AbstractObjectivesThis study is aimed to develop and validate a prediction model for multi-state transitions across different stages of chronic kidney disease in patients with type 2 diabetes mellitus under primary care.SettingWe retrieved the anonymized electronic health records of a population based retrospective cohort in Hong Kong.ParticipantsA total of 26,197 patients were included in the analysis.Primary and secondary outcome measuresThe new-onset, progression, and regression of chronic kidney disease were defined by the transitions of four stages that were classified by combining glomerular filtration rate and urine albumin-to-creatinine ratio. We applied a multi-scale multi-state Poisson regression model to estimate the rates of the stage transitions by integrating the baseline demographic characteristics, routine laboratory test results and clinical data from electronic health records.ResultsDuring the mean follow-up time of 1.7 years, there were 2,935 patients newly diagnosed with chronic kidney disease, 1,443 progressed to the next stage and 1,971 regressed into an earlier stage. The models achieved the best performance in predicting the new-onset and progression with the predictors of sex, age, body mass index, systolic blood pressure, diastolic blood pressure, serum creatinine, HbA1c, total cholesterol, LDL, HDL, triglycerides and drug prescriptions.ConclusionsThis study demonstrated that individual risks of new-onset and progression of chronic kidney disease can be predicted from the routine physical and laboratory test results. The individualized prediction curves developed from this study could potentially be applied to routine clinical practices, to facilitate clinical decision making, risk communications with patients and early interventions.Article summaryStrengths of this studyEarly predictions for chronic kidney disease progression and timely intervention is critical for clinical management of patients with diabetes.We successfully developed a multi-scale multi-state Poisson regression models that achieved the satisfactory performance in predicting the new-onset and progression of chronic kidney diseases.The model incorporates the predictors of demographic characteristics, routine laboratory test results and clinical data from electronic health records.The individualized prediction curves could potentially be applied to facilitate clinical decision making, risk communications with patients and early interventions of CKD progression.Limitations of this studyThe cohort has a relatively short follow-up period and the retrospective study design might suffer from report bias and selection bias.
An external validation of models to predict the onset of chronic kidney disease using population-based electronic health records from Salford, UK