A recent collaborative study by researchers from the University of Surrey, University of Southern California, University of Michigan, and the All India Institute of Medical Sciences suggests that the prevalence of dementia in India may be higher than previous estimates have suggested and could be closer to the prevalence rates for countries like the United States and the United Kingdom.
Researchers analyzed data from 31,477 older adults in the first study of its kind using an artificial intelligence (AI) method known as semi-supervised machine learning. They discovered that 10.08 million senior citizens, or 8.44% of persons in India who are 60 years of age or older, could have dementia.
This contrasts with prevalence rates of 8.8% in the United States, 9% in the United Kingdom, and between 8.5% and 9% in Germany and France, which were observed in similar age groups (in different research investigations).
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. 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. Haomiao Jin, Study Co-Author and Lecturer, Health Data Sciences, University of Surrey
The study team created a model for AI learning. The model was tested using data, 70% of which were labeled datasets with dementia diagnoses from a recent online consensus.
To evaluate the AI’s prediction efficacy, the remaining 30% of the data was set aside as a test set. Without dementia diagnoses in the dataset, the AI trained itself to predict the presence of dementia for unlabeled observations.
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.
Adrian Hilton, Professor and Director, Institute for People-Centred AI, University of Surrey
Jin, H., et al. (2023) Estimating the Prevalence of Dementia in India Using a Semi-Supervised Machine Learning Approach. Neuroepidemiology. doi.org/10.1159/000528904.