Arvind Sivaramakrishnan
CIO Sep 14th 2015 A-A+

Arvind Sivramakrishnan is the Group CIO at Apollo Hospitals. He is responsible for the IT strategy, technology enablement of business process and driving business efficiency using technology. He specializes in managing large IT enterprises to drive business effectiveness by adopting effective digital technologies. He has a total experience of more than 28 years.   

Digital Strategy

Nearly three million heart attacks happen in India every year and there are 30 million people who are suffering from coronary diseases. While there are some scores or algorithms available worldwide that predict the probability of a patient having a heart attack in the next 10 to 20 years, doctors cannot extrapolate the same risk-factors and apply them to patients in India since most of them are derived from western studies and don’t have a high degree of accuracy for the Indian population.

In this context, Apollo Hospitals formed a core project team comprising chief cardiologists, data scientists, and AI experts. They developed an India-specific heart risk score to better predict cardiac diseases for general population with the help of Apollo’s database and expertise in the field. More than seven years of data from master health check-ups conducted in Apollo hospitals across India from 2010 to 2017, which consisted clinical and lab data of 400,000 patients was analysed to get actionable insights.

This was a large transactional sample of data and Apollo Hospitals had to work with clinical experts and data scientists to ensure that the entire dataset, and not just a sample dataset, was correct and entailed a significant amount of compute power and design guidelines from a technology perspective. This data was uploaded to the cloud and some of SQL tools were used to put it into the data warehouse from where data scientists and clinicians were statistically correlated and trained the machine learning models.

The team also ensured that the security and privacy aspects of the data. They started with 100 health check-up risk-factors and 200 lab data points and correlated each factor in relation to its significance to the occurrence of the disease. Eventually, they narrowed down to 21 risk factors to build model to predict heart risk for Indian population.

Related Winners