Prediction of in-hospital hypokalemia using machine learning and first hospitalization day records in patients with traumatic brain injury

Abstract

Aims: Hypokalemia is a common complication following traumatic brain injury, which may complicate treatment and lead to unfavorable outcomes. Identifying patients at risk of hypokalemia on the first day of admission helps to implement prophylactic treatment, reduce complications, and improve prognosis.

Methods: This multicenter retrospective study was performed between January 2017 and December 2020 using the electronic medical records of patients admitted due to traumatic brain injury. A propensity score matching approach was adopted with a ratio of 1:1 to overcome overfitting and data imbalance during subgroup analyses. Five machine learning algorithms were applied to generate a best-performed prediction model for in-hospital hypokalemia. The internal fivefold cross-validation and external validation were performed to demonstrate the interpretability and generalizability.

Results: A total of 4445 TBI patients were recruited for analysis and model generation. Hypokalemia occurred in 46.55% of recruited patients and the incidences of mild, moderate, and severe hypokalemia were 32.06%, 12.69%, and 1.80%, respectively. Hypokalemia was associated with increased mortality, while severe hypokalemia cast greater impacts. The logistic regression algorithm had the best performance in predicting decreased serum potassium and moderate-to-severe hypokalemia, with an AUC of 0.73 ± 0.011 and 0.74 ± 0.019, respectively. The prediction model was further verified using two external datasets, including our previous published data and the open-assessed Medical Information Mart for Intensive Care database. Linearized calibration curves showed no statistical difference (p > 0.05) with perfect predictions.

Conclusions: The occurrence of hypokalemia following traumatic brain injury can be predicted by first hospitalization day records and machine learning algorithms. The logistic regression algorithm showed an optimal predicting performance verified by both internal and external validation.

Keywords: hypokalemia; machine learning; perioperative risks; traumatic brain injury.

FIGURE 1

A flow chart for the screening process of eligible patients.

FIGURE 2

Risk factors of in‐hospital mortality among TBI patients.

FIGURE 3

The ROC curves and top features for in‐hospital hypokalemia prediction. The ROC curves of three prediction models for (A) in‐hospital hypokalemia and (D) moderate‐to‐severe hypokalemia. Features of the top 15 weights predicting (B) hypokalemia and (E) moderate‐to‐severe hypokalemia via logistic regression model. Features of the top 15 averaged weights predicting (C) hypokalemia and (F) moderate‐to‐severe hypokalemia according to the logistic regression, gradient‐boosted trees, and naive Bayes models.

FIGURE 4

Model validation using the external dataset. Calibration curve of external validation using the logistic regression model predicting (A) in‐hospital hypokalemia and (C) moderate‐to‐severe hypokalemia. The ROC curve of the logistic regression model predicting (B) in‐hospital hypokalemia and (D) moderate‐to‐severe hypokalemia.