Advancing Public Health Surveillance With Artificial Intelligence: A Systematic Review of Real‐Time Data Analytics and Disease Prediction
Bibliographic record
Abstract
Background The integration of artificial intelligence (AI) into public health surveillance is revolutionizing how health threats are monitored, predicted, and managed. Traditional surveillance systems often face challenges such as reporting delays, limited scalability, and inefficiencies in real‐time response. Leveraging approaches such as machine learning (ML), deep learning (DL), and natural language processing (NLP), AI enables the analysis of extensive and diverse datasets, facilitating the generation of timely and actionable insights for disease prevention and control. Aim This review aimed to systematically explore how AI is utilized to enhance public health surveillance through real‐time data analytics and disease prediction. Methods An extensive literature search was performed using five major databases: PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar to identify relevant studies published between 2010 and 2025. Eligible studies applied AI methodologies to real‐time surveillance, utilized structured or unstructured health‐related data, and reported predictive or prescriptive outcomes. All the studies included were evaluated for methodological rigor, and the results were thematically synthesized. Results Thirty‐nine studies met the inclusion criteria. The majority employed ML and DL models such as Random Forests (RFs), while others incorporated NLP for analyzing text‐based data. AI systems were utilized for descriptive monitoring, predictive modeling of disease outbreaks, and prescriptive analytics to support resource allocation. Real‐time analytics demonstrated high accuracy and timeliness in forecasting disease trends, particularly for conditions such as COVID‐19, influenza, and dengue. Hybrid models that combined multiple AI techniques further enhanced predictive performance. Conclusion AI–driven surveillance systems hold considerable promise for transforming public health monitoring. They enable faster detection, improved forecasting, and more efficient public health responses. However, challenges remain, including data standardization, ethical governance, and infrastructure disparities. Addressing these barriers is essential for equitable, scalable AI implementation in global health surveillance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".