• Satoshi Maki, Takeo Furuya, Keiichi Katsumi, Hideaki Nakajima, Kazuya Honjoh, Shuji Watanabe, Takashi Kaito, Shota Takenaka, Yuya Kanie, Motoki Iwasaki, Masayuki Furuya, Gen Inoue, Masayuki Miyagi, Shinsuke Ikeda, Shiro Imagama, Hiroaki Nakashima, Sadayuki Ito, Hiroshi Takahashi, Yoshiharu Kawaguchi, Hayato Futakawa, Kazuma Murata, Toshitaka Yoshii, Takashi Hirai, Masao Koda, Seiji Ohtori, and Masashi Yamazaki.
• Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chuo-ku Chiba, Chiba, Japan.
• Spine. 2024 Nov 15; 49 (22): 156115691561-1569.

Study DesignA retrospective analysis.ObjectiveThis research sought to develop a predictive model for surgical outcomes in patients with cervical ossification of the posterior longitudinal ligament (OPLL) using deep learning and machine learning (ML) techniques.Summary Of Background DataDetermining surgical outcomes assists surgeons in communicating prognosis to patients and setting their expectations. Deep learning and ML are computational models that identify patterns from large data sets and make predictions.MethodsOf the 482 patients, 288 patients were included in the analysis. A minimal clinically important difference (MCID) was defined as gain in Japanese Orthopaedic Association (JOA) score of 2.5 points or more. The predictive model for MCID achievement at 1 year postsurgery was constructed using patient background, clinical symptoms, and preoperative imaging features (x-ray, CT, MRI) analyzed through LightGBM and deep learning with RadImagenet.ResultsThe median preoperative JOA score was 11.0 (IQR: 9.0-12.0), which significantly improved to 14.0 (IQR: 12.0-15.0) at 1 year after surgery ( P < 0.001, Wilcoxon signed-rank test). The average improvement rate of the JOA score was 44.7%, and 60.1% of patients achieved the MCID. Our model exhibited an area under the receiver operating characteristic curve of 0.81 and the accuracy of 71.9% in predicting MCID at 1 year. Preoperative JOA score and certain preoperative imaging features were identified as the most significant factors in the predictive models.ConclusionA predictive ML and deep learning model for surgical outcomes in OPLL patients is feasible, suggesting promising applications in spinal surgery.Level Of Evidence4.Copyright © 2024 Wolters Kluwer Health, Inc. All rights reserved.

28 keywords...

hide…