Multi-scenario evaluation of federated learning for privacy-preserving malaria prediction with Ghana DHS data

Improving malaria prediction in Ghana requires data from across its health system, yet Ghana’s Data Protection Act (Act 843) restricts inter-institutional data sharing, and many facilities decline to transfer patient records regardless of legal permission. Federated learning (FL) offers a solution: each site trains a local model and shares only weight updates, not raw patient data. Whether FL holds up under Ghana’s 10-fold regional prevalence difference had not been tested. Using a controlled simulation framework, we partitioned Ghana Demographic and Health Survey and Malaria Indicator Survey data (2016–2022, n = 10,287 children aged 6–59 months) into five regional clients and evaluated FedAvg and FedProx under three scenarios: uniform distribution (S1), real-world prevalence variation from 2.9% to 30.1% (S2), and heterogeneity combined with 5–20% missing data per client (S3). When data was uniformly distributed, FedAvg matched centralized logistic regression (AUC-PR 0.8852 vs. 0.8854; p = 0.057). The performance drop under 10-fold heterogeneity was only 2.21%, far below the 20–55% degradation seen in vision benchmarks. When regional heterogeneity compounded with missing data quality issues, FedProx outperformed FedAvg (AUC-PR 0.8725 vs. 0.8684; Cohen’s d = 1.257). Federated models retained 97.8–98.5% of centralized AUC-PR without sharing patient data. FL is a feasible privacy-preserving approach for malaria predictions in diverse sub-Saharan African health systems, and the selection of algorithms has a significant impact on the actual performance. These benchmarks are based on a full clinical symptom panel at point of care; with the DHS-native features alone, AUC-PR is 0.34–0.37, compared to 0.87–0.89 with the full feature set (S1 Text, sensitivity analysis). Prior to deployment, prospective validation with facility collected records is required. A critical fairness gap exists: Greater Accra’s 2.9% prevalence produced an approximately 50% false negative rate, meaning half of urban malaria cases would be missed. Prevalence-aware aggregation is required.Author summary: Malaria kills hundreds of thousands of children in Africa every year, but the data needed to create prediction models cannot be shared between hospitals and clinics because of privacy regulations. This paper used a federated learning method, which enables health facilities to collectively train a joint prediction model without ever transmitting patient records to a central point. Using survey data of children in Ghana, we discovered that our federated method was close to a model trained on the combined data even when the disease rates were 10-fold different in different regions. We also found that a modified algorithm worked better in an environment where the data are skewed, but required more communication rounds to converge. One notable outcome is that in low-prevalence urban areas like Accra, the model could not detect approximately 50 percent of actual malaria cases, meaning that existing algorithms require fairness-conscious correction before deployment. We show that precise, privacy-aware malaria prediction can be done in Africa using current survey data, and this provides an effective avenue through which health facilities can cooperate without compromising patient privacy.