Adaptive Treatment Assisting System for Patients Using Machine Learning

Nowadays, one of the clinical challenge is the realization of personalized treatments, which falls into the more general paradigm of the precision medicine. On the other hand, over the last years we have assisted the rising of technologies able to assist people at home during their daily activities. In this paper we present an intelligent system, which is able to self-adapt to user's skills aiming at assisting her/him in the healthcare treatment. The system adopts the Reinforcement Learning paradigm to adapt the way to communicate with the patient. By this way, in case of patients with physical disabilities (e.g. auditory or visual impairments) or cognitive disabilities (e.g. mild cognitive impairments), the system automatically searches for the most effective way to communicate and remind the daily treatment plan to the patient.