Can we predict when to start renal replacement therapy in patients with chronic kidney disease using 6 months of clinical data?

Abstract

PurposeWe aimed to develop a model of chronic kidney disease (CKD) progression for predicting the probability and time to progression from various CKD stages to renal replacement therapy (RRT), using 6 months of clinical data variables routinely measured at healthcare centers.MethodsData were derived from the electronic medical records of Ajou University Hospital, Suwon, South Korea from October 1997 to September 2012. We included patients who were diagnosed with CKD (estimated glomerular filtration rate [eGFR] < 60 mL·min–1·1.73 m–2 for ≥ 3 months) and followed up for at least 6 months. The study population was randomly divided into training and test sets.ResultsWe identified 4,509 patients who met reasonable diagnostic criteria. Patients were randomly divided into 2 groups, and after excluding patients with missing data, the training and test sets included 1,625 and 1,618 patients, respectively. The integral mean was the most powerful explanatory (R2 = 0.404) variable among the 8 modified values. Ten variables (age, sex, diabetes mellitus[DM], polycystic kidney disease[PKD], serum albumin, serum hemoglobin, serum phosphorus, serum potassium, eGFR (calculated by Chronic Kidney Disease Epidemiology Collaboration [CKD-EPI]), and urinary protein) were included in the final risk prediction model for CKD stage 3 (R2 = 0.330). Ten variables (age, sex, DM, GN, PKD, serum hemoglobin, serum blood urea nitrogen[BUN], serum calcium, eGFR(calculated by Modification of Diet in Renal Disease[MDRD]), and urinary protein) were included in the final risk prediction model for CKD stage 4 (R2 = 0.386). Four variables (serum hemoglobin, serum BUN, eGFR(calculated by MDRD) and urinary protein) were included in the final risk prediction model for CKD stage 5 (R2 = 0.321).ConclusionWe created a prediction model according to CKD stages by using integral means. Based on the results of the Brier score (BS) and Harrel’s C statistics, we consider that our model has significant explanatory power to predict the probability and interval time to the initiation of RRT.

Chronic Kidney Disease Progression and Transition Probabilities in a Large Preventive Cohort in Colombia

“…There is scarcity of data about the transition between CKD stages over time; however, extensive research has been done regarding models that predict the progression of this disease [ 13 ], as well as variables associated with fast or slow progression [ 14 , 15 ].…”

Chronic kidney disease progression in a large prevention program in Colombia: A cohort study

“…It should be noted that the linear progression paradigm has been challenged by several studies showing that progression patterns often differ from linearity 13,14 . These understandings have favored the use of different statistical models in the way of knowing the influence that multiple predictive variables may have on outcomes such as the speed of progression or initiation of kidney replacement therapy (KRT) [15][16][17][18] .…”

Using machine learning models to predict the initiation of renal replacement therapy among chronic kidney disease patients

“…AI is being increasingly used to assist diagnosis, therapy, automatic classification and rehabilitation. For example, ML algorithms have been applied for the prediction of starting RRT within a few months to a year [16][17][18][19][20], and prediction of acute kidney injury that required RRT within a few hours to a few days [21][22][23][24]. However, the existing work uses laboratory (and demographic) data for the analysis and prediction of RRT.…”

“…al. analyzed electronic medical records of 4,500 patients from South Korea from 1997 to 2012 in order to predict the time of RRT[16]. For this purpose, they used six months of 12 clinical data variables such as serum albumin, serum hemoglobin, serum phosphorus, serum potassium, and eGFR, in addition to demographic variables, and five comorbidities.…”