Abstract
It is currently accepted that aging and unhealthy lifestyles increase high-risk metabolic conditions including obesity and type-2 diabetes. European countries are currently experiencing an epidemic of these disorders which benefit from physical activity, to improve motor performance and physiological/stress-related profile of patients. Unfortunately, preventive and/or adapted motor rehabilitation and the relative supervision are available only at specialized centers and in the presence of healthcare professionals, limiting their availability to a small part of the population. We propose an innovative framework to dispense with costly infrastructures and increase the number of patients a healthcare professional can supervise. To achieve this, we aim to integrate real-time and semi-autonomic monitoring, motor training and rehabilitation supervision directly at a patient’s home. Integration of patient’s physio-metabolic and inertial data, dynamically collected and processed at runtime, with diagnostic concepts, related to patient’s state and needs, is an open research problem. Here we introduce SORTT, a new approach to merge physio-metabolic data remotely obtained via cutting-edge Internet of Things (IoT) and edge computing technologies into an ontology-based knowledge representation system that models the healthcare professional’s view of the patient. Specifically, the SORTT project envisages a smart space where a variety of sensors acquire a grid of motor, physiological and stress-related conditions, to describe and monitor patient's performance during a well-defined motor rehabilitation session. The smart space consists of a set of wearable sensors and features integration of an IoT system and an ontology-based modeling system. The IoT system (a) collects the sensor data sources available in the environment, which can be dedicated or generic and may differ in type, collection rate, data quality, and the like; (b) establishes whether the incoming data is sufficient to safely monitor the patient, in particular by comparing pathological and normal subjects data; (c) elaborates on the edge data into digital biomarkers that are significant to healthcare professionals. The Ontology-based Modeling system (a) collects the biomarkers, possibly suggesting data types to monitor more closely; (b) integrates biomarkers and environment data to evaluate the patient’s context and her/his state during rehabilitation exercises; (c) generates an Ontology-based Human Digital Twin of the patient in the language of healthcare professionals, and uses it to monitor the situation and alert when professional intervention is needed. Our project brings significant knowledge advances in multiple fields (rehabilitation, IoT, applied ontology, AI for healthcare) and involves a highly interdisciplinary team. SORTT is a feasibility study and proof-of-concept implementation of the architecture and paves the way for further funding opportunities and research efforts.
Project details
Unibo Team Leader: Marco Di Felice
Unibo involved Department/s:
Dipartimento di Informatica - Scienza e Ingegneria
Coordinator:
CNR - Consiglio Nazionale delle Ricerche(Italy)
Total Unibo Contribution: Euro (EUR) 79.574,00
Project Duration in months: 27
Start Date:
30/11/2023
End Date:
28/02/2026
