¹Internal Medicine IX: Department of Clinical Pharmacology and Pharmacoepidemiology, Heidelberg University, Medical Faculty/Heidelberg University Hospital, Heidelberg, Germany
²Department of Statistics, TU Dortmund University, Dortmund, Germany
³Institute of General Practice and Family Medicine, University Hospital, LMU Munich, Munich, Germany

Text

Background: Hypo- and hyperkalemia can have serious consequences, especially in patients with heart failure (HF), chronic kidney disease (CKD), and diabetes mellitus (DM). As general monitoring recommendations for ambulatory care may be too loose to catch individual risk situations in outpatients, prediction models could assist by revealing individual trends that may require close clinical action (e.g., adjustments in monitoring intervals or medication regimens). We aimed to develop a dynamic prediction model for potassium concentration in the outpatient sector for patients with HF, CKD, and/or DM.

Materials and Methods: We used administrative claims data from Scotland collected at the Tayside Health Informatics Centre and selected patients between January 1^st and June 30^th, 2020 and underlying conditions of HF, CKD, and/or DM. The follow-up time of each patient was divided into assessment periods to predict a patient’s maximum potassium value within the next four weeks (prediction periods). Three linear mixed-effect models were fitted and model performance was assessed using root-mean-squared-error (RMSE), mean absolute error (MAE), and mean squared error (MSE).

Results: Among 5,918 patients with a mean age of 76.2 years, a median of 17.0 potassium concentrations were measured per patient corresponding with 1.71 measurements per assessment period. In total, we predicted 5,478 maximum potassium values. The final model performed with a RMSE of 0.52, MAE of 0.39, MSE of 0.27, and with no apparent trends in the residuals over time. Prediction was more accurate within the potassium reference range, and tended to underestimate extremely high and overestimate low observations. Among the strongest predictors were newly acquired acute kidney injury, last measured potassium, and use of low ceiling and high ceiling diuretics.

Conclusion: We propose a blueprint of a decision support tool which predicts potassium concentration longitudinally by updating the predictions based on accumulating data. Our findings demonstrate that dynamically reassessing predictors can aid in estimating potassium levels over multiple months with reasonable accuracy in the outpatient setting.

Figure 1 [Fig. 1]

Literatur

[1] Scherkl C, Grytzka J, Rottenkolber M, Dreischulte T, Seidling HM, Czock D, Groll A, Meid AD. Predicting potassium trajectories for risk monitoring in outpatients with heart failure, diabetes mellitus or chronic kidney disease. Br J Clin Pharmacol. 2025 Aug 28. DOI: 10.1002/bcp.70250