文献速递消化、代谢与肾脏急症重症综合管理与镇静镇痛

基于机器学习的糖尿病酮症酸中毒患者个体化血糖管理

[Personalized glycemic management for patients with diabetic ketoacidosis based on machine learning].
PubMed 文献 · Zhonghua Wei Zhong Bing Ji Jiu Yi Xue · 2024-01-01
一句话结论基于MIMIC-IV数据库的机器学习模型可预测DKA患者低血糖、低钾血症、GCS下降和住院延长,并据此个体化推荐血糖下降速率范围。

该研究利用MIMIC-IV数据库中2008至2019年贝斯以色列女执事医疗中心ICU收治的2096例DKA患者数据,构建机器学习模型预测低血糖、低钾血症、GCS评分下降和住院时间延长四种不良结局,ROC曲线下面积分别为0.826、0.850、0.925和0.901。分析血糖下降速率与不良结局风险的关系发现,最大血糖下降速率>6.26 mmol×L-1×h-1显著增加低血糖风险(P<0.001),>2.72 mmol×L-1×h-1显著升高低钾血症风险(P<0.001),>5.53 mmol×L-1×h-1显著降低GCS评分下降风险(P<0.001),>8.03 mmol×L-1×h-1显著缩短住院时间(P<0.001)。多因素Logistic回归显示最高碳酸氢盐水平、血尿素氮水平和总胰岛素剂量与低钾血症风险显著相关(均P<0.01)。作者提出个体化最优血糖下降阈值:降低低钾血症和低血糖风险应≤min{x1, x2},降低GCS下降和住院延长风险应≥max{x3, x4},两范围重叠时即为推荐最优血糖下降区间,不重叠时需结合个体差异动态调整。

要点

  • 最大血糖下降速率>2.72 mmol×L-1×h-1显著升高低钾血症风险(P<0.001),>6.26 mmol×L-1×h-1显著增加低血糖风险(P<0.001)。
  • 最大血糖下降速率>5.53 mmol×L-1×h-1显著降低GCS评分下降风险(P<0.001),>8.03 mmol×L-1×h-1显著缩短住院时间(P<0.001)。
  • 机器学习模型预测低血糖、低钾血症、GCS下降和住院延长的AUROC分别为0.826(95%CI 0.803-0.849)、0.850(95%CI 0.828-0.870)、0.925(95%CI 0.903-0.946)和0.901(95%CI 0.883-0.920)。
  • 多因素Logistic回归显示最高碳酸氢盐水平、血尿素氮水平和总胰岛素剂量与低钾血症风险显著相关(均P<0.01)。
  • 作者提出的个体化血糖下降速率推荐:降低低钾血症和低血糖风险应≤min{x1, x2},降低GCS下降和住院延长风险应≥max{x3, x4};两范围重叠时取交集为最优区间,不重叠时需结合个体差异动态调整。

适用人群与场景

  • 2008至2019年贝斯以色列女执事医疗中心ICU收治的糖尿病酮症酸中毒(DKA)患者,共2096例(MIMIC-IV数据库)。

研究设计与关键结果

  • 研究类型:基于MIMIC-IV数据库的机器学习建模研究,样本量2096例DKA患者,数据来自贝斯以色列女执事医疗中心2008至2019年ICU收治病例。
  • 机器学习模型预测低血糖、低钾血症、GCS评分下降和住院时间延长的AUROC(95%CI)分别为0.826(0.803-0.849)、0.850(0.828-0.870)、0.925(0.903-0.946)和0.901(0.883-0.920)。
  • 最大血糖下降速率>6.26 mmol×L-1×h-1显著增加低血糖风险(P<0.001);>2.72 mmol×L-1×h-1显著升高低钾血症风险(P<0.001);>5.53 mmol×L-1×h-1显著降低GCS评分下降风险(P<0.001);>8.03 mmol×L-1×h-1显著缩短住院时间(P<0.001)。
  • 多因素Logistic回归分析显示最高碳酸氢盐水平、血尿素氮水平和总胰岛素剂量与低钾血症风险显著相关(均P<0.01)。
  • 作者提出的个体化最优血糖下降阈值:降低低钾血症和低血糖风险应≤min{x1, x2},降低GCS评分下降和住院延长风险应≥max{x3, x4};当max{x3, x4}≤min{x1, x2}时该区间为推荐最优血糖下降范围;当max{x3, x4}>min{x1, x2}时需结合个体差异动态调整治疗策略。

证据类型、等级与局限

  • 证据类型:基于MIMIC-IV数据库的机器学习建模研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 机器学习模型在预测DKA患者低血糖、低钾血症、GCS评分下降和住院时间延长方面表现良好,作者认为有助于个体化血糖管理并具有重要临床应用前景。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开

OBJECTIVE: To explore the optimal blood glucose-lowering strategies for patients with diabetic ketoacidosis (DKA) to enhance personalized treatment effects using machine learning techniques based on the United States Critical Care Medical Information Mart for Intensive Care- IV (MIMIC- IV).

METHODS: Utilizing the MIMIC- IV database, the case data of 2 096 patients with DKA admitted to the intensive care unit (ICU) at Beth Israel Deaconess Medical Center from 2008 to 2019 were analyzed. Machine learning models were developed, and receiver operator characteristic curve (ROC curve) and precision-recall curve (PR curve) were plotted to evaluate the model's effectiveness in predicting four common adverse outcomes: hypoglycemia, hypokalemia, reductions in Glasgow coma scale (GCS), and extended hospital stays. The risk of adverse outcomes was analyzed in relation to the rate of blood glucose decrease. Univariate and multivariate Logistic regression analyses were conducted to examine the relationship between relevant factors and the risk of hypokalemia. Personalized risk interpretation methods and predictive technologies were applied to individualize the analysis of optimal glucose control ranges for patients.

RESULTS: The machine learning models demonstrated excellent performance in predicting adverse outcomes in patients with DKA, with areas under the ROC curve (AUROC) and 95% confidence interval (95%CI) for predicting hypoglycemia, hypokalemia, GCS score reduction, and extended hospital stays being 0.826 (0.803-0.849), 0.850 (0.828-0.870), 0.925 (0.903-0.946), and 0.901 (0.883-0.920), respectively. Analysis of the relationship between the rate of blood glucose reduction and the risk of four adverse outcomes showed that a maximum glucose reduction rate > 6.26 mmol×L-1×h-1 significantly increased the risk of hypoglycemia (P < 0.001); a rate > 2.72 mmol×L-1×h-1 significantly elevated the risk of hypokalemia (P < 0.001); a rate > 5.53 mmol×L-1×h-1 significantly reduced the risk of GCS score reduction (P < 0.001); and a rate > 8.03 mmol×L-1×h-1 significantly shortened the length of hospital stay (P < 0.001). Multivariate Logistic regression analysis indicated significant correlations between maximum bicarbonate levels, blood urea nitrogen levels, and total insulin doses with the risk of hypokalemia (all P < 0.01). In terms of establishing personalized optimal treatment thresholds, assuming optimal glucose reduction thresholds for hypoglycemia, hypokalemia, GCS score reduction, and extended hospital stay were x1, x2, x3, x4, respectively, the recommended glucose reduction rates to minimize the risks of hypokalemia and hypoglycemia should be ≤min{x1, x2}, while those to reduce GCS score decline and extended hospital stay should be ≥ max{x3, x4}. When these ranges overlap, i.e., max{x3, x4} ≤ min{x1, x2}, this interval was the recommended optimal glucose reduction range. If there was no overlap between these ranges, i.e., max{x3, x4} > min{x1, x2}, the treatment strategy should be dynamically adjusted considering individual differences in the risk of various adverse outcomes.

CONCLUSIONS: The machine learning models shows good performance in predicting adverse outcomes in patients with DKA, assisting in personalized blood glucose management and holding important clinical application prospects.

来源:Zhonghua Wei Zhong Bing Ji Jiu Yi Xue,查看原文。版权归原作者所有。

参考来源

  1. Wang R, Wu L, Li H, et al. [Personalized glycemic management for patients with diabetic ketoacidosis based on machine learning]. Zhonghua Wei Zhong Bing Ji Jiu Yi Xue. 2024. PMID: 38991964. doi:10.3760/cma.j.cn121430-20240130-00096

供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。