ABSTRACT
BACKGROUND: Tuberculosis, like COVID-19, is most often a pulmonary disease. The COVID-19 pandemic has severely disrupted tuberculosis services in myriad ways: health facility closures, lockdowns, travel bans, overwhelmed healthcare systems, restricted export of antituberculous drugs, etc. The effects of the shared risk on outcomes of the two diseases is not known, particularly for the first year of the pandemic, during the period before COVID-19 vaccines became widely available. OBJECTIVE: We embarked on a systematic review to elucidate the consequences of tuberculosis on COVID-19 outcomes and of COVID-19 on tuberculosis outcomes during the pre-vaccination period of the pandemic. METHODS: The systematic review protocol is registered in PROSPERO. We conducted an initial search of PubMed, Embase, Web of Science, WHO coronavirus database, medRxiv, bioRxiv, preprints.org, and Google Scholar using terms relating to COVID-19 and tuberculosis. We selected cohort and case-control studies for extraction and assessed quality with the Newcastle-Ottawa scale. RESULTS AND CONCLUSION: We identified 2108 unique abstracts published between December 2019 and January 2021. We extracted data from 18 studies from 8 countries. A total of 650,317 persons had a diagnosis of COVID-19, and 4179 had a diagnosis of current or prior tuberculosis. We explored links between tuberculosis and COVID-19 incidence, mortality, and other adverse outcomes. Nine studies reported on mortality and 13 on other adverse outcomes; results on the association between tuberculosis and COVID-19 mortality/adverse outcomes were heterogenous. Tuberculosis outcomes were not fully available in any studies, due to short follow-up (maximum of 3 months after COVID-19 diagnosis), so the effects of COVID-19 on tuberculosis outcomes could not be assessed. Much of the rapid influx of literature on tuberculosis and COVID-19 during this period was published on preprint servers, and therefore not peer-reviewed. It offered limited examination of the effect of tuberculosis on COVID-19 outcomes and even less on the effect of COVID-19 on tuberculosis treatment outcomes.
ABSTRACT
Artificial intelligence (AI) represents a valuable tool that could be widely used to inform clinical and public health decision-making to effectively manage the impacts of a pandemic. The objective of this scoping review was to identify the key use cases for involving AI for pandemic preparedness and response from the peer-reviewed, preprint, and grey literature. The data synthesis had two parts: an in-depth review of studies that leveraged machine learning (ML) techniques and a limited review of studies that applied traditional modeling approaches. ML applications from the in-depth review were categorized into use cases related to public health and clinical practice, and narratively synthesized. One hundred eighty-three articles met the inclusion criteria for the in-depth review. Six key use cases were identified: forecasting infectious disease dynamics and effects of interventions; surveillance and outbreak detection; real-time monitoring of adherence to public health recommendations; real-time detection of influenza-like illness; triage and timely diagnosis of infections; and prognosis of illness and response to treatment. Data sources and types of ML that were useful varied by use case. The search identified 1167 articles that reported on traditional modeling approaches, which highlighted additional areas where ML could be leveraged for improving the accuracy of estimations or projections. Important ML-based solutions have been developed in response to pandemics, and particularly for COVID-19 but few were optimized for practical application early in the pandemic. These findings can support policymakers, clinicians, and other stakeholders in prioritizing research and development to support operationalization of AI for future pandemics.