Rapid, accurate detection of coronavirus disease 2019 (COVID-19) has been essential for epidemic control. While reverse-transcription polymerase chain reaction (RT-PCR) remains the reference standard, constraints in turnaround time, access, and sensitivity under certain conditions have motivated the use of Artificial Intelligence (AI) to assist screening and diagnosis from complementary data sources: medical images (chest radiographs and computed tomography), respiratory audio (cough/voice/breath), wearable and consumer-device signals, and clinical/electronic health record (EHR) data. This review synthesizes key datasets, model families, validation strategies, and performance trends, and highlights persistent pitfalls including dataset bias, information leakage, lack of external validation, and explainability gaps. We conclude with a roadmap for robust, clinically useful AI systems: rigorous study design, standardized reporting, multicenter external testing, prospective evaluation, human factors integration, and governance for safety, privacy, and equity.
1. Bai, H. X., et al. “Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia on Chest CT.” Radiology, vol. 296, no. 3, 2020, pp. E156–65. 10.1148/radiol.2020201491.
2. Brown, C., J. Chauhan, A. Grammenos, et al. “Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data.” IEEE Trans Audio Speech Lang Process., vol. 29, 2021, pp. 2010–23. 10.48550/arXiv.2006.05919
3. Cohen, J. P., P. Morrison, and L. Dao. “COVID-19 Image Data Collection.” arXiv, 2020, arXiv:2003.11597.
4. de la Iglesia Vayá, M., et al. “BIMCV COVID-19+: A Large Annotated Dataset of Chest Radiograph Images and Clinical Data.” medRxiv, 2020. 10.48550/arXiv.2006.01174
5. de Souza, J., et al. “Lung Ultrasound in COVID-19: Insights and Prospects for AI.” Ultrasound in Medicine and Biology, vol. 47, no. 6, 2021, pp. 1465–80.
6. Harmon, S. A., et al. “Artificial Intelligence for the Detection of COVID-19 Pneumonia on Chest CT Using Multinational Datasets.” Nat Commun, vol. 11, 2020, p. 4080. doi:10.1038/s41467-020-17971-2.
7. He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. “Deep Residual Learning for Image Recognition.”, 2016. 10.1109/CVPR.2016.90
8. Laguarta, Jordi, Ferran Hueto, and Brian Subirana. “COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings.” IEEE Open Journal of Engineering in Medicine and Biology, vol. 1, 2020, pp. 275–81. 10.1109/OJEMB.2020.3026928
9. Li, L., et al. “Artificial Intelligence Distinguishes COVID-19 from Community-Acquired Pneumonia on Chest CT.” Radiology, vol. 296, no. 2, 2020, pp. E65–71. 10.1148/radiol.2020200905.
10. Lundberg, Scott M., and Su-In Lee. “A Unified Approach to Interpreting Model Predictions.” Advances in Neural Information Processing Systems (NeurIPS), 2017. https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf
11. Mishra, T., et al. “Pre-Symptomatic Detection of COVID-19 from Smartwatch Data.” Nature Biomedical Engineering, vol. 4, 2020, pp. 1208–10. 10.1038/s41551-020-00640-6
12. Morozov, S. P., et al. “MosMedData: Chest CT Scans with COVID-19 Related Findings Dataset.” medRxiv, 2020. 10.1101/2020.05.20.20100362
13. Ozturk, T., et al. “Automated Detection of COVID-19 Cases Using Deep Neural Networks with X-Ray Images.” Computers in Biology and Medicine, vol. 121, 2020, p. 103792. 10.1016/j.compbiomed.2020.103792
14. Orlandic, L., T. Teijeiro, and D. Atienza. “The COUGHVID Crowdsourcing Dataset.” Scientific Data, vol. 8, 2021, p. 156. 10.1038/s41597-021-00937-4
15. Quer, G., et al. “Wearable Sensor Data and Self-Reported Symptoms for COVID-19 Detection.” Nature Medicine, vol. 27, 2021, pp. 73–77. 10.1038/s41591-020-1123-x
16. Radin, J. M., et al. “Harnessing Wearable Device Data to Improve COVID-19 Detection.” Scientific Reports, vol. 10, 2020, p. 13773.
17. Rajpurkar, P., et al. “CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning.” arXiv, 2017, arXiv:1711.05225.
18. Roberts, M., et al. “Common Pitfalls and Recommendations for Using ML to Detect and Prognosticate for COVID-19 Using Chest Radiographs and CT Scans.” Nature Machine Intelligence, vol. 3, 2021, pp. 199–217. 10.1038/s42256-021-00307-0
19. RSNA/ACR. RICORD – The RSNA International COVID-19 Open Radiology Database, 2021. 10.1148/radiol.2021203957
20. Selvaraju, R. R., et al. “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization.” Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. 10.1109/ICCV.2017.74
21. Shorten, C., and T. M. Khoshgoftaar. “A Survey on Image Data Augmentation for Deep Learning.” Journal of Big Data, vol. 6, 2019, p. 60. 10.1186/s40537-019-0197-0
22. UK Biobank. COVID-19 Imaging Data. (Consortium Resources).
23. Wang, L., Z. Q. Lin, and A. Wong. “COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images.” arXiv, 2020, arXiv:2003.09871.
24. Wynants, L., et al. “Prediction Models for Diagnosis and Prognosis of COVID-19: Systematic Review and Critical Appraisal.” BMJ, vol. 369, 2020, m1328. 10.1136/bmj.m1328
25. Yan, L., et al. “An Interpretable Mortality Prediction Model for COVID-19 Patients.” Nature Machine Intelligence, vol. 2, 2020, pp. 283–88. 10.1038/s42256-020-0180-7
