The National Center for Healthy Aging, a research institute of Monash University and Peninsula Health in Australia, has developed a new AI-driven method to efficiently identify dementia in hospitals.
It investigated ways to elevate dementia detection in health care institutions by combining traditional and AI-driven case identification pavements.
Findings
Based on a media release, the NCA research team developed dementia-finding algorithms in two streams: a traditional stream for routine structured structured structured data from EMRs on the healthy aging data platform and an AI-stream For unstructured text records, Driven by natural language processing (NLP) and led by clinical experts.
“Special software was used to use the large amount of free text data in a way in which NLP could be applied,” Dr. Taya Collyer, one of the research pipes.
In addition to standard dementia codes, the research also considered information about demography, socio-economic status, medicines, emergency and clinical health use and hospital events.
The algorithms were tested in one study With more than 1,000 seniors being 60 years and older on the Frankston-Mornington peninsula. It showed “high classification bluence” – 72.2% specificity and 80.6% sensitivity – when identifying people with or without dementia, which presents a potential to improve how dementia is detected, counted and managed in health care.
The research received subsidies from the National Health and Medical Research Council, the Medical Research Future Fund and the Ministry of Health and Elderly Care.
Why it matters
The number of people living with dementia is expected to increase to 150 million worldwide in 2050, according to the World Alzheimer’s report. To prepare for this, “[a]Ccurate identification is crucial to understand the true size of the problem nationally and to be able to plan services effectively, “said Monash University.
Market Snapshot
Although aids for algorithmic detection of dementia are available on a large scale, they often do not use clinically meaningful case definitions and have familiar with proxy’s, such as diagnostic codes or medicines, to determine cases, the NCHA research team. That is why they took a double algorithm-based approach when searching structured and unstructured EMR data, with one lever NLP and its untouched potential.
Large language models (LLMS) have also seen a growing application in the detection of cognitive disorders. In Super Agenting South Korea, for example, a study of the Electronics and Telecommunications Research Institute recently showed a high accuracy of a LLM-driven model in recognizing Alzheimer’s disease.
A Gamification approach has also demonstrated the effectiveness in screening mild cognitive impairment as part of the health screening in Singapore.
On the edge
“Given that clinical recognition of people with the diagnosis of dementia that present to hospitals is poor, with the help of this new approach, we could more people identify for appropriate diagnostic and clinical care. I am sure that many people miss good care because we are not very good at identifying Henken or Project Leader and Project leader and leader director.
#Study #combines #NLP #conventional #coding #improve #dementia #detection