Data Analytics and Machine Learning for Disease Identification in Electronic Health Records

Predicting heart failure in-hospital mortality by integrating longitudinal and category data in electronic health records

Heart failure is a life-threatening syndrome that is diagnosed in 3.6 million people worldwide each year. We propose a deep fusion learning model (DFL-IMP) that uses time series and category data from electronic health records to predict in-hospital mortality in patients with heart failure. We considered 41 time series features (platelets, white blood cells, urea nitrogen, etc.) and 17 category features (gender, insurance, marital status, etc.) as predictors, all of which were available within the time of the patient's last hospitalization, and a total of 7696 patients participated in the observational study. Our model was evaluated against different time windows. The best performance was achieved with an AUC of 0.914 when the observation window was 5 days and the prediction window was 30 days. Outperformed other baseline models including LR (0.708), RF (0.717), SVM (0.675), LSTM (0.757), GRU (0.759), GRU-U (0.766) and MTSSP (0.770). This tool allows us to predict the expected pathway of heart failure patients and intervene early in the treatment process, which has significant implications for improving the life expectancy of heart failure patients.

Assessment of utilization efficiency using machine learning techniques: A study of heterogeneity in preoperative healthcare utilization among super-utilizers

INTRODUCTION

In the United States, 5% of patients represent up to 55% of all health care costs. This study sought to define healthcare utilization patterns among super-utilizers, as well as assess possible variation in patient outcomes.

METHODS

Medicare super-utilizers undergoing either a total hip or knee arthroplasty were identified and entered into a cluster analysis using annual preoperative charges to identify distinct patterns of utilization.

RESULTS

Among 19,522 super-utilizers who underwent THA or TKA, there was a marked heterogeneity in overall utilization with 5 distinct clusters of utilization patterns. Of note, comorbidity burden was similar among the 5 clusters. Patient outcomes also varied by Cluster type, ranging from 6.9% to 16.5% experiencing complications and 1.0%-3.2% experiencing 90-day mortality.

CONCLUSION

While previous studies have suggested that super-utilizers are a homogenous group of patients, the current study demonstrated a large degree of heterogeneity within super-utilizers. Variations in utilization patterns were associated with postoperative outcomes and subsequent health care costs.