An Equation Based on Fuzzy Mathematics to Assess the Timing of Haemodialysis Initiation

Abstract

In order to develop an equation that integrates multiple clinical factors including signs and symptoms associated with uraemia to assess the initiation of dialysis, we conducted a retrospective cohort study including 25 haemodialysis centres in Mainland China. Patients with ESRD (n = 1281) who commenced haemodialysis from 2008 to 2011 were enrolled in the development cohort, whereas 504 patients who began haemodialysis between 2012 and 2013 were enrolled in the validation cohort comprised. An artificial neural network model was used to select variables, and a fuzzy neural network model was then constructed using factors affecting haemodialysis initiation as input variables and 3-year survival as the output variable. A logistic model was set up using the same variables. The equation’s performance was compared with that of the logistic model and conventional eGFR-based assessment. The area under the bootstrap-corrected receiver-operating characteristic curve of the equation was 0.70, and that of two conventional eGFR-based assessments were 0.57 and 0.54. In conclusion, the new equation based on Fuzzy mathematics, covering laboratory and clinical variables, is more suitable for assessing the timing of dialysis initiation in a Chinese ESRD population than eGFR, and may be a helpful tool to quantitatively evaluate the initiation of haemodialysis.

Update of dialysis initiation timing in end stage kidney disease patients: is it a resolved question? A systematic literature review

“…Chang et al [ 14 ] quantified uremic burden based on 7 uremic indicators that reached the predefined threshold (hemoglobin, serum albumin, blood urea nitrogen, serum creatinine, potassium, phosphorus, and bicarbonate); dialysis timing was classified as standard (met 0–2 uremic indicators), late (3–5indicators), and very late (6–7 indicators); and no correlation was found between late or very late group and mortality. Ying et al [ 26 ] developed an equation based on fuzzy mathematics to assess the timing of haemodialysis initiation, the results showed that the combination of sex, age, serum creatinine, blood urea nitrogen, serum albumin, haemoglobin, serum phosphorus, diabetes mellitus, and heart failure as equation variables resulted in the best accuracy to prognose 3-year survival. Matthew et al [ 19 ] categorized clinically documented primary indication for dialysis initiation into 4 groups: laboratory evidence of kidney function decline (reference category), uremic symptoms, volume overload or hypertension, and other/unknown; and found that volume overload or hypertension was associated with the highest risk for subsequent mortality.…”

Mortality and associated risk factors between young and elderly maintenance haemodialysis patients: a multicentre retrospective cohort study in China

“…We conducted this population-based multicentre retrospective cohort study from the database of Dialysis Initiation based on Fuzzy mathematics Equation study (DIFE),14 which focuses on adults patients with ESKD undergoing maintenance haemodialysis in China and aims to establish a novel equation of timing of haemodialysis initiation based on a fuzzy mathematical method 15 16…”

Assessment of dialysis initiation by a fuzzy mathematics equation (ADIFE): a study protocol for a randomised controlled trial

“…The sample size estimate is mainly based on the primary endpoint of the 3-year all-cause mortality from the previous retrospective cohort DIFE study, which showed that the 3-year mortality of the optimal start dialysis group was 8.38% and that of the late start dialysis group was 19.4% 21. Using PASS V.15 of the Power and Sample Size Calculation program (NCSS, LLC), we estimated a sample size of 154 per group (assuming a type I error rate of 5% with 80% power, two-sided test, with p<0.05 considered statistically significant).…”

“…The DIFE study showed that the 3-year dialysis mortality of patients in the optimal start dialysis group (DIFE value of 30 to 35) was markedly lower (8.38%) than the late-start dialysis group (DIFE value less than 30) of 19.4%. Moreover, receiver operating characteristic curve analysis indicated that the area under the curve for the prediction of a 3-year death during dialysis initiation assessed by the DIFE was significantly higher than that predicted by eGFR (0.70 vs 0.55, p<0.01) 21. Therefore, the DIFE is more accurate and effective to assess the timing of haemodialysis initiation than eGFR alone.…”

“…Thus, our research team established a novel equation to determine the optimal timing, called dialysis initiation based on a fuzzy mathematical method (DIFE), which was derived from a previous multicentre, retrospective cohort study with large-scale samples 21. The DIFE includes nine parameters: sex, age, blood urea nitrogen, serum creatinine, haemoglobin, serum albumin, serum phosphorus, heart failure condition and diabetes condition, which effectively combines subjective clinical variables with objective biochemical markers for dialysis initiation decision- making.…”