Indicators for predicting continuous insulin infusion therapy-related hypokalemia: multicenter retrospective cohort study
Abstract
Hypokalemia is a common and potentially life-threatening complication of continuous intravenous insulin infusion (CII) in patients with hyperglycemic crises. However, no simple quantitative indicator can estimate the risk of hypokalemia at treatment initiation. This multicenter retrospective cohort study enrolled patients hospitalized for hyperglycemic crises who received CII. Clinical data available at CII initiation were collected. Machine-learning techniques were primarily employed for feature selection and model comparison to develop a simple, clinically interpretable prediction model. A logistic regression-based indicator was constructed using the most contributory variables and validated internally and externally. Hypokalemia was defined as a serum potassium level <3.5 mmol/L. The model-building and external validation cohorts included 99 and 55 patients, respectively. Among multiple candidate models, a lightweight logistic regression model using only two variables, serum potassium level and insulin infusion rate per body weight, was selected for clinical applicability. In internal validation, the model demonstrated good discriminative performance (receiver operating characteristic-area under the curve [ROC-AUC] 0.821). When applied to the external validation cohort, the ROC-AUC was 0.655, and accuracy decreased slightly. A lower threshold may increase sensitivity in screening, whereas a higher threshold may improve specificity. In conclusion, this study presents a simple and clinically applicable indicator for predicting CII-related hypokalemia using only two routinely available variables at treatment initiation. This model supports individualized electrolyte monitoring during the acute management of hyperglycemic crises. Additionally, it may facilitate safer and more efficient clinical decision-making without reliance on complex algorithms.
Related
- Nomogram for predicting survival in patients with motor-complete cervical spinal cord injury without fracture-dislocation: a multicenter retrospective study
- Development and external validation of machine learning models for predicting mortality in patients with lung cancer: a multicenter retrospective cohort study
- Development and validation of a nomogram for predicting chest drainage after CT-guided percutaneous lung biopsy: a multicenter retrospective study
- A nomogram integrating YTHDC2 expression and clinicopathological parameters for predicting endometrial cancer recurrence: a multicenter retrospective study
- Head-to-head comparison of glucose-to-albumin ratio against five albumin-derived indices for predicting 28-day ICU mortality in critically ill patients with spontaneous intracerebral hemorrhage: a multicenter retrospective study.
BibTeX
@article{iwamoto2026indicators,
title = {{Indicators for predicting continuous insulin infusion therapy-related hypokalemia: multicenter retrospective cohort study}},
author = {Yuichiro Iwamoto and Tomohiko Kimura and Masato Kubo and Yui Okamoto and Ryo Inaba and Takashi Itoh and Toshitomo Sugisaki and Kazunori Dan and Hideyuki Iwamoto and Yoshiro Fushimi and Junpei Sanada and Hayato Isobe and Fuminori Tatsumi and Yukiko Kimura and Fumiko Kawasaki and Masashi Shimoda and Shuhei Nakanishi and Kohei Kaku and Hideaki Kaneto},
journal = {Endocrine Journal},
year = {2026},
month = sep,
doi = {10.1507/endocrj.ej26-0061},
url = {https://www.jstage.jst.go.jp/article/endocrj/73/9/73_EJ26-0061/_article},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Indicators for predicting continuous insulin infusion therapy-related hypokalemia: multicenter retrospective cohort study
AU - Yuichiro Iwamoto
AU - Tomohiko Kimura
AU - Masato Kubo
AU - Yui Okamoto
AU - Ryo Inaba
AU - Takashi Itoh
AU - Toshitomo Sugisaki
AU - Kazunori Dan
AU - Hideyuki Iwamoto
AU - Yoshiro Fushimi
AU - Junpei Sanada
AU - Hayato Isobe
AU - Fuminori Tatsumi
AU - Yukiko Kimura
AU - Fumiko Kawasaki
AU - Masashi Shimoda
AU - Shuhei Nakanishi
AU - Kohei Kaku
AU - Hideaki Kaneto
PY - 2026
DA - 2026/09/01
JO - Endocrine Journal
DO - 10.1507/endocrj.ej26-0061
UR - https://www.jstage.jst.go.jp/article/endocrj/73/9/73_EJ26-0061/_article
AB - Hypokalemia is a common and potentially life-threatening complication of continuous intravenous insulin infusion (CII) in patients with hyperglycemic crises. However, no simple quantitative indicator can estimate the risk of hypokalemia at treatment initiation. This multicenter retrospective cohort study enrolled patients hospitalized for hyperglycemic crises who received CII. Clinical data available at CII initiation were collected. Machine-learning techniques were primarily employed for feature selection and model comparison to develop a simple, clinically interpretable prediction model. A logistic regression-based indicator was constructed using the most contributory variables and validated internally and externally. Hypokalemia was defined as a serum potassium level <3.5 mmol/L. The model-building and external validation cohorts included 99 and 55 patients, respectively. Among multiple candidate models, a lightweight logistic regression model using only two variables, serum potassium level and insulin infusion rate per body weight, was selected for clinical applicability. In internal validation, the model demonstrated good discriminative performance (receiver operating characteristic-area under the curve [ROC-AUC] 0.821). When applied to the external validation cohort, the ROC-AUC was 0.655, and accuracy decreased slightly. A lower threshold may increase sensitivity in screening, whereas a higher threshold may improve specificity. In conclusion, this study presents a simple and clinically applicable indicator for predicting CII-related hypokalemia using only two routinely available variables at treatment initiation. This model supports individualized electrolyte monitoring during the acute management of hyperglycemic crises. Additionally, it may facilitate safer and more efficient clinical decision-making without reliance on complex algorithms.
SN - 1348-4540
SN - 0918-8959
ER -