Ten tips for successfully and sustainably implementing Federated learning for Biomedical applications, ensuring both ethical data governance and improved model performance in sensitive domains are outlined.
Abstract
Modern statistical and machine learning techniques are effective at describing, testing hypotheses and making predictions from complex data. This effectiveness is strongly influenced by the volume and heterogeneity of available data. In many fields, including much of biomedicine, large centralized datasets are not available because of cost, privacy, regulatory or other restrictions. In these cases, smaller datasets are distributed across a large number of independent sites. Medical record data is a classic example of this challenge: the total number of patients may be large, but their records are distributed across many health systems and cannot easily be centralized. Federated learning (FL) is a machine learning paradigm that enables training and validation of a shared model in settings of decentralized data. FL can improve model accuracy and generalizability by increasing sample size, but has trade-offs ranging from operational complexity to data-privacy risks to the potential to introduce unexpected imbalances in model accuracy. We outline ten tips for successfully and sustainably implementing FL for Biomedical applications, ensuring both ethical data governance and improved model performance in sensitive domains.
Eleven practical tips for reducing unintentional overfitting in supervised biomedical machine learning studies are presented and stress principled data splitting, domain-informed preprocessing, controlled model complexity, systematic tuning, comprehensive performance evaluation, and robustness analysis.
D. Chicco, L. Oneto· International Journal of Dat...· 0 citations
Imperfect interoperability (IIO), where health facilities record different, often sparse subsets of clinical variables, remains a major barrier to deploying models trained with Federated Learning (FL) in global health settings. We introduce FedMoDN, a novel federated modular neural network architecture for collaborative learning across all features of an IIO distributed dataset, allowing healthcare facilities to use the full complement of their features without sharing, discarding, or imputing any data. We evaluate FedMoDN on a multi-site pediatric dataset comprising ~130,000 medical visits across 92 healthcare facilities in Tanzania and Rwanda. Across both internal and external validation health facilities, FedMoDN matches or surpasses models trained with centralized data sharing and competitive monolithic FL baselines, achieving a mean AUPRC of 0.80 versus 0.77 for the monolithic FL model on 18 external validation health facilities. Its relative advantage over a monolithic FL model rose from 4% (complete data) to 22% when 70% of test-time features were missing, and, unlike monolithic FL models, performance remained stable when health facilities contributed disjoint feature or label subsets. Furthermore, step-wise predictions provide clinically interpretable feature-attribution scores. By coupling IIO resilience with built-in interpretability, FedMoDN offers a promising decision support tool for resource-limited facilities sidelined by conventional FL.
Cécile Trottet, Jonathan Doenz, P. M. Mastel et al.· npj Digital Medicine· 0 citations
IntroductionClinical trials are usually analysed in a single environment allowing for flexible analysis including adjustment or stratification by subgroup: `one-stage' analysis of individual-level data. Health systems datasets, often distributed across geography and providers, can streamline clinical trials. Data are increasingly accessible in secure data environments (SDEs). Future trial analyses may involve working across multiple SDEs. Row-level data and identifiable data often cannot leave, requiring a `two-stage approach', where summary data from each SDE are meta-analysed.
ObjectiveTo quantify the potential loss of precision and concomitant increases in required sample sizes, and to make recommendations for trial design and conduct, if clinical trial data are split across silos (e.g. SDEs).
MethodsSimulations used data from clinical trials in breast cancer, tuberculosis and prostate cancer with time-to-event, binary and continuous outcome measures. Silos were mimicked by 1000 random partitions into 2, 4, 10 and 25 equal silos and 4 unequal silos proportionate to the UK nations. Data were analysed as if the data could be pooled ignoring silo, pooled accounting for silo (one-stage) or not pooled (two-stage). Estimates and standard errors were presented graphically.
ResultsFor all three outcome measure types, standard errors increased while point estimates spread out as more silos were introduced. Small biases occurred for binary and time-to-event outcomes. This did not always appreciably reduce efficiency. However, in one example with time-to-event data and the largest number of silos, a near-doubling of sample size would have been required to pre-emptively offset the loss of efficiency.
ConclusionAny need to use a two-stage analysis approach has a negative effect compared to doing a one-stage analysis. Technical and data governance solutions to support one-stage analyses are recommended.
Stella Maris Fabiane, Sharon B. Love, D. Fisher et al.· International Journal of Pop...· 0 citations
CoMedBench is introduced, a reproducible benchmark that evaluates a family of generators under a common clinical-validity framework and one shared training and evaluation engine, spanning static tabular and temporal downstream tasks on established critical-care datasets.
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.
Ahmed Abdalaali· Ibn AL-Haitham Journal For P...· 0 citations
This narrative review summarizes applications of supervised learning, unsupervised learning, and deep learning in clinical diagnosis, prognosis prediction, patient stratification, and biomarker discovery and finds that machine learning is useful when the clinical question is clear, data quality is acceptable, and validation is strict.
Xiuyi Wei· Journal of Clinical Technolo...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
