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
Imaging Reveals Skull Changes and Immune Impact in Glioblastoma
Advanced imaging uncovers that glioblastoma affects the skull and immune system, not just the brain.
•EurekAlert
AI-Based CT Analysis Predicts Outcomes in Fibrotic Lung Disease
AI analysis of one-year CT changes predicts disease progression and survival in fibrotic interstitial lung disease.
•EurekAlert
AI and Multiphoton Microscopy Achieve 96% Accuracy in Pancreatic Tumor Detection
University of Arizona researchers combined label-free multiphoton microscopy with neural networks to accurately classify pancreatic neuroendocrine neoplasms in tissue samples.