Aster Innovation and Research Center, the Aster DM Healthcare Group Innovation Center, has partnered with Intel Corporation and AI platform provider CARPL.ai to develop and deploy a AI-powered healthcare data in India.
WHAT HE DOES
The health data platform is based on federated learning, a machine learning technique that trains AI algorithms on multiple decentralized sources containing local data samples without exchanging them.
Intel has applied OpenFL, its open source framework for training machine learning algorithms, to facilitate the adoption of federated learning. This framework was combined with the data extraction, transformation and loading capabilities of CARPL.ai for end-to-end training of the AI model.
Intel Software Guard extensions have also been applied to protect workload intellectual property and secure health data.
According to a press release, the health data platform was piloted using hospital data from the Kerala, Bengaluru and Vijayawada clusters of Aster Hospitals. Over 125,000 chest X-ray images were extracted to train a CheXNet AI model using a two-site approach, which is then able to detect abnormalities in X-ray reports.
WHY IS IT IMPORTANT
A single patient generates approximately 80 megabytes of imaging and EMR data each year. By 2025, the CAGR of healthcare data could reach 36%, according to a projection by RBC Capital Market.
While AI solutions in medical imaging have proven useful in solving pressing healthcare issues such as staffing shortages, access to data silos in healthcare facilities, sites and other healthcare systems while complying with regulatory policies remains a “tremendous challenge”, according to Aster DM.
“Access to high-quality training datasets and addressing limitations in the form of regulatory frameworks and geographic boundaries are critical imperatives” in the development of AI applications, said Nivruti Rai, lead Intel India National.
By providing access to huge datasets, Aster DM’s federated learning-based platform enables organizations to collaborate on the development of AI-based health technology solutions, further driving innovation in areas such as drug discovery, diagnostics, genomics and predictive healthcare. It also allows clinical trials to access relevant datasets in a secure and distributed way.
Now offered as a service, the platform is expected to increase the accuracy of AI model training while helping data scientists from different organizations perform AI training without sharing raw data. Along with security and privacy safeguards, the platform also provides compliance and organizational data governance.
Its recent pilot, according to Aster DM, also showed how the platform is able to “democratize access to health data across organizational and geographic boundaries without compromising privacy and data security aspects.”
THE GREAT TREND
In recent years, Aster DM Healthcare Group has made strides in expanding its application of AI technologies in India’s healthcare landscape. Proof of this commitment, the opening of an AI laboratory by Aster CMI Hospital, its multi-specialty hospital in Banglore. Launched in partnership with the Indian Institute of Science in March, the Aster AI lab aims to build AI-based healthcare tools and train healthcare professionals in AI. He will initially work on the development of AI tools for neurology before expanding to other clinical specialties.
Intel India’s Rai said the development of the federated learning-based health data platform “marks a paradigm shift in ‘bringing the compute to the data’ rather than ‘bringing the data to the compute’ “.
“So far, only a few such initiatives have been carried out, 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, the affirmation of data security and privacy. patients”.
“There is no doubt that decentralized storage of data and subsequent training of AI models in a federated manner is the future, especially as the lack of generalizability of AI becomes a bigger issue,” said commented the CEO of CARPL.ai, Dr. Vidur Mahajan.