JMIR Publications

ABSTRACT

Background:

Heart failure (HF) patients are the most commonly readmitted group of adult patients in Germany. Most HF patients are readmitted for non-cardiovascular reasons. Understanding the relevance of HF management outside the hospital setting is critical to understanding HF and factors that lead to readmission. Application of machine learning (ML) on data from statutory health insurance (SHI) allows evaluation of large longitudinal datasets representative of the general population in order to support clinical decision making.

Objective:

To evaluate the ability of machine learning methods to predict HF readmission in outpatient data and identify important predictors

Methods:

Using six years of outpatient data from the AOK Baden-Württemberg SHI in Germany, we applied a machine learning approach to predict 1-year all-cause and HF-specific readmission after the first admission for HF. We fitted a random forest, an elastic net, a stepwise regression, and a logistic regression to use diagnosis codes, drug exposures, and demographics to predict readmission.

Results:

Our final dataset consisted of 97,529 individuals, 78044 (80%) of whom were readmitted within the observation period. The random forest approach best predicted all-cause and HF specific readmission with a C-statistic of 0.68 and 0.69, respectively. Important predictors for all-cause readmission included prescription of pantoprazole, chronic obstructive pulmonary disease, atherosclerosis, sex, rurality, and participation in disease management programs for type 2 diabetes mellitus and coronary heart disease.

Conclusions:

While many of the predictors we identified were known to be relevant comorbidities for HF, we also uncovered several novel associations. Disease management programs have widely been shown to be effective at managing chronic disease, however, our results indicate that in the short term they may be useful for targeting HF patients with comorbidity at increased risk of readmission. Our results also show that living in a more rural location increases risk of readmission. Overall, factors beyond comorbid disease were relevant for risk of HF readmission. This finding may impact how outpatient physicians identify and monitor patients at risk of HF readmission.