Samuel S Rudisill1,2, Alexander L Hornung1,2, J Nicolás Barajas1,2, Jack J Bridge1,3, G Michael Mallow1,2, Wylie Lopez1,2, Arash J Sayari1,2, Philip K Louie4, Garrett K Harada1,2, Youping Tao5, Hans-Joachim Wilke5, Matthew W Colman1,2, Frank M Phillips1,2, Howard S An1,2, Dino Samartzis6,7. 1. Department of Orthopaedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL, USA. 2. International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, IL, USA. 3. Department of Data Science and Analytics, University of Missouri, Colombia, MO, USA. 4. Virginia Mason Medical Center, Neuroscience Institute, Seattle, WA, USA. 5. Institute of Orthopaedic Research and Biomechanics, Ulm University Medical Centre, Ulm, Germany. 6. Department of Orthopaedic Surgery, Rush University Medical Center, 1611 W. Harrison Street, Chicago, IL, USA. Dino_Samartzis@rush.edu. 7. International Spine Research and Innovation Initiative, Rush University Medical Center, Chicago, IL, USA. Dino_Samartzis@rush.edu.
Abstract
PURPOSE: Anterior cervical discectomy and fusion (ACDF) is a common surgical treatment for degenerative disease in the cervical spine. However, resultant biomechanical alterations may predispose to early-onset adjacent segment degeneration (EO-ASD), which may become symptomatic and require reoperation. This study aimed to develop and validate a machine learning (ML) model to predict EO-ASD following ACDF. METHODS: Retrospective review of prospectively collected data of patients undergoing ACDF at a quaternary referral medical center was performed. Patients > 18 years of age with > 6 months of follow-up and complete pre- and postoperative X-ray and MRI imaging were included. An ML-based algorithm was developed to predict EO-ASD based on preoperative demographic, clinical, and radiographic parameters, and model performance was evaluated according to discrimination and overall performance. RESULTS: In total, 366 ACDF patients were included (50.8% male, mean age 51.4 ± 11.1 years). Over 18.7 ± 20.9 months of follow-up, 97 (26.5%) patients developed EO-ASD. The model demonstrated good discrimination and overall performance according to precision (EO-ASD: 0.70, non-ASD: 0.88), recall (EO-ASD: 0.73, non-ASD: 0.87), accuracy (0.82), F1-score (0.79), Brier score (0.203), and AUC (0.794), with C4/C5 posterior disc bulge, C4/C5 anterior disc bulge, C6 posterior superior osteophyte, presence of osteophytes, and C6/C7 anterior disc bulge identified as the most important predictive features. CONCLUSIONS: Through an ML approach, the model identified risk factors and predicted development of EO-ASD following ACDF with good discrimination and overall performance. By addressing the shortcomings of traditional statistics, ML techniques can support discovery, clinical decision-making, and precision-based spine care.
PURPOSE: Anterior cervical discectomy and fusion (ACDF) is a common surgical treatment for degenerative disease in the cervical spine. However, resultant biomechanical alterations may predispose to early-onset adjacent segment degeneration (EO-ASD), which may become symptomatic and require reoperation. This study aimed to develop and validate a machine learning (ML) model to predict EO-ASD following ACDF. METHODS: Retrospective review of prospectively collected data of patients undergoing ACDF at a quaternary referral medical center was performed. Patients > 18 years of age with > 6 months of follow-up and complete pre- and postoperative X-ray and MRI imaging were included. An ML-based algorithm was developed to predict EO-ASD based on preoperative demographic, clinical, and radiographic parameters, and model performance was evaluated according to discrimination and overall performance. RESULTS: In total, 366 ACDF patients were included (50.8% male, mean age 51.4 ± 11.1 years). Over 18.7 ± 20.9 months of follow-up, 97 (26.5%) patients developed EO-ASD. The model demonstrated good discrimination and overall performance according to precision (EO-ASD: 0.70, non-ASD: 0.88), recall (EO-ASD: 0.73, non-ASD: 0.87), accuracy (0.82), F1-score (0.79), Brier score (0.203), and AUC (0.794), with C4/C5 posterior disc bulge, C4/C5 anterior disc bulge, C6 posterior superior osteophyte, presence of osteophytes, and C6/C7 anterior disc bulge identified as the most important predictive features. CONCLUSIONS: Through an ML approach, the model identified risk factors and predicted development of EO-ASD following ACDF with good discrimination and overall performance. By addressing the shortcomings of traditional statistics, ML techniques can support discovery, clinical decision-making, and precision-based spine care.
Authors: Dino Samartzis; Francis H Shen; Don K Matthews; S Tim Yoon; Edward J Goldberg; Howard S An Journal: Spine J Date: 2003 Nov-Dec Impact factor: 4.166
Authors: Clayton L Dean; Josue P Gabriel; Ezequiel H Cassinelli; Michael J Bolesta; Henry H Bohlman Journal: Spine J Date: 2008-12-25 Impact factor: 4.166
Authors: Dino Samartzis; Francis H Shen; Craig Lyon; Mathew Phillips; Edward J Goldberg; Howard S An Journal: Spine J Date: 2004 Nov-Dec Impact factor: 4.166
Authors: Samuel S Rudisill; Alexander L Hornung; J Nicolás Barajas; Jack J Bridge; G Michael Mallow; Wylie Lopez; Arash J Sayari; Philip K Louie; Garrett K Harada; Youping Tao; Hans-Joachim Wilke; Matthew W Colman; Frank M Phillips; Howard S An; Dino Samartzis Journal: Eur Spine J Date: 2022-08-27 Impact factor: 2.721