Department of Anesthesia, Huashan Hospital, Fudan University, Shanghai, China.
Health Consultation and Physical Examination Center, Zhongshan Hospital, Fudan University, Shanghai, China.
CNS Neurosci Ther. 2023 Jan;29(1):181-191. doi: 10.1111/cns.13993. Epub 2022 Oct 18.
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.
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.
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.
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.
低钾血症是颅脑外伤后的常见并发症，可能使治疗复杂化，并导致不良预后。在入院第一天识别低钾血症风险患者有助于实施预防治疗，减少并发症，改善预后。
本多中心回顾性研究于 2017 年 1 月至 2020 年 12 月期间使用颅脑外伤患者的电子病历进行。采用倾向评分匹配方法，采用 1:1 的比例，以克服亚组分析中的过度拟合和数据不平衡。应用 5 种机器学习算法生成最佳预测模型，以预测住院期间低钾血症。采用内部 5 折交叉验证和外部验证来证明其可解释性和泛化性。
共纳入 4445 例 TBI 患者进行分析和模型生成。低钾血症的发生率为 46.55%，轻度、中度和重度低钾血症的发生率分别为 32.06%、12.69%和 1.80%。低钾血症与死亡率增加相关，而重度低钾血症的影响更大。逻辑回归算法在预测血清钾降低和中重度低钾血症方面表现最佳，其 AUC 分别为 0.73±0.011 和 0.74±0.019。该预测模型进一步通过包括我们之前发表的数据和开放评估的医疗信息重症监护数据库在内的两个外部数据集进行验证。线性校准曲线显示无统计学差异（p>0.05），具有完美的预测效果。
颅脑外伤后低钾血症的发生可通过入院第一天的记录和机器学习算法进行预测。逻辑回归算法在内部和外部验证中均表现出最佳的预测性能。
Zotero 插件
