Analysis of related factors between sudden sensorineural hearing loss and serum indices base on artificial intelligence and big data
-
摘要: 目的 通过人工智能和大数据方法探讨突发性聋与血清生化等指标的相关性。方法 选取突发性聋患者1218例为实验组, 选取同期接受健康体检者95 861例为对照组, 收集两组目标人群血清生化等检测指标, 通过TreeNet和CART机器学习算法分析筛选出与突发性聋高度相关的指标, 并挖掘出突发性聋高风险人群的临床特征。结果 通过TreeNet、CART算法得到突发性聋的发病与嗜酸粒细胞、网织红细胞和纤维蛋白原高度相关, 经ROC曲线评估TreeNet模型具有较高的预测性能, 其中AUC=0.99, 查全率和准确率均为99.90%。结论 突发性聋患者的血清生化等指标跟正常人相比存在显著差异, 嗜酸粒细胞是区分是否患有突发性聋的第一重要指标, TreeNet模型对于突发性聋的筛查与诊断有重要的参考意义。Abstract: Objective The etiology and pathophysiologic mechanism of sudden sensorineural hearing loss are undefined. We will use artificial intelligence and big data methods to explore the correlation between sudden sensorineural hearing loss and serum indices. Method A total of 1218 patients with sudden deafness admitted to Sun Yat-sen Memorial Hospital were selected as the experimental group, 95 861 healthy subjects were randomly selected as the control group at the same period. Serum biochemical indexes in two groups were collected and analyzed by TreeNet and CART machine learning algorithms, to screen out highly correlated indicators with sudden sensorineural hearing loss and dig out a set of clinical features for people with high risk of sudden sensorineural hearing loss. Result It was found that high prevalence rate of sudden sensorineural hearing loss is related to eosinophils, reticulocyte and fibrinogen. The areas under the receiver operator characteristic curves(ROC-AUC) were exploited to evaluate the prediction performance of TreeNet model. Overall the TreeNet model has provided high predictive ability by ROC curve, achieving AUC of 0.99, both recall and accuracy rate of 99.90%. Conclusion There is significant difference between sudden deadness and normal people in serum biochemical indexes. Eosinophil is the first important indicator to distinguish sudden sensorineural hearing loss. Treenet model has important referenced significance for the screening and diagnosis of sudden sensorineural hearing loss.
-
Key words:
- Sudden sensorineural hearing loss /
- artificial intelligence /
- machine learning /
- TreeNet /
- CART
-
-
表 1 影响突聋发病重要性排名表
变量 评分 嗜酸粒细胞 100.00 中荧光强度网织红细胞 56.17 纤维蛋白原 45.94 凝血酶原国际比值 33.97 谷草转氨酶 33.47 尿白细胞 17.82 血清淀粉酶 14.36 血清钙 12.31 白细胞计数 11.22 中性粒细胞数 10.84 血清镁 8.72 D-二聚体 8.03 红细胞平均体积 5.09 球蛋白 4.57 尿酸 3.58 淋巴细胞 3.34 中性粒细胞百分比 3.32 凝血酶原比值 3.28 
下载: 导出CSV
-
[1] 中华耳鼻咽喉头颈外科杂志编辑委员会, 中华医学会耳鼻咽喉头颈外科学分会. 突发性聋诊断和治疗指南(2015)[J]. 中华耳鼻咽喉头颈外科杂志, 2015, 50(6): 443-447. doi: 10.3760/cma.j.issn.1673-0860.2015.06.002
[2] Levy JM, Amedee RG. In reference to Systematic review of the evidence for the etiology of adult sudden sensorineural hearing loss[J]. Laryngoscope, 2010, 120(11): 2347. doi: 10.1002/lary.21213
[3] 孙亮. 突发性耳聋的病因及预后因素研究进展[J]. 海南医学, 2013, 24(13): 1967-1969. doi: 10.3969/j.issn.1003-6350.2013.13.0813
[4] 赵紫奉, 李韶斌, 孔抗美. 基于决策树算法的疾病诊断分析[J]. 中国卫生信息管理杂志, 2011, 8(5): 67-69. doi: 10.3969/j.issn.1672-5166.2011.05.017
[5] 蒋杰. 基于分类技术的电子支付平台作弊账户的识别模型研究[C]. 浙江工业大学, 2012.
[6] 吴邦华, 黄海莹, 姚强, 等. 大数据及人工智能方法在妊娠期糖尿病预测的应用[J]. 中国卫生信息管理杂志, 2017, 14(6): 832-837. https://www.cnki.com.cn/Article/CJFDTOTAL-WSGL201706024.htm
[7] Matsubara A, Nishizawa H, Kurose A, et al. An experimental study of inner ear injury in an animal model of eosinophilic otitis media[J]. Acta Otolaryngol, 2014, 134(3): 227-232. doi: 10.3109/00016489.2013.859395
[8] Roberts RL, Ank BJ, Stiehm ER. Human eosinophils are more toxic than neutrophils in antibody-independent killing[J]. J Allergy Clin Immunol, 1991, 87(6): 1105-1115. doi: 10.1016/0091-6749(91)92156-U
[9] Shult PA, Graziano FM, Wallow IH, et al. Comparison of superoxide generation and luminol-dependent chemiluminescence with eosinophils and neutrophils from normal individuals[J]. J Lab Clin Med, 1985, 106(6): 638-645.
[10] 张蕾, 肖玉丽. 突发性聋的研究现状[J]. 中国医学文摘(耳鼻咽喉科学), 2005, 20(6): 337-340. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHER202102023.htm
[11] 血浆D-二聚体及纤维蛋白原水平与突发性聋的相关性研究[C]. 周小英. 昆明医科大学2016
[12] 辛洁. 血液流变学指标分析与突发性耳聋的治疗[J]. 中国血液流变学杂志, 2002, 12(4): 353-354. doi: 10.3969/j.issn.1009-881X.2002.04.044
[13] 付原, 严德凤. 突发性聋的血液流变学指标检测分析[J]. 微量元素与健康研究, 2005, 22(1): 11-12. doi: 10.3969/j.issn.1005-5320.2005.01.006
[14] 倪茂美, 李德宏, 彭维晖, 等. 双耳突聋与单耳突聋的临床比较[J]. 临床耳鼻咽喉头颈外科杂志, 2010, 24(2): 74-76. https://www.cnki.com.cn/Article/CJFDTOTAL-LCEH201002012.htm
-
图(4)
表(1)
计量
- 文章访问数: 970
- PDF下载数: 268
- 施引文献: 0