According to a groundbreaking study, more than 10 million older persons in India who are 60 or older may have dementia, which is comparable to the prevalence rates for nations like the US and the UK.
Dementia substantially limits a person’s capacity to do daily tasks by causing mental processes including memory, thinking, reasoning, and judgment to become impaired.
Those over 60 are expected to make up 19.1% of India’s population by 2050, according to a study that appeared in the journal Nature Public Health Emergency Collection.
As the population ages, dementia prevalence is predicted to rise dramatically. Dementia is a syndrome that is rarely treated seriously in this country.
In the most recent study, which was published in the journal Neuroepidemiology, data from 31,477 older persons were analyzed using a semi-supervised machine learning AI technique.
According to the findings of the worldwide research team, there may be 10.08 million elderly people in India who have dementia or an estimated 8.44 percent of adults in India who are 60 or older.
According to them, this contrasts with prevalence rates of 8.8% in the US, 9% in the UK, and between 8.5 and 9% in Germany and France for similar age groups.
The researchers discovered that those who were older, female, had no formal education, and resided in rural areas had a higher prevalence of dementia.
Haomiao Jin, the co-author of the study and Lecturer in Health Data Sciences at the University of Surrey, UK, said, “Our research was based on the first and only nationally representative aging study in India with more than 30,000 participating older persons in the country.
According to Jin’s findings, the prevalence of dementia may be higher than previous estimates based on local samples. “AI has a particular strength in analyzing huge and complex data like this,” Jin said in a release.
An AI learning model was created by a research team from the Universities of Surrey, Southern California, Michigan, and All India Institute of Medical Sciences in New Delhi, all in the United States.
The model was trained using data that included a novel online consensus with dementia diagnoses that made up 70% of the labeled dataset.
The remaining 30% of the data was set aside as a test set to evaluate how well the AI predicted outcomes.
For unlabelled observations without dementia diagnoses in the dataset, the AI trained itself to predict dementia status.
Professor Adrian Hilton, Director of the University of Surrey’s Institute for People-Centered AI, said, “As we are seeing with this research, AI has a huge potential to discover patterns in complex data, improving our understanding of how diseases impact people across very different communities to support the development of precision medical interventions to save lives.
