Researchers from the National Centre for Healthy Ageing (NCHA), a collaboration between Monash University and Peninsula Health, have developed a new method to improve the detection of dementia in hospitals. The approach combines traditional data analysis with artificial intelligence (AI), specifically natural language processing (NLP), to identify individuals with dementia more accurately using electronic health records.
The World Alzheimer Report estimates that approximately 50 million people live with dementia globally, with projections indicating this figure could triple by 2050. In Australia, accurate identification remains a challenge, affecting how healthcare services are planned and delivered. Current routine health data likely underreports the number of people with dementia, as dementia is often under-identified in hospital settings due to the limitations of manual medical coding.
To address this issue, researchers from NCHA’s Healthy Ageing Data Platform, along with clinicians from Australia and the United States, analysed data from over 1,000 individuals aged 60 and above in the Frankston-Mornington Peninsula. The team developed dual-stream algorithms that use both structured and unstructured data from electronic health records. Their findings were published in the peer-reviewed journal Alzheimer’s & Dementia, in a paper titled “Dual-Stream Algorithms for Dementia Detection: Harnessing Structured and Unstructured Electronic Health Record Data.”
Lead author Dr Taya Collyer explained that the study compared individuals diagnosed with dementia using gold standard clinical methods to those without dementia. “Accessing high-quality curated electronic health records from our Healthy Ageing Data Platform helped assemble the data efficiently to address this problem. Special software was used to harness the large amount of free text data in a way that NLP could then be applied,” she said.
“We then developed dementia-finding algorithms through a traditional stream for usual structured data and an NLP stream for text records,” Dr Collyer added.
The traditional stream incorporated variables beyond standard diagnostic codes, such as demographic information, medication use, healthcare utilisation, and hospital events indicating confusion or behavioural distress. The NLP stream analysed unstructured clinical notes with guidance from clinical experts to maintain relevance.
Professor Velandai Srikanth, NCHA Director and project lead, highlighted the importance of this work in improving the identification of dementia in healthcare settings. “Given that clinical recognition of people diagnosed with dementia presenting to hospitals is poor, using this new approach we could be identifying people earlier for appropriate diagnostic and clinical care. I am sure that many people are missing out on good care because we are not very good at identifying them or their needs,” he said.
“This new method offers a novel digital strategy for capturing and combining clues in written text, such as descriptions of confusion or forgetfulness, or alerts for distressed behaviour, to flag them for suitable care and support,” Professor Srikanth said.
The research received support from the National Health and Medical Research Council, the Medical Research Future Fund, and the Department of Health and Aged Care.
The National Centre for Healthy Ageing was established in 2019 with foundational investment from the Federal Government. It operates across four key themes: healthy ageing across the lifespan, dementia, hospital and home, and health and care in aged care.