Jian Gao1, Eileen Moran, Yu-Fang Li, Peter L Almenoff. 1. *Department of Veterans Affairs, Office of Productivity, Efficiency and Staffing, Albany, NY †Department of Veterans Affairs, Office of Productivity, Efficiency and Staffing, West Haven, CT ‡Department of Veterans Affairs, Operational Analytics and Reporting, Office of Informatics and Analytics §Department of Veterans Affairs, Office of Secretary ∥Department of Veterans Affairs, Center of Innovation ¶University of Missouri-Kansas City School of Medicine, Kansas City, MO.
Abstract
BACKGROUND: Hospitalizations due to ambulatory care sensitive conditions (ACSCs) are widely accepted as an indicator of primary care access and effectiveness. However, broad early intervention to all patients in a health care system may be deemed infeasible due to limited resources. OBJECTIVE: To develop a predictive model to identify high-risk patients for early intervention to reduce ACSC hospitalizations, and to explore the predictive power of different variables. METHODS: The study population included all patients treated for ACSCs in the VA system in fiscal years (FY) 2011 and 2012 (n=2,987,052). With all predictors from FY2011, we developed a statistical model using hierarchical logistic regression with a random intercept to predict the risk of ACSC hospitalizations in the first 90 days and the full year of FY2012. In addition, we configured separate models to assess the predictive power of different variables. We used a random split-sample method to prevent overfitting. RESULTS: For hospitalizations within the first 90 days of FY2012, the full model reached c-statistics of 0.856 (95% CI, 0.853-0.860) and 0.856 (95% CI, 0.852-0.860) for the development and validation samples, respectively. For predictive power of the variables, the model with only a random intercept yielded c-statistics of 0.587 (95% CI, 0.582-0.593) and 0.578 (95% CI, 0.573-0.583), respectively; with patient demographic and socioeconomic variables added, the c-statistics improved to 0.725 (95% CI, 0.720-0.729) and 0.721 (95% CI, 0.717-0.726), respectively; adding prior year utilization and cost raised the c-statistics to 0.826 (95% CI, 0.822-0.830) and 0.826 (95% CI,0.822-0.830), respectively; the full model was reached with HCCs added. For the 1-year hospitalizations, only the full model was fitted, which yielded c-statistics of 0.835 (95% CI, 0.831-0.837) and 0.833 (95% CI, 0.830-0.837), respectively, for development and validation samples. CONCLUSIONS: Our analyses demonstrate that administrative data can be effective in predicting ACSC hospitalizations. With high predictive ability, the model can assist primary care providers to identify high-risk patients for early intervention to reduce ACSC hospitalizations.
BACKGROUND: Hospitalizations due to ambulatory care sensitive conditions (ACSCs) are widely accepted as an indicator of primary care access and effectiveness. However, broad early intervention to all patients in a health care system may be deemed infeasible due to limited resources. OBJECTIVE: To develop a predictive model to identify high-risk patients for early intervention to reduce ACSC hospitalizations, and to explore the predictive power of different variables. METHODS: The study population included all patients treated for ACSCs in the VA system in fiscal years (FY) 2011 and 2012 (n=2,987,052). With all predictors from FY2011, we developed a statistical model using hierarchical logistic regression with a random intercept to predict the risk of ACSC hospitalizations in the first 90 days and the full year of FY2012. In addition, we configured separate models to assess the predictive power of different variables. We used a random split-sample method to prevent overfitting. RESULTS: For hospitalizations within the first 90 days of FY2012, the full model reached c-statistics of 0.856 (95% CI, 0.853-0.860) and 0.856 (95% CI, 0.852-0.860) for the development and validation samples, respectively. For predictive power of the variables, the model with only a random intercept yielded c-statistics of 0.587 (95% CI, 0.582-0.593) and 0.578 (95% CI, 0.573-0.583), respectively; with patient demographic and socioeconomic variables added, the c-statistics improved to 0.725 (95% CI, 0.720-0.729) and 0.721 (95% CI, 0.717-0.726), respectively; adding prior year utilization and cost raised the c-statistics to 0.826 (95% CI, 0.822-0.830) and 0.826 (95% CI,0.822-0.830), respectively; the full model was reached with HCCs added. For the 1-year hospitalizations, only the full model was fitted, which yielded c-statistics of 0.835 (95% CI, 0.831-0.837) and 0.833 (95% CI, 0.830-0.837), respectively, for development and validation samples. CONCLUSIONS: Our analyses demonstrate that administrative data can be effective in predicting ACSC hospitalizations. With high predictive ability, the model can assist primary care providers to identify high-risk patients for early intervention to reduce ACSC hospitalizations.
Authors: Elizabeth A Bayliss; Jennifer L Ellis; Mary Jo Strobel; Deanna B Mcquillan; Irena B Petsche; Jennifer C Barrow; Arne Beck Journal: Perm J Date: 2015-06-01
Authors: Eric M Schmidt; Simone Behar; Alinne Barrera; Matthew Cordova; Leonard Beckum Journal: J Behav Health Serv Res Date: 2018-07 Impact factor: 1.505
Authors: Leif I Solberg; Kris A Ohnsorg; Emily D Parker; Robert Ferguson; Sanne Magnan; Robin R Whitebird; Claire Neely; Emily Brandenfels; Mark D Williams; Mark Dreskin; Todd Hinnenkamp; Jeanette Y Ziegenfuss Journal: Perm J Date: 2018
Authors: Judith H Hibbard; Jessica Greene; Rebecca M Sacks; Valerie Overton; Carmen Parrotta Journal: Health Serv Res Date: 2016-08-22 Impact factor: 3.402
Authors: Young-Rock Hong; Michelle Cardel; Ryan Suk; Ivana A Vaughn; Ashish A Deshmukh; Carla L Fisher; Gregory Pavela; Kalyani Sonawane Journal: J Gen Intern Med Date: 2019-08-05 Impact factor: 5.128
Authors: José F Figueroa; Laura G Burke; Kathryn E Horneffer; Jie Zheng; E John Orav; Ashish K Jha Journal: Health Aff (Millwood) Date: 2020-06 Impact factor: 6.301