Machine Learning Approaches for Early Detection of Ossification of Posterior Longitudinal Ligament in Health Screening Settings

TL;DR

This study developed a machine learning model to detect OPLL early during routine health screenings, aiming to improve early diagnosis and reduce unnecessary follow-ups.

Contribution

The study introduces an interpretable machine learning model for early OPLL detection using routine health examination data.

Findings

A logistic regression model achieved 65% accuracy and an AUROC of 0.69 for OPLL detection.

Advanced age and elevated CA19-9 levels were identified as independent risk factors for OPLL.

The model offers fewer false-negatives and is suitable for high-volume screening programs.

Abstract

Early detection of ossification of the posterior longitudinal ligament (OPLL) is hampered by the late onset of neurological symptoms, so we built and validated an interpretable machine learning model to identify OPLL during routine health examinations. We retrospectively analyzed 1442 Japanese adults screened between 2020 and 2023, including 432 imaging-confirmed cases, after median imputation, one-hot encoding, Random Forest feature selection that reduced 235 variables to 20, and class-balance correction with SMOTE. Logistic regression, Random Forest, Gradient Boosting, and XGBoost models were tuned using a 5-fold cross-validated grid search, in which a re-estimated logistic regression yielded odds ratios for clinical interpretation. The logistic model achieved 65% accuracy and an AUROC of 0.69 (95% CI 0.66–0.76), matching tree-based models, yet with fewer false-negatives. Advanced age (OR 1.60, 95% CI 1.27–2.00) and elevated CA19-9 (OR 1.24, 95% CI 1.00–1.35) independently increased OPLL odds. This concise, explainable tool could facilitate early recognition of OPLL, reduce unnecessary follow-up, and enable timely preventive interventions in high-volume screening programs.

Figures