Interpretability Bounds for Federated Clinical Text Classifiers Under Differential Privacy Noise Injection: A Computer Privacy-Utility Evaluation

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 allows clinical text classifiers to be trained across hospitals without centralising patient records, and differential privacy (DP) noise injection is the standard mechanism for bounding what any single record can reveal. Both techniques, however, degrade the internal representations on which post hoc interpretability methods depend, and the resulting loss of explanation fidelity has not been characterised as a formal quantity. The framework is evaluated through a replication-based design study of the before-after-control-impact estimator under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.640), with power estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 56 clusters are required for 80% power at a 5 percentage point effect, and that the interpretability bound tightens superlinearly as the privacy budget falls below unity. The contribution is a computable bound that lets clinical deployers reason about explanation reliability before committing to a privacy budget, rather than discovering attribution collapse after deployment.

• Auditing Explanation Faithfulness in Privacy-Preserving Federated Intrusion Detection

  Preprints.org 2026 · 0 citations

• Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning

  arXiv (Cornell University) 2026 · 0 citations

• Federated Inference for Computer Agriculture Pest-Risk Prediction Under Cross-Farm Non-IID Data: An Artificial Intelligence Differential-Privacy Utility Bound

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

• Interpretability Audits of Federated Clinical Text Classifiers Under Differential Privacy Budget Depletion: A Computer Fairness Estimation

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

• Artificial Intelligence Governance of Differential Privacy Budget Allocation in Federated Clinical Learning Under Unmeasured Health Ministry Disclosure Audit Frequency: A Healthcare Privacy-Political Bargaining Evaluation

  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

• Interpretability Guarantees for Federated Clinical Prediction Models Under Heterogeneous Label Noise: A Computer Privacy-Robustness Trade-off Estimation