1型糖尿病患儿酮症酸中毒风险预测模型的构建及验证

doi:10.3761/j.issn.2096-7446.2026.01.004

摘要/Abstract

摘要：

目的分析1型糖尿病（type 1 diabetes mellitus，T1DM）患儿发生酮症酸中毒的危险因素，通过决策树算法建立T1DM患儿酮症酸中毒的风险预测模型。方法回顾性分析2021年2月—2024年9月收治的218例T1DM患儿的临床资料，根据患儿是否发生酮症酸中毒将其分为酮症酸中毒组和非酮症酸中毒组，采用Logistic回归分析筛选T1DM患儿发生酮症酸中毒的危险因素，通过R语言构建预测T1DM患儿发生酮症酸中毒的随机森林模型，采用5折交叉验证法对模型进行内部验证，并对比模型的预测效能。结果该研究218例T1DM患儿中，有66例患儿发生了酮症酸中毒，酮症酸中毒发生率为30.28%；单因素分析结果显示，年龄、入院随机血糖、糖化血红蛋白、前驱感染、甲状腺功能等差异有统计学意义（P<0.05）；Logistic回归结果表明，年龄增加是T1DM患儿发生酮症酸中毒的保护因素，而入院随机血糖升高、糖化血红蛋白升高、有前驱感染、甲状腺功能异常是T1DM患儿发生酮症酸中毒的危险因素（P<0.05）；模型预测总体正确性为84.2%；内部验证显示，模型预测正确率为77.6%；随机森林模型预测T1DM患儿酮症酸中毒发生的AUC值与Logistic回归模型相近，两种模型均具有较好的预测效能。结论该研究构建的随机森林模型可预测T1DM患儿发生酮症酸中毒风险，有助于护理人员根据不同因素的重要性排序制订相应的护理干预策略。

关键词: 1型糖尿病, 患儿, 酮症酸中毒, 影响因素, 随机森林模型

Abstract:

Objective To analyze the risk factors of ketoacidosis in children with type 1 diabetes mellitus （T1DM），and establish a risk prediction model of ketoacidosis in children with T1DM by using decision tree algorithm. Methods The clinical data of 218 children with T1DM treated from February 2021 to September 2024 were retrospectively analyzed. The children were divided into ketoacidosis group and non-ketoacidosis group according to whether they had ketoacidosis. The risk factors of ketoacidosis in children with T1DM were screened by Logistic regression analysis. A random forest model for predicting ketoacidosis in children with T1DM was constructed using R language，and the model was internally verified by using 5-fold cross-validation method，and the prediction efficiency of the model was compared. Results Among 218 children with T1DM，66 cases had ketoacidosis，and the incidence of ketoacidosis was 30.28%. Univariate factor results showed that age，blood glucose at admission，glycated hemoglobin，preinfection，thyroid function had statistically differences（P<0.05）. The Logistic regression results indicated that increased age was a protective factor for ketoacidosis in children with T1DM，while random elevation of blood glucose at admission，elevated glycated hemoglobin，presence of propositional infection，and thyroid dysfunction were risk factors for ketoacidosis in children with T1DM（P<0.05）. The overall accuracy of the model prediction was 84.2%. Internal verification showed that the prediction accuracy of the model was 77.6%. The AUC value of random forest model in predicting the occurrence of ketoacidosis in children with T1DM was similar to that of Logistic regression model，and both models had better predictive efficacy. Conclusion The random forest model constructed in this study can predict the risk of developing ketoacidosis in children with T1DM，which is helpful for nursing staff to formulate corresponding nursing intervention strategies according to the importance of different factors.

Key words: Type 1 Diabetes Mellitus, Children, Ketoacidosis, Influencing Factors, Random Forest Model

赫连静靓, 张少华. 1型糖尿病患儿酮症酸中毒风险预测模型的构建及验证[J]. 中华急危重症护理杂志, 2026, 7(1): 30-35.

HELIAN Jingliang, ZHANG Shaohua. The development and validation of a risk prediction model for ketoacidosis in children with type 1 diabetes[J]. Chinese Journal of Emergency and Critical Care Nursing, 2026, 7(1): 30-35.

图/表 6

表1

表2

表3

图1

图2

图3

参考文献 19

[1]	Desai S, Deshmukh A. Mapping of type 1 diabetes mellitus[J]. Curr Diabetes Rev, 2020, 16(5):438-441. doi: 10.2174/1573399815666191004112647 pmid: 31584373
[2]	Akil AA, Yassin E, Al-Maraghi A, et al. Diagnosis and treatment of type 1 diabetes at the dawn of the personalized medicine era[J]. J Transl Med, 2021, 19(1):137. doi: 10.1186/s12967-021-02778-6 pmid: 33794915
[3]	Ješić MD, Ješić MM, StanisavljevićD, et al. Ketoacidosis at presentation of type 1 diabetes mellitus in children:a retrospective 20-year experience from a tertiary care hospital in Serbia[J]. Eur J Pediatr, 2013, 172(12):1581-1585. doi: 10.1007/s00431-013-2083-7 pmid: 23835857
[4]	American Diabetes Association Professional Practice Committee. 4. Comprehensive medical evaluation and assessment of comorbidities:standards of care in diabetes-2024[J]. Diabetes Care, 2024, 47(1):52-76. doi: 10.2337/dci23-0078
[5]	American Diabetes Association. 4. Comprehensive medical evaluation and assessment of comorbidities:standards of medical care in diabetes-2019[J]. Diabetes Care, 2019, 42(1):34-45.
[6]	陶雅辉, 房胜辉, 李文会. 糖尿病酮症酸中毒临床误诊分析[J]. 临床误诊误治, 2024, 37(14):10-13.
	Tao YH, Fang SH, Li WH. Analysis of clinical misdiagnosis of diabetic ketoacidosis[J]. Clin Misdiagn Misther, 2024, 37(14):10-13.
[7]	刘晨红, 赵英娜, 刘艳存, 等. 糖尿病患者酮症酸中毒危险因素的巢式病例对照研究[J]. 中华急危重症护理杂志, 2024, 5(9):773-778.
	Liu CH, Zhao YN, Liu YC, et al. A nested case-control study of risk factors for ketoacidosis in patients with diabetes mellitus[J]. Chin J Emerg Crit Care Nurs, 2024, 5(9):773-778.
[8]	Long B, Lentz S, Koyfman A, et al. Euglycemic diabetic ketoacidosis:Etiologies,evaluation,and management[J]. Am J Emerg Med, 2021, 44:157-160. doi: 10.1016/j.ajem.2021.02.015
[9]	Glaser N, Fritsch M, Priyambada L, et al. ISPAD clinical practice consensus guidelines 2022:Diabetic ketoacidosis and hyperglycemic hyperosmolar state[J]. Pediatr Diabetes, 2022, 23(7):835-856. doi: 10.1111/pedi.v23.7
[10]	王晓佳, 龚爱红, 齐晟宏, 等. 儿童青少年1型糖尿病患儿发生酮症酸中毒的危险因素分析及预测模型的建立[J]. 中国当代儿科杂志, 2024, 26(1):62-66.
	Wang XJ, Gong AH, Qi SH, et al. Risk factors for ketoacidosis in children/adolescents with type 1 diabetes mellitus and establishment of a predictive model[J]. Chin J Contemp Pediatr, 2024, 26(1):62-66.
[11]	中华医学会儿科学分会内分泌遗传代谢学组, 中华儿科杂志编辑委员会. 中国儿童1型糖尿病标准化诊断与治疗专家共识(2020版)[J]. 中华儿科杂志, 2020, 58(6):447-454.
	Endocrine Genetics and Metabolism Group of Pediatrics Branch of Chinese Medical Association, the Editorial Board of Chinese Journal of Pediatrics. Expert consensus on the standardized diagnosis and management of type 1 diabetes mellitus in Chinese children(2020)[J]. Chin J Pediatr, 2020, 58(6):447-454.
[12]	中华医学会儿科学分会内分泌遗传代谢学组, 《中华儿科杂志》编辑委员会. 巩纯秀. 儿童糖尿病酮症酸中毒诊疗指南(2009年版)[J]. 中华儿科杂志, 2009, 47(6):421-425.
	The Subspecialty Group of Endocrinologic,Hereditary and Metabolic Diseases, The Society of Pediatrics, Chinese Medical Association; The Editorial Board of Chinese Journal of Pediatrics; Gong CX. Guidelines for the diagnosis and management of diabetic ketoacidosis in children and adolescents(2009)[J]. Chin J Pediatr, 2009, 47(6):421-425.
[13]	Cherubini V, Grimsmann JM, Åkesson K, et al. Temporal trends in diabetic ketoacidosis at diagnosis of paediatric type 1 diabetes between 2006 and 2016:results from 13 countries in three continents[J]. Diabetologia, 2020, 63(8):1530-1541. doi: 10.1007/s00125-020-05152-1
[14]	曹冰燕, 巩纯秀. 重视糖尿病酮症酸中毒的识别和规范诊治[J]. 中华全科医师杂志, 2023, 22(7):676-681.
	Cao BY, Gong CX. Attaching importance to the identification,standardized diagnosis and treatment of diabetic ketoacidosis in children[J]. Chin J Gen Pract, 2023, 22(7):676-681.
[15]	Ehrmann D, Kulzer B, Roos T, et al. Risk factors and prevention strategies for diabetic ketoacidosis in people with established type 1 diabetes[J]. Lancet Diabetes Endocrinol, 2020, 8(5):436-446. doi: 10.1016/S2213-8587(20)30042-5
[16]	王静, 刘莉, 程安娜, 等. 儿童糖尿病酮症酸中毒的临床特征及相关影响因素分析[J]. 临床儿科杂志, 2024, 42(4):333-338.
	Wang J, Liu L, Cheng AN, et al. Analysis of clinical features and related influencing factors of diabetic ketoacidosis in children[J]. J Clin Pediatr, 2024, 42(4):333-338.
[17]	王瑞晔, 王丽敏, 王金雪, 等. 儿童糖尿病酮症酸中毒危险因素的研究进展[J]. 糖尿病新世界, 2024, 27(10):190-194.
	Wang RY, Wang LM, Wang JX, et al. Research progress on risk factors of diabetic ketoacidosis in children[J]. Diabetes New World, 2024, 27(10):190-194.
[18]	范言诗, 丁曙霞, 谢晓恬. 儿童1型糖尿病合并酮症酸中毒的临床特征分析[J]. 现代实用医学, 2022, 34(2):231-234.
	Fan YS, Ding SX, Xie XT. Clinical characteristics of type 1 diabetes mellitus complicated with ketoacidosis in children[J]. Mod Pract Med, 2022, 34(2):231-234.
[19]	周晓燕, 魏申奥, 卢曼曼. 基于Lasso-logistic回归和随机森林模型的癌症患者抑郁影响因素分析[J]. 安徽医学, 2024, 45(9):1177-1182.
	Zhou XY, Wei SA, Lu MM. Analysis of influencing factors of depression in cancer patients based on Lasso-logistic regression and random forest model[J]. Anhui Med J, 2024, 45(9):1177-1182.