Over 10 million older adults in India likely have dementia: AI study

More than 10 million older adults aged 60 or over in India may have dementia, comparable to the prevalence rates for countries such as the US and the UK, according to a first-of-its-kind study.

Dementia leads to impairment of mental processes, such as memory, thinking, reasoning and judgement, and thus seriously impairs an individual's ability to perform daily functions.

According to a study published in the journal Nature Public Health Emergency Collection, by 2050 people over 60 years of age are predicted to constitute 19.1 per cent of the total population in India.

This ageing of the population is expected to be accompanied by a dramatic increase in the prevalence of dementia, a syndrome not taken very seriously in the country.

The latest research, published in the journal Neuroepidemiology, used an artificial intelligence (AI) technique known as semi-supervised machine learning to analyse data from 31,477 older adults.

The international team of researchers found that the prevalence rate of dementia in adults aged 60 or over in India could be 8.44 per cent -- equating to 10.08 million older adults in the country.

This compares to prevalence rates recorded in similar age groups of 8.8 per cent in the US, 9 per cent in the UK and between 8.5 and 9 per cent in Germany and France, they said.

The prevalence of dementia was greater for those who were older, were females, received no education, and lived in rural areas, the researchers found.

"Our research was based on the first and only nationally representative aging study in India with more than 30,000 participating older adults in the country," said Haomiao Jin, co-author of the study and Lecturer in Health Data Sciences at the University of Surrey, UK.

"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," Jin said in a statement.

The research team from the University of Surrey, University of Southern California, University of Michigan, both in the US, and All India Institute of Medical Sciences, New Delhi developed an AI learning model.

The model was trained on data, which consisted of 70 per cent labelled dataset with dementia diagnoses from a novel online consensus.

The remaining 30 per cent of the data was reserved as a test set to assess the AI's predictive accuracy.

The AI taught itself to predict dementia status for unlabelled observations without dementia diagnoses in the dataset.

"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," Professor Adrian Hilton, Director of the University of Surrey's Institute for People-Centered AI, added.