School of Nursing, Kunming Medical University;Department of Nursing, the Second Affiliated Hospital of Kunming Medical University;School of Public Health, Kunming Medical University;
Objective To apply machine learning algorithms to construct a stroke recurrence emergency response capability prediction model for stroke caregivers and to select and verify the model with the best predictive performance.Methods A total of 515 caregivers of stroke patients hospitalized from April to August 2024 were recruited. Caregivers were categorized into "deficient" and "non-deficient" groups based on their emergency response capacity deficits. Four machine learning algorithms, random forest, artificial neural network, extreme gradient boosting, and gradient boosting decision tree(GBDT), were employed to construct predictive models. The performance of the models was compared using accuracy, precision, recall, specificity, sensitivity, Youden's index, and the area under the receiver operating characteristic curve(AUC). The Gini index was applied to determine significant influencing factors of stroke caregivers' emergency response capacity. Results The GBDT model demonstrated the best performance in predicting stroke recurrence emergency response capability among stroke caregivers, with an AUC value reaching 0.896, indicating high prediction accuracy. Ten core predictors were identified in the GBDT model, including caregiver burden score, social support score, education level, personal burden score, relationship to the patient, age, primary family economic provider status, participation in stroke knowledge education programs, monthly income, and subjective support score. Conclusions By comparing multiple machine learning algorithms, this study found that the GBDT model excelled in predicting stroke recurrence emergency response capability of stroke caregivers. The model effectively pinpointed critical factors influencing this capacity, enabling dynamic monitoring of predictor changes. These findings lay a technical foundation for personalized intervention protocols, thereby forming a closed-loop support system to improve home-based care quality for stroke patients.
| 0 | 0 | 0 |
| Downloads | Citas | Reads |
[1]《中国脑卒中防治报告2021》概要[J].中国脑血管病杂志，2023,20(11):783-793.
[2] BODEN-ALBALA B, CARMAN H, MORAN M, et al. Perception of recurrent stroke risk among black, white and Hispanic ischemic stroke and transient ischemic attack survivors:the SWIFT study[J]. Neuroepidemiology, 2011,37(2):83-87.
[3]刘雪婷，林蓓蕾，李昕，等.脑卒中配偶照顾者版复发风险感知评估量表的调试及信效度检验[J].中国实用神经疾病杂志，2024,27(7):887-891.
[4] MEI Y X, LIN B, ZHANG W, et al. Benefits finding among Chinese family caregivers of stroke survivors:a qualitative descriptive study[J]. BMJ Open, 2020,10(10):e038344.
[5] FAVILLA C G, REEHAL N, CUMMINGS S R, et al. Personalized video-based educational platform to improve stroke knowledge:a randomized clinical trial[J]. J Am Heart Assoc, 2024,13(15):e035176.
[6]华小倩.脑卒中照顾者对卒中复发应急能力评估量表的研制与应用[D].延安：延安大学，2023.
[7]肖水源.《社会支持评定量表》的理论基础与研究应用[J].临床精神医学杂志，1994,4(2):98-100.
[8]王烈，杨小湜，侯哲，等.护理者负担量表中文版的应用与评价[J].中国公共卫生，2006,22(8):970-972.
[9] ZARIT S H, REEVER K E, BACH-PETERSON J. Relatives of the impaired elderly:correlates of feelings of burden[J]. Gerontologist, 1980,20(6):649-655.
[10]黄桂生，洪建芳，叶振强.脑卒中高危人群家属的急救意识及影响因素调查研究[J].中国医学创新，2022,19(35):73-77.
[11] BEN PAZI H, JAHASHAN S, HAR NOF S, et al. Pre-hospital stroke monitoring past, present, and future:a perspective[J].Front Neurol, 2024,15:1341170.
[12] HALEY W E, MARINO V R, SHEEHAN O C, et al. Stroke survivor and family caregiver reports of caregiver engagement in stroke care[J]. Rehabil Nurs, 2019,44(6):302-310.
[13] LIU F, YAO J, LIU C, et al. Construction and validation of machine learning models for sepsis prediction in patients with acute pancreatitis[J]. BMC Surg, 2023,23(1):267.
[14] YE Z, AN S, GAO Y, et al. The prediction of in-hospital mortality in chronic kidney disease patients with coronary artery disease using machine learning models[J]. Eur J Med Res, 2023,28(1):33.
[15] GONG J, ZHANG Y, ZHONG X, et al. Liver function test indices-based prediction model for post-stroke depression:a multicenter, retrospective study[J]. BMC Med Inform Decis Mak,2023,23(1):127.
[16] HU J, SZYMCZAK S. A review on longitudinal data analysis with random forest[J]. Brief Bioinform, 2023,24(2):bbad002.
[17] YUN K, HE T, ZHEN S, et al. Development and validation of explainable machine-learning models for carotid atherosclerosis early screening[J]. J Transl Med, 2023,21(1):353.
[18] LIAO J, WU X, WANG C, et al. Couple-based collaborative management model of type 2 diabetes mellitus for communitydwelling older adults in China:protocol for a hybrid type 1 randomized controlled trial[J]. BMC Geriatr, 2020,20:1-11.
[19]王贝贝，段思雨，冉明，等. 251例缺血性脑卒中患者复发风险感知现状及影响因素分析[J].护理学报，2023,30(15):69-73.
[20]殷学芳，高衍丽，曲丽红，等.中风病人主要照顾者的中风复发应急能力现状及影响因素[J].循证护理，2024,10(2):268-274.
[21]张译友，田媛，帕孜来提·赛登，等.脑卒中患者经济毒性现状及影响因素分析[J].中国临床护理，2023,15(3):183-186.
[22] WANG H, PAN S, XU Q, et al. The effect of intensive familycentered health education on the awareness rate, diagnosis, and treatment of post-stroke depression in community families[J].BMC Primary Care, 2022,23(1):282.
Basic Information:
DOI：
China Classification Code:TP181;R743.3
Citation Information:
[1]李博,杨明莹,王娅等.脑卒中照顾者卒中复发应急能力预测最优机器学习模型筛选及验证[J].老年医学研究,2025,6(02):1-6.
Fund Information:
云南省科技厅昆明医科大学应用基础研究联合专项（202301AY070001-223,省—县协同视角下农村地区首发脑卒中偏瘫患者移动健康管理模式的构建与实证研究）; 昆明医科大学大学2024年研究生教育创新基金（2024S218,脑卒中患者照顾者的卒中复发应急能力现状调查及其预测模型的构建）