COVID-19 focused series: diagnosis and forecast of COVID-19

How to successfully manage the globally coronavirus disease 2019 (COVID-19) pandemic which encompasses prevention and control of the disease as well as patient treatment, has always been a grand challenge since the beginning of the pandemic. Non-drug preventative and control measures have been proven to be crucial (1) in limiting the spreading of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus. As more effective medicines and vaccines are developed and put into use, the incidence and fatality rates of critically ill patients have declined greatly.

Nevertheless, the SARS-CoV-2 virus has kept evolving into multiple variants, which are not only highly transmissible but also can escape the immune surveillance of people. Hence, it is imperative to reliably predict and accurately identify new SARS-CoV-2 variants and their transmission pattern. Precise forecast of epidemic trends can facilitate rational decision-making by authority, leading to reduced number of illnesses and fatalities (2). Furthermore, prompt and accurate diagnosis of SARS-CoV-2 virus infection can provide medical/pharmaceutical researchers with reliable data, which can be applied to develop more appropriate therapeutics (3).

Predictive modeling and diagnosis can influence one another in the COVID-19 epidemic. Accurate diagnosis generates a significant amount of training data for prediction models, while reliable predictions provide references for diagnosis. Only when both measures generate reliable results and corroborate each other in practice can the number of infections be drastically decreased and a significant number of fatalities prevented.

Currently, COVID-19 is diagnosed by molecular detection of SARS-CoV-2, together with clinical symptoms and lung computed tomography (CT) scans. Common SARS-COV-2 detection methods can be divided into two main categories: (I) nucleic acid test, including real-time reverse transcription polymerase chain reaction (RT-PCR), gene sequencing, etc. (4-6); (II) antigen detection. The primary objective of antigen detection is to identify the nucleocapsid protein (N) and spike (S) protein of SARS-CoV-2 virus in a person’s sample in the early stage of infection. Because of its ease of use, antigen detection is used in Point-of-Care testing and for large-scale epidemic screening (7). RT-PCR is regarded as the gold standard for identifying SARS-CoV-2 infection. As the epidemic spreads rapidly and affects a wide range of areas, the heavy workload of molecular detection calls for more rapid and integrated approaches for nucleic acid testing, as well as multi-variants detection at the same time. Large-scale mobile screening devices have also been developed to identify infection cases as fast as possible (8). During the current COVID-19 pandemic, there has been growing interest in using reverse-transcription loop-mediated isothermal amplification (RT-LAMP) and clustered regularly interspaced short palindromic repeats (CRISPR)-based diagnostic techniques to develop rapid and accurate assays for detecting SARS-CoV-2. In addition to these detection methods, artificial intelligence (AI)-assisted diagnosis based on lung CT scan images is also actively under development (9).

For successful model building, data accuracy is most crucial in epidemic prediction; thus, the premise of predictive modelling is the reliability of diagnostic results. Globally, multiple modelling approaches have been developed by many research teams, such as statistical models, classic transmission dynamics models, training-based AI or machine learning methods to predict and analyze the epidemic trend, which are utilized to evaluate the effectiveness of governments’ prevention and control measures and to assist in decision-making of public health policies (10-14).

To finally end the COVID-19 pandemic, however, there are many problems ahead of us to be resolved, for example, (I) how to rapidly translate novel diagnostic products and technologies developed in a laboratory into clinical applications; (II) how to exploit the application of different diagnostic products in various scenarios; (III) how to improve the accuracy and timeliness of epidemic forecasting; (IV) how to effectively communicate epidemic prediction results to medical professionals and public health officers.

This focused series is primarily intended to keep professionals in related fields up-to-date on the most recent diagnostic technologies and prediction methodologies, as well as to provide a solid communication platform for studying the technologies and applications.

Acknowledgments

Funding: None.

Footnote

Provenance and Peer Review: This article was commissioned by the editorial office, Journal of Thoracic Disease for the series “Current Status of Diagnosis and Forecast of COVID-19”. The article did not undergo external peer review.

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://jtd.amegroups.com/article/view/10.21037/jtd-23-141/coif). The series “Current Status of Diagnosis and Forecast of COVID-19” was commissioned by the editorial office without any funding or sponsorship. JC, TX, ZY and WG served as the unpaid Guest Editors of the series. The authors have no other conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Chu DK, Akl EA, Duda S, et al. Physical distancing, face masks, and eye protection to prevent person-to-person transmission of SARS-CoV-2 and COVID-19: a systematic review and meta-analysis. Lancet 2020;395:1973-87. [Crossref] [PubMed]
2. Yang Z, Zeng Z, Wang K, et al. Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions. J Thorac Dis 2020;12:165-74. [Crossref] [PubMed]
3. Surkova E, Nikolayevskyy V, Drobniewski F. False-positive COVID-19 results: hidden problems and costs. Lancet Respir Med 2020;8:1167-8. [Crossref] [PubMed]
4. Wang H, Miller JA, Verghese M, et al. Multiplex SARS-CoV-2 Genotyping Reverse Transcriptase PCR for Population-Level Variant Screening and Epidemiologic Surveillance. J Clin Microbiol 2021;59:e0085921. [Crossref] [PubMed]
5. Dao Thi VL, Herbst K, Boerner K, et al. A colorimetric RT-LAMP assay and LAMP-sequencing for detecting SARS-CoV-2 RNA in clinical samples. Sci Transl Med 2020;12:eabc7075. [Crossref] [PubMed]
6. Liang Y, Lin H, Zou L, et al. Rapid detection and tracking of Omicron variant of SARS-CoV-2 using CRISPR-Cas12a-based assay. Biosens Bioelectron 2022;205:114098. [Crossref] [PubMed]
7. Zhang X, Meng H, Liu H, et al. Advances in laboratory detection methods and technology application of SARS-CoV-2. J Med Virol 2022;94:1357-65. [Crossref] [PubMed]
8. Luo L, Yang Z, Liang J, et al. Crucial control measures to contain China’s first Delta variant outbreak. Natl Sci Rev 2022;9:nwac004. [Crossref] [PubMed]
9. Liang H, Guo Y, Chen X, et al. Artificial intelligence for stepwise diagnosis and monitoring of COVID-19. Eur Radiol 2022;32:2235-45. [Crossref] [PubMed]
10. Abbasimehr H, Paki R, Bahrini A. A novel approach based on combining deep learning models with statistical methods for COVID-19 time series forecasting. Neural Comput Appl 2022;34:3135-49. [Crossref] [PubMed]
11. Alassafi MO, Jarrah M, Alotaibi R. Time series predicting of COVID-19 based on deep learning. Neurocomputing 2022;468:335-44. [Crossref] [PubMed]
12. Chandra R, Jain A, Singh Chauhan D. Deep learning via LSTM models for COVID-19 infection forecasting in India. PLoS One 2022;17:e0262708. [Crossref] [PubMed]
13. Cinaglia P, Cannataro M. Forecasting COVID-19 Epidemic Trends by Combining a Neural Network with R(t) Estimation. Entropy (Basel) 2022;24:929. [Crossref] [PubMed]
14. Cooper I, Mondal A, Antonopoulos CG. A SIR model assumption for the spread of COVID-19 in different communities. Chaos Solitons Fractals 2020;139:110057. [Crossref] [PubMed]