AI-driven techniques for detection and mitigation of SARS-CoV-2 spread: a review, taxonomy, and trends
Abstract
The SARS-CoV-2 RNA virus, with its rapid spread and frequent genetic changes, has posed unparalleled obstacles for public health and treatment efforts. Early diagnosis of the disease and the development of effective treatment strategies are the main pillars of epidemic control. In this regard, machine learning (ML) methods, an advanced subset of artificial intelligence (AI), can play an effective role in improving the accuracy of diagnosis and the effectiveness of treatments related to SARS-CoV-2. However, the implementation of ML in clinical settings faces issues such as data heterogeneity, lack of training data, model interpretability challenges, patient privacy protection, and implementation limitations. This article provides a systematic review of the applications of federated learning (FL), deep learning (DL), reinforcement learning (RL), and hybrid approaches in the field of SARS-CoV-2 diagnosis and treatment. Based on the analysis of the results, the main focus of the research was on increasing privacy and security (P&S) with a share of 26%, improving detection accuracy and robustness (DAR) with 24%, and improving computational and communication efficiency (CCE) with 20%. These statistics indicate the importance of prioritizing patient information confidentiality and improving systems' accuracy and stability against data variability. In conclusion, the findings of this review can pave the way for the practical application of ML technologies in clinical decision-making…
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.