Derivation and Validation of Risk Scores to Predict Cerebrovascular Mortality Among Incident Peritoneal Dialysis Patients

Abstract

Background/Aims: Cerebrovascular disease (CeVD) is one of the leading causes of death in patients initialising peritoneal dialysis (PD). Currently there is no risk score to predict the future risk of CeVD on entry into PD. This study aimed to derive and validate a risk prediction model for CeVD mortality in 2 years after the initialisation of PD. Methods: All patients registered with the Henan Peritoneal Dialysis Registry (HPDR) between 2007 and 2014 were included. Multivariable logistic regression modelling was applied to derive the risk score. All accessible clinical measurements were screened as potential predictors. Internal validation through bootstrapping was applied to test the model performance. Results: The absolute risk of CeVD mortality was 2.9%. Systolic and diastolic blood pressure, total cholesterol, phosphate, and sodium concentrations were the strongest predictors of CeVD mortality in the final risk score. Good model discrimination with C statistics above 0.70 and calibration of agreed observed and predicted risks were identified in the model. Conclusion: The new risk score, developed and validated using clinical measurements that are accessible on entry into PD, could be used clinically to screen for patients at high risk of CeVD mortality. Such patients might benefit from therapies reducing the incidence of CeVD related events.

[Retracted] Deconstruction of Risk Prediction of Ischemic Cardiovascular and Cerebrovascular Diseases Based on Deep Learning

“…Kelly et al' study found that chronic kidney disease was associated with severe stroke severity, prognosis, and a high burden of asymptomatic cerebrovascular disease and vascular cognitive impairment [ 1 ]. Zhang et al studied the risk prediction model for CeVD mortality by all accessible clinical measures which were screened as potential predictors [ 2 ]. Zeng et al studied the usefulness of predicting CVD in an Inner Mongolian population using the China-PAR equation for 10-year risk [ 3 ].…”

A low‐cost laboratory‐based method for predicting newly diagnosed biopsy‐proven diabetic nephropathy in people with type 2 diabetes

“…Model discrimination was assessed using the concordance statistic (C-statistic), which was estimated from the adjusted receiveroperating characteristic curves, disregarding the matching. Unconditional logistic regression was performed, with additional adjustment using matching factors [20]. A value of 0.50 represents no discrimination and 1.00 represents perfect discrimination.…”

Derivation and validation of a risk score predicting risk of early-onset peritonitis among patients initializing peritoneal dialysis: A cohort study

“…For our study, having an incident episode of peritonitis within the first 6 months after initializing PD was treated as a binary outcome measure. Candidate prognostic factors that were not statistically significant were excluded from the backward elimination logistic regression model (p > 0.1, based on change in log likelihood) (Zhang et al, 2018b). Two-degree fractional polynomial terms were used to model non-linear associations between outcomes and continuous predictors (Yu et al, 2019).…”

“…We used the concordance statistic (C-statistic) to evaluate model discrimination (Sultan et al, 2016). Model discrimination was internally validated by calculating the bootstrap optimism-corrected c-statistic with 1000 bootstrap replications (Zhang et al, 2018b).…”

“…To facilitate model utilization in clinical practice, the logistic regression equations were transformed into prognostic score charts (Zhang et al, 2018b). The coefficients in the logistic regression equation were multiplied by 50 and rounded to the nearest integer to obtain the prognostic score per predictor (Yu et al, 2018b).…”