Standardized Learning for Applicable Local Medical Systems: A Pilot Assessment
TL;DR
The findings suggest that FL is able to achieve reliable predictive performance while preserving the locality of data and can thus be employed as a method for privacy-aware learning in a collaborative local medical system.
Abstract
Federated learning (FL) has become a feasible approach to developing medical prediction models by using distributed institutions without transferring the patient’s raw data to the central server. The pilot experiment presented herewith confirms the usability of FL in local medical systems using the Wisconsin Breast Cancer Diagnostic dataset, which is divided into five clients simulating independent medical institutions under IID and Non-IID settings. A lightweight multilayer perceptron was trained with the Federated Averaging (FedAvg) algorithm and compared to a centralized baseline under the same training conditions. Assessment Metrics for Model Performance: Accuracy, Precision, Recall, F1-Score, and Training Time. The accuracy of the centralized model was 96.49% while the federated model’s accuracy was 94.74% under IID partitioning and 93.86% under Non-IID partitioning. This shows that the performance of the models dropped by an overall 2.6 percentage points in the heterogeneous setting. Notably, recall remained stable at 98.61% across all configurations, suggesting consistent sensitivity in picking up malignant cases. These findings suggest that FL is able to achieve reliable predictive performance while preserving the locality of data and can thus be employed as a method for privacy-aware learning in a collaborative local medical system.