Patient Health Monitoring in Dementia Using K-Nearest Neighbor Model

Abstract

Dementia is a progressive neurological condition that severely affects memory, behavior, and everyday functioning, necessitating ongoing surveillance of patients' health state.  Conventional healthcare methods often lack timely treatments owing to restricted real-time data analysis.  This paper presents a patient health monitoring system using the K-Nearest Neighbour (K-NN) classification model to identify and assess essential health metrics in dementia patients.  The system amalgamates sensor-derived physiological data, including heart rate, blood pressure, and activity levels, to categorize patient health situations into normal, warning, or critical categories.  The k-NN method is used for its simplicity, versatility, and efficacy in managing non-linear medical data.  Experimental findings indicate that k-NN provides dependable accuracy in forecasting health hazards, hence assisting carers and healthcare professionals in their decision-making processes.  This methodology enhances patient safety, individualized treatment, and proactive disease management in dementia monitoring.