Table 7.

Results for diagnostic and prognostic Imaging models.

Study, Country, Outcome	No. of CPP*	AI methods	Predictors	Val. methods	Performance (AUC, Accuracy (Acc%), Sensitivity (SEN%), Specificity (SPE%), PPV/NPV (%), (95% CI))	Risk of Bias**: Participants/Predictors/Outcome/Analysis/Overall
Chassagnon et al. [45], France, Quantification, Staging and Prognosis of COVID-19 Pneumonia	693	DL, 2D-3D CNN, RBF SVM, Linear SVM, AdaBoost, RF, DT, XGBoost	15 radiomics features: imaging from the disease regions (5features), lung regions (5features) and heart features (5features), biological and clinical data (6features: age, sex, high blood pressure (HBP), diabetes, lymphocyte count, CRP level), image indexes (2features: disease extent and fat ratio).	TTS	Acc 70, SEN 64, SPE 77 (Holistic Multi-Omics Profiling & Staging), Acc 71, SEN 74, SPE 82 (AI prognosis model performance)	L	U	L	L	U

*CPP = COVID-19 Positive Patients, Abbreviations of medical terms included in this Table are provided in the Appendix.

**L: Low, H: High, U: Unclear