Researchers developed a machine learning model to proactively identify cancer patients at high risk of financial stress from treatment.
Key Details
- 1Study used data from 793 cancer patients undergoing or recently completing treatment.
- 2Six machine learning models were tested; best achieved 84% sensitivity and 75% specificity.
- 3Key predictors included younger age, lower income, poorer health, active treatment, and higher out-of-pocket costs.
- 4A web-based calculator was developed for clinical use to estimate individual financial toxicity risk.
- 5The tool aims to shift financial toxicity screening from reactive to proactive, connecting patients with support earlier.
Why It Matters
Early identification of financial toxicity risk could allow healthcare teams to intervene before financial burdens affect cancer treatment adherence or outcomes. The study demonstrates a practical AI application that supports better patient care and resource allocation, a principle translatable to radiology and imaging AI contexts.
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.