A Context-Aware and Technology-Assisted Informal Caregiver Selection Method to support Medical Emergency

Communities globally are experiencing an increasing number of patients with medical conditions and elderly people, living alone, who need immediate attention and support in case of medical emergency incidents. At times, even calling an ambulance becomes difficult for them and even then ambulance may turn up late causing to their sufferings. On the other hand, ambulances may turn up only to find a situation a non-emergency one not requiring an ambulance but that costs them money and wastes their time. In context to such situations, informal caregivers, in forms of friends, families and neighbours, can initially attend the patients and elderly people before the arrival of ambulance. Selection of appropriate informal caregivers is critical for a patient or a particular medical emergency situation and in this paper we propose a context-aware recommendation system (CARS) to recommend appropriate informal caregivers based on a list of pre-identified context information of informal caregivers, patients and elderly people. CARS operates as part of the technology-assisted medical emergency framework introduced by us. This work discusses the different phases of CARS, namely, context dimension, context acquisition and processing and context recommendation, and explains the entire informal caregiver recommendation procedure of CARS. Preliminary simulation results have shown that our proposed CARS perform better than other such existing systems.