Data-driven multiscale modelling and analysis of COVID-19 spatiotemporal evolution using explainable AI

Innovative applications of artificial intelligence during the COVID-19 pandemic

The COVID-19 pandemic has created unprecedented challenges worldwide. Artificial intelligence (AI) technologies hold tremendous potential for tackling key aspects of pandemic management and response. In the present review, we discuss the tremendous possibilities of AI technology in addressing the global challenges posed by the COVID-19 pandemic. First, we outline the multiple impacts of the current pandemic on public health, the economy, and society. Next, we focus on the innovative applications of advanced AI technologies in key areas such as COVID-19 prediction, detection, control, and drug discovery for treatment. Specifically, AI-based predictive analytics models can use clinical, epidemiological, and omics data to forecast disease spread and patient outcomes. Additionally, deep neural networks enable rapid diagnosis through medical imaging. Intelligent systems can support risk assessment, decision-making, and social sensing, thereby improving epidemic control and public health policies. Furthermore, high-throughput virtual screening enables AI to accelerate the identification of therapeutic drug candidates and opportunities for drug repurposing. Finally, we discuss future research directions for AI technology in combating COVID-19, emphasizing the importance of interdisciplinary collaboration. Though promising, barriers related to model generalization, data quality, infrastructure readiness, and ethical risks must be addressed to fully translate these innovations into real-world impacts. Multidisciplinary collaboration engaging diverse expertise and stakeholders is imperative for developing robust, responsible, and human-centered AI solutions against COVID-19 and future public health emergencies.

Effectiveness of testing, contact tracing and isolation interventions among the general population on reducing transmission of SARS-CoV-2: a systematic review

We conducted a systematic literature review of general population testing, contact tracing, case isolation and contact quarantine interventions to assess their effectiveness in reducing SARS-CoV-2 transmission, as implemented in real-world settings. We designed a broad search strategy and aimed to identify peer-reviewed studies of any design provided there was a quantitative measure of effectiveness on a transmission outcome. Studies that assessed the effect of testing or diagnosis on disease outcomes via treatment, but did not assess a transmission outcome, were not included. We focused on interventions implemented among the general population rather than in specific settings; these were from anywhere in the world and published any time after 1 January 2020 until the end of 2022. From 26 720 titles and abstracts, 1181 were reviewed as full text, and 25 met our inclusion criteria. These 25 studies included one randomized control trial (RCT) and the remaining 24 analysed empirical data and made some attempt to control for confounding. Studies included were categorized by the type of intervention: contact tracing (seven studies); specific testing strategies (12 studies); strategies for isolating cases/contacts (four studies); and 'test, trace, isolate' (TTI) as a part of a package of interventions (two studies). None of the 25 studies were rated at low risk of bias and many were rated as serious risk of bias, particularly due to the likely presence of uncontrolled confounding factors, which was a major challenge in assessing the independent effects of TTI in observational studies. These confounding factors are to be expected from observational studies during an on-going pandemic, when the emphasis was on reducing the epidemic burden rather than trial design. Findings from these 25 studies suggested an important public health role for testing followed by isolation, especially where mass and serial testing was used to reduce transmission. Some of the most compelling analyses came from examining fine-grained within-country data on contact tracing; while broader studies which compared behaviour between countries also often found TTI led to reduced transmission and mortality, this was not universal. There was limited evidence for the benefit of isolation of cases/contacts away from the home environment. One study, an RCT, showed that daily testing of contacts could be a viable strategy to replace lengthy quarantine of contacts. Based on the scarcity of robust empirical evidence, we were not able to draw any firm quantitative conclusions about the quantitative impact of TTI interventions in different epidemic contexts. While the majority of studies found that testing, tracing and isolation reduced transmission, evidence for the scale of this impact is only available for specific scenarios and hence is not necessarily generalizable. Our review therefore emphasizes the need to conduct robust experimental studies that help inform the likely quantitative impact of different TTI interventions on transmission and their optimal design. Work is needed to support such studies in the context of future emerging epidemics, along with assessments of the cost-effectiveness of TTI interventions, which was beyond the scope of this review but will be critical to decision-making. This article is part of the theme issue 'The effectiveness of non-pharmaceutical interventions on the COVID-19 pandemic: the evidence'.