Artificial Intelligence and Features Investigating to Detect Neuropsychiatric Symptoms in Patients with Dementia: A Pilot Study

Dementia is a chronic and irreversible condition characterized by progressive cognitive and functional decline, along with non-cognitive Neuropsychiatric Symptoms (NPS) that significantly affect patients' quality of life. This study explores the application of artificial intelligence using wearable sensor data collected from dementia patients (PwD) to develop an AI system for detecting NPS, particularly episodes of agitation, in an institutional setting. We present preliminary results from a real-world study at the Ontario Shores Center for Mental Health Sciences. The study outcomes indicate that by employing sequential feature selection, we are able to improve detection accuracy while reducing the number of features from an initial set of 198. Further, the Extra Trees classification model outper-formed other algorithms in accurately classifying non-agitated normal events from agitated events. The study also shows that personalized models yielded superior results, with an average accuracy improvement of 5-10% compared to models trained on all patient data combined.