Their findings, published in Proceedings of the ACM, showed that a “Multi-Modal Multi-Task Learning” method could make a predicted change for patients’ postoperative pain interference and physical function scores.
Past work to predict patient outcomes used patient questionnaires. But that didn’t factor in the multidimensional aspects of recovery, PhD student Ziqi Xu and the study’s first author, said in a June 3 feature.
The new research shows a “proof of principle” that multimodal machine learning can give a big picture look at recovery. Researchers drew on past findings that Fitbit wearable data improved recovery predictions, along with ecological momentary assessments and statistical tools. The AI learned to weigh relatedness among outcomes while capturing differences from multimodal data.
At the Becker’s 32nd Annual Meeting: The Business and Operations of ASCs, taking place October 29-31 in Chicago, ASC leaders, surgeons and healthcare executives will explore strategies to drive growth, enhance operational performance, navigate reimbursement challenges and prepare for the future of ambulatory surgery. Apply for complimentary registration now.
