Scientists use AI to find true scale of dementia in India

The prevalence of dementia in India might be more in line with rates reported in countries like the US and UK and thus, greater than previous estimates, according to a new study that has used artificial intelligence to arrive at the findings.

The one-of-its kind research was conducted by scientists, including those from the All India Institute of Medical Sciences (AIIMS) in Delhi who used AI to analyse data from 31,477 older adults.

The findings, published recently in the journal Neuroepidemiology, said the prevalence rate of dementia in adults in India aged 60 or over could be as much as 8.4 per cent.

This equated to over 10 million older adults in the country.

In comparison, prevalence rates recorded in similar age groups in the US and UK was found to be 8.8 per cent and 9 per cent respectively, while dementia rates in Germany and France were found to be between 8.5 and 9 per cent.

“Our research was based on the first and only nationally representative ageing study in India with more than 30,000 participating older adults in the country,” said study co-author Haomiao Jin from the University of Surrey.

“AI has a unique strength in interpreting large and complex data like this, and our research found that the prevalence of dementia may be higher than prior estimates from local samples,” Dr Jin added.

In the study, scientists developed an AI learning model trained on data that consisted of 70 per cent pre-labeled dataset with known cases of dementia.

The remaining 30 per cent of the data was reserved as a test to see how accurate the AI’s predictive capabilities were.

Researchers made the AI teach itself to predict the dementia status for unlabelled observations.

The prevalence of dementia in India may be higher than prior estimates derived from local studies,” they concluded in the study.

“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,” said Adrian Hilton, Director of the University of Surrey’s Institute for People-Centered AI.

Scientists hope the new findings provide the necessary information for long-term planning of public and social care policy.