Microsoft AI Network for Cardiology Collaborates with Apollo Hospitals to Harness New Perspectives for Curing Heart Diseases
Annually, three million Indians suffer from heart attacks — another 30 million from related heart ailments. With such a large populace dealing with life-threatening conditions, there is a massive opportunity for healthcare technology providers to provide macro antidote that counters the problem efficiently. Cardiologists at Apollo hospital(s) say that they cannot predict the probability of the heart ailments because irrespective of the assessment data available worldwide, it is not tailored for India. Hence, now, this major Indian healthcare chain is partnering with Microsoft to innovate the Indian cardiac healthcare space. Microsoft Healthcare NExT is transforming healthcare worldwide with its AI and Cloud capabilities.
It all began with doctors collecting seven years’ worth of cross-country medical history/data of 400,000 patients. The data was analyzed/mined considering HIPPA as well as Indian healthcare laws.
Read More: Security Tips for Online Marketing
“This was a large transactional sample of data and we had to work with clinical experts and data scientists to ensure that the entire dataset, and not just a sample dataset, was correct. It required a significant amount of compute power and design guidelines from a technology perspective. This is where we used Microsoft Azure to upload the data to the cloud and some of the SQL tools to put it into the data warehouse from where data scientists and clinicians could statistically correlate and train the machine learning models,” he adds,” explains Arvind Sivaramakrishnan, Chief Information Officer, Apollo Hospitals.
The Result — 60,000 patients admitted for cardiac problems even after regular health check-ups.
The Question — Why did 60,000 people go through a cardiac event even after regular health check-ups?
The next step was to feed this data to Azure Machine Learning Services and develop a model to build up a culture of proper cardiac care. After co-relating data of 100 check-ups and 200 lab data points, the caregivers narrowed down to 21 risk factors and started building their model. So, did the model work? Hear it from them!
“We found that the accuracy of our model for Indian population in predicting the probability of coronary disease in the future was twice than the existing ones. It’s a game changer! This is just the beginning. It has given us a glimpse of how we can implement AI to get predictive healthcare. We could possibly apply it to other sub-specialties of heart problems. All we need to do is fill in some relevant information into the AI system and we’d be able to classify them under mild, moderate or severe risk category. We’d be able to find this even before a detailed health check-up,” exclaims Dr. Kumar.
Microsoft’s AI network is an extension of their flagship technology MINE. MINE channelizes the efficient development of predictive models to prevent eye-related diseases. Microsoft wishes to achieve the same with heart ailments with its AI Healthcare Network.
“Over the last two years, we have been working with a dynamic partner ecosystem of local, regional and global organizations to bring the power of AI to healthcare. We started with eyecare and today, we are expanding into cardiac care. We have been working with our customers and partners within the healthcare sector to create AI models that can help provide doctors and health care providers insights in their treatment plans. Our partnership with Apollo Hospitals will be a major step in the journey towards providing accessible healthcare to everyone,” says Anil Bhansali, Corporate Vice President, Cloud, and Enterprise, Microsoft India (R&D).
Apollo Hospitals has already integrated the cardiac predictive model in their EMR systems.