Gauging the Impact of Artificial Intelligence and Mathematical Modeling in Response to the COVID-19 Pandemic: A Systematic Review

Abstract

While the world continues to grapple with the devastating effects of the SARS-nCoV-2 virus, different scientific groups, including researchers from different parts of the world, are trying to collaborate to discover solutions to prevent the spread of the COVID-19 virus permanently. Henceforth, the current study envisions the analysis of predictive models that employ machine learning techniques and mathematical modeling to mitigate the spread of COVID-19. A systematic literature review (SLR) has been conducted, wherein a search into different databases, viz., PubMed and IEEE Explore, fetched 1178 records initially. From an initial of 1178 records, only 50 articles were analyzed completely. Around (64%) of the studies employed data-driven mathematical models, whereas only (26%) used machine learning models. Hybrid and ARIMA models constituted about (5%) and (3%) of the selected articles. Various Quality Evaluation Metrics (QEM), including accuracy, precision, specificity, sensitivity, Brier-score, F1-score, RMSE, AUC, and prediction and validation cohort, were used to gauge the effectiveness of the studied models. The study also considered the impact of Pfizer-BioNTech (BNT162b2), AstraZeneca (ChAd0x1), and Moderna (mRNA-1273) on Beta (B.1.1.7) and Delta (B.1.617.2) viral variants and the impact of administering booster doses given the evolution of viral variants of the virus.

Clinical decision support systems (CDSS) in assistance to COVID‐19 diagnosis: A scoping review on types and evaluation methods

“…The most common ML methods in the reviewed studies were CNN 34–85 . In line with this result, other review studies also indicated CNN to be the most common method to develop a system for COVID‐19 diagnosis 23,25,27,28,30,100 . A CNN is a type of DL algorithm used for processing medical images, particularly for identifying specific features in chest radiographs of COVID‐19 patients 30 .…”

“…In line with this result, other review studies also indicated CNN to be the most common method to develop a system for COVID-19 diagnosis. 23,25,27,28,30,100 A CNN is a type of DL algorithm used for processing medical images, particularly for identifying specific features in chest radiographs of COVID-19 patients. 30 CNN is more valuable than other methods for developing CDSS due to its excellent performance accuracy and much lower preprocessing.…”

A sytematic study of covid-19 prediction models of India

“…In [22], the proposed iCovidCare model increases the prediction ratio by 89% and with the training and testing accuracy of 95.13% and 91.68%. In [23], using Capnobase and sEMG datasets with Bi-LSTM + Attn gives the best results, and using MIMIC II dataset with 2-Layer LSTM gives the best results over CNN-LSTM. Also found that the 64s window showed more accurate results than the 32s window, and the trend showed that performance increased as the size of the window increased.…”

“…These questions were framed by considering the demands of research questions. The quality assessment questions framework has already been used in several earlier SLRs (Hassan et al, 2022, Haafza et al, 2021, Saleem et al, 2022. In this SLR, we have considered six questions that demand objectivity: the topic's context, data sources, limitations or gaps, discussion of future directions, and performance evaluation criteria used in the selected studies.…”

Antigenicity of genomic epidemiology concerning viral evolution and vaccine efficacy for SARS-COV-2- A review

“…Since the beginning of October 2021, the infection rate has surged tenfold. There has been an unexpected spike in infections and a likely spike in the proportion of hospital admissions and fatalities, having a detrimental effect on healthcare resources [30,31]. It is the nature of the viruses to mutate; henceforth emergence of new variants with time cannot be overlooked.…”