Artificial intelligence based real-time microcirculation analysis system for laparoscopic colorectal surgery

Figure 7 Statistical performance verification using classification performance evaluation metrics between artificial intelligence-based analysis and perfusion parameter of quantitative analysis. True positive (TP), false positive (FP), false negative (FN), true negative (TN), accuracy [(TP + TN)/(TP + FN + FP + TN)], recall [TP/(TP + FN)], and precision [TP/(TP + FP)] were the classification performance evaluation metrics. F1 score represents a harmonized average of recall and precision, artificial intelligence analysis was evaluated as the most accurate parameter to predict the risk of anastomotic complications. TR: Time ratio; RS: Rising slope; AI: Artificial intelligence.