Evaluation of the Predictors for Unfavorable Clinical Outcomes of Degenerative Lumbar Spondylolisthesis After Lumbar Interbody Fusion Using Machine Learning

Clinical and Radiologic Predictors of Slower Improvement and Nonimprovement After Surgical Treatment of L4-L5 Degenerative Spondylolisthesis: Preliminary Results

STUDY DESIGN

Retrospective cohort.

OBJECTIVE

To identify the predictors of slower and nonimprovement after surgical treatment of L4-5 degenerative lumbar spondylolisthesis (DLS).

SUMMARY OF BACKGROUND DATA

There is limited evidence regarding clinical and radiologic predictors of slower and nonimprovement following surgery for L4-5 DLS.

METHODS

Patients who underwent minimally invasive decompression or fusion for L4-5 DLS and had a minimum of 1-year follow-up were included. Outcome measures were: (1) minimal clinically important difference (MCID), (2) patient acceptable symptom state (PASS), and (3) global rating change (GRC). Clinical variables analyzed for predictors were age, gender, body mass index (BMI), surgery type, comorbidities, anxiety, depression, smoking, osteoporosis, and preoperative patient-reported outcome measures (PROMs) (Oswestry disability index, ODI; visual analog scale, VAS back and leg; 12-Item Short Form Survey Physical Component Score, SF-12 PCS). Radiologic variables analyzed were slip percentage, translational and angular motion, facet diastasis/cyst/orientation, laterolisthesis, disc height, scoliosis, main and fractional curve Cobb angles, and spinopelvic parameters.

RESULTS

Two hundred thirty-three patients (37% decompression and 63% fusion) were included. At less than three months, high pelvic tilt (PT) (OR: 0.92, P= 0.02) and depression (OR: 0.28, P= 0.02) were predictors of MCID nonachievement and GRC nonbetterment, respectively. Neither retained significance at above six months and hence, were identified as predictors of slower improvement. At above six months, low preoperative VAS leg (OR: 1.26, P= 0.01) and high facet orientation (OR: 0.95, P= 0.03) were predictors of MCID nonachievement, high L4-5 slip percentage (OR: 0.86, P= 0.03) and L5-S1 angular motion (OR: 0.78, P= 0.01) were predictors of GRC nonbetterment, and high preoperative ODI (OR: 0.96, P= 0.04) was a predictor of PASS nonachievement.

CONCLUSIONS

High PT and depression were predictors of slower improvement and low preoperative leg pain, high disability, high facet orientation, high slip percentage, and L5-S1 angular motion were predictors of nonimprovement. However, these are preliminary findings and further studies with homogeneous cohorts are required to establish these findings.

Revolutionizing spinal interventions: a systematic review of artificial intelligence technology applications in contemporary surgery

Leveraging its ability to handle large and complex datasets, artificial intelligence can uncover subtle patterns and correlations that human observation may overlook. This is particularly valuable for understanding the intricate dynamics of spinal surgery and its multifaceted impacts on patient prognosis. This review aims to delineate the role of artificial intelligence in spinal surgery. A search of the PubMed database from 1992 to 2023 was conducted using relevant English publications related to the application of artificial intelligence in spinal surgery. The search strategy involved a combination of the following keywords: "Artificial neural network," "deep learning," "artificial intelligence," "spinal," "musculoskeletal," "lumbar," "vertebra," "disc," "cervical," "cord," "stenosis," "procedure," "operation," "surgery," "preoperative," "postoperative," and "operative." A total of 1,182 articles were retrieved. After a careful evaluation of abstracts, 90 articles were found to meet the inclusion criteria for this review. Our review highlights various applications of artificial neural networks in spinal disease management, including (1) assessing surgical indications, (2) assisting in surgical procedures, (3) preoperatively predicting surgical outcomes, and (4) estimating the occurrence of various surgical complications and adverse events. By utilizing these technologies, surgical outcomes can be improved, ultimately enhancing the quality of life for patients.

Limitations in Evaluating Machine Learning Models for Imbalanced Binary Outcome Classification in Spine Surgery: A Systematic Review

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models' effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44% to 42.4%. A total of 59 papers reported the model's area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings.