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
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.