Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients

Abstract

Recent health reforms have created incentives for cardiologists and accountable care organizations to participate in value-based care models for heart failure (HF). Accurate risk stratification of HF patients is critical to efficiently deploy interventions aimed at reducing preventable utilization. The goal of this paper was to compare deep learning approaches with traditional logistic regression (LR) to predict preventable utilization among HF patients. We conducted a prognostic study using data on 93,260 HF patients continuously enrolled for 2-years in a large U.S. commercial insurer to develop and validate prediction models for three outcomes of interest: preventable hospitalizations, preventable emergency department (ED) visits, and preventable costs. Patients were split into training, validation, and testing samples. Outcomes were modeled using traditional and enhanced LR and compared to gradient boosting model and deep learning models using sequential and non-sequential inputs. Evaluation metrics included precision (positive predictive value) at k, cost capture, and Area Under the Receiver operating characteristic (AUROC). Deep learning models consistently outperformed LR for all three outcomes with respect to the chosen evaluation metrics. Precision at 1% for preventable hospitalizations was 43% for deep learning compared to 30% for enhanced LR. Precision at 1% for preventable ED visits was 39% for deep learning compared to 33% for enhanced LR. For preventable cost, cost capture at 1% was 30% for sequential deep learning, compared to 18% for enhanced LR. The highest AUROCs for deep learning were 0.778, 0.681 and 0.727, respectively. These results offer a promising approach to identify patients for targeted interventions.

Impact of nurse‐led education on the prognosis of heart failure patients: A systematic review and meta‐analysis

“…Managing HF remains a significant challenge, and the cost is one of the system barriers to HF management. HF costs $30 billion annually in the United States; by 2030, about 3% of the population will have HF, potentially increasing costs to $53 billion (Lewis et al., 2021). Therefore, the advantage of nurse‐led educational interventions has unfolded due to their cost‐effectiveness.…”

Systems Anesthesiology: Integrating Insights From Diverse Disciplines to Improve Perioperative Care

“…Complex deep learning models have better accuracy than traditional statistical models in, for example, predicting preventable acute care use and medical spending. 15 However, difficulty in understanding how such models arrive at their predictions limits translation to a clinical action plan. 16 Many newer ML models include interpretability as part of their design, such as models providing explainable causes of intraoperative hypoxemia 17 or identifying keywords in patient clinical notes that influence the calculated risk of readmission.…”

Incorporating longitudinal history of risk factors into atherosclerotic cardiovascular disease risk prediction using deep learning

“…In recent years, deep learning methods have been applied to many clinical predictive and classification problems to much success 14 – 16 . Compared with traditional statistical methods, deep learning methods are often superior at processing and creating representations of complex data, such as radiology images and unstructured physician notes 17 , 18 , without the need of prior feature engineering or selection 15 , 19 .…”