比较决策树与logistic回归模型对老年股骨粗隆间骨折患者术后脑梗死风险的预测效能

doi:10.3969/j.issn.1006-5725.2026.08.023

Abstract

Abstract:

Objective To analyze the risk factors for cerebral infarction after surgery for intertrochanteric fracture of the femur （IFF） among elderly patients and establish a decision-tree risk prediction model， so as to provide a scientific theoretical basis for clinical medical staff to formulate targeted prevention and treatment plans. Methods Clinical data of 215 elderly patients who underwent surgery for IFF at our hospital from November 2017 to December 2023 were retrospectively selected. The patients were divided into the cerebral infarction group and the non-cerebral infarction group according to the postoperative occurrence of cerebral infarction. Univariate and multivariate logistic regression analyses were conducted to identify the risk factors for cerebral infarction after IFF surgery in elderly patients. A decision tree model and logistic regression were utilized to construct a risk prediction model， and the predictive values of both models for cerebral infarction after IFF surgery were compared. Results Among the 215 elderly patients who underwent surgery for IFF， 61 suffered from cerebral infarction post-operatively， with an incidence rate of 28.37%. Multivariate logistic regression analysis indicated that hypertension， diabetes， the duration of hospital bed rest， homocysteine， and D-dimer were risk factors for cerebral infarction after IFF surgery in elderly patients， while quality nursing was identified as a protective factor （P < 0.05）. A decision tree model was constructed based on these risk factors， with diabetes， the duration of hospital bed rest， Hcy， D-D， and quality nursing selected as explanatory variables. The model had a total of 4 layers and 15 nodes. The duration of hospital bed rest was the most significant influencing factor for cerebral infarction after IFF surgery in elderly patients. The area under the curve （AUC） value of the decision tree model for cerebral infarction after IFF surgery in elderly patients was 0.964 （95%CI： 0.930 - 0.985）， whereas the AUC value of the logistic regression model was 0.896 （95%CI： 0.847 - 0.933）. The DeLong test result for the two models was Z = 3.401， P = 0.000 7. Conclusions Hypertension， diabetes， the duration of hospital bed rest， Hcy， and D-D are identified as risk factors for cerebral infarction after IFF surgery in elderly patients， while quality nursing is recognized as a protective factor. The decision tree risk prediction model constructed based on these risk factors demonstrates significantly higher predictive efficacy compared to the logistic regression model.

Key words: decision tree model, logistic regression model, elderly intertrochanteric femoral fracture, cerebral infarction, influencing factors

CLC Number:

R473.6

Hongyu WU,Yupeng WU,Shaojuan HUANG,Suzhen HUANG,Yingjie HOU,Yi YANG,Zhirong ZHANG,Qingxi LI,Zhixin WU. Risk prediction of postoperative cerebral infarction in elderly patients with intertrochanteric femoral fracture： A comparative study of decision tree and logistic regression model[J]. The Journal of Practical Medicine, 2026, 42(8): 1471-1478.

Figures/Tables 9

Tab.1

Tab.2

Tab.3

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Tab.4

References 28

[1]	KIM K， WOO S， KIM S H， et al. The prediction model of non-suicidal self-injury in psychiatric patients using decision tree analysis［J］. Yonsei Med J， 2024， 65（3）： 137-147. doi：10.3349/ymj.2023.0129 . doi: 10.3349/ymj.2023.0129
[2]	POLAT G， BAYRAM S， GÖKÇEOĞLU Y S， et al. The effect of bone morphology on fracture type and treatment result in patients with intertrochanteric femur fracture aged over 65 year［J］. Ulus Travma Acil Cerrahi Derg， 2022， 28（12）： 1731-1738. doi：10.14744/tjtes.2022.57400 . doi: 10.14744/tjtes.2022.57400
[3]	MENG Y， LIU Y， FU M， et al. Clinical characteristics of elderly hip fracture patients with chronic cerebrovascular disease and construction of a clinical predictive model for perioperative pneumonia［J］. Orthop Traumatol Surg Res， 2024， 110（3）： 103821. doi：10.1016/j.otsr.2024.103821 . doi: 10.1016/j.otsr.2024.103821
[4]	COSTA A， PAIS M， LOUREIRO J， et al. Decision tree-based classification as a support to diagnosis in the Alzheimer's disease continuum using cerebrospinal fluid biomarkers： Insights from automated analysis［J］. Braz J Psychiatry， 2022， 44（4）： 370-377. doi：10.47626/1516-4446-2021-2277 . doi: 10.47626/1516-4446-2021-2277
[5]	TOYODA H， TERAI H， YAMADA K， et al. A decision tree analysis to predict clinical outcome of minimally invasive lumbar decompression surgery for lumbar spinal stenosis with and without coexisting spondylolisthesis and scoliosis［J］. Spine J， 2023， 23（7）： 973-981. doi：10.1016/j.spinee.2023.01.023 . doi: 10.1016/j.spinee.2023.01.023
[6]	PEDUZZI P， CONCATO J， KEMPER E， et al. A simulation study of the number of events per variable in logistic regression analysis［J］. J Clin Epidemiol， 1996， 49（12）： 1373-1379. doi：10.1016/s0895-4356（96）00236-3 . doi: 10.1016/s0895-4356（96）00236-3
[7]	LIU L， LI Z， ZHOU H， et al. Chinese Stroke Association guidelines for clinical management of ischaemic cerebrovascular diseases： Executive summary and 2023 update［J］. Stroke Vasc Neurol， 2023， 8（6）： e3. doi：10.1136/svn-2023-002998 . doi: 10.1136/svn-2023-002998
[8]	ZHANG T， ZHAO Y N， NIU Z X， et al. Analysis of risk factors for readmission in elderly patients with hip fractures undergoing hip hemiarthroplasty［J］. China J Orthop Traumatol， 2022， 35（5）： 460-463. doi：10.12200/j.issn.1003-0034.2022.05.010 . doi: 10.12200/j.issn.1003-0034.2022.05.010
[9]	YUAN J， ZHU G， ZHAO Y， et al. Effect of hip fracture on prognosis of acute cerebral infarction［J］. Clinics， 2021， 76： e3059. doi：10.6061/clinics/2021/e3059 . doi: 10.6061/clinics/2021/e3059
[10]	ZHANG Y， FU M， GUO J， et al. Characteristics and perioperative complications of hip fracture in the elderly with acute ischemic stroke： A cross-sectional study［J］. BMC Musculoskelet Disord， 2022， 23（1）： 642. doi：10.1186/s12891-022-05585-2 . doi: 10.1186/s12891-022-05585-2
[11]	RAJEEV V， FANN D Y， DINH Q N， et al. Pathophysiology of blood brain barrier dysfunction during chronic cerebral hypoperfusion in vascular cognitive impairment［J］. Theranostics， 2022， 12（4）： 1639-1658. doi：10.7150/thno.68304 . doi: 10.7150/thno.68304
[12]	KHANDELWAL S， LANE N E. Osteoporosis： Review of etiology， mechanisms， and approach to management in the aging population［J］. Endocrinol Metab Clin North Am， 2023， 52（2）： 259-275. doi：10.1016/j.ecl.2022.10.009 . doi: 10.1016/j.ecl.2022.10.009
[13]	CZERWINSKI E， CARDONA J， PLEBANSKI R， et al. The efficacy and safety of abaloparatide-SC in men with osteoporosis： A randomized clinical trial［J］. J Bone Miner Res， 2022， 37（12）： 2435-2442. doi：10.1002/jbmr.4719 . doi: 10.1002/jbmr.4719
[14]	钟智荣，俞志茹，钟智华，等. 股骨粗隆间骨折患者术后并发心脑血管疾病风险因素分析［J］. 当代护士（上旬刊）， 2023， 30（1）： 66-69. doi：10.19791/j.cnki.1006-6411.2023.01.018 . doi: 10.19791/j.cnki.1006-6411.2023.01.018
[15]	应金萍，蔡根莲，项雪佳，等. 维持性血液透析患者并发脑梗死的危险因素分析［J/OL］. 中华危重症医学杂志（电子版）， 2021， 14（3）： 206-212. doi：10.3877/cma.j.issn.1674-6880.2021.03.006 . doi: 10.3877/cma.j.issn.1674-6880.2021.03.006
[16]	牛稳，邱晓晖，刘艺超. 颈动脉粥样硬化狭窄的血管周围脂肪密度与脑梗死之间的关系［J］. 实用医学杂志， 2023， 39（1）： 103-108.doi：10.3969/j.issn.1006-5725.2023.01.018 . doi: 10.3969/j.issn.1006-5725.2023.01.018
[17]	黄慧，苏金虎，吴冰. 不同降压水平对老年高血压患者复合心血管事件的影响［J］. 实用医学杂志， 2023， 39（17）： 2225-2229. doi：10.3969/j.issn.1006-5725.2023.17.013 . doi: 10.3969/j.issn.1006-5725.2023.17.013
[18]	JIA H， HUANG B， KANG L， et al. Preoperative and intraoperative risk factors of postoperative stroke in total aortic arch replacement and stent elephant trunk implantation［J］. EClinicalMedicine， 2022， 47： 101416. doi：10.1016/j.eclinm.2022.101416 . doi: 10.1016/j.eclinm.2022.101416
[19]	孔静渊，郭巧云. 急性脑梗塞发病的危险因素及急性脑梗塞与凝血酶激活纤溶抑制物的相关性分析［J］. 血栓与止血学， 2022， 28（2）： 230-232. doi：10.3969/j.issn.1009-6213.2022.02.022 . doi: 10.3969/j.issn.1009-6213.2022.02.022
[20]	LAURETTA M P， MELOTTI R M， SANGERMANO C， et al. Homocysteine plasmatic concentration in brain-injured neurocritical care patients： Systematic review of clinical evidence［J］. J Clin Med， 2022， 11（2）： 394. doi：10.3390/jcm11020394 . doi: 10.3390/jcm11020394
[21]	蒋兴亮，刘素兰，易婷婷. 高同型半胱氨酸血症患者氧化应激指标的研究［J］. 检验医学， 2014， 29（2）： 125-129. doi：10.3969/j.issn.1673-8640.2014.02.009 . doi: 10.3969/j.issn.1673-8640.2014.02.009
[22]	范文慧. 急性Stanford A型主动脉夹层术后并发脑梗死相关因素分析［D］. 石家庄：河北医科大学， 2023.
[23]	周有婷，李志鹏，王嘉鹏. 急性脑梗死患者血清CTRP-3、D-二聚体、sTREM2水平及相关临床特征与溶栓后出血性转化的关系［J］. 中国现代医学杂志， 2023， 33（24）： 60-66. doi：10.3969/j.issn.1005-8982.2023.24.011 . doi: 10.3969/j.issn.1005-8982.2023.24.011
[24]	KONISHI T， INOKUCHI H， SASABUCHI Y， et al. Association between care-need level after discharge and long-term outcomes in 7491 patients requiring rehabilitation for stroke［J］. JMA J， 2024， 7（1）： 52-59. doi：10.31662/jmaj.2023-0094 . doi: 10.31662/jmaj.2023-0094
[25]	李莹，陈杰，沙培，等. 个性化康复训练结合循证护理在老年股骨粗隆间骨折患者术后康复中的应用［J］. 中西医结合护理（中英文）， 2024， 10（2）： 112-114. doi：10.11997/nitcwm.202402033 . doi: 10.11997/nitcwm.202402033
[26]	DU P， WU X， LIU X， et al. The application of decision tree model based on clinicopathological risk factors and pre-operative MRI radiomics for predicting short-term recurrence of glioblastoma after total resection： A retrospective cohort study［J］. Am J Cancer Res， 2023， 13（8）： 3449-3462.
[27]	TANAKA S， JUNG H， YAMASHINA S， et al. Clinical prediction rule for locomotive syndrome in older adults： A decision tree model［J］. J Orthop Sci， 2023， 28（4）： 886-894. doi：10.1016/j.jos.2022.04.008 . doi: 10.1016/j.jos.2022.04.008
[28]	HEINRICH M， WOIKE J K， SPIES C D， et al. Forecasting postoperative delirium in older adult patients with fast-and-frugal decision trees［J］. J Clin Med， 2022， 11（19）： 5629. doi：10.3390/jcm11195629 . doi: 10.3390/jcm11195629

因素	脑梗死组（n = 61）	非脑梗死组（n = 154）	t/χ²值	P值
性别			0.040	0.842
男	33	81
女	28	73
年龄（x ± s）/岁	72.43 ± 3.51	73.06 ± 3.54	1.179	0.240
BMI ≤ 24 kg/m²	42	93	1.339	0.247
饮酒（是）	26	51	1.718	0.190
吸烟（是）	23	45	1.454	0.228
高血压（有）	41	67	9.822	0.002
糖尿病（有）	37	57	9.926	0.002
手术时间≥ 2 h	40	65	9.547	0.002
术中输血（有）	19	33	2.251	0.134
深静脉血栓（有）	11	24	0.192	0.661
肺部感染（有）	16	28	1.739	0.187
尿路感染（有）	13	22	1.582	0.208
压疮（有）	25	57	0.292	0.589
住院卧床时间（x ± s）/d	9.57 ± 2.31	6.95 ± 1.47	9.946	0.000
人血白蛋白（x ± s）/（U/L）	41.17 ± 3.69	40.92 ± 3.52	0.463	0.644
甘油三酯（x ± s）/（mmol/L）	2.51 ± 0.49	2.48 ± 0.47	0.417	0.677
总胆固醇（x ± s）/（mmol/L）	5.96 ± 1.32	5.83 ± 1.17	0.708	0.480
Hcy（x ± s）/（μmol/L）	22.65 ± 2.97	18.43 ± 2.79	9.816	0.000
C反应蛋白（x ± s）/（mg/L）	13.27 ± 3.49	12.65 ± 3.16	1.259	0.210
血肌酐（x ± s）/（μmol/L）	330.14 ± 35.62	328.52 ± 32.75	0.319	0.750
甲状旁腺激素（x ± s）/（mIU/L）	3.15 ± 0.57	3.06 ± 0.52	1.113	0.267
D-D（x ± s）/（mg/L）	2.08 ± 0.42	1.54 ± 0.37	9.277	0.000
优质护理（是）	21	89	9.547	0.002

变量	赋值
IFF术后合并脑梗死	脑梗死组=“1”；非脑梗死组=“0”
高血压	有=“1”；无=“0”
糖尿病	有=“1”；无=“0”
手术时间	≥ 2 = “1”；< 2 = “0”
住院卧床时间	原值载入
Hcy	原值载入
D-D	原值载入
优质护理	有=“1”；无=“0”

自变量	β	S.E.	Wald值	P值	OR	95%CI
自变量	β	S.E.	Wald值	P值	OR	下限	上限
高血压	1.120	0.585	3.668	0.049	3.063	0.974	9.633
糖尿病	1.108	0.555	3.984	0.046	3.028	1.020	8.991
住院卧床时间	0.712	0.173	16.846	< 0.001	2.038	1.451	2.863
Hcy	0.450	0.102	19.379	< 0.001	1.569	1.284	1.917
D-D	3.091	0.798	15.003	< 0.001	21.991	4.603	105.063
优质护理	-1.616	0.586	7.599	0.006	0.199	0.063	0.627
常量	-22.120	3.389	42.611	< 0.001	0.000	-	-

Risk prediction of postoperative cerebral infarction in elderly patients with intertrochanteric femoral fracture： A comparative study of decision tree and logistic regression model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 28

Related Articles 15

Recommended Articles

Metrics

Comments

模型	AUC	标准误	P值	95%CI
logistic回归	0.896	0.022 5	< 0.05	0.847 ~ 0.933
决策树模型	0.964	0.011 2	< 0.05	0.930 ~ 0.985

[1]	Wei GONG,Tianle GAO,Jin WANG. Analysis of influencing factors for secondary fractures in adjacent vertebrae after percutaneous kyphoplasty in patients with osteoporotic vertebral compression fractures based on sagittal parameters of the spine-pelvis， fracture characteristics， and treatment-related clinical features [J]. The Journal of Practical Medicine, 2026, 42(6): 1088-1096.
[2]	Jinsong LI,Senxin HUA,Ludan HUANG,Qing SU. Changes in serum levels of NRG-1， CHIT1， Cx43， and MECP2 in patients with acute cerebral infarction and their relationship with severity and prognosis [J]. The Journal of Practical Medicine, 2026, 42(4): 691-697.
[3]	Pengzheng LI,Baoguo CHENG,Jinzhan LIU,Weixing LI. Application of CT perfusion parameters and serum CEA/AFP in monitoring post-TACE recurrence in primary hepatocellular carcinoma [J]. The Journal of Practical Medicine, 2026, 42(2): 176-184.
[4]	Yuxin ZHOU,Lixin ZHANG,Fang BA,Xiaolan ZHOU. Effect of repeated transcranial magnetic stimulation combined with hydrogel feeding training on dysphagia after subacute cerebral infarction and its influence on swallowing function [J]. The Journal of Practical Medicine, 2025, 41(9): 1339-1344.
[5]	Yingdao CHEN,Haining LI,Yuying LI,Qiping ZHANG,Bingsong LIANG,Guohui. LI. The predictive value of serum miR-143-3p and miR-188-5p levels for poor prognosis in patients with acute cerebral infarction after thrombolysis [J]. The Journal of Practical Medicine, 2025, 41(8): 1117-1122.
[6]	Hanqi YANG,Lingna. HE. The therapeutic effect of acupuncture combined with moxibustion on insomnia related to cerebral infarction based on the "Yuan⁃Luo Point Pairing" and its impact on serum Hcrt⁃1， 5⁃HT， and slow wave EEG [J]. The Journal of Practical Medicine, 2025, 41(8): 1253-1258.
[7]	Ruiyi JIA,Bo ZHANG,Guoyun YU,Jiawei QIANG,Xinyu WANG,Guifen. PANG. The impact of chronic obstructive pulmonary disease combined with hypertension on cardiovascular events [J]. The Journal of Practical Medicine, 2025, 41(21): 3358-3364.
[8]	Yanmin ZHENG,Qingqing WANG,Shenghao LI,Ye LI,Lu. ZHANG. Analysis of factors influencing hyperdynamic circulation indicators in patients with liver cirrhosis and ascites [J]. The Journal of Practical Medicine, 2025, 41(20): 3228-3234.
[9]	Minhua LAI,Yanshan LIN,Fangliang ZOU,Yang ZHANG,Jing LONG,Huaan XIA,Lihong LIN,Yunzhi DENG,Ruiyun CHEN,Jianhua YANG,Yao XU,Tianwen. PENG. Research on the current status of penile erection hardness and its influencing factors in patients with non-obstructive azoospermia [J]. The Journal of Practical Medicine, 2025, 41(20): 3276-3282.
[10]	Yanyan JIA,Yijia SUN,Di ZHAO,Yan. SONG. Elderly acute progressive cerebral infarction patients′ serum PLA2， called S100B levels and the relationship between carotid plaques [J]. The Journal of Practical Medicine, 2025, 41(2): 244-249.
[11]	Wei LU,Pan ZHANG,Yushu. QIN. Clinical significance of CT perfusion imaging combined with artificial intelligence in evaluating reperfusion injury after cerebral infarction [J]. The Journal of Practical Medicine, 2025, 41(2): 264-270.
[12]	Xiaoyi CHEN,Chao WANG,Yan. NIE. A predictive model for bowel preparation quality and mild adverse events in colonoscopy [J]. The Journal of Practical Medicine, 2025, 41(19): 3016-3025.
[13]	Shuting ZHENG,Xixi LIU,Shiyang CHEN,Peiqian LAI,Chunhong GUO,Shaohua. CHEN. Latent profiles analysis and influencing factors of Health⁃Promoting Lifestyle in patients with conservative treatment of Lumbar Disc Herniation [J]. The Journal of Practical Medicine, 2025, 41(19): 3052-3059.
[14]	Fengwei QIN,Jiang LIU,Wen CHEN,Yonghui FENG,Sineng ZHANG. Analysis of influencing factors for early residual low back pain after percutaneous vertebro plasty [J]. The Journal of Practical Medicine, 2025, 41(18): 2884-2889.
[15]	Biao LENG,Dequan HONG,Ming TAN,Ming TIAN,Shanliang XIE,Yaoran. TU. Value of serum TFPI-1 combined with NF-κB in prognostic analysis of severe traumatic brain injury [J]. The Journal of Practical Medicine, 2025, 41(16): 2455-2460.