An Artificial Intelligence-Based Support Tool for Lumbar Spinal Stenosis Diagnosis from Self-Reported History Questionnaire.

OBJECTIVES: Symptomatic lumbar spinal stenosis (LSS) leads to functional impairment and pain. While radiologic characterization of the morphological stenosis grade can aid in the diagnosis, it may not always correlate with patient symptoms. Artificial intelligence (AI) may diagnose symptomatic LSS in patients solely based on self-reported history questionnaires. METHODS: We evaluated multiple machine learning (ML) models to determine the likelihood of LSS using a self-reported questionnaire in patients experiencing low back pain and/or numbness in the legs. The questionnaire was built from peer-reviewed literature and a multidisciplinary panel of experts. Random forest, lasso logistic regression, support vector machine, gradient boosting trees, deep neural networks, and automated machine learning models were trained and performance metrics were compared. RESULTS: Data from 4827 patients (4690 patients without LSS: mean age 62.44, range 27-84 years, 62.8% females, and 137 patients with LSS: mean age 50.59, range 30-71 years, 59.9% females) were retrospectively collected. Among the evaluated models, the random forest model demonstrated the highest predictive accuracy with an area under the receiver operating characteristic curve (AUROC) between model prediction and LSS diagnosis of 0.96, a sensitivity of 0.94, a specificity of 0.88, a balanced accuracy of 0.91, and a Cohen's kappa of 0.85. CONCLUSIONS: Our results indicate that ML can automate the diagnosis of LSS based on self-reported questionnaires with high accuracy. Implementation of standardized and intelligence-automated workflow may serve as a supportive diagnostic tool to streamline patient management and potentially lower health care costs.

Less correction with minimally invasive surgery for adolescent idiopathic scoliosis compared to open surgical correction.

Purpose: In this study, we investigated the relationship between the results of thoracic curve correction using minimally invasive surgeries in 35 patients and open surgical correction in 47 patients with adolescent idiopathic scoliosis. Methods: The correlations between the Cobb's angle of the primary and postoperative curves, angle of thoracic kyphosis and lumbar lordosis, correction percentage, derotation values, estimated blood loss, duration of surgery, and period of hospitalization after surgery were assessed by calculating the mean and standard deviation. Calculation and comparison were performed using Pearson correlation. Results: The Cobb's angle correction ranged from 53.4° ± 11.8° to 6.7° ± 5.2° (p < 0.001) in the open surgical correction group and from 51.2° ± 11.4° to 11.7° ± 5.8° (p < 0.001) in the minimally invasive surgery group before and after surgery, respectively. The percentage of curvature correction was 88.2% ± 8.0% and 77.7% ± 10.7% (p < 0.001) in the open surgical correction and minimally invasive surgery groups, respectively. The estimated blood loss was higher in the open surgical correction group than in the minimally invasive surgery group (208.7 ± 113.4 vs 564.3 ± 242.7 mL). Axial rotation was changed from 29.1°± 7.5 to 17.1°± 6.8 (p < 0.001) in the open surgical correction group and from 28.9°± 7.8 to 19.4°± 6.4 (p < 0.001) in the minimally invasive surgery group. The duration of surgery was shorter in the open surgical correction group than in the minimally invasive surgery group (266.6 ± 64.3 vs 346.2 ± 70.5 min). A positive correlation between time of operation and Cobb's angle correction (in °) in open surgical correction (r = 0.37) and minimally invasive surgery (r = 0.43) was found. Conclusion: The open surgical correction procedures were more effective than minimally invasive surgery in correcting the spinal curve. The increase in the duration of open surgical correction increases the estimated blood loss, but it also more significantly improves the correction of Cobb's angle. Level of evidence: III.