OBJECTIVE The incidence of leptomeningeal disease (LMD) has increased as treatments for brain metastases (BMs) have improved and patients with metastatic disease are living longer. Sample sizes of... Show moreOBJECTIVE The incidence of leptomeningeal disease (LMD) has increased as treatments for brain metastases (BMs) have improved and patients with metastatic disease are living longer. Sample sizes of individual studies investigating LMD after surgery for BMs and its risk factors have been limited, ranging from 200 to 400 patients at risk for LMD, which only allows the use of conventional biostatistics. Here, the authors used machine learning techniques to enhance LMD prediction in a cohort of surgically treated BMs.METHODS A conditional survival forest, a Cox proportional hazards model, an extreme gradient boosting (XGBoost) classifier, an extra trees classifier, and logistic regression were trained. A synthetic minority oversampling technique (SMOTE) was used to train the models and handle the inherent class imbalance. Patients were divided into an 80:20 training and test set. Fivefold cross-validation was used on the training set for hyperparameter optimization. Patients eligible for study inclusion were adults who had consecutively undergone neurosurgical BM treatment, had been admit-ted to Brigham and Women's Hospital from January 2007 through December 2019, and had a minimum of 1 month of follow-up after neurosurgical treatment.RESULTS A total of 1054 surgically treated BM patients were included in this analysis. LMD occurred in 168 patients (15.9%) at a median of 7.05 months after BM diagnosis. The discrimination of LMD occurrence was optimal using an XGboost algorithm (area under the curve = 0.83), and the time to LMD was prognosticated evenly by the random forest algorithm and the Cox proportional hazards model (C-index = 0.76). The most important feature for both LMD clas-sification and regression was the BM proximity to the CSF space, followed by a cerebellar BM location. Lymph node metastasis of the primary tumor at BM diagnosis and a cerebellar BM location were the strongest risk factors for both LMD occurrence and time to LMD.CONCLUSIONS The outcomes of LMD patients in the BM population are predictable using SMOTE and machine learn-ing. Lymph node metastasis of the primary tumor at BM diagnosis and a cerebellar BM location were the strongest LMD risk factors. Show less
Background: Patients who undergo surgery for cervical radiculopathy are at risk for developing adjacent segment disease (ASD). Identifying patients who will develop ASD remains challenging for... Show moreBackground: Patients who undergo surgery for cervical radiculopathy are at risk for developing adjacent segment disease (ASD). Identifying patients who will develop ASD remains challenging for clinicians.Purpose: To develop and validate a deep learning algorithm capable of predicting ASD by using only preoperative cervical MRI in patients undergoing single-level anterior cervical diskectomy and fusion (ACDF).Materials and Methods: In this Health Insurance Portability and Accountability Act-compliant study, retrospective chart review was performed for 1244 patients undergoing single-level ACDF in two tertiary care centers. After application of inclusion and exclusion criteria, 344 patients were included, of whom 60% (n = 208) were used for training and 40% for validation (n = 43) and testing (n = 93). A deep learning-based prediction model with 48 convolutional layers was designed and trained by using preoperative T2-sagittal cervical MRI. To validate model performance, a neuroradiologist and neurosurgeon independently provided ASD prediction sfor the test set. Validation metrics included accuracy, areas under the curve, and F1 scores. The difference in proportion of wrongful predictions between the model and clinician was statistically tested by using the McNemar test.Results: A total of 344 patients (median age, 48 years; interquartile range, 41-58 years; 182 women) were evaluated. The model predicted ASD on the 93 test images with an accuracy of 88 of 93 (95%; 95% CI: 90, 99), sensitivity of 12 of 15 (80%; 95% CI: 60, 100), and specificity of 76 of 78 (97%; 95% CI: 94, 100). The neuroradiologist and neurosurgeon provided predictions with lower accuracy (54 of 93; 58%; 95% CI: 48, 68), sensitivity (nine of 15; 60%; 95% CI: 35, 85), and specificity (45 of 78; 58%; 95% CI: 56, 77) compared with the algorithm. The McNemar test on the contingency table demonstrated that the proportion of wrongful predictions was significantly lower by the model (test statistic, 2.000; P < .001).Conclusion: A deep learning algorithm that used only preoperative cervical T2-weighted MRI outperformed clinical experts at predicting adjacent segment disease in patients undergoing surgery for cervical radiculopathy. (C) RSNA, 2021 Show less
