Aster DM Healthcare, Intel, CARPL.ai Launch AI Platform for Health Data in India

The Aster Innovation and Research Centre, the innovation hub of the Aster DM Healthcare Group, has partnered with Intel Corporation and AI platform provider CARPL.ai to develop and roll out an AI-powered health data platform in India.

WHAT IT DOES

The health data platform is based on federated learning, a machine learning technique that trains AI algorithms in multiple decentralized sources that contain local data samples without exchanging them.

Intel has adopted OpenFL, the open source framework for training machine learning algorithms, to facilitate the adoption of federated learning. This framework is combined with CARPL.ai’s data extraction, transformation and loading capabilities for end-to-end AI model training.

The Intel Software Guard extensions have also been applied to protect workload intellectual property and protect health data.

According to a press statement, the health data platform has been tested using hospital data from the Kerala, Bengaluru and Vijayawada clusters of Aster Hospitals. More than 125,000 chest X-rays were extracted to train a CheXNet AI model using a two-site approach, which can then detect anomalies in X-ray reports.

WHY IT MATTER

A single patient generates approximately 80 megabytes of imaging and EMR data each year. According to a forecast by RBC Capital Market, the CAGR of healthcare data could reach 36% by 2025.

While AI solutions in medical imaging have proven useful in solving pressing health problems such as staff shortages, it remains a “huge challenge” to access silos of data in healthcare facilities, sites and other health systems, while complying with regulatory policies a” huge challenge”. DM.

“Accessing high-quality training datasets and addressing constraints in the form of regulatory frameworks and geographic boundaries are critical requirements” in developing AI applications, said Intel India Country Head Nivruti Rai.

By providing access to massive data sets, Aster DM’s federated learning-based platform enables organizations to collaborate in the development of AI-enabled health tech solutions, driving innovation in areas such as drug discovery, diagnosis, genomics and predictive health care is further promoted. It also enables clinical trials to access relevant data sets in a secure and distributed manner.

Now offered as a service, the platform is expected to increase the accuracy of AI model training while supporting data scientists from various organizations to conduct AI training without sharing raw data. With security and privacy guarantees, the platform also ensures compliance and governance of organizational data.

The recent pilot, according to Aster DM, also demonstrated how the platform can “democratize access to health data across organizational and geographic boundaries without compromising data privacy and security aspects”.

THE BIGGER TREND

In recent years, Aster DM Healthcare Group has made progress in expanding the application of AI technologies in the Indian healthcare landscape. Proof of this commitment is the opening of an AI lab by Aster CMI Hospital, the multi-specialty hospital in Banglore. Launched in March in partnership with the Indian Institute of Science, the Aster AI lab aims to build AI tools for healthcare and educate healthcare professionals in AI. It will initially work on developing AI tools for neurology before expanding into other clinical specialties.

ON THE REGISTRATION

Intel India’s Rai stated that the development of the federated learning-based health data platform “marks a paradigm shift by ‘getting the computer to the data’ rather than ‘getting the data to the computer'”.

“To date, only a few such initiatives have been taken, especially in healthcare,” said Dr. Azad Moopen, president and founder of Aster DM Healthcare. He said their health data platform will “support the development of a predictive mechanism for patients, the opportunity for a second opinion on treatments, and most importantly, affirming patient data security and confidentiality.”

“There is no doubt that decentralized data storage and subsequent training of AI models in a federated manner is the future, especially as the lack of generalizability of AI becomes a bigger problem,” said CARPL.ai CEO Dr. Vidur Mahajan.

Leave a Comment

Your email address will not be published.