Apollo Hospitals has released a cardiovascular disease risk prediction AI tool, the first of its type for Indians. The new tool- Cardiovascular Disease Risk Score provides an immediate assessment and cardiologists will be able to use the 'app' to assist forecast their patients' risk of heart illness and begin intervention as early as possible.

Western tools not reliable in Indian population

In the medical community, the Framingham Risk Score is one of the most widely used scoring systems for determining the risk of heart disease. While there are some tools to assist doctors to estimate the likelihood that their patients will acquire heart disease, the majority of them are based on Western data sets and do not take regional risk differences into consideration. As a result, when used in an Indian context, they lose some of their accuracy.

To build the AI tool, the team at Apollo Hospitals used data gathered over the course of 10 years to analyse the health records of approximately 400,000 people from around the nation to create algorithms that can detect and prevent heart disease before it occurs. Microsoft Azure Platform federated learning has also been used to verify the tool globally. Built on Microsoft Azure Platform, the application asks a few simple questions to get a sense of the user's general health. Once the information is entered, the algorithms will provide a unique score for the user.

How it works

When using a large sample of retrospective data on health checks and coronary events, the tool was developed using a combination of applied AI and clinical expertise to deliver a risk score that takes into account all contributing factors, including lifestyle attributes such as diet, tobacco and smoking preferences and physical activity. It also takes into account the effects of psychological stress and anxiety, which are shown by the rate of respiration and high blood pressure.

Depending on the level of danger, the risk is either classified as high, moderate, or minimal. Using this software, you may see which risk factors are affecting your score and make adjustments to them. As a result, doctors may provide their patients with more comprehensive counsel that includes specific suggestions for modifying their lifestyles.

Why is it significant?

According to the World Health Organization, India was responsible for one in every five of the 17.7 million people who died globally in 2016 as a result of cardiovascular diseases including ischemic heart disease and stroke. According to the Global Burden of Disease research, 272 Indian residents die from cardiovascular disease (CVD) for every 100,000 persons worldwide, which is higher than the global average of 235.

The broader pattern

Artificial intelligence (AI) is being tested to help forecast the likelihood of developing heart disease. Together with Kyoto University in Japan, Omron is researching the application of AI and self-reported health data in detecting CVD symptoms before they become more serious. This technology, being developed by researchers at the University of Western Australia, can estimate the risk of coronary heart disease based on CT scan results.

Meanwhile, a VUNO-developed AI-enabled gadget assesses the likelihood of cardiac arrest based on basic vital indicators such as blood pressure and heart rate. In South Korea, the VUNO Med DeepCARS have recently been approved by regulatory authorities.

Disclaimer- The views and opinions expressed in this article are those of the author's and do not necessarily reflect the official policy or position of M3 India.

The author is a practising super specialist from New Delhi.