Bland–Altman agreement analysis between CT predicted and surgical peritoneal cancer index in pseudomyxoma peritonei of appendiceal origin

Abstract

AbstractPeritoneal cancer index (PCI) is the surgical variable most commonly used to quantify the extent of peritoneal metastases for pseudomyxoma peritonei (PMP) patients. The present study aimed to investigate the agreement between CT predicted and surgical PCI by the Bland–Altman method for PMP of appendiceal origin. A total of 167 PMP patients of appendiceal origin were included between 2016 and 2021. Bland–Altman analysis was performed for both total PCI and selected PCI (regions 2 + 9–12). After the Bland–Altman plot was drawn, the mean bias and its 95% limit of agreements (LoAs) was quantified. Besides, the correlation coefficients between CT-PCI and surgical PCI were also been calculated. The Bland–Altman plot showed the mean bias ± SD between total CT-PCI and surgical PCI as 0.431 ± 3.005, with the LoAs from − 5.459 to 6.321. There were nine points of difference in total PCI exceeded the 95% LoAs, with the rate of 5.39% (9/167). As for selected CT-PCI, Bland–Altman plot showed the mean bias ± SD between selected CT-PCI and surgical PCI as − 0.287 ± 1.955, with the LoAs from − 4.118 to 3.544. There were ten points of difference in selected PCI exceeded the 95% LoAs, with the rate of 5.99% (10/167). The Spearman's rank correlation coefficient between total CT-PCI and surgical PCI was 0.911, P < 0.001, as for selected CT-PCI and surgical PCI, the coefficient was 0.909, P < 0.001. Although there was a strong correlation for both total and selected CT-PCI with surgical PCI, however, the agreement is still not good in Bland–Altman analysis, which suggested that CT-PCI cannot predict surgical PCI accurately even in professional PMP treatment centers. In brief explanation, CT makes it difficult to distinguish the borderline between tumor tissue and mucus and to detect tumor lesions in the small intestine regions, which caused overestimation or underestimation by CT-PCI. In the future, a multiple linear regression model based on CT-PCI might accurately predict surgical PCI preoperatively.