Reproducibility materials for predicting 12- and 24-month documented CKD progression from routine laboratory data

This repository contains the reproducibility package accompanying the manuscript “Predicting 12- and 24-month documented CKD progression from routine laboratory data: a single-centre temporal evaluation.” It includes the analysis code, environment specifications, input-data schema, synthetic example data, non-identifying aggregate outputs, supplementary analyses, verification scripts, and publication figures. The package supports the 12-month cumulative-risk model, the conditional months 13–24 model, and the coherent 24-month risk calculation reported in the manuscript. Raw institutional laboratory data and patient-level records are not included because they contain confidential health information and are subject to institutional and ethical restrictions. Exact aggregate counts from 1 to 4 are suppressed to reduce re-identification risk. The synthetic interface example does not represent any real patient and was not used in model development or evaluation. Instructions for reproducing and verifying the reported results are provided in the README and accompanying documentation.