Ofir Ben-Assuli1, Joshua R Vest2. 1. Faculty of Business Administration, Ono Academic College, Kiryat Ono 55000, Israel. Electronic address: Ofir.benassuli@gmail.com. 2. Fairbanks School of Public Health, Indiana University and Regenstrief Institute, IN 46202, USA. Electronic address: joshvest@iu.edu.
Abstract
BACKGROUND: The use of machine learning techniques is especially pertinent to the composite and challenging conditions of emergency departments (EDs). Repeat ED visits (i.e. revisits) are an example of potentially inappropriate utilization of resources that can be forecasted by these techniques. OBJECTIVE: To track the ED revisit risk over time using the hidden Markov model (HMM) as a major latent class model. Given the HMM states, we carried out forecasting of future ED revisits with various data mining models. METHODS: Information integrated from four distributed sources (e.g. electronic health records and health information exchange) was integrated into four HMMs which capture the relationships between an observed and a hidden progression that shift over time through a series of hidden states in an adult patient population. RESULTS: Assimilating a pre-analysis of the various patients by applying latent class models and directing them to well-known classifiers functioned well. The performance was significantly better than without utilizing pre-analysis of HMM for all prediction models (classifiers(. CONCLUSIONS: These findings suggest that one prospective approach to advanced risk prediction is to leverage the longitudinal nature of health care data by exploiting patients' between state variation.
BACKGROUND: The use of machine learning techniques is especially pertinent to the composite and challenging conditions of emergency departments (EDs). Repeat ED visits (i.e. revisits) are an example of potentially inappropriate utilization of resources that can be forecasted by these techniques. OBJECTIVE: To track the ED revisit risk over time using the hidden Markov model (HMM) as a major latent class model. Given the HMM states, we carried out forecasting of future ED revisits with various data mining models. METHODS: Information integrated from four distributed sources (e.g. electronic health records and health information exchange) was integrated into four HMMs which capture the relationships between an observed and a hidden progression that shift over time through a series of hidden states in an adult patient population. RESULTS: Assimilating a pre-analysis of the various patients by applying latent class models and directing them to well-known classifiers functioned well. The performance was significantly better than without utilizing pre-analysis of HMM for all prediction models (classifiers(. CONCLUSIONS: These findings suggest that one prospective approach to advanced risk prediction is to leverage the longitudinal nature of health care data by exploiting patients' between state variation.
Authors: Xiaomei Wang; H Joseph Blumenthal; Daniel Hoffman; Natalie Benda; Tracy Kim; Shawna Perry; Ella S Franklin; Emilie M Roth; A Zachary Hettinger; Ann M Bisantz Journal: Int J Med Inform Date: 2021-04-09 Impact factor: 4.730