Predictive Interpretability of Machine Learning Models for In-Hospital Bleeding Risk Following PCI in Diabetic Patients with Acute Coronary Syndrome: A Retrospective Analysis - Takeaways - MDSpire

Predictive Interpretability of Machine Learning Models for In-Hospital Bleeding Risk Following PCI in Diabetic Patients with Acute Coronary Syndrome: A Retrospective Analysis

  • By

  • Huasheng Lv

  • Ruotong Cao

  • Yuchen Zhang

  • Fengyu Sun

  • Yitong Ma

  • Xinrong Zhou

  • February 20, 2026

  • 0 min

Share

  • 1

    Diabetes significantly increases the risk of cardiovascular diseases and complicates the management of acute coronary syndrome (ACS).

  • 2

    Post-PCI bleeding is a serious complication that can lead to prolonged hospitalization and increased mortality, especially in diabetic patients.

  • 3

    Traditional bleeding risk scores may not adequately assess the unique risk profile of diabetic patients undergoing PCI.

  • 4

    Machine learning models can analyze complex patient data more effectively than traditional methods, improving risk prediction for in-hospital bleeding.

  • 5

    The study aimed to develop interpretable machine learning models to predict in-hospital bleeding in diabetic patients after PCI, enhancing clinical risk stratification.

Original Source(s)

Predictive Interpretability of Machine Learning Models for In-Hospital Bleeding Risk Following PCI in Diabetic Patients with Acute Coronary Syndrome: A Retrospective Analysis

  • by Huasheng Lv, Ruotong Cao, Yuchen Zhang, Fengyu Sun, Yitong Ma, Xinrong Zhou

  • February 20, 2026

Related Content

Drug-coated balloons vs. drug-eluting stents for coronary artery disease: an updated systematic review and meta-analysis of randomized controlled trials with lesion-specific insights

Complete revascularization and heart failure risk in acute coronary syndrome across the ejection fraction spectrum: focus on LVEF-dependent effects

Serum resistin as a potential biomarker for stratifying the severity of coronary heart disease: a network meta-analysis