Patrick J Tighe1, Christopher A Harle2, Robert W Hurley1, Haldun Aytug3, Andre P Boezaart1,4, Roger B Fillingim5. 1. Department of Anesthesiology, University of Florida College of Medicine, Gainesville, Florida, USA. 2. Department of Health Services Research, Management and Policy, College of Public Health and Health Professions, Gainesville, Florida, USA. 3. Department of Information Systems and Operations Management, Warrington College of Business Administration, Gainesville, Florida, USA. 4. Department of Orthopaedic Surgery and Rehabilitation, University of Florida College of Medicine, Gainesville, Florida, USA. 5. Department of Community Dentistry and Behavioral Science, University of Florida College of Dentistry, Gainesville, Florida, USA.
Abstract
BACKGROUND: Given their ability to process highly dimensional datasets with hundreds of variables, machine learning algorithms may offer one solution to the vexing challenge of predicting postoperative pain. METHODS: Here, we report on the application of machine learning algorithms to predict postoperative pain outcomes in a retrospective cohort of 8,071 surgical patients using 796 clinical variables. Five algorithms were compared in terms of their ability to forecast moderate to severe postoperative pain: Least Absolute Shrinkage and Selection Operator (LASSO), gradient-boosted decision tree, support vector machine, neural network, and k-nearest neighbor (k-NN), with logistic regression included for baseline comparison. RESULTS: In forecasting moderate to severe postoperative pain for postoperative day (POD) 1, the LASSO algorithm, using all 796 variables, had the highest accuracy with an area under the receiver-operating curve (ROC) of 0.704. Next, the gradient-boosted decision tree had an ROC of 0.665 and the k-NN algorithm had an ROC of 0.643. For POD 3, the LASSO algorithm, using all variables, again had the highest accuracy, with an ROC of 0.727. Logistic regression had a lower ROC of 0.5 for predicting pain outcomes on POD 1 and 3. CONCLUSIONS: Machine learning algorithms, when combined with complex and heterogeneous data from electronic medical record systems, can forecast acute postoperative pain outcomes with accuracies similar to methods that rely only on variables specifically collected for pain outcome prediction. Wiley Periodicals, Inc.
BACKGROUND: Given their ability to process highly dimensional datasets with hundreds of variables, machine learning algorithms may offer one solution to the vexing challenge of predicting postoperative pain. METHODS: Here, we report on the application of machine learning algorithms to predict postoperative pain outcomes in a retrospective cohort of 8,071 surgical patients using 796 clinical variables. Five algorithms were compared in terms of their ability to forecast moderate to severe postoperative pain: Least Absolute Shrinkage and Selection Operator (LASSO), gradient-boosted decision tree, support vector machine, neural network, and k-nearest neighbor (k-NN), with logistic regression included for baseline comparison. RESULTS: In forecasting moderate to severe postoperative pain for postoperative day (POD) 1, the LASSO algorithm, using all 796 variables, had the highest accuracy with an area under the receiver-operating curve (ROC) of 0.704. Next, the gradient-boosted decision tree had an ROC of 0.665 and the k-NN algorithm had an ROC of 0.643. For POD 3, the LASSO algorithm, using all variables, again had the highest accuracy, with an ROC of 0.727. Logistic regression had a lower ROC of 0.5 for predicting pain outcomes on POD 1 and 3. CONCLUSIONS:Machine learning algorithms, when combined with complex and heterogeneous data from electronic medical record systems, can forecast acute postoperative pain outcomes with accuracies similar to methods that rely only on variables specifically collected for pain outcome prediction. Wiley Periodicals, Inc.
Authors: Christine Miaskowski; Andrea Barsevick; Ann Berger; Rocco Casagrande; Patricia A Grady; Paul Jacobsen; Jean Kutner; Donald Patrick; Lani Zimmerman; Canhua Xiao; Martha Matocha; Sue Marden Journal: J Natl Cancer Inst Date: 2017-01-24 Impact factor: 13.506
Authors: Whitney E Muhlestein; Dallin S Akagi; Justiss A Kallos; Peter J Morone; Kyle D Weaver; Reid C Thompson; Lola B Chambless Journal: J Neurol Surg B Skull Base Date: 2017-08-08