Deep Learning-Based Missing Value Imputation for Heart Failure Mortality risk Prediction Data from MIMIC-III: A Comparative Study of DAE, SAITS, and MICE+LightGBM

This study demonstrates that deep learning-based imputation methods, specifically Denoising Autoencoders (DAE) and Self-Attention Imputation for Time Series (SAITS), significantly outperform the traditional MICE+LightGBM approach in handling missing data for heart failure mortality risk prediction using MIMIC-III EHR data.

SHARMA, S., KAUR, M., GUPTA, S.2026-02-17📄 health systems and quality improvement

Differences in Treatment and Outcome of Patients with ST- Elevation Myocardial Infarction (STEMI) and Non-STEMI in Germany

This study of over 540,000 German patients reveals that while STEMI and NSTEMI differ significantly in comorbidities, treatment intensity, and survival patterns, the consistent use of guideline-directed medical therapy substantially improves long-term survival for both groups despite a concerning decline in prescription rates over time.

Lange, S. A., Engelbertz, C., Makowski, L. + 6 more2026-02-17📄 health systems and quality improvement

Determinants of Collaborative Physician-PA Teams in Ambulatory Care: A Qualitative Study

This qualitative study of physicians and physician assistants in North Carolina identifies that effective collaborative teams in ambulatory care rely on intentional onboarding, clear role definitions, and aligned organizational policies to overcome barriers related to professional identity, power dynamics, and systemic regulations.

Nordan, A. G., Ward, I., Stancil, M. L. + 2 more2026-02-17📄 health systems and quality improvement