基于生物电阻抗与决策树模型的学龄前儿童超重肥胖筛查与亚型识别研究

马瑞; 沈张逸霏; 陆乐; 唐锦阳

doi:10.11852/zgetbjzz2025-0336

PDF(2495 KB)

中国儿童保健杂志 ›› 2025, Vol. 33 ›› Issue (10) : 1114-1120. DOI: 10.11852/zgetbjzz2025-0336

儿童代谢性疾病专栏

基于生物电阻抗与决策树模型的学龄前儿童超重肥胖筛查与亚型识别研究

马瑞, 沈张逸霏, 陆乐, 唐锦阳

作者信息 +

Screening and subtype identification of overweight and obesity in preschool children based on bioelectrical impedance analysis and decision tree modeling

MA Rui, SHEN Zhangyifei, LU Le, TANG Jinyang

Author information +

文章历史 +

摘要

目的基于生物电阻抗技术(BIA)与决策树模型,构建肥胖亚型分类规则,旨在识别学龄前儿童超重肥胖的敏感指标及其亚型特征,为精准干预提供依据。方法于2024年3—12月采用方便抽样选取上海市550名3~6岁学龄前儿童,通过INBODY J30测定身体成分指标,对比BMI与体脂百分比(PBF)的肥胖检出差异;通过共线性分析筛选出关键变量,采用CRT决策树构建亚型分类规则,并借助XGboost评估特征重要性,通过10折交叉验证模型的稳健性。结果 BMI标准超重肥胖检出率为26.5%,而PBF标准为21.78%。体成分分析显示,超重肥胖儿童与正常体重儿童有29项指标存在显著差异,通过逐步回归分析解决变量间的共线性问题,保留10项变量进入决策树模型构建。基于CRT算法生成的决策树包含17个节点(9个终端节点),将超重肥胖分为三型:下肢脂肪主导型(节点10)、骨骼肌质量低下型(节点16)和高肌肉量型(节点11),模型总体准确率达97.5%。结论基于BIA与决策树的多维筛查模型可精准识别学龄前儿童超重肥胖亚型,研究提出的亚型分类框架为制定差异化干预策略提供参考和依据,对优化儿童肥胖早期防控措施具有重要实践价值。

Abstract

Objective To develop a classification framework for overweight/obesity subtypes based on bioelectrical impedance analysis (BIA) and decision tree modeling, with the goal of identifying sensitive indicators and characteristic features of overweight/obesity subtypes among preschool children, so as to provide a basis for targeted interventions. Methods A convenience sample of 550 preschool children aged 3 - 6 years was recruited in Shanghai from March to December 2024.Body composition was measured using the INBODY J30 device.Differences in obesity detection between body mass index (BMI) and percent body fat (PBF) were compared.Key variables were selected through collinearity analysis.A classification and regression tree (CRT) algorithm was applied to construct subtype classification rules.Feature importance was evaluated using XGBoost, and model robustness was assessed via 10-fold cross-validation. Results The detection rate of overweight/obesity was 26.5% based on BMI criteria and 21.78% based on PBF criteria.Body composition analysis revealed 29 indicators that significantly differed between overweight/obese and normal-weight children.Stepwise regression was used to address multicollinearity, resulting in 10 variables being included in the decision tree model.The CRT-generated tree contained 17 nodes (9 terminal nodes) and classified obesity into three subtypes: lower-body fat-dominant (Node 10), low skeletal muscle mass (Node 16), and high muscle mass (Node 11).The overall accuracy of the model reached 97.5%. Conclusions A multidimensional screening model integrating BIA and decision tree analysis can accurately identify overweight/obesity subtypes in preschool children.The proposed subtype classification framework offers valuable insights for developing differentiated intervention strategies and has practical significance for optimizing early prevention and control measures for childhood obesity.

导出引用

马瑞, 沈张逸霏, 陆乐, 唐锦阳. 基于生物电阻抗与决策树模型的学龄前儿童超重肥胖筛查与亚型识别研究[J]. 中国儿童保健杂志. 2025, 33(10): 1114-1120 https://doi.org/10.11852/zgetbjzz2025-0336

MA Rui, SHEN Zhangyifei, LU Le, TANG Jinyang. Screening and subtype identification of overweight and obesity in preschool children based on bioelectrical impedance analysis and decision tree modeling[J]. Chinese Journal of Child Health Care. 2025, 33(10): 1114-1120 https://doi.org/10.11852/zgetbjzz2025-0336

中图分类号： R179

参考文献

[1] 中国居民营养与慢性病状况报告(2020年)[J].营养学报,2020,42(6):521.
Report on the status of nutrition and chronic diseases in Chinese residents[J].Acta Nutriologica Sinica,2020,20,42(6):521.(in Chinese)
[2] 国家卫生健康委.关于印发“体重管理年”活动实施方案的通知[EB/OL].(2024-06-06)[2025-03-12].https://www.gov.cn/zhengce/zhengceku/202406/content_6959543.htm.
[3] Dietz WH.Critical periods in childhood for the development of obesity[J].Am J Clin Nutr,1994,59:955-959.
[4] 马冠生,米杰,马军.中国儿童肥胖报告[M].北京:人民卫生出版社:14,2021.
[5] Gardner DS, Hosking J, Metcalf BS,et al.Contribution of early weight gain to childhood overweight and metabolic health: A longitudinal study (EarlyBird 36)[J].Pediatrics, 2009,123, e67-e73.
[6] Cunningham SA, Kramer MR, Narayan KM.Incidence of childhood obesity in the United States[J].N.Engl.J.Med.2014,370, 403-411.
[7] Geserick M, Vogel M, Gausche R,et al.Acceleration of BMI in early childhood and risk of sustained obesity[J].N Engl J Med, 2018,379(14), 1303-1312.
[8] 国家卫生健康委办公厅.肥胖症诊疗指南(2024版)[EB/OL].(2024-10-12)[2025-3-12].https://www.gov.cn/zhengce/zhengceku/202410/content_6981734.htm.
[9] 李辉,季成叶,宗心南,等.中国0~18岁儿童、青少年体块指数的生长曲线[J].中华儿科杂志,2009,47(7):493-498.
Li H, Ji CY, Zong XN, et al.Growth curve of body mass index in Chinese children and adolescents aged 0 - 18 years[J].Chin J Pediatr,2009,47(7):493-498.(in Chinese)
[10] Kyle UG, Bosaeus I, De Lorenzo AD,et al.Bioelectrical impedance analysis—part I: Review of principles and methods[J].Clin Nutri,2004, 23(5), 1226-1243.
[11] Kim HS, Park SY, Kim HJ.Validation of InBody 770 for body composition analysis in children and adolescents[J].J Pedia Endo and Meta, 2020,33(5), 623-631.
[12] 李子奈,潘文卿.计量统计学[M].5版.北京:高等教育出版社,2020.
[13] Tchoukalova YD, Votruba SB, Tchkonia T, et al.Regional differences in cellular mechanisms of adipose tissue gain with overfeeding[J].Proc Natl Acad Sci USA,2010, 107: 18226-18231.
[14] 刘娟.不同智力障碍程度儿童BMI水平与基本动作技能关系研究[J].石家庄学院学报,2024,26(6):113-119.
Liu J.Research on the Relationship between BMI levels and basic motor skills in children with different degrees of intellectual disability[J].Journal of Shijiazhuang University,2024,26(6):113-119.(in Chinese)
[15] 中华医学会儿科学分会内分泌遗传代谢学组, 中华医学会儿科学分会儿童保健学组, 中华医学会儿科学分会临床营养学组, 等.中国儿童肥胖诊断评估与管理专家共识[J].中华儿科杂志, 2022, 60(6): 507-515.
Endocrinology, Genetics and Metabolism Group, Pediatrics Branch of Chinese Medical Association, Child Health Care Group, Pediatrics Branch of Chinese Medical Association, Clinical Nutrition Group, Pediatrics Branch of Chinese Medical Association, etc.Expert consensus on diagnosis, evaluation and management of childhood obesity in China[J].Chin J Pediatr, 2022, 60(6): 507-515.(in Chinese)
[16] Gyllenhammer LE, Alderete TL, Toledo-Corral CM, et al.Saturation of subcutaneous adipose tissue expansion and accumulation of ectopic fat associated with metabolic dysfunction during late and post-pubertal growth[J].Int J Obes,2016,40(4):601-606.
[17] 曹棨,米佳.生长激素与脂肪组织及脂肪因子的关系研究[J].检验医学与临床,2020,17(13):1939-1942,1948.
Cao Q, Mi J.Study on the relationship between growth hormone and adipose tissue and adipokine[J].Laboratory Medicine & Clinic, 2020,17(13):1939-1942,1948.(in Chinese)
[18] 范艳芝,乔玉成.运动辅助治疗幼儿肥胖减肥效果的系统分析[J].吉林体育学院学报,2019,35(2):75-80.
Fan YZ, Qiao YC.Systematic analysis of the weight loss effect of exercise-assisted therapy for childhood obesity[J].Journal of Jilin Institute of Physical Education,2019,35(2):75-80.(in Chinese)
[19] 方柯红,吕烨,张玲玲,等.学龄前儿童进食速度和咀嚼程度与超重肥胖关系的研究[J].中国食物与营养,2025,31(8):75-79.
Fang KH, Lu Y, Zhang LL, et al.Research on the relationship between eating speed, chewing degree and overweight and obesity in preschool children[J].Chinese Food and Nutrition,2025,31(8):75-79.(in Chinese)
[20] 李望,陈培友,吴志建,等.以家庭为基础的运动干预对学龄前儿童超重肥胖影响的Meta分析[J].中国儿童保健杂志,2025,33(2):214-220.
Li W, Chen PY, Wu ZJ, et al.Meta-analysis of the impact of family-based exercise intervention on overweight and obesity in preschool children[J].Chin J Child Health Care,2025,33(2):214-220.(in Chinese)
[21] 张变子,雷昱,马雪文,等.学龄前肥胖儿童的影响因素及干预研究进展[J].全科护理,2024,22(15):2810-2813.
Zhang BZ, Lei Y, Ma XW, et al.Research progress on influencing factors and intervention of obese preschool children[J].General Practice Nursing,2024,22(15):2810-2813.(in Chinese)
[22] 刘妍慧, 陈树春.2022年欧洲临床营养与代谢学会和欧洲肥胖研究学会《肌肉减少性肥胖的定义和诊断标准共识》解读及启示[J].中国全科医学, 2023, 26(12): 1422-1428.
Liu YH, Chen SC.Interpretation and implications of the Consensus on the definition and diagnostic criteria of muscle-reducing obesity issued by the European Society for Clinical Nutrition and Metabolism and the European Society for Obesity Research in 2022[J].Chinese Journal of General Medicine, 2023, 26(12): 1422-1428.(in Chinese)
[23] Lurz E,Patel H,Lebovic G,et al.Paediatric reference val-ues for total psoas muscle area[J].J Cachexia Sarcopenia Muscle,2020,11(2):405-414.
[24] Sack C,Ferrari N,Friesen D,et al.Health risks of sar-copenic obesity in overweight children and adolescents:Data from the CHILT Ⅲ Programme(Cologne)[J].J Clin Med,2022,11(1):277.
[25] 邹亦飞,杨一卓,郭建军.儿童肌少症评估方法研究进展[J].中国儿童保健杂志,2024,32(8):891-896.
Zou YF, Yang YZ, GUO JJ.Research progress of evaluation methods for sarcopenia in children[J].Chin J Child Health Care, 2024,32(8):891-896.(in Chinese)
[26] Gatjens I,Schmidt SCE,Plachta-Danielzik S,et al.Body composition characteristics of a load-capacity model:Age-dependent and sex-specific percentiles in 5-to 17-year-old children[J].Obes Facts,2021,14(6):593-603.
[27] Yang B,Tang C,Shi Z,et al.Association of macronutri-ents intake with body composition and sarcopenic obesity inchildren and adolescents:A population-based analysis of the national health and nutrition examination survey(NHANES)2011-2018[J].Nutrition,2023,15(10):2307.
[28] 赵玮婷,付欢欢,戴慧敏.3～6岁超重肥胖儿童血清维生素A、D水平研究[J].中国初级卫生保健,2025,39(4):44-47.
Zhao WT, Fu HH, Dai HM.Study on serum vitamin A and D levels in overweight and obese children aged 3-6 years[J].Primary Health Care in China, 25,39(4):44-47.(in Chinese)
[29] 师亚楠,燕武,曹梦瑶,等.南京地区3~16岁儿童青少年颈围的参照标准值及其评估腹型肥胖准确性的横断面调查[J].中国循证儿科杂志, 2023, 18(5): 334-340.
Shi YN, Yan W, Cao MY, et al.A cross-sectional survey on the reference standard values of neck circumference and its Accuracy in evaluating abdominal obesity among children and adolescents aged 3 - 16 in Nanjing area[J].Chin J Evid Based Pediatr, 2023, 18(5): 334-340.(in Chinese)
[30] 冯建荣,王凌娟.体能训练联合寒冷刺激对幼儿免疫和肥胖的影响[J].中国学校卫生,2020,41(11):1734-1736.
Feng JR, Wang LJ.The influence of physical training combined with cold stimulation on the immunity and obesity of young children[J].Chin J Sch Health,2020,41(11):1734-1736.(in Chinese)