Next Generation Infectious Diseases Monitoring Gages via Incremental Federated Learning: Current Trends and Future...

Area of Science:

• Public Health
• Infectious Diseases
• Machine Learning

Background:

• Infectious diseases pose a significant threat to human survival and public health.
• The early and accurate diagnosis of novel infectious diseases like coronavirus is a critical demand for modern healthcare systems.
• Machine learning (ML) and deep learning (DL) offer promising avenues for robust disease recognition.

Purpose of the Study:

• To systematically review and identify machine learning techniques for the robust recognition of general infectious diseases.
• To address research questions (RQs) related to the accurate detection of infectious diseases.
• To propose a framework for sharing the disease detection process using ML models.

Main Methods:

• A systematic literature review was conducted following Kitchenham guidelines.
• Research articles were extracted from four electronic databases (IEEE, ACM, Springer, ScienceDirect) between 2018 and 2021.
• 21 studies were filtered and mapped to defined research questions, analyzing various ML, DL, and federated learning models.

Main Results:

• Various machine learning techniques, including deep learning and federated learning, have been employed for accurate infectious disease recognition.
• The reviewed studies demonstrate the potential of ML models in enhancing the early detection of infectious diseases.
• A framework for sharing the disease detection process using ML models was introduced.

Conclusions:

• Machine learning models show significant promise for the early and accurate diagnosis of infectious diseases.
• Future advancements may involve wearable health monitoring devices for real-time disease detection, reducing mortality rates.
• Continued research in ML for infectious disease detection is essential for public health preparedness.