Kyle N Kunze1, Evan M Polce2, Jonathan Rasio2, Shane J Nho2. 1. Department of Orthopedic Surgery, Division of Sports Medicine, Section of Young Adult Hip Surgery, Rush University Medical Center, Chicago, Illinois, U.S.A.. Electronic address: Kylekunze7@gmail.com. 2. Department of Orthopedic Surgery, Division of Sports Medicine, Section of Young Adult Hip Surgery, Rush University Medical Center, Chicago, Illinois, U.S.A.
Abstract
PURPOSE: To develop machine learning algorithms to predict failure to achieve clinically significant satisfaction after hip arthroscopy. METHODS: We queried a clinical repository for consecutive primary hip arthroscopy patients treated between January 2012 and January 2017. Five supervised machine learning algorithms were developed in a training set of patients and internally validated in an independent testing set of patients by discrimination, Brier score, calibration, and decision-curve analysis. The minimal clinically important difference (MCID) for the visual analog scale (VAS) score for satisfaction was derived by an anchor-based method and used as the primary outcome. RESULTS: A total of 935 patients were included, of whom 148 (15.8%) did not achieve the MCID for the VAS satisfaction score at a minimum of 2 years postoperatively. The best-performing algorithm was the neural network model (C statistic, 0.94; calibration intercept, -0.43; calibration slope, 0.94; and Brier score, 0.050). The 5 most important features to predict failure to achieve the MCID for the VAS satisfaction score were history of anxiety or depression, lateral center-edge angle, preoperative symptom duration exceeding 2 years, presence of 1 or more drug allergies, and Workers' Compensation. CONCLUSIONS: Supervised machine learning algorithms conferred excellent discrimination and performance for predicting clinically significant satisfaction after hip arthroscopy, although this analysis was performed in a single population of patients. External validation is required to confirm the performance of these algorithms. LEVEL OF EVIDENCE: Level III, therapeutic case-control study.
PURPOSE: To develop machine learning algorithms to predict failure to achieve clinically significant satisfaction after hip arthroscopy. METHODS: We queried a clinical repository for consecutive primary hip arthroscopy patients treated between January 2012 and January 2017. Five supervised machine learning algorithms were developed in a training set of patients and internally validated in an independent testing set of patients by discrimination, Brier score, calibration, and decision-curve analysis. The minimal clinically important difference (MCID) for the visual analog scale (VAS) score for satisfaction was derived by an anchor-based method and used as the primary outcome. RESULTS: A total of 935 patients were included, of whom 148 (15.8%) did not achieve the MCID for the VAS satisfaction score at a minimum of 2 years postoperatively. The best-performing algorithm was the neural network model (C statistic, 0.94; calibration intercept, -0.43; calibration slope, 0.94; and Brier score, 0.050). The 5 most important features to predict failure to achieve the MCID for the VAS satisfaction score were history of anxiety or depression, lateral center-edge angle, preoperative symptom duration exceeding 2 years, presence of 1 or more drug allergies, and Workers' Compensation. CONCLUSIONS: Supervised machine learning algorithms conferred excellent discrimination and performance for predicting clinically significant satisfaction after hip arthroscopy, although this analysis was performed in a single population of patients. External validation is required to confirm the performance of these algorithms. LEVEL OF EVIDENCE: Level III, therapeutic case-control study.
Authors: Samir Kaveeshwar; Michael P Rocca; Brittany A Oster; Matheus B Schneider; Andrew Tran; Matthew P Kolevar; Farshad Adib; R Frank Henn; Sean J Meredith Journal: Knee Surg Sports Traumatol Arthrosc Date: 2022-04-13 Impact factor: 4.114
Authors: Kyle N Kunze; Evan M Polce; Anil S Ranawat; Per-Henrik Randsborg; Riley J Williams; Answorth A Allen; Benedict U Nwachukwu; Andrew Pearle; Beth S Stein; David Dines; Anne Kelly; Bryan Kelly; Howard Rose; Michael Maynard; Sabrina Strickland; Struan Coleman; Jo Hannafin; John MacGillivray; Robert Marx; Russell Warren; Scott Rodeo; Stephen Fealy; Stephen O'Brien; Thomas Wickiewicz; Joshua S Dines; Frank Cordasco; David Altcheck Journal: Orthop J Sports Med Date: 2021-10-14
Authors: Bryant M Song; Yining Lu; Ryan R Wilbur; Ophelie Lavoie-Gagne; Ayoosh Pareek; Brian Forsythe; Aaron J Krych Journal: Arthrosc Sports Med Rehabil Date: 2021-11-12