Moffitt Cancer Center researchers created machine learning models that use patient-reported outcomes and wearable data to predict urgent care visits for non-small cell lung cancer patients.
Key Details
- 1Machine learning models incorporated wearable sensor data (Fitbit) and quality-of-life surveys from 58 non–small cell lung cancer patients.
- 2Models using patient-reported and wearable data outperformed those using only clinical/demographic data in predicting urgent care visits during systemic therapy.
- 3Researchers employed explainable Bayesian Networks, revealing how symptom, sleep, and lab data affect risk.
- 4Study highlights potential to proactively intervene and prevent hospitalizations due to treatment complications.
- 5This was a single-center study with a modest sample; larger validation is planned.
Why It Matters
Integrating diverse patient-originated health data with explainable AI models could transform personalized cancer care by allowing real-time identification of high-risk patients and early intervention, potentially preventing costly or harmful acute events. Such approaches expand the role of AI in predictive analytics for oncology.
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.