Researchers employ swarm learning to create algorithms that are used in a program for secure cancer detection.

Swarm Learning Can Help Keep Medical Info Secure, Detect Cancer

The University of Leeds in the UK has found a way to use AI to predict the development of cancer from patient data, without putting personal information. The project employs “swarm learning,” to predict cancer by using medical images of patient tissue samples, without releasing the data from hospitals. It’s a way of protecting medical data security in the U.S. as required by the HIPPA law.

The Health Insurance Portability and Accountability Act of 1996 (HIPAA) is a federal law that required the creation of national standards to protect sensitive patient health information from being disclosed without the patient’s consent or knowledge. And this includes information being used by various AI systems providing medical care. According to Github, swarm learning is a decentralized, privacy-preserving Machine Learning framework that uses computing power at, or near, the distributed data sources to run the Machine Learning algorithms that train the models. It also uses the security of a blockchain platform to share learnings with peers in a safe and secure manner. In this decentralized architecture, only the insights learned are shared with the collaborating ML peers, not the raw data.

A story on explains how swarm learning trains AI algorithms to detect patterns in data in a local hospital or university, such as genetic changes in images of human tissue. The swarm learning system then sends this newly trained algorithm—but importantly no local data or patient information—to a central computer, ensuring privacy and security.

The algorithm is added to algorithms generated by other hospitals in an identical way to create an optimized algorithm. This is then sent back to the local hospital, where it is reapplied to the original data, improving the detection of genetic changes thanks to its more sensitive detection capabilities.

By undertaking this several times, the algorithm can be improved and create one that works on all the data sets. This means that the technique can be applied without the need for any data to be released to third-party companies or to be sent between hospitals or across international borders.

The Leeds researchers studied three groups with their AI. The groups studied were from the United States, Northern Ireland, and Germany. The research was led by Jakob Nikolas Kather, Visiting Associate Professor at the University of Leeds School of Medicine and Researcher at the University Hospital RWTH Aachen.

Dr Kather said: “Based on data from over 5,000 patients, we were able to show that AI models trained with swarm learning can predict clinically relevant genetic changes directly from images of tissue from colon tumors.”

Swarm learning might be the best solution for the medical field to keep patient information private while using other algorithms for care.

Phil Quirke, Professor of Pathology at the University of Leeds’s School of Medicine, said:

“We have shown that swarm learning can be used in medicine to train independent AI algorithms for any image analysis task. This means it is possible to overcome the need for data transfer without institutions having to relinquish secure control of their data.