ABSTRACT
Purpose The purpose of this study was to train a deep learning-based method for the prediction of postoperative recurrence of symptoms in Chiari malformation type 1 (CM1) patients undergoing surgery. Studies suggest that certain radiological and clinical features do exist in patients with treatment failure, though these are inconsistent and poorly defined. Methodology This study was a retrospective cohort study of patients who underwent primary surgical intervention for CM1 from January 2010 to May 2020. Only patients who completed pre- and postoperative 12-item short form (SF-12) surveys were included and these were used to classify the recurrence or persistence of symptoms. Forty patients had an improvement in overall symptoms while 17 had recurrence or persistence. After magnetic resonance imaging (MRI) data augmentation, a ResNet50, pre-trained on the ImageNet dataset, was used for feature extraction, and then clustering-constrained attention multiple instance learning (CLAM), a weakly supervised multi-instance learning framework, was trained for prediction of recurrence. Five-fold cross-validation was used for the development of MRI only, clinical features only, and a combined machine learning model. Results This study included 57 patients who underwent CM1 decompression. The recurrence rate was 30%. The combined model incorporating MRI, pre-operative SF-12 physical component scale (PCS), and extent of cerebellar ectopia performed best with an area under the curve (AUC) of 0.71 and an F1 score of 0.74. Conclusion This is the first study to our knowledge to explore the prediction of postoperative recurrence of symptoms in CM1 patients using machine learning methods and represents the first step toward developing a clinically useful prognostication machine learning model. Further studies utilizing a similar deep learning approach with a larger sample size are needed to improve the performance.
ABSTRACT
BACKGROUND: There is limited information on patients' ability to return to work (RTW) after the majority of shoulder surgical procedures. METHODS: This study was a retrospective analysis of prospectively collected data on 1,773 consecutive patients who underwent shoulder surgery performed by a single surgeon from 2004 to 2017. A validated L'Insalata Shoulder Questionnaire was used to collect information on 32 preoperative factors, which were used for analysis. The questionnaire included the premorbid level of work and the levels preoperatively and at 6 months postoperatively. RESULTS: Six months following the shoulder operations, 77% of the patients returned to work (40% with full duties and 37% with light duties). Concomitant rotator cuff repair and stabilization was associated with the highest RTW rate (90%) whereas some of the lowest RTW rates were associated with reverse total shoulder arthroplasty (56%) and total shoulder arthroplasty (71%). The highest rate of RTW with full duties was associated with debridement for calcific tendinitis (62%). Capsular release provided a significant improvement in work level (on a scale ranging from none to strenuous) from preoperatively to postoperatively (p = 0.0116). Older patients with stiffer shoulders who were not working preoperatively had the lowest RTW rate at 6 months. CONCLUSIONS: To our knowledge, this is the largest study of RTW outcomes of shoulder surgical procedures, and it showed that 4 out of 5 patients were able to RTW 6 months postoperatively with approximately half resuming full duties and half, lighter duties. Capsular release was the only procedure to result in a significant improvement in work level within 6 months. The best independent predictors of RTW were younger age, less stiffness, and working preoperatively. LEVEL OF EVIDENCE: Therapeutic Level IV. See Instructions for Authors for a complete description of levels of evidence.
