Prediction to Policy decision: The evolving role of artificial intelligence in public health
- 1Department of Community Medicine, Kasturba Medical College Mangalore, Manipal Academy of Higher Education, Manipal, India
- 2Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India; Corresponding author.
Abstract
Problem considered: Artificial intelligence (AI) is increasingly shaping public health through its ability to analyze complex datasets for surveillance, prediction, and decision making. Advances in machine learning, deep learning, and natural language processing have assisted AI in disease monitoring, diagnostics, and health system management. But concerns regarding data governance, ethics, and equity remain. This narrative review was aimed to integrate current evidence of AI in public health, technological approaches, programmatic experiences, and challenges. Methods: A narrative literature review was conducted using a structured search using electronic databases including PubMed, Scopus, and Google Scholar for relevant articles. Policy documents from international and national organizations like the WHO, Centers for Disease Control and Prevention, and the ICMR were also reviewed. Peer-reviewed articles, narrative reviews, ethical guidelines were identified, screened and were included. Results: Applications of AI were identified across several public health domains. Digital epidemiology tools have shown potential for early outbreak detection. AI models have improved diagnostic performance in many fields like TB and cancer screening. Digital health platforms in India illustrate the growing use of digital infrastructure and data driven approaches in public health programme, while selected AI-supported applications are emerging in specific areas. Challenges related to data quality, transparency, privacy, and workforce capacity remain barriers to large scale implementation. Conclusion: AI has the potential to strengthen public health systems by improving surveillance, diagnostics, and decision-making. Responsible integration requires strong data governance, ethical oversight, interdisciplinary collaboration, and investment in digital infrastructure to ensure equitable and sustainable public health impact.
Related
- Artificial Intelligence in Eye Disease: A Systematic Review of Screening, Diagnosis, Prognosis, Treatment-Response Prediction, and Clinical Decision Support
- Maternal–Fetal Oncology Intelligence: Self-Evolving Foundation Models and Digital Twin Ecosystems for Precision Cancer Prediction, Treatment Optimization, and Maternal–Fetal Outcome Forecasting
- Human–artificial intelligence collaboration in emergency medical services: from diagnostic algorithms to shared decision support
- Reliable Detection, Unreliable Clinical Decision-making: Artificial Intelligence Models in Burn Assessment
- An assisted telemedicine model with digital diagnostics and artificial intelligence-supported clinical decision in hard-to-reach rural communities: a community-based mixed-methods study from Rajasthan, India
BibTeX
@article{sreedevi2026prediction,
title = {{Prediction to Policy decision: The evolving role of artificial intelligence in public health}},
author = {S.R. Sreedevi and D.N. Sindhura and Ramesh Holla and Mithun Rao and Ajay Mallya and Bhaskaran Unnikrishnan},
journal = {Clinical Epidemiology and Global Health},
year = {2026},
month = oct,
doi = {10.1016/j.cegh.2026.102514},
url = {https://doi.org/10.1016/j.cegh.2026.102514},
note = {CC BY},
}
RIS
TY - JOUR
TI - Prediction to Policy decision: The evolving role of artificial intelligence in public health
AU - S.R. Sreedevi
AU - D.N. Sindhura
AU - Ramesh Holla
AU - Mithun Rao
AU - Ajay Mallya
AU - Bhaskaran Unnikrishnan
PY - 2026
DA - 2026/10/30
JO - Clinical Epidemiology and Global Health
DO - 10.1016/j.cegh.2026.102514
UR - https://doi.org/10.1016/j.cegh.2026.102514
AB - Problem considered: Artificial intelligence (AI) is increasingly shaping public health through its ability to analyze complex datasets for surveillance, prediction, and decision making. Advances in machine learning, deep learning, and natural language processing have assisted AI in disease monitoring, diagnostics, and health system management. But concerns regarding data governance, ethics, and equity remain. This narrative review was aimed to integrate current evidence of AI in public health, technological approaches, programmatic experiences, and challenges. Methods: A narrative literature review was conducted using a structured search using electronic databases including PubMed, Scopus, and Google Scholar for relevant articles. Policy documents from international and national organizations like the WHO, Centers for Disease Control and Prevention, and the ICMR were also reviewed. Peer-reviewed articles, narrative reviews, ethical guidelines were identified, screened and were included. Results: Applications of AI were identified across several public health domains. Digital epidemiology tools have shown potential for early outbreak detection. AI models have improved diagnostic performance in many fields like TB and cancer screening. Digital health platforms in India illustrate the growing use of digital infrastructure and data driven approaches in public health programme, while selected AI-supported applications are emerging in specific areas. Challenges related to data quality, transparency, privacy, and workforce capacity remain barriers to large scale implementation. Conclusion: AI has the potential to strengthen public health systems by improving surveillance, diagnostics, and decision-making. Responsible integration requires strong data governance, ethical oversight, interdisciplinary collaboration, and investment in digital infrastructure to ensure equitable and sustainable public health impact.
SN - 2213-3984
SN - 2452-0918
ER -