The following is the summary of  “Established risk prediction models for the incidence of a low lean tissue index in patients with peritoneal dialysis” published in the December 2022 issue of Renal failure by Li, et al

The purpose of this research is to examine the prevalence of low lean tissue index (LTI) and the risk variables for low LTI in peritoneal dialysis (PD) patients, as well as to develop risk prediction models. Between October 2019 and September 2021, 104 PD patients were enrolled. Bioimpedance spectroscopy was used to evaluate LTI. Those characteristics associated with low LTI in PD patients were analyzed using multivariate logistic regression and machine learning. In addition, the survival rate of patients with poor LTI was analyzed using Kaplan-Meier.

Significant differences were between the low LTI and normal LTI groups on measures of interleukin-6 (IL-6), red cell distribution width (RDW), overhydration, body mass index (BMI), and subjective global assessment (SGA) score. Risk variables for LTI were shown to be IL-6 (1.10 [95% CI: 1.02-1.18]), RDW (1.87 [95% CI: 1.18-2.97]), BMI (0.97 [95% CI: 0.68-0.91]), and the SGA rating (6.33 [95% CI: 1.59-25.30]) by multivariate logistic regression. According to Cox regression analysis, poor LTI was the only independent risk factor for death in peritoneal dialysis patients (HR 3.14, [95% CI: 1.12-8.80]). 

Machine learning was used to construct a decision procedure to predict the occurrence of low LTI in PD patients, with an area under the curve of internal validation of 0.6349. Patients with PD who have low LTI have a much higher risk of dying. Low LTI is associated with a micro-inflammatory state, high RDW, low BMI, and low SGA rating in PD patients. The developed prediction model is potentially helpful in evaluating patients with PD for low LTI.

Source: tandfonline.com/doi/full/10.1080/0886022X.2022.2113794