Fig 1.
PRISMA figure.
Table 1.
Overview of included studies.
Table 2.
Performance of ML models predicting SSI in general per surgical specialism.
Table 3.
Performance of ML models predicting superficial SSI per surgical specialism.
Table 4.
Performance of ML models predicting deep SSI per surgical specialism.
Table 5.
Performance of ML models predicting organ space SSI per surgical specialism.
Fig 2.
Predictors used in proportion of the ML models.
All predictors used five times or more are included in the figure. ASA classification (American Society of Anesthesiologists); BMI, (Body Mass Index); COPD (Chronic Obstructive Pulmonary Disease); INR, (International Normalized Ratio); PT, (Prothrombin time); WBC, (White blood count).
Fig 3.
Area under the curve (AUC) for each article that presented both ML and regression-based models.
Green dots represent the AUC of the ML models, orange dots represent the AUC of the regression-based models. The green and orange lines represent the median.
Fig 4.
Summary of risk of bias assessment using the PROBAST.
Green low risk of bias, yellow unclear risk of bias due to lack of information, red high risk of bias. ROB; Risk of bias.