With MINE, Microsoft Is Taking Machine Learning for Eyecare Global

Microsoft on Monday announced a new launch, called Microsoft Intelligent Network for Eyecare (MINE), an application based on machine learning and artificial intelligence, which it developed alongside the LV Prasad Eye Institute (LVPEI) in Hyderabad with the aim of delivering better eye care. MINE has been an ongoing project under Microsoft's R&D Division, alongside similar projects for other kinds of hospitals, amongst other efforts.

With the announcement on Monday, Microsoft is taking MINE beyond the pilot program it was running in India to bring this to a number of global partners such as the Bascom Palmer - University of Miami, Flaum Eye Institute - University of Rochester (USA), Federal University of Sao Paulo (Brazil), and Brien Holden Vision Institute (Australia).

“By using our capabilities and pioneering work in the field of machine learning over the years, Microsoft has helped accelerate digital transformation in various key sectors in India, including agriculture and education," explains Anil Bhansali, Managing Director, Microsoft India (R&D). "MINE, a global collaboration, reinforces Microsoft’s belief in the combined power of data, cloud and advanced analytics to drive public good.”

(Also see: 'Research Allows You to Take Risks,' Says Microsoft Research's Sriram Rajamani)

The idea behind MINE is simple - use large amounts of data gathered by these specialist organisations to create databases that can then be intelligently analysed through artificial intelligence modules developed around eye care, in order to identify key areas where intervention can be applied to good effect. This will include the rate of change of myopia in children, conditions that impact children’s eyesight, predictive outcomes of refractive surgery, optimal surgery parameters, as well as ways to personalise a surgery and maximise its probability of success. By studying this data and applying advanced analytics with Microsoft machine learning technology to derive insights, MINE can come up with strategies on how to more effectively improve the success rates people in the field see.

For example, Microsoft Research is currently running a project called 99Dots to improve medication adherence for tuberculosis patients. It tracks a lot of patient data to predict who is at risk of dropping out of their treatments, because although TB is curable, missing doses can make it mutate into a more dangerous, and contagious form. With 99Dots, a lot of different algorithms are used to figure out which people are going to stop taking their medicines, for a variety of reasons, and then to reach out to them and help prevent this.

Using some of the same intelligence Microsoft applied in its 99Dots project, hospitals could predict which patients are likely to come back because they did not follow the treatment properly. The analytics could also help to identify at risk populations more easily, which could be used for preventative care and procedures.

“At LVPEI, we have been using Microsoft Azure machine learning and Power business insights to drive clinical interventions and improve patient outcomes," explains Dr. GN Rao, Founder-Chair LV Prasad Eye Institute. "Today, we take great pride in taking forward our partnership with Microsoft and joining forces with global institutes to revolutionise the field of ophthalmology in India and across the world. We are confident that this will pave way for others to leverage technology to address several other critical eye diseases.”

(Also see: Talking AI at Microsoft's First Machine Learning Conference in India)

As explained by Dr. Rao, the impact of using Microsoft's machine learning tools has been quite quantifiable. Identifying populations at risk, helping allocate resources, and bringing in expertise where it's needed has had a direct impact.

In practical terms, Bhansali says, the expansion of MINE now will allow not just the other hospitals and research bodies to benefit, but also, with a lot more data being generated, the usefulness of the insights will also go up.

"LVPEI has decade of data which we have used along with Azure and Cortana machine learning to provide targeting insights," explains Bhansali "But this is region specific. With the partnerships announced today, we will not only get a lot more data from all these institutions, but also it comes from across various continents. This will allow us to build more universal models, offering greater standardisation so that the solution is useful for many more people. Working with LVPEI, we've been able to carry out a lot of analytics which has been great for operational efficiency, and that will only increase now."