Search

Background: Machine learning (ML) is extensively employed for forecasting the outcome of various illnesses. The objective of the study was to develop ML based classifiers using a stacking ensemble strategy to predict the Japanese Orthopedic Association (JOA) recovery rate for patients with degenerative cervical myelopathy (DCM). Methods: A total of 672 patients with DCM were included in the study and labeled with JOA recovery rate by 1-year follow-up. All data were collected during 2012–2023 and were randomly divided into training and testing (8:2) sub-datasets. A total of 91 initial ML classifiers were developed, and the top 3 initial classifiers with the best performance were further stacked into an ensemble classifier with a supported vector machine (SVM) classifier. The area under the curve (AUC) was the main indicator to assess the prediction performance of all classifiers. The primary predicted outcome was the JOA recovery rate. Results: By applying an ensemble learning strategy (e.g., stacking), the accuracy of the ML classifier improved following combining three widely used ML models (e.g., RFE-SVM, EmbeddingLR-LR, and RFE-AdaBoost). Decision curve analysis showed the merits of the ensemble classifiers, as the curves of the top 3 initial classifiers varied a lot in predicting JOA recovery rate in DCM patients. Conclusions: The ensemble classifiers successfully predict the JOA recovery rate in DCM patients, which showed a high potential for assisting physicians in managing DCM patients and making full use of medical resources. [ABSTRACT FROM AUTHOR]

Abstract Background Machine learning (ML) is extensively employed for forecasting the outcome of various illnesses. The objective of the study was to develop ML based classifiers using a stacking ensemble strategy to predict the Japanese Orthopedic Association (JOA) recovery rate for patients with degenerative cervical myelopathy (DCM). Methods A total of 672 patients with DCM were included in the study and labeled with JOA recovery rate by 1-year follow-up. All data were collected during 2012–2023 and were randomly divided into training and testing (8:2) sub-datasets. A total of 91 initial ML classifiers were developed, and the top 3 initial classifiers with the best performance were further stacked into an ensemble classifier with a supported vector machine (SVM) classifier. The area under the curve (AUC) was the main indicator to assess the prediction performance of all classifiers. The primary predicted outcome was the JOA recovery rate. Results By applying an ensemble learning strategy (e.g., stacking), the accuracy of the ML classifier improved following combining three widely used ML models (e.g., RFE-SVM, EmbeddingLR-LR, and RFE-AdaBoost). Decision curve analysis showed the merits of the ensemble classifiers, as the curves of the top 3 initial classifiers varied a lot in predicting JOA recovery rate in DCM patients. Conclusions The ensemble classifiers successfully predict the JOA recovery rate in DCM patients, which showed a high potential for assisting physicians in managing DCM patients and making full use of medical resources.

Machine learning (ML) is widely used to predict the prognosis of numerous diseases. This retrospective analysis aimed to develop a prognostic prediction model using ML algorithms and identify predictors associated with poor surgical outcomes in patients with degenerative cervical myelopathy (DCM). A retrospective study. A total of 406 symptomatic DCM patients who underwent surgical decompression were enrolled and analyzed from three independent medical centers. We calculated the area under the curve (AUC), classification accuracy, sensitivity, and specificity of each model. The Japanese Orthopedic Association (JOA) score was obtained before and 1 year following decompression surgery, and patients were grouped into good and poor outcome groups based on a cut-off value of 60% based on a previous study. Two datasets were fused for training, 1 dataset was held out as an external validation set. Optimal feature-subset and hyperparameters for each model were adjusted based on a 2,000-resample bootstrap-based internal validation via exhaustive search and grid search. The performance of each model was then tested on the external validation set. The Support Vector Machine (SVM) model showed the highest predictive accuracy compared to other methods, with an AUC of 0.82 and an accuracy of 75.7%. Age, sex, disease duration, and preoperative JOA score were identified as the most commonly selected features by both the ML and statistical models. Grid search optimization for hyperparameters successfully enhanced the predictive performance of each ML model, and the SVM model still had the best performance with an AUC of 0.93 and an accuracy of 86.4%. Overall, the study demonstrated that ML classifiers such as SVM can effectively predict surgical outcomes for patients with DCM while identifying associated predictors in a multivariate manner. [ABSTRACT FROM AUTHOR]

Objective: To assess the effectiveness and safety of manipulation intervention for degenerative lumbar spondylolisthesis (DLS). Methods: This is a systematic review and meta-analysis. A full-scale retrieval method was performed until February 1, 2021, including nine databases. The homogeneity of different studies was summarized using the Review Manager. The quality of studies was determined with the Cochrane risk-of-bias tool. The evidence quality was graded with the Grading of Recommendations, Assessment, Development, and Evaluations approach. Results: A total of 6 studies involving 524 participants were included. The review demonstrated that manipulation has statistically significant improvements for treating DLS according to Japanese Orthopedic Association scores (mean difference, 3.76; 95% confidence interval, 2.63 to 4.90; P

Study Design: Retrospective analysis of prospectively collected multicenter observational data.Objective: The aim was to examine the preoperative factors affecting postoperative satisfaction following posterior lumbar interbody fusion (PLIF) and microendoscopic muscle-preserving interlaminar decompression (ME-MILD) in patients with degenerative lumbar spondylolisthesis (DLS).Summary Of Background Data: The technique involved in DLS surgery may either be decompression alone or decompression-fixation. Poor performance may occur after either of these surgical treatments. The author hypothesized that evaluating the correlation between preoperative quality of life and postoperative performance would aid in determining the optimal procedure.Materials and Methods: This study included 138 patients who underwent surgery for 1-level mild DLS. The authors performed PLIF for 79 patients and ME-MILD for 59 patients. When the satisfaction subscale of the Zurich Claudication Questionnaire exceeded 2 points, postoperative satisfaction was considered poor. The clinical characteristics were investigated. Responses to preoperative health-related quality of life questionnaires, such as the Japanese Orthopedic Association Back Pain Evaluation Questionnaire (JOABPEQ), short form-36 health survey (SF-36), and visual analog scale, were compared between the satisfied and unsatisfied groups.Results: In the PLIF group, no endogenous factors influenced postoperative satisfaction. The ME-MILD cohort's satisfied and unsatisfied patients differed significantly in terms of preoperative lumbar spine dysfunction ( P <0.001) items of the JOABPEQ, role physical ( P =0.03), and role emotional ( P =0.03) items of the SF-36. A strong correlation ( r =-0.609 P =0.015) was found between preoperative lumbar spine dysfunction and postoperative satisfaction.Conclusions: In the ME-MILD group, preoperative lumbar spine function was correlated with postoperative satisfaction. Decompression alone may be ineffective in cases with decreased lumbar spine function prior to surgery. The degree of low back pain on movement should be considered before selecting the surgical method.Level Of Evidence: 3. [ABSTRACT FROM AUTHOR]

Background Context: Multilevel ossification of the posterior longitudinal ligament in thoracic spine (mT-OPLL) is a rare but clinically significant spinal condition. Various surgical methods have been developed to address this disease. However, the outcomes are commonly unfavorable, and no standard surgical strategy has been established. To solve this problem, we introduced a new surgical strategy based on an innovative decompression concept, namely "de-tension."Purpose: This study aimed to investigate the safety and efficacy of this new treatment, and to establish an improved surgical strategy.Study Design: A prospective observational study with at least 3 years of follow-up.Patient Sample: Fifty-one patients with consecutive mT-OPLL who were treated between August-2012 and June-2018 were enrolled in this study.Outcome Measures: A modified Japanese Orthopedic Association (mJOA) scale assessing thoracic spine, recovery rate (RR), and surgical complications.Methods: All patients underwent 1-stage thoracic posterior laminectomy, selective OPLL resection, and spinal column shortening with/without reduction of kyphosis (dekyphosis). Initially, we recommended that when thoracic kyphosis of T1-T12 in sagittal reconstruction CT (TK) was less than 20°, no dekyphosis should be performed; when this angle was greater than 20°, dekyphosis could be conducted. Patients' demographic data, radiological findings, and intra/postoperative complications were recorded and analyzed. Neurological status was evaluated with mJOA score and RR. The correlation of preoperative TK or kyphosis angle in fusion area (FSK) with postoperative dekyphosis angle and spinal column shortening distance (SD) were respectively evaluated by Pearson correlation analysis.Results: Cerebrospinal fluid leakage (58.8%) and neurological deterioration (15.7%) were the most common complications. Average mJOA score was improved from preoperative 4.0±2.1 to 8.9±2.4 at the last follow-up, and the mean RR was 71.3±33.7%. There was no correlation between preoperative TK and SD (p=.56) or between preoperative FSK and SD (p=.21), but dekyphosis angle was significantly correlated with TK (r=0.504, p<.01) and FSK (r=0.5734, p<.01). TK of 24.6° and FSK of 23.0° were determined as the critical angles for dekyphosis, and a modified surgical strategy was formulated.Conclusions: This new strategy provided a novel solution for mT-OPLL, and was proved to be safe and effective during long-term follow-up. Further rigorously designed large-scale prospective studies are needed to validate our findings. [ABSTRACT FROM AUTHOR]

Objectives: Recently several Korean medical doctors have begun practicing applied kinesiology (AK). Although the efficacy of combining traditional acupuncture (TA) and pharmacopuncture (PP) on lumbar diseases such as lumbar spinal stenosis (LSS) and lumbar herniation of intervertebral disk (LHID) has been examined, the possible benefits of combining TA, PP and AK approaches have not been examined. Therefore the aim of this study was to develop effective treatment for lumbar disorders by combining TA, PP, and AK treatments. Methods: Twenty-four patients hospitalized at Samse Korean Traditional Medicine Hospital between March and September 2018 with L5 or S1 root radiculopathy associated with LSS and LHID were included in this study. They were treated for 10 days with TA, PP and AK approaches that included category block, manipulation and strain/counterstrain treatments. The primary outcomes were mainly assessed using Japanese Orthopedic Association lumbar scores (JOALS). JOALS were determined before the start of treatment as well as five and 10 days after treatment started. Results: The treatments improved the lumbar condition of the patients based on JOA pain score. Conclusion: The combined TA, PP and AK treatments were effective in treating spinal diseases of resident patients. Prospective, controlled, and relevant protocols using multimodal strategies to define the role of TA, PP and AK are needed.

Objectives: Recently several Korean medical doctors have begun practicing applied kinesiology (AK). Although the efficacy of combining traditional acupuncture (TA) and pharmacopuncture (PP) on lumbar diseases such as lumbar spinal stenosis (LSS) and lumbar herniation of intervertebral disk (LHID) has been examined, the possible benefits of combining TA, PP and AK approaches have not been examined. Therefore the aim of this study was to develop effective treatment for lumbar disorders by combining TA, PP, and AK treatments., Methods: Twenty-four patients hospitalized at Samse Korean Traditional Medicine Hospital between March and September 2018 with L5 or S1 root radiculopathy associated with LSS and LHID were included in this study. They were treated for 10 days with TA, PP and AK approaches that included category block, manipulation and strain/counterstrain treatments. The primary outcomes were mainly assessed using Japanese Orthopedic Association lumbar scores (JOALS). JOALS were determined before the start of treatment as well as five and 10 days after treatment started., Results: The treatments improved the lumbar condition of the patients based on JOA pain score., Conclusion: The combined TA, PP and AK treatments were effective in treating spinal diseases of resident patients. Prospective, controlled, and relevant protocols using multimodal strategies to define the role of TA, PP and AK are needed., Competing Interests: Conflict of interest I declare that I have no conflict of interest., (© 2019 Korean Pharmacopuncture Institute.)