Satoshi Maki1,2, Takeo Furuya1,2, Toshitaka Yoshii3,2, Satoru Egawa3,2, Kenichiro Sakai4,2, Kazuo Kusano5,2, Yukihiro Nakagawa6,2, Takashi Hirai3,2, Kanichiro Wada7,2, Keiichi Katsumi8,2, Kengo Fujii9,2, Atsushi Kimura10,2, Narihito Nagoshi11,2, Tsukasa Kanchiku12,2, Yukitaka Nagamoto13,2, Yasushi Oshima14,2, Kei Ando15,2, Masahiko Takahata16,2, Kanji Mori17,2, Hideaki Nakajima18,2, Kazuma Murata19,2, Shunji Matsunaga20,2, Takashi Kaito21,2, Kei Yamada22,2, Sho Kobayashi23,2, Satoshi Kato24,2, Tetsuro Ohba25,2, Satoshi Inami26,2, Shunsuke Fujibayashi27,2, Hiroyuki Katoh28,2, Haruo Kanno29,2, Shiro Imagama15,2, Masao Koda9,2, Yoshiharu Kawaguchi30,2, Katsushi Takeshita10,2, Morio Matsumoto11,2, Seiji Ohtori1, Masashi Yamazaki9,2, Atsushi Okawa3,2. 1. Department of Orthopedic Surgery, Graduate School of Medicine, Chiba University, Chiba, Chiba, Japan. 2. Japanese Multicenter Research Organization for Ossification of the Spinal Ligament, Japan. 3. Department of Orthopedic Surgery, Tokyo Medical and Dental University, Bunkyo-ku, Tokyo, Japan. 4. Department of Orthopedic Surgery, Saiseikai Kawaguchi General Hospital, Kawaguchi, Saitama, Japan. 5. Department of Orthopedic Surgery, Kudanzaka Hospital, Chiyoda-ku, Tokyo, Japan. 6. Department of Orthopedic Surgery, Wakayama Medical University Kihoku Hospital, Itogun, Wakayama, Japan. 7. Department of Orthopedic Surgery, Hirosaki University Graduate School of Medicine, Hirosaki, Aomori, Japan. 8. Department of Orthopedic Surgery, Niigata University Medical and Dental General Hospital, Niigata, Niigata, Japan. 9. Department of Orthopedic Surgery, Faculty of Medicine, University of Tsukuba, Tsukuba, Ibaraki, Japan. 10. Department of Orthopedics, Jichi Medical University, Shimotsuke, Tochigi, Japan. 11. Department of Orthopedic Surgery, School of Medicine, Keio University, Shinjuku-ku, Tokyo japan. 12. Department of Orthopedic Surgery, Yamaguchi University School of Medicine, Ube, Yamaguchi, Japan. 13. Department of Orthopedic Surgery, Osaka Rosai Hospital, Sakai, Osaka, Japan. 14. Department of Orthopedic Surgery, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan. 15. Department of Orthopedic Surgery, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan. 16. Orthopedic Surgery, Reconstructive Surgery and Rehabilitation Medicine, Division of Advanced Medical Science, Hokkaido University, Graduate School of Medicine, Sapporo, Japan. 17. Department of Orthopedic Surgery, Shiga University of Medical Science, Otsu, Shiga, Japan. 18. Department of Orthopedics and Rehabilitation Medicine, University of Fukui Faculty of Medical Sciences, Matsuoka, Fukui, Japan. 19. Department of Orthopedic Surgery, Tokyo Medical University, Shinjuku-ku, Tokyo, Japan. 20. Department Department of Orthopedic Surgery, Imakiire General Hospital, Kagoshima, Kagoshima, Japan. 21. Department of Orthopedic Surgery, Graduate School of Medicine, Osaka University, Suita, Osaka, Japan. 22. Department of Orthopedic Surgery, Kurume University School of Medicine, Kurume, Fukuoka, Japan. 23. Department of Orthopedic Surgery, Hamamatsu University School of Medicine, Hamamatsu, Shizuoka, Japan. 24. Department of Orthopedic Surgery, Graduate School of Medical Sciences, Kanazawa University, Kanazawa, Ishikawa, Japan. 25. Department of Orthopedic Surgery, University of Yamanashi, Chuo, Yamanashi, Japan. 26. Department of Orthopedic Surgery, Dokkyo Medical University School of Medicine, Shimotsuga-gun, Tochigi, Japan. 27. Department of Orthopedic Surgery, Graduate School of Medicine, Kyoto University, Kyoto, Kyoto, Japan. 28. Department of Orthopedic Surgery, Surgical Science, Tokai University School of Medicine, isehara, Kanagawa, Japan. 29. Department of Orthopedic Surgery, Tohoku University School of Medicine, Sendai, Miyagi, Japan. 30. Department of Orthopedic Surgery, Faculty of Medicine, University of Toyama, Toyama, Toyama, Japan.
Abstract
STUDY DESIGN: A retrospective analysis of prospectively collected data. OBJECTIVE: This study aimed to create a prognostic model for surgical outcomes in patients with cervical ossification of the posterior longitudinal ligament (OPLL) using machine learning (ML). SUMMARY OF BACKGROUND DATA: Determining surgical outcomes helps surgeons provide prognostic information to patients and manage their expectations. ML is a mathematical model that finds patterns from a large sample of data and makes predictions outperforming traditional statistical methods. METHODS: Of 478 patients, 397 and 370 patients had complete follow-up information at 1 and 2 years, respectively, and were included in the analysis. A minimal clinically important difference (MCID) was defined as an acquired Japanese Orthopedic Association (JOA) score of ≥2.5 points, after which a ML model that predicts whether MCID can be achieved 1 and 2 years after surgery was created. Patient background, clinical symptoms, and imaging findings were used as variables for analysis. The ML model was created using LightGBM, XGBoost, random forest, and logistic regression, after which the accuracy and area under the receiver-operating characteristic curve (AUC) were calculated. RESULTS: The mean JOA score was 10.3 preoperatively, 13.4 at 1 year after surgery, and 13.5 at 2 years after surgery. XGBoost showed the highest AUC (0.72) and high accuracy (67.8) for predicting MCID at 1 year, whereas random forest had the highest AUC (0.75) and accuracy (69.6) for predicting MCID at 2 years. Among the included features, total preoperative JOA score, duration of symptoms, body weight, sensory function of the lower extremity sub-score of the JOA, and age were identified as having the most significance in most of ML models. CONCLUSION: Constructing a prognostic ML model for surgical outcomes in patients with OPLL is feasible, suggesting the potential application of ML for predictive models of spinal surgery.Level of Evidence: 4.
STUDY DESIGN: A retrospective analysis of prospectively collected data. OBJECTIVE: This study aimed to create a prognostic model for surgical outcomes in patients with cervical ossification of the posterior longitudinal ligament (OPLL) using machine learning (ML). SUMMARY OF BACKGROUND DATA: Determining surgical outcomes helps surgeons provide prognostic information to patients and manage their expectations. ML is a mathematical model that finds patterns from a large sample of data and makes predictions outperforming traditional statistical methods. METHODS: Of 478 patients, 397 and 370 patients had complete follow-up information at 1 and 2 years, respectively, and were included in the analysis. A minimal clinically important difference (MCID) was defined as an acquired Japanese Orthopedic Association (JOA) score of ≥2.5 points, after which a ML model that predicts whether MCID can be achieved 1 and 2 years after surgery was created. Patient background, clinical symptoms, and imaging findings were used as variables for analysis. The ML model was created using LightGBM, XGBoost, random forest, and logistic regression, after which the accuracy and area under the receiver-operating characteristic curve (AUC) were calculated. RESULTS: The mean JOA score was 10.3 preoperatively, 13.4 at 1 year after surgery, and 13.5 at 2 years after surgery. XGBoost showed the highest AUC (0.72) and high accuracy (67.8) for predicting MCID at 1 year, whereas random forest had the highest AUC (0.75) and accuracy (69.6) for predicting MCID at 2 years. Among the included features, total preoperative JOA score, duration of symptoms, body weight, sensory function of the lower extremity sub-score of the JOA, and age were identified as having the most significance in most of ML models. CONCLUSION: Constructing a prognostic ML model for surgical outcomes in patients with OPLL is feasible, suggesting the potential application of ML for predictive models of spinal surgery.Level of Evidence: 4.
Authors: Babak Saravi; Frank Hassel; Sara Ülkümen; Alisia Zink; Veronika Shavlokhova; Sebastien Couillard-Despres; Martin Boeker; Peter Obid; Gernot Michael Lang Journal: J Pers Med Date: 2022-03-22