This observational study aims to (1) validate a multimodal artificial intelligence (AI) model for early detection of cancer-associated cachexia in pancreatic cancer patients and (2) assess the feasibility and acceptability of diet and exercise interventions for cachexia management. The study will use retrospective data from the Florida Pancreas Collaborative and prospective data from newly diagnosed patients at Moffitt Cancer Center.
Study Type
OBSERVATIONAL
Enrollment
120
Dietary questionnaire (VioScreen), symptom and QoL surveys (ESAS-r, FAACT, PROMIS PF, PG-SGA), physical activity survey (Modified GLTEQ), functional fitness tests, DEXA scans, blood draws.
Wearable monitoring (Fitbit) and diet/physical activity preference survey at 9 months.
One-time structured survey assessing integration of diet and exercise interventions into clinical workflow.
Moffitt Cancer Center
Tampa, Florida, United States
RECRUITINGAI Model Performance
Investigators will rigorously assess model performance using clinically meaningful metrics (AUC-ROC, sensitivity, specificity, etc.) to confirm its reliability and readiness for clinical use.
Time frame: Up to 9 months
Survey Completion Rate
Percentage of patients completing all scheduled questionnaires.
Time frame: Up to 9 months
Wearable Adherence
Percentage of longitudinal participants syncing Fitbit weekly for ≥80% of study weeks.
Time frame: Up to 9 months
Quality of Life Change
Mean change in FAACT total score from baseline to 9 months.
Time frame: Up to 9 months
Physical Activity Change
Mean increase in weekly moderate-to-vigorous activity minutes.
Time frame: Up to 9 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.