Performance of artificial intelligence in predicting the prognossis of severe COVID-19: a systematic review and meta-analysis

Abstract

BackgroundCOVID-19-induced pneumonia has become a persistent health concern, with severe cases posing a significant threat to patient lives. However, the potential of artificial intelligence (AI) in assisting physicians in predicting the prognosis of severe COVID-19 patients remains unclear.MethodsTo obtain relevant studies, two researchers conducted a comprehensive search of the PubMed, Web of Science, and Embase databases, including all studies published up to October 31, 2023, that utilized AI to predict mortality rates in severe COVID-19 patients. The PROBAST 2019 tool was employed to assess the potential bias in the included studies, and Stata 16 was used for meta-analysis, publication bias assessment, and sensitivity analysis.ResultsA total of 19 studies, comprising 26 models, were included in the analysis. Among them, the models that incorporated both clinical and radiological data demonstrated the highest performance. These models achieved an overall sensitivity of 0.81 (0.64–0.91), specificity of 0.77 (0.71–0.82), and an overall area under the curve (AUC) of 0.88 (0.85–0.90). Subgroup analysis revealed notable findings. Studies conducted in developed countries exhibited significantly higher predictive specificity for both radiological and combined models (p < 0.05). Additionally, investigations involving non-intensive care unit patients demonstrated significantly greater predictive specificity (p < 0.001).ConclusionThe current evidence suggests that artificial intelligence prediction models show promising performance in predicting the prognosis of severe COVID-19 patients. However, due to variations in the suitability of different models for specific populations, it is not yet certain whether they can be fully applied in clinical practice. There is still room for improvement in their predictive capabilities, and future research and development efforts are needed.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/ with the Unique Identifier CRD42023431537.