Key points from article :
Researchers at Linköping University have developed an AI-based method that can accurately estimate people's age, determine whether they have smoked, and diagnose the disease systemic lupus erythematosus (SLE).
The method uses autoencoders, a type of neural network that can learn complex patterns in data.
The researchers trained their autoencoder on data with epigenetic information from more than 75,000 human samples.
The autoencoder was able to identify previously known epigenetic markers associated with these conditions, as well as new markers.
In the next step, the researchers plan to use the autoencoder to create models that can classify people based on a large number of environment-related and individual-specific factors.
The research was published in Briefings in Bioinformatics and funded by various organisations, including the Swedish Research Council.
