Back to all news
AI Model Enhances Prediction of Infection Risks from Oral Mucositis in Stem Cell Transplant Patients
Researchers developed an explainable AI tool that accurately predicts infection risks related to oral mucositis in hematopoietic stem cell transplant patients.
Key Details
- 1Patients with oral mucositis after HSCT are almost 4x more likely to develop serious infections.
- 2A new AI-driven nomogram using demographic and clinical features shows superior predictive accuracy versus traditional models.
- 3Explainable AI provided clinicians with rationale for predictions, enabling targeted preventive care.
- 4Meta-analysis identified high-risk groups and specific risk factors such as chemotherapy types, age, and kidney issues.
- 5Researchers are working towards broad clinical adoption, including validation for other adverse events in cancer therapy.
- 6Findings were recently published in the journal Cancers and presented at MASCC 2025.
Why It Matters
This work leverages advanced AI to proactively identify high-risk cancer patients, supporting multidisciplinary care and personalizing preventive strategies. Enhanced prediction of adverse events can improve outcomes, reduce complications, and optimize resource use in cancer therapy.
Source
EurekAlert
Related News
•EurekAlert
Debate Intensifies: Autonomous AI vs. Physician-Led Care in Medicine
A new perspective piece explores whether autonomous AI could outperform physician-led care in clinical settings.
•EurekAlert
AI-Powered 3D Intraoperative Imaging Transforms Glioma Surgery
Researchers develop ULTRA, an AI-driven platform enabling 3D intraoperative tissue imaging for detecting glioma infiltration within 30 minutes.
•EurekAlert
AI 'Tissue Clocks' Estimate Organ-Specific Biological Age from Images
Researchers developed AI models that estimate the biological age of human organs from histological images, revealing organs age at different rates.