Estimating Chronic Kidney Disease Stage Transitions from Irregular Electronic Health Record Data Using an...

To estimate chronic kidney disease (CKD) stage transition probabilities in patients with small renal masses (SRMs) using irregularly observed electronic health record (EHR) data, addressing challenges of interval censoring and irregular measurement intervals in real-world clinical practice.

We used EHR data from the institutional Small Renal Mass registry (2006-January 2026), capturing outpatient renal function data prior to any definitive treatment for SRM. CKD stages were defined using estimated glomerular filtration rate (eGFR) thresholds based on KDIGO guidelines.

The final analytic cohort included 527 patients with at least 2 outpatient eGFR measurements prior to definitive treatment. We applied an expectation-maximization (EM) algorithm to estimate discrete-time CKD stage transition matrices while accounting for irregular eGFR measurement intervals and unobserved intermediate transitions. Transition matrices were estimated under 3- and 6-mo cycle lengths overall as well as stratified by age and sex. The likelihood ratio statistic was used to compare EM-based estimates with the empirical counting estimator.

The EM framework yielded clinically plausible transition structures dominated by self-transitions and progression primarily to adjacent CKD stages, with reduced spurious backward transitions relative to the empirical estimator. Transition patterns were consistent across 3- and 6-mo cycle lengths. Age-stratified analyses showed that older patients had slightly higher probabilities of progression to more advanced CKD stages compared with younger patients, whereas sex-stratified differences were minimal. Likelihood ratio comparisons supported the consistency of the EM-based models with the observed transition data in both the overall cohort and subgroup analyses.

The EM approach provides a principled and computationally efficient method for estimating CKD stage progression from irregularly observed EHR data, yielding transition matrices suitable for discrete-time decision-analytic and health economic models.