中国骨伤2026，Vol.39Issue(8)：825-832,8.DOI:10.12200/j.issn.1003-0034.20260298
膝骨关节炎双疼痛维度变化差异的多层可解释性建模与分析
Multilevel interpretable modeling and analysis of changes in dual pain dimensions in knee osteoarthritis
摘要
Abstract
Objective Based on real-world clinical data,aimed to systematically characterize the key factors,decision-making pathways,and structural relationships influencing pain,and to investigate the differences and associated structural ef-fects of changes across two pain dimensions in patients with knee osteoarthritis(KOA).Methods Using the visual analog scale(VAS)and Traditional Chinese Medicine(TCM)pain symptom score as bimodal pain dimensions,XGBoost models were con-structed under a unified feature system.Multi-layer interpretability analysis was conducted through SHAP,rule extraction,and Bayesian networks to examine the observational data from 187 cases of KOA.Results The model identified age,disease dura-tion,body mass index(BMI),administration time and local joint symptoms as key factors influencing changes in the TCM pain symptom score,while baseline VAS and medication use were key factors for changes in the VAS.Decision path analysis re-vealed that the primary pathway for changes in TCM pain symptoms was"age＜69 years,BMI ≥23.94 kg·m-2,and joint swelling score＜4,"while the main pathway for VAS changes was"baseline VAS ≥ 6 and concurrent use of analgesics."Furthermore,the structural relationships between variables and the two pain dimensions were revealed.For example,under the condition of"age＜69 years,BMI ≥23.94 kg·m-2,and joint swelling score＜4",the conditional probability of a"significant change"in the TCM pain symptom score was higher than that in the VAS.Conclusion Under a unified model framework,an analytical approach for examining differential changes in related indicators was explored.Through multi-layered interpretability analysis encompassing"feature importance assessment-decision rule extraction-Bayesian network inference,"it was found that the dual pain dimen-sions share common influencing factors in reflecting pain changes in knee osteoarthritis,yet also exhibit structural association differences.These findings provide a reference basis for identifying pain change characteristics and selecting pain assessment tools in KO A patients,and offer a replicable methodological paradigm for similar analyses.关键词
机器学习/疼痛测量/多层可解释性/真实世界数据/膝骨关节炎Key words
Machine learning/Pain measurement/Multi-layered interpretability/Real-world data/Knee os-teoarthritis分类
医药卫生引用本文复制引用
韩嘉旭,彭叶辉,杨伟,吴孟洁,向兴华,田雅欣,唐德志..膝骨关节炎双疼痛维度变化差异的多层可解释性建模与分析[J].中国骨伤,2026,39(8):825-832,8.基金项目
中国中医科学院创新工程项目(编号:CI2023C066YLL （）
ZB2025014)Innovation Project of the China Academy of Chinese Medical Sciences(No.CI2023C066YLL （）
ZB2025014) （）
