Predicting post-surgical functional status in high-grade glioma with resting state fMRI and machine learning.

PURPOSE: High-grade glioma (HGG) is the most common and deadly malignant glioma of the central nervous system. The current standard of care includes surgical resection of the tumor, which can lead to functional and cognitive deficits. The aim of this study is to develop models capable of predicting functional outcomes in HGG patients before surgery, facilitating improved disease management and informed patient care. METHODS: Adult HGG patients (N = 102) from the neurosurgery brain tumor service at Washington University Medical Center were retrospectively recruited. All patients completed structural neuroimaging and resting state functional MRI prior to surgery. Demographics, measures of resting state network connectivity (FC), tumor location, and tumor volume were used to train a random forest classifier to predict functional outcomes based on Karnofsky Performance Status (KPS < 70, KPS ≥ 70). RESULTS: The models achieved a nested cross-validation accuracy of 94.1% and an AUC of 0.97 in classifying KPS. The strongest predictors identified by the model included FC between somatomotor, visual, auditory, and reward networks. Based on location, the relation of the tumor to dorsal attention, cingulo-opercular, and basal ganglia networks were strong predictors of KPS. Age was also a strong predictor. However, tumor volume was only a moderate predictor. CONCLUSION: The current work demonstrates the ability of machine learning to classify postoperative functional outcomes in HGG patients prior to surgery accurately. Our results suggest that both FC and the tumor's location in relation to specific networks can serve as reliable predictors of functional outcomes, leading to personalized therapeutic approaches tailored to individual patients.

Making Meaningful Use of Price Transparency Data: Describing Price Variation of Spine Surgery and Imaging in a Single System.

Price transparency is an increasingly popular solution for high healthcare expenditures in the United States, but little is known about its potential to facilitate patient price shopping. Our objective was to analyze interhospital and interpayer price variability in spine surgery and spine imaging using newly public payer-specific negotiated charges (PNCs). We selected a subset of billing codes for spine surgery and spine imaging at 12 hospitals within a Saint Louis metropolitan area healthcare system. We then compared PNCs for these procedures and tested for significant differences in interhospital and interinsurer IQR using the Mann-Whitney U Test. We found significantly greater IQRs of PNCs as a factor of the insurance plan than as a factor of the hospital for cervical spinal fusions (interinsurer IQR $8256; interhospital IQR $533; P < .0001), noncervical spinal fusions (interinsurer IQR $28 423; interhospital IQR $5512; P < .001), computed tomographies of the lower spine (interinsurer IQR $595; interhospital IQR $113; P < .0001), and MRIs lower spinal canal (interinsurer IQR $1010; interhospital IQR $158; P < .0001). There was no significant difference between the interinsurer IQR and the interhospital IQR for lower spine x-rays (interinsurer IQR $107; interhospital IQR $67; P = .0543). Despite some between-hospital heterogeneity, we show significantly higher price variability between insurers than between hospitals. Our single system analysis limits our ability to generalize, but our results suggest that savings depend more on hospital and provider negotiations than patient price shopping, given the difficulty of switching insurers.