Calendar
YRM W7 - Kristian Romano on HMM to model the Circadian Timing System in patients with advanced pancreatic cancer
Title: MultiDom: Remote Monitoring of Patient With Advanced Pancreatic Cancer
Abstract: Wearable devices allow for non-invasive telemonitoring of patients. Physiological data, such as physical activity (PA) and body temperature, can be collected in the daily living environment of the patient without the need for hospitalization. The devices can be used to monitor the Circadian Timing System (CTS), which regulates many critical cellular processes, such as the cell cycle and metabolism, and to detect adverse events which pose a risk to health. The appraisal of the CTS in real time could lead to chronopharmacological strategies and personalized medicine. The MultiDom clinical trial ( NCT04263948) telemonitors Pancreatic cancer patients undergoing chemotherapy aiming to reduce the rate of patients undergoing toxicity-related emergency hospitalisations. MultiDom telemonitors continuously for PA, temperature and 3D-orientation via a sensor worn on the chest. Data are automatically transmitted and alerts are generated according to automatically computed critical parameters to trigger proactive interventions from Medical Experts.
We developed a Hidden Markov Model (HMM) to suit the specific data collected by MultiDom and the relative Bayesian Inference. Thanks to our Bayesian approach we are also capable to provide Medical Experts with credibility intervals for the circadian parameters.