MATERIAL and METHODS: We conducted a single-center retrospective study. Patients at our hospital who met the inclusion and exclusion criteria were identified between August 2015 and August 2020 for inclusion. Candidate predictors, such as demographics, clinical scores, radiographic parameters, and outcome, were included. The primary outcome was the prognosis evaluated by the change in patient-reported Japanese orthopaedic association (PRO-JOA) score. Conventional logistic regression models and machine learning algorithms were implemented. Models were compared, considering the area under the curve (AUC), sensitivity, specificity, positive and negative predictive values, and calibration curve.

RESULTS: Overall, the machine learning algorithms and traditional logistic regression models performed similarly. The postoperative cervicomedullary angle, head?neck flexion angle (HNFA), atlantodental interval, postoperative clivo-axial angle, age, postoperative clivus slope, postoperative cranial incidence, weight, postoperative HNFA, and postoperative Boogaard?s angle (BoA) were identified as important predictors for BI prognosis. Among the surveyed radiographic parameters, postoperative BoA was the most important predictor of BI prognosis. In the validation dataset, the bagged trees model performed best (AUC, 0.90).

CONCLUSION: Through machine learning, we have demonstrated predictors of BI prognosis. Machine learning methods did not provide too many advantages over logistic regression in predicting BI prognosis but remain promising. Keywords : Machine learning; basilar invagination, craniocervical junction, sagittal parameter, patient-reported Japanese Orthopaedic Association score