Background: Lumbar degenerative disc disease (LDDD) is a leading cause of chronic lower back pain; however, a lack of clear diagnostic criteria and solid LDDD interventional therapies have made predicting the benefits of therapeutic strategies challenging. Our goal is to develop machine learning (ML)–based radiomic models based on pre-treatment imaging for predicting the outcomes of lumbar nucleoplasty (LNP), which is one of the interventional therapies for LDDD. Methods: The input data included general patient characteristics, perioperative medical and surgical details, and pre-operative magnetic resonance imaging (MRI) results from 181 LDDD patients receiving lumbar nucleoplasty. Post-treatment pain improvements were categorized as clinically significant (defined as a ≥80% decrease in the visual analog scale) or non-significant. To develop the ML models, T2-weighted MRI images were subjected to radiomic feature extraction, which was combined with physiological clinical parameters. After data processing, we developed five ML models: support vector machine, light gradient boosting machine, extreme gradient boosting, extreme gradient boosting random forest, and improved random forest. Model performance was measured by evaluating indicators, such as the confusion matrix, accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC), which were acquired using an 8:2 allocation of training to testing sequences. Results: Among the five ML models, the improved random forest algorithm had the best performance, with an accuracy of 0.76, a sensitivity of 0.69, a specificity of 0.83, an F1 score of 0.73, and an AUC of 0.77. The most influential clinical features included in the ML models were pre-operative VAS and age. In contrast, the most influential radiomic features had the correlation coefficient and gray-scale co-occurrence matrix. Conclusions: We developed an ML-based model for predicting pain improvement after LNP for patients with LDDD. We hope this tool will provide both doctors and patients with better information for therapeutic planning and decision-making.

Purpose:Intradiscal biacuplasty (IDB) has been proven to be effective for treating lumbar degenerative disc disease (DDD). However, there hasn’t been a reported prognostic factor for IDB. The present study meticulously evaluate the general and radiographic features which may serve as markers for predicting the therapeutic outcome of IDB.Methods:Forty-two patients suffering from chronic discogenic low back pain for more than 6 months and subsequently received lumbar cool radiofrequency IDB were enrolled. Twenty-three patients completed follow-up questionnaires at 1, 3, 6, and 12 months. The surgical outcomes were reported using visual analogue scale (VAS), Oswestry disability index (ODI), and the consumption of nonsteroidal anti-inflammatory drugs (NSAID). Furthermore, a univariate analysis was performed to identify prognostic factors associated with pain relief from age, gender, body mass index (BMI), and pre-operative lumbar magnetic resonance imaging reading. Results:Significant reductions were found in estimated VAS and ODI at the post-operative period at 1, 3, 6, and 12 months (P < 0.001). The NSAID dosage was significantly decreased at 3- and 6-month follow-up (P < 0.05). No procedure-related complications were detected. The prognosis of IDB was not related to disc height, Pfirrmann grading or Modic endplate change. However, disc extrusions were associated with promising outcomes (VAS improvement ≥ 50%) on pain relief (P < 0.05).Conclusion:IDB is a good choice for treating lumbar DDD. Patients with a disc extrusion may have a higher success rate of IDB, which can be used as an indicator in the physician’s decision-making process.