Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Artificial Intelligence for Infectious Disease Prediction and Prevention: A Comprehensive Review

Selestine Melchane, Youssef Elmir, Farid Kacimi, Larbi Boubchir

TL;DR

This review maps AI-driven approaches for infectious disease prediction and prevention across three data-driven objectives: using Public Health Data to forecast regional spread, using Patients' Medical Data to detect infection, and combining both data streams to estimate population-level dynamics. It catalogs a spectrum of methods—Naive Bayes, clustering, LSTM, Transformer, SSL, CNN, and Transformer-based models—applied to numerical time-series, textual, image, and clinical data, highlighting performance trends and data-specific challenges. Key contributions include identifying when specific data types (e.g., geospatial images or routine blood tests) yield strongest signals, and illustrating how hybrid models (e.g., T-SIRGAN, TEMPO, MOAU) improve long-range forecasting and mutation prediction. The paper emphasizes practical implications, such as the need for real-time data fusion, privacy-preserving analyses, and careful handling of data biases to realize AI’s potential in outbreak forecasting and control.

Abstract

Artificial Intelligence (AI) and infectious diseases prediction have recently experienced a common development and advancement. Machine learning (ML) apparition, along with deep learning (DL) emergence, extended many approaches against diseases apparition and their spread. And despite their outstanding results in predicting infectious diseases, conflicts appeared regarding the types of data used and how they can be studied, analyzed, and exploited using various emerging methods. This has led to some ongoing discussions in the field. This research aims not only to provide an overview of what has been accomplished, but also to highlight the difficulties related to the types of data used, and the learning methods applied for each research objective. It categorizes these contributions into three areas: predictions using Public Health Data to prevent the spread of a transmissible disease within a region; predictions using Patients' Medical Data to detect whether a person is infected by a transmissible disease; and predictions using both Public and patient medical data to estimate the extent of disease spread in a population. The paper also critically assesses the potential of AI and outlines its limitations in infectious disease management.

Artificial Intelligence for Infectious Disease Prediction and Prevention: A Comprehensive Review

TL;DR

This review maps AI-driven approaches for infectious disease prediction and prevention across three data-driven objectives: using Public Health Data to forecast regional spread, using Patients' Medical Data to detect infection, and combining both data streams to estimate population-level dynamics. It catalogs a spectrum of methods—Naive Bayes, clustering, LSTM, Transformer, SSL, CNN, and Transformer-based models—applied to numerical time-series, textual, image, and clinical data, highlighting performance trends and data-specific challenges. Key contributions include identifying when specific data types (e.g., geospatial images or routine blood tests) yield strongest signals, and illustrating how hybrid models (e.g., T-SIRGAN, TEMPO, MOAU) improve long-range forecasting and mutation prediction. The paper emphasizes practical implications, such as the need for real-time data fusion, privacy-preserving analyses, and careful handling of data biases to realize AI’s potential in outbreak forecasting and control.

Abstract

Artificial Intelligence (AI) and infectious diseases prediction have recently experienced a common development and advancement. Machine learning (ML) apparition, along with deep learning (DL) emergence, extended many approaches against diseases apparition and their spread. And despite their outstanding results in predicting infectious diseases, conflicts appeared regarding the types of data used and how they can be studied, analyzed, and exploited using various emerging methods. This has led to some ongoing discussions in the field. This research aims not only to provide an overview of what has been accomplished, but also to highlight the difficulties related to the types of data used, and the learning methods applied for each research objective. It categorizes these contributions into three areas: predictions using Public Health Data to prevent the spread of a transmissible disease within a region; predictions using Patients' Medical Data to detect whether a person is infected by a transmissible disease; and predictions using both Public and patient medical data to estimate the extent of disease spread in a population. The paper also critically assesses the potential of AI and outlines its limitations in infectious disease management.

Paper Structure

This paper contains 33 sections, 5 figures, 13 tables.

Table of Contents

  1. Introduction
  2. Research methodology
  3. Background
  4. Prediction Based on Public Health Data
  5. Numerical Data : Time-series Epidemiological and locational Data
  6. Naive Bayes algorithms.
  7. Clustering Algorithms.
  8. Long short-term memory based models.
  9. Transformer Based Models.
  10. Textual Data : Social and News Data
  11. Matrix factorization.
  12. Semi-supervised learning based models.
  13. Support vector machine models.
  14. Deep neural network based models.
  15. Image Data : Geospatial Images
  16. ...and 18 more sections

Figures (5)

  • Figure 1: Research Methodology
  • Figure 2: Diagram summarizing the techniques employed for each selected and studied dataset in the field of infectious disease prediction
  • Figure 3: Situational Awareness screen showing asthma articles and Tweets in London from April 2014 thapen2016defender
  • Figure 4: CT images taken from COVID-19 CT Scan dataset. Typical examples showing a) Common pneumonia (CP), b) COVID-19 (NCP), and c) normal CT scan image sahoo2021potential
  • Figure 5: Sample chest X-rays taken from the COVID-19 Radiography dataset. a) Normal case, b) COVID-19 case showing bilateral ground-glass opacities with prominent peripheral, perihilar and basal distribution within a multilobar involvement, and c) viral pneumonia case with visible left basilar opacity sahoo2021potential