A revolutionary approach using artificial intelligence (AI) to scan medical records could dramatically improve how Australia identifies and counts people with dementia, potentially transforming patient care nationwide.
Researchers from the National Centre for Healthy Ageing (NCHA), a partnership between Monash University and Peninsula Health, have developed an AI system that can detect dementia cases often missed by traditional hospital coding methods.
The research, which analysed over 1,000 individuals aged 60 and above in the Frankston-Mornington Peninsula region, revealed that combining AI with conventional data approaches achieves remarkably high accuracy in identifying dementia cases.
“Accessing high-quality curated electronic health records from our Healthy Ageing Data Platform helped assemble the data efficiently to address this problem,” said lead author Dr. Taya Collyer. “Special software was used to harness the large amount of free text data in a way that NLP could then be applied.”
The system uses natural language processing (NLP) to analyse unstructured text in patient records, finding subtle clues that human coders often miss. These might include descriptions of confusion, forgetfulness, or behavioural changes that don’t get formally coded as dementia but could indicate its presence.
This development comes at a critical time, with dementia cases projected to triple globally by 2050 according to the World Alzheimer Report. In Australia, current methods for counting people with dementia are widely believed to underestimate the true scale of the condition.
“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,” said NCHA Director and project lead Professor Velandai Srikanth. “I am sure that many people are missing out on good care because we are not very good at identifying them or their needs.”
The dual-stream algorithm combines traditional structured data analysis with AI text processing. For the traditional stream, researchers analysed demographic information, socioeconomic status, medication data, healthcare utilisation patterns, and in-hospital events like confusion. The NLP stream examined written clinical notes with guidance from clinical experts to ensure medical relevance.
The findings, published in the prestigious Alzheimer’s & Dementia Journal under the title “Dual-Stream Algorithms for Dementia Detection: Harnessing Structured and Unstructured Electronic Health Record Data,” demonstrate that this combined approach significantly outperforms conventional identification methods.
“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 explained.
The research received substantial support from Australia’s top health bodies, including grants from the National Health and Medical Research Council, the Medical Research Future Fund, and the Department of Health & Aged Care.
Beyond improving national statistics, the technology could revolutionise patient care by identifying individuals who might benefit from early intervention but are currently falling through the cracks of the healthcare system.
“Responsibly using AI in scientific research and dementia identification is potentially game-changing,” Professor Srikanth added. “The NCHA’s Healthy Ageing Data Platform, an Australian-first initiative, has been able to bring together various sources of data from electronic health records, safety and governance, and the technical capacity to enable such high-value projects.”
Related: Australian dementia training model becomes global gold standard
Ritchelle is a Content Producer for Healthcare Channel, Australia’s premier resource of information for healthcare.
