age-defined population (26%) and/or geographic boundary (26%). Most RPSMs (51%) focused on predicting hospital admissions, followed by costs (43%) and emergency department visits (31%), with some models predicting more than one outcome. The most common predictors were age, gender, and diagnostic codes included in 82%, 77%, and 69% of models, respectively. DISCUSSION: Our critical review of existing RPSMs has identified a lack of comprehensive models that integrate data from multiple sources for application to whole populations. Highly depending on diagnostic codes to define high-risk populations overlooks the functional, social, and behavioral factors that are of great significance to health. CONCLUSION: More emphasis on including nonbilling data and providing holistic perspectives of individuals is needed in RPSMs. Nursing-generated data could be beneficial in addressing this gap, as they are structured, frequently generated, and tend to focus on key health status elements like functional status and social/behavioral determinants of health. Published by Oxford University Press on behalf of the American Medical Informatics Association 2019.
Entities:
Keywords:
community health planning; decision support techniques; population health; risk assessment
Authors: Sachin Yende; Karina Alvarez; Laura Loehr; Aaron R Folsom; Anne B Newman; Lisa A Weissfeld; Richard G Wunderink; Stephen B Kritchevsky; Kenneth J Mukamal; Stephanie J London; Tamara B Harris; Doug C Bauer; Derek C Angus Journal: Chest Date: 2013-09 Impact factor: 9.410
Authors: John F McAna; Albert G Crawford; Benjamin W Novinger; Jaan Sidorov; Franklin M Din; Vittorio Maio; Daniel Z Louis; Neil I Goldfarb Journal: Am J Manag Care Date: 2013-05-01 Impact factor: 2.229
Authors: Ron Z Goetzel; Xiaofei Pei; Maryam J Tabrizi; Rachel M Henke; Niranjana Kowlessar; Craig F Nelson; R Douglas Metz Journal: Health Aff (Millwood) Date: 2012-11 Impact factor: 6.301
Authors: Tamara D Simon; Mary Lawrence Cawthon; Susan Stanford; Jean Popalisky; Dorothy Lyons; Peter Woodcox; Margaret Hood; Alex Y Chen; Rita Mangione-Smith Journal: Pediatrics Date: 2014-05-12 Impact factor: 7.124
Authors: Michael T Schmeltz; Grace Sembajwe; Peter J Marcotullio; Jean A Grassman; David U Himmelstein; Stephanie Woolhandler Journal: PLoS One Date: 2015-03-05 Impact factor: 3.240