Reducing COPD readmissions through predictive modeling and incentive-based interventions

Abstract

This paper introduces a case study at a community hospital to develop a predictive model to quantify readmission risks for patients with chronic obstructive pulmonary disease (COPD), and use it to support decision making for appropriate incentive-based interventions. Data collected from the community hospital's database are analyzed to identify risk factors and a logistic regression model is developed to predict the readmission risk within 30 days post-discharge of an individual COPD patient. By targeting on the high-risk patients, we investigate the implementability of the incentive policy which encourages patients to take interventions and helps them to overcome the compliance barrier. Specifically, the conditions and scenarios are identified for either achieving the desired readmission rate while minimizing the total cost, or reaching the lowest readmission rate under incentive budget constraint. Currently, such models are under consideration for a pilot study at the community hospital.

Prognostic models for outcome prediction in patients with chronic obstructive pulmonary disease: systematic review and critical appraisal

“…For three prognostic models, the non-linear association of predictors with the predicted outcome was considered using polynomials (n=1), fractional polynomials (n=1) and Box-Tidwell transformation (n=1). One study did a decision analysis after developing a prognostic model 24…”

Risk factors and associated outcomes of hospital readmission in COPD: A systematic review

“…The studies were conducted in 30 different countries, with three in multiple countries [14,28,29]. The majority of studies were conducted in the USA (n=15) [17,[29][30][31][32][33][34][35][36][37][38][39][40][41][42], Spain (n=13) [13,28,29,[43][44][45][46][47][48][49][50][51][52] and Canada (n=9) [16,[53][54][55][56][57][58][59] [14,28,35,38,46,49,[60][61][62] and three (5.4%) reported only patient-related outcomes of readmission [63][64]…”

“…After comprehensive assessment, study quality was identified as being good for most studies (n=50), with seven studies rating as fair [27,30,42,47,51,65,67] (Supplement D). The main area of weakness was lack of clarity in the definition and representativeness of readmitted patients.…”

“…Four studies defined frequent readmission as ³2 readmissions [26,27,51,68], two studies defined it as >2 readmissions [31,62], while another used ³4 readmissions [69]. Two studies did not report parameter estimates (likelihood ratios) [30,42], one study [51] reported univariate analysis, and two studies reported only p values for the multivariate analysis [37,67]. Table 5 outlines all the studies that considered any of the variables in relation to association or no association with readmission.…”

Care Strategies for Reducing Hospital Readmissions Using Stochastic Programming

“…Predictive models use techniques such as logistic regression, survival analysis, and machine learning. Some articles focus on specific health conditions, such as Zhong et al (2019) [27] who developed a logistic regression model to predict readmission risks for high-risk COPD patients. Chen et al (2019) [28] introduced readmission risk models with the incorporation of latent heterogeneity to represent superior prediction performance, recognize risk factors to target the most at-risk individuals, and evaluate multiple hospitals with composite metrics.…”