Interdisciplinary team wins award for paper on predicting postoperative complications with wearables, artificial intelligence
The award to Chenyang Lu and collaborators was announced at the UbiComp/ISWC 2023 conference
A paper published by an interdisciplinary team led by Chenyang Lu has been chosen to receive a Distinguished Paper Award of the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (PACM IMWUT). The paper is one of eight selected out of the 210 papers published in Volume 6 of PACM IMWUT that represent outstanding and exemplary contributions to the research community. The award was announced Oct. 11, 2023, at the UbiComp/ISWC, a conference on the interdisciplinary field of ubiquitous, pervasive and wearable computing.
The paper, “Predicting Post-Operative Complications with Wearables: A Case Study with Patients Undergoing Pancreatic Surgery,” presented a machine learning model for predicting postoperative outcomes of patients undergoing pancreatic surgery using Fitbit wristbands. Lu, the Fullgraf Professor in the McKelvey School of Engineering, collaborated with Chet Hammill, MD, who was associate professor of surgery at the School of Medicine and a surgeon at Barnes-Jewish Hospital, and several other colleagues. Jingwen Zhang, a doctoral student in Lu’s lab, is first author on the paper.
For the study, the team provided Fitbits to 61 patients with pancreatic cancer about a month before they were scheduled to have pancreas resection surgery at Barnes-Jewish Hospital. The Fitbit devices tracked the number of steps each patient took per day, their sleep patterns and heart rate. The team took that data, along with patient characteristics, and developed a robust machine learning pipeline to predict surgical outcomes.
Of the 61 patients, 36 had a textbook outcome after their surgery, a complex procedure to remove their tumors. The other 25 patients either had severe complications or were readmitted to the hospital – a complication rate similar to the national average. The team’s model, which combined the patients’ clinical characteristics with the Fitbit data, achieved significantly higher predictive performance compared with the American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator.
The study was funded by the Foundation for Barnes-Jewish Hospital; the Big Ideas Competition presented by the Healthcare Innovation Lab and the Institute for Informatics, Data Science and Biostatistics (I2DB); and the Fullgraf Foundation.
