Many technology commentators got all excited a few months ago when Microsoft launched how-old.net, a website where users could upload a photo and the site would guess the age of the person in the picture. The service was a great way to showcase the opportunity that applying artificial intelligence to a problem set introduces.
Insilico hopes to deliver a similar sort of an offering, but with a far more important purpose.
Insilico Medicine is an organization focused on aging research. Headquartered at the Emerging Technology Centers at the Johns Hopkins University Eastern campus in Baltimore, it has R&D resources in Belgium, Poland, Russia and China employing 39 scientists worldwide. It is one of the leaders in artificial intelligence trained on some of the largest repositories of gene expression and pharmacological data. Its approach to aging research is to eschew animal testing and instead apply high-performance computing to the problem. Insilico is a service provider who offers analytical services to biopharmaceutical companies, repurposes existing drugs and develops molecular biomarkers of aging and age-related diseases.
Insilico is working on a beta version of its aging.ai service. The service takes data from regular blood tests and "guesses" the age of the patient. Already, at this early stage, the accuracy of the test is a reported 80% within the 10-year interval and 99% accuracy for guessing gender without relying on hormones.
Currently, there are no cheap biomarkers of aging. At the same time, there is no readily available way of tying actions (i.e. a drug regime) to particular aging biomarkers. The value of the service comes when it is combined with clinical activities:
As clinicians try out various procedures, drugs, diets or exercise, they may use aging.ai to see if it starts guessing a lower age for the patient. Initially, the service will not be used for medical purposes since regulatory approval is always a difficult journey. Instead aging.ai is currently focused on gamification of consumer blood testing and attracting the attention of the general public to the importance of periodic blood tests.
In terms of the artificial intelligence that is at work here, almost a million samples were used to train an ensemble of deep neural networks to predict age and gender of the patient. “Deep learning is revolutionizing machine vision and many other fields, but very few groups are exploring its power to extend healthy productive longevity. We encourage experts in machine learning to work with our team to significantly accelerate progress in applied human aging research,” said Alex Zhavoronkov, Ph.D., CEO of Insilico Medicine.
It is still early days and there are likely both technological and regulatory hurdles to overcome to see this sort of offering used for mainstream diagnostic work. However as an indication of how technology can be applied to health to drive good outcomes, it is an instructive one.