Key result
Sequential deep learning models outperform logistic regression in predicting preventable HF hospitalizations, achieving ~0.78 AUROC.
Why the study?
Accurate risk stratification is critical to efficiently deploy interventions aimed at reducing preventable utilization, motivating a comparison between deep learning and traditional models.
Do deep learning models improve the prediction of preventable acute care use and spending compared to traditional logistic regression in heart failure patients?
Cohort (n=93,260)
Do deep learning models improve the prediction of preventable acute care use and spending compared to traditional logistic regression in heart failure patients?
Absolute Event Rate: 0.778% vs 0.676%
Deep learning models using commercial claims data significantly outperform traditional logistic regression in predicting preventable acute care utilization and costs among heart failure patients, enabling more efficient targeting of care management resources.
May support targeting care management in HF; leaves open prospective validation before clinical use.
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.
No takes yet. Share an insight, caveat, or question.
Lewis et al. (2021) conducted a cohort in Heart failure (n=93,260). Sequential deep learning models vs. Traditional logistic regression was evaluated on Prediction of preventable hospitalizations (AUROC) (95% CI 0.784-0.790). Sequential deep learning models outperformed traditional logistic regression in predicting preventable hospitalizations among heart failure patients, achieving an AUROC of 0.778 compared to 0.676.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: