Artificial Intelligence that learns in a collective manner, sharing data across the globe, is often called Swarm Learning. Hospitals are improving upon their swarm learning by ramping up the amount of information shared between them. Swarm learning enables the interpretation of local hospital data to improve the care available to patients across the entire network, and allow the connected hospitals to consistently learn from each other.
Dr. Eng Lim Goh, senior vice president and chief technology officer for AI at Hewlett Packard Enterprise Co (HPE), stated that “Swarm learning only shares the learnings, not the private patient data. We hope this approach would allow all the different hospitals to come together and unite — sharing the learnings, removing biases so that we have high accuracy in our predictions, and at the same time maintaining privacy,”
Dr. Goh from HPE further commented on swarm learning, relating it to an analogous swarm of bees, likening the collective of accumulated data as the beehive, and the individual facets of data as the bees. He says that swarm data allows each hospital to learn locally and amalgamate the data, once combined, to offer insights towards improving patient care that would not have been possible had the individual hospital’s findings remained isolated.
The new findings made available through swarm data findings are then sent back to the hospitals on the network on a periodic schedule, making the cyclical nature of collected data and improved research through gathered findings a resounding success in accelerating health science application in real-time.
Once again, machine learning delivers substantial results through flexibility and innovation.