Prediction models for severe hand-foot-mouth disease risk
XU Jing1, ZHANG Junhong1, FENG Huifen2
1. The Second Affiliated Hospital of Soochow University, Suzhou, Jiangsu 215026, China; 2. The Fifth Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
Abstract：Objective To construct and compare risk prediction models for severe hand-foot-mouth disease (HFMD), analyze the influencing factors of severe HFMD, so as to provide a reference for early identification and intervention of severe HFMD. Methods HFMD patients who were hospitalized in a hospital in Zhengzhou City from November 2018 to December 2021 were selected as study subjects. Demographic information, clinical symptoms, and laboratory test indicators were collected. The subjects were randomly divided into a training set and a validation set at a 7∶3 ratio. According to the Guidelines for Diagnosis and Treatment of Hand-Foot-Mouth Disease (2018 Edition), the patients were divided into a mild HFMD group and a severe HFMD group. Variables with statistically significant differences between the two groups were identified as predictive variables. Random forest model, linear support vector machine (LSVM) model, and logistic regression model were constructed. The predictive performance of the three models was evaluated using accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). Results A total of 1 650 HFMD patients were included, including 1 094 males (66.30%) and 556 females (33.70%). The mean age was (1.97±1.17) years. There were 1 293 cases in the mild HFMD group (78.36%) and 357 cases in the severe HFMD group (21.64%). The accuracy of random forest model, LSVM model, and logistic regression model in predicting severe HFMD were 95.76%, 88.28%, and 88.08%, respectively. The sensitivity were 94.55%, 59.09%, and 58.18%, respectively. The specificity were 96.10%, 96.66%, and 96.66%, respectively. The AUC values were 0.981, 0.895, and 0.899, respectively. The random forest model results showed that the top three important predictors for severe HFMD were neutrophil ratio, alanine aminotransferase, and platelet count. Conclusions The constructed random forest model demonstrates good predictive performance and can be applied in predicting severe HFMD. It is recommended to pay attention to changes in neutrophil ratio, alanine aminotransferase, and platelet count in HFMD patients, which can assist in early identification and intervention of severe HFMD.
[1] YAN R,HE J H,LIU G,et al.Drug repositioning for hand,foot,and mouth disease[J/OL].Viruses,2022,15(1)[2026-02-03].https://doi.org/10.3390/v1501007. [2] LEUNG A K C,LAM J M,BARANKIN B,et al.Hand,foot,and mouth disease:a narrative review[J].Recent Adv Inflamm Allergy Drug Discov,2022,16(2):77-95. [3] FONG S Y,MORI D,RUNDI C,et al.A five-year retrospective study on the epidemiology of hand,foot and mouth disease in Sabah,Malaysia[J/OL].Sci Rep,2021,11[2026-02-03].https://doi.org/10.1038/s41598-021-96083-3. [4] MIAO L,LIU Y J,LUO P L,et al.Association between platelet count and the risk and progression of hand,foot,and mouth disease among children[J/OL].Clinics(Sao Paulo),2020,75[2026-02-03].https://doi.org/10.6061/clinics/2020/e1619. [5] SARKAR S,MALI K.Breast cancer subtypes classification with hybrid machine learning model[J].Methods Inf Med,2022,61(3/4):68-83. [6] ZHANG H W,WANG Y R,HU B,et al.Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases[J/OL].Sci Rep,2024,14(1)[2026-02-03].https://doi.org/10.1038/s41598-024-80210-x. [7] 《手足口病诊疗指南(2018版)》编写专家委员会.手足口病诊疗指南(2018年版)[J].中华临床感染病杂志,2018,36(5):257-263. [8] 杨溪,寸建萍,曹亿会,等.2009—2019年云南省手足口病重症病例流行病学特征及危险因素分析[J].现代预防医学,2022,49(15):2689-2693. [9] XU S S,LI H J,QIAO P,et al.Neonatal hand,foot,and mouth disease due to coxsackievirus A6 in Shanghai[J/OL].BMC Pediatr,2020,20(1)[2026-02-03].https://doi.org/10.1186/s12887-020-02262-y. [10] 杨青青. 精氨酸代谢对重症HFMD小鼠模型中由巨噬细胞介导的细胞因子风暴作用机制研究[D].广州:南方医科大学,2024. [11] LI P Q,HUANG Y G,ZHU D P,et al.Risk factors for severe hand-foot-mouth disease in China:a systematic review and meta-analysis[J/OL].Front Pediatr,2021[2026-02-03].https://doi.org/10.3389/fped.2021.716039. [12] YI Z J,PEI S J,SUO W S,et al.Epidemiological characteristics,routine laboratory diagnosis,clinical signs and risk factors for hand-foot-and-mouth disease:a systematic review and meta-analysis[J/OL].PLoS One,2022,17(4)[2026-02-03].https://doi.org/10.1371/journal.pone.0267716. [13] 董琦. 重症和危重症手足口病风险因子的寻找和预测模型的建立[D].南昌:南昌大学,2022. [14] ZHANG Y,CHEN S Y,SUN T T,et al.Abundant neutrophil-initiated acute myocardial injury following coxsackievirus A6 infection[J].J Infect Dis,2024,229(5):1440-1450. [15] XIE Y Q,HU Q M,DUAN G C,et al.NLRP3 inflammasome activation contributes to acute liver injury caused by CVA6 infection in mice[J/OL].BMC Infect Dis,2024,24(1)[2026-02-03].https://doi.org/10.1186/s12879-024-10136-2. [16] JIN Y F,LI D,SUN T T,et al.Pathological features of enterovirus 71-associated brain and lung damage in mice based on quantitative proteomic analysis[J/OL].Front Microbiol,2021,12[2026-02-03].https://doi.org/10.3389/fmicb.2021.663019. [17] FANG L,YU S C,TIAN X X,et al.Severe fever with thrombocytopenia syndrome virus replicates in platelets and enhances platelet activation[J].J Thromb Haemost,2023,21(5):1336-1351. [18] LI Q W,WANG Y M,XUE W Y,et al.Immunomodulatory effects of platelets on the severity of hand,foot,and mouth disease infected with enterovirus 71[J].Pediatr Res,2021,89(4):814-822. [19] 嵇红,陈庆会,张雪峰,等.儿童重症手足口病的临床特征和预后以及预警指标分析[J].中华实验和临床病毒学杂志,2021,35(1):89-95. [20] 郑珊,冯慧芬,徐晶,等.郑州市2015年至2019年手足口病患者外周血炎症细胞和电解质水平变化与预后关联的巢式病例对照研究[J].重庆医科大学学报,2023,48(3):304-309.
