Nutzung von künstlicher Intelligenz zur Bekämpfung der COVID-19-Pandemie

COVID-19 hat viele Gesundheitssysteme völlig unvorbereitet getroffen. Insbesondere in der Frühphase der Pandemie herrschte großer Druck, trotz fehlenden Wissens über die neue Erkrankung die Lage wieder in den Griff zu bekommen. In dieser Situation wollten Forscher weltweit mithelfen, die Pandemie durch Nutzung künstlicher Intelligenz zu bewältigen. Welche Ansätze man verfolgt hat und welche erfolgreich waren, stellt dieser Artikel dar.

Abstract

The COVID-19 pandemic is a global health emergency of historic dimension. In this situation, researchers worldwide wanted to help manage the pandemic by using artificial intelligence (AI). This narrative review aims to describe the usage of AI in the combat against COVID-19. The addressed aspects encompass AI algorithms for analysis of thoracic X-rays or CTs, prediction models for severity and outcome of the disease, AI applications in development of new drugs and vaccines as well as forecasting models for spread of the virus. The review shows, which approaches were pursued, and which were successful.

Kernaussagen

• Viele KI-Anwendungen zur Bekämpfung der Pandemie werden durch einen Mangel an Daten in ausreichender Menge und Qualität beeinträchtigt.

• KI-Algorithmen sind bereits jetzt in der Lage, COVID-19 in Röntgenbildern oder CTs mit 90%iger Genauigkeit zu erkennen.

• KI-Modelle können dabei helfen, Risikofaktoren für schwere Verläufe zu identifizieren und den Krankheitsverlauf präzise vorherzusagen, wenn ihre Datenbasis dazu ausreichend groß ist.

• Durch die Nutzung von KI-Modellen kann die Entwicklung neuer medikamentöser Wirkstoffe dramatisch beschleunigt werden.

• Die ersten Warnungen vor dem Ausbruch einer bisher nicht bekannten Lungenerkrankung in China stammten von 2 KI-basierten Systemen.

• Mithilfe KI-basierter Modelle kann die Entwicklung einer Fallzahl und der Behandlungskapazitäten regional präzise vorhergesagt werden.

Schlüsselwörter

COVID-19 - künstliche Intelligenz - maschinelles Lernen - Verlaufsvorhersage - Medikamentenentwicklung

Keywords

COVID-19 - artificial intelligence - machine learning - disease prediction - drug discovery

Publication History

Article published online:
23 March 2022

• Literatur

• 1 Kaplan A, Haenlein M. Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Business Horizons 2019; 62: 15-25
• 2 Wynants L, Van Calster B, Collins GS. et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ 2020; 369: m1328 DOI: 10.1136/bmj.m1328. (PMID: 32265220)
• 3 Rahaman MM, Li C, Yao Y. et al. Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches. Xray Sci Technol 2020; 28: 821-839 DOI: 10.3233/XST-200715. (PMID: 32773400)
• 4 Moezzi M, Shirbandi K, Shahvandi HK. et al. The diagnostic accuracy of Artificial Intelligence-Assisted CT imaging in COVID-19 disease: A systematic review and meta-analysis. Inform Med Unlocked 2021; 24: 100591 DOI: 10.1016/j.imu.2021.100591. (PMID: 33977119)
• 5 Helwan A, Ma’aitah MKS, Hamdan H. et al. Radiologists versus Deep Convolutional Neural Networks: A comparative study for diagnosing COVID-19. Comput Math Methods Med 2021; 2021: 5527271 DOI: 10.1155/2021/5527271. (PMID: 34055034)
• 6 Born J, Beymer D, Rajan D. et al. On the role of artificial intelligence in medical imaging of COVID-19. Patterns 2021; 2: 100269 DOI: 10.1016/j.patter.2021.100269. (PMID: 34405156)
• 7 Chen D, Liu S, Kingsbury P. et al. Deep learning and alternative learning strategies for retrospective real-world clinical data. NPJ Digit Med 2019; 2: 43 DOI: 10.1038/s41746-019-0122-0. (PMID: 31304389)
• 8 Brown C, Chauhan J, Grammenos A. et al. Exploring automatic diagnosis of covid-19 from crowdsourced respiratory sound data. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2020; 3474-3484
• 9 Levy TJ, Richardson S, Coppa K. et al. Estimating survival of hospitalized COVID-19 patients from admission information. medRxiv 2020; DOI: 10.1101/2020.04.22.20075416.
• 10 Woo SH, Rios-Diaz AJ, Kubey AA. et al. Development and validation of a web-based severe COVID-19 risk prediction model. Am J Med Sci 2021; 362: 355-362 DOI: 10.1016/j.amjms.2021.04.001. (PMID: 34029558)
• 11 Alballa N, Al-Turaiki I. Machine learning approaches in COVID-19 diagnosis, mortality, and severity risk prediction: A review. Inform Med Unlocked 2021; 24: 100564 DOI: 10.1016/j.imu.2021.100564. (PMID: 33842685)
• 12 Gupta RK, Marks M, Samuels THA. et al. Systematic evaluation and external validation of 22 prognostic models among hospitalised adults with COVID-19: an observational cohort study. Eur Respir J 2020; 56: 2003498 DOI: 10.1183/13993003.03498-2020. (PMID: 32978307)
• 13 Gupta RK, Harrison EM, Ho A. et al. Development and validation of the ISARIC 4C Deterioration model for adults hospitalised with COVID-19: a prospective cohort study. Lancet Respir Med 2021; 9: 349-359 DOI: 10.1016/s2213-2600(20)30559-2. (PMID: 33444539)
• 14 Kelly M. Lessons from Moderna: Leverage the Power of Artificial Intelligence. 2020 Accessed January 14, 2022 at: http://sternspeakers.com/news/lessons-from-moderna-leverage-the-power-of-artificial-intelligence/
• 15 Keshavarzi Arshadi A, Webb J, Salem M. et al. Artificial Intelligence for COVID-19 Drug Discovery and Vaccine Development. Front Artif Intell 2020; 3: 65 DOI: 10.3389/frai.2020.00065. (PMID: 33733182)
• 16 Jumper J, Tunyasuvunakool K, Kohli P. et al. Computational predictions of protein structures associated with COVID-19. Version 3. 2020 Accessed January 14, 2022 at: http://deepmind.com/research/open-source/computational-predictions-of-protein-structures-associated-with-COVID-19
• 17 Hie B, Zhong ED, Berger B. et al. Learning the language of viral evolution and escape. Science 2021; 371: 284-288 DOI: 10.1126/science.abd7331. (PMID: 33446556)
• 18 Talele TT, Khedkar SA, Rigby AC. Successful applications of computer aided drug discovery: moving drugs from concept to the clinic. Curr Top Med Chem 2010; 10: 127-141 DOI: 10.2174/156802610790232251.
• 19 Serafim MSM, Gertrudes JC, Costa DMA. et al. Knowing and combating the enemy: a brief review on SARS-CoV-2 and computational approaches applied to the discovery of drug candidates. Biosci Rep 2021; 41: BSR20202616 DOI: 10.1042/BSR20202616. (PMID: 33624754)
• 20 Zeng X, Song X, Ma T. et al. Repurpose Open Data to Discover Therapeutics for COVID-19 Using Deep Learning. J Proteome Res 2020; 19: 4624-4636 DOI: 10.1021/acs.jproteome.0c00316. (PMID: 32654489)
• 21 Bogoch II, Watts A, Thomas-Bachli A. et al. Pneumonia of unknown aetiology in Wuhan, China: potential for international spread via commercial air travel. J Travel Med 2020; 27: taaa008 DOI: 10.1093/jtm/taaa008. (PMID: 31943059)
• 22 Tiwari D, Bhati BS, Al-Turjman F. et al. Pandemic coronavirus disease (COVID-19): World effects analysis and prediction using machine-learning techniques. Expert Syst 2021; DOI: 10.1111/exsy.12714. (PMID: 34177035)
• 23 Schuppert A, Polotzek K, Schmitt J. et al. Different spreading dynamics throughout Germany during the second wave of the COVID-19 pandemic: a time series study based on national surveillance data. Lancet Reg Health Eur 2021; 6: 100151 DOI: 10.1016/j.lanepe.2021.100151. (PMID: 34557834)