In partnership with Peninsula Health, researchers from Monash University’s National Centre for Healthy Ageing (NCHA) have developed a groundbreaking method that uses artificial intelligence (AI) to improve dementia detection in hospitals. The initiative combines traditional medical data analysis with natural language processing (NLP) to assess electronic health records, identifying signs of dementia with high accuracy.
The study, involving over 1,000 individuals aged 60 and over in the Frankston-Mornington Peninsula area, demonstrated that AI could significantly improve the identification of dementia cases. The algorithms were trained to assess structured data such as demographics, medications, and hospital events, alongside unstructured data like written notes and behavioural descriptions.
Lead author Dr Taya Collyer explained that the team employed NLP to extract critical information from free-text data in medical records. “We developed dementia-finding algorithms through a traditional stream for structured data and an NLP stream for text records,” Dr Collyer said. “Accessing high-quality curated electronic health records allowed us to address this problem efficiently.”
According to NCHA Director Professor Velandai Srikanth, the use of AI in dementia detection is a significant step forward.
“Many people are missing out on good care because we are not very good at identifying them or their needs.”
Professor Velandai Srikanth
The research, funded by the National Health and Medical Research Council, the Medical Research Future Fund, and the Department of Health & Aged Care, was published in the journal Alzheimer’s & Dementia.
