Artificial intelligence in early warning systems for infectious disease surveillance: a systematic review
Abstract
Introduction: Infectious diseases pose a significant global health threat, exacerbated by factors like globalization and climate change. Artificial intelligence (AI) offers promising tools to enhance crucial early warning systems (EWS) for disease surveillance. This systematic review evaluates the current landscape of AI applications in EWS, identifying key techniques, data sources, benefits, and challenges.
Methods: Following PRISMA guidelines, a systematic search of Semantic Scholar (2018-onward) was conducted. After screening 600 records and removing duplicates and non-relevant articles, the search yielded 67 relevant studies for review.
Results: Key findings reveal the prevalent use of machine learning (ML), deep learning (DL), and natural language processing (NLP), which often integrate diverse data sources (e.g., epidemiological, web, climate, wastewater). The major benefits identified include earlier outbreak detection and improved prediction accuracy. However, significant challenges persist regarding data quality and bias, model transparency (the "black box" issue), system integration difficulties, and ethical considerations such as privacy and equity.
Discussion: AI demonstrates considerable potential to strengthen infectious disease EWS. Realizing this potential, however, requires concerted efforts to address data limitations, enhance model explainability, ensure ethical implementation, improve infrastructure, and foster collaboration between AI developers and…
How strong is the evidence?
Evidence Hub reads this as a systematic review, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.