Abstract

Advances in medical and digital technology are generating large volumes of patient mental health data. Interpreting these rich data is key for improved early diagnosis, patient stratification and new drug discovery. Specifically, in the case of dementia, diagnosis at early stages of neurocognitive decline has major implications for timely clinical management. We currently intervene too late and often target the wrong patients. Here, we propose an innovative AI-guided healthcare solution that uses machine learning to improve early precision diagnosis and prognosis from low-cost, non-invasive data. Our aim is to deliver a clinical decision support system that will: a) help clinicians assign the right patient at the right time to the right diagnostic or treatment pathway, b) improve patient wellbeing and reduce healthcare costs, as patients undergo fewer, less invasive, less expensive tests, c) guide patient selection for clinical trials to enhance their efficacy and pave the way to drug discovery.