Evaluating the Impact of Machine Learning and Ethical AI Training on Public Health Workforce Competency and Epidemiological Decision-Making in Municipal Health Departments

• Abilly Elly

  Texas University

  Author

The integration of artificial intelligence (AI) into public health practice presents transformative opportunities for epidemiological surveillance and decision-making, yet municipal health departments face critical gaps in workforce AI competency and ethical implementation frameworks. This mixed-methods research examines the impact of a structured Machine Learning and Ethical AI Training program on workforce competency and epidemiological decision-making across 12 municipal health departments in the United States. The study employed a pre-post intervention design with 240 public health professionals, combining competency assessments, predictive model performance evaluation, and qualitative interviews with department leaders. The Random Forest model for disease outbreak prediction achieved an accuracy of 89.4% (AUC = 0.91) when deployed by trained personnel, compared to 76.2% (AUC = 0.79) when utilized by untrained staff, representing a statistically significant improvement (p < 0.01). Training intervention significantly enhanced AI literacy across technical, ethical, and applied domains (p < 0.001), with the strongest gains observed in algorithmic bias detection and mitigation competencies. This study contributes a validated competency framework and replicable training model for municipal health departments. Findings indicate that ethical AI training must be integrated alongside technical skill development to achieve the full potential of machine learning tools in public health practice. The research provides actionable recommendations for workforce development, policy formulation, and AI implementation strategies at the local health department level.

• PDF

Copyright (c) 2026 Abilly Elly (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.