Federated Computer Vision for Malaria Slide Diagnosis Under Clinic-Level Label Scarcity: An Asynchronous Aggregation Evaluation of Diagnostic Sensitivity Retention

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Federated learning promises to train malaria slide classifiers across clinics without centralising images, but clinic-level label scarcity means that most participating sites hold few or no confirmed parasitology labels. the present analysis characterises the operating characteristics of asynchronous federated aggregation under that constraint. The design is a replication-based evaluation of a before-after-control-impact estimator applied to a declared variance structure: between-cluster standard deviation 6.0, residual standard deviation 4.5, and intraclass correlation 0.640. Power was estimated across 2000 design cells spanning cluster counts of 8, 16, 24 and 32 and sensitivity effects of 3, 5 and 8 percentage points.54 clusters are required to detect a 5-percentage-point sensitivity difference at 80% power, a requirement that exceeds the largest cluster count examined. Minimum detectable effects at 80% power fall as cluster count rises but remain above the 3-percentage-point threshold at every cluster count evaluated. The results indicate that asynchronous aggregation can retain diagnostic sensitivity only when the number of participating clinics is large relative to the effect size of interest, and that label-scarce deployments should be planned around detectable-effect curves rather than around nominal power targets.

• Federated Learning Under Non-IID Patient Distributions for Malaria Diagnosis in Low-Connectivity Clinics: A Robustness Evaluation of Differential Privacy Budgets

  Zenodo (CERN European Organization for Nuclear Research) 2026 · 0 citations

• Privacy-Preserving Federated Learning for Artificial Intelligence Healthcare in Uganda: Robustness Under Distribution Shift and Sparse Labels

  Zenodo (CERN European Organization for Nuclear Research) 2026 · 0 citations

• Federated Learning for Multi-Site Malaria Microscopy Under Variable Giemsa Staining Protocols: A Privacy-Utility Evaluation of Artificial Intelligence Diagnostic Parity

  Zenodo (CERN European Organization for Nuclear Research) 2026 · 0 citations

• Artificial Intelligence Benchmarking of Federated Learning Aggregation Under Unmeasured Clinic-Specific Label Shift in Multi-Site Diabetes Retinopathy Grading: A Healthcare Fairness-Transfer Evaluation

  Zenodo (CERN European Organization for Nuclear Research) 2026 · 0 citations

• Federated Learning for Computer Vision Cassava Disease Triage Under Clinic-Level Label Shift: An Agricultural Fairness Evaluation

  Zenodo (CERN European Organization for Nuclear Research) 2026 · 0 citations