No abstract

No abstract

BACKGROUND:The development of accurate machine learning algorithms requires sufficient quantities of diverse data. This poses a challenge in health care because of the sensitive and siloed nature of biomedical information. Decentralized algorithms through federated learning (FL) avoid data aggregation by instead distributing algorithms to the data before centrally updating one global model.OBJECTIVE:To establish a multicenter collaboration and assess the feasibility of using FL to train machine learning models for intracranial hemorrhage (ICH) detection without sharing data between sites.METHODS:Five neurosurgery departments across the United States collaborated to establish a federated network and train a convolutional neural network to detect ICH on computed tomography scans. The global FL model was benchmarked against a standard, centrally trained model using a held-out data set and was compared against locally trained models using site data.RESULTS:A federated network of practicing neurosurgeon scientists was successfully initiated to train a model for predicting ICH. The FL model achieved an area under the ROC curve of 0.9487 (95% CI 0.9471-0.9503) when predicting all subtypes of ICH compared with a benchmark (non-FL) area under the ROC curve of 0.9753 (95% CI 0.9742-0.9764), although performance varied by subtype. The FL model consistently achieved top three performance when validated on any site's data, suggesting improved generalizability. A qualitative survey described the experience of participants in the federated network.CONCLUSION:This study demonstrates the feasibility of implementing a federated network for multi-institutional collaboration among clinicians and using FL to conduct machine learning research, thereby opening a new paradigm for neurosurgical collaboration.

BACKGROUND:Spine surgery outcomes assessment currently relies on patient-reported outcome measures, which satisfy established reliability and validity criteria, but are limited by the inherently subjective and discrete nature of data collection. Physical activity measured from smartphones offers a new data source to assess postoperative functional outcomes in a more objective and continuous manner.OBJECTIVE:To present a methodology to characterize preoperative mobility and gauge the impact of surgical intervention using objective activity data garnered from smartphone-based accelerometers.METHODS:Smartphone mobility data from 14 patients who underwent elective lumbar decompressive surgery were obtained. A time series analysis was conducted on the number of steps per day across a 2-year perioperative period. Five distinct clinical stages were identified using a data-driven approach and were validated with clinical documentation.RESULTS:Preoperative presentation was correctly classified as either a chronic or acute mobility decline in 92% of patients, with a mean onset of acute decline of 11.8 ± 2.9 weeks before surgery. Postoperative recovery duration demonstrated wide variability, ranging from 5.6 to 29.4 weeks (mean: 20.6 ± 4.9 weeks). Seventy-nine percentage of patients ultimately achieved a full recovery, associated with an 80% ± 33% improvement in daily steps compared with each patient's preoperative baseline (P = .002). Two patients subsequently experienced a secondary decline in mobility, which was consistent with clinical history.CONCLUSION:The perioperative clinical course of patients undergoing spine surgery was systematically classified using smartphone-based mobility data. Our findings highlight the potential utility of such data in a novel quantitative and longitudinal surgical outcome measure.