基于人工智能的辅助诊断在先天性房间隔缺损筛查中的应用研究

doi:10.3969/j.issn.1006-5725.2019.16.027

实用医学杂志 ›› 2019, Vol. 35 ›› Issue (16): 2637-2640.doi: 10.3969/j.issn.1006-5725.2019.16.027

基于人工智能的辅助诊断在先天性房间隔缺损筛查中的应用研究

杨宏波¹, 潘家华¹, 王威廉², 郭涛¹, 张戈军³, 唐永研¹, 许虹莉¹

1昆明医科大学附属心血管病医院（昆明 650000）;
2云南大学（昆明 650000）;
3国家心血管病中心（北京 100000）

收稿日期:2019-03-18 出版日期:2019-08-27 发布日期:2019-08-27
基金资助:
云南省基础研究计划基金项目[编号：2018FE001（-105）]

Application of artificial intelligence-based auxiliary diagnosis in screening of congenital atrial septal defect

YANG Hongbo^*, PAN Jiahua, WANG Weilian, GUO Tao, ZHANG Gejun, TANG Yongyan, XU Hongli

Yunnan Cardiovascular Hospital, Kunming Medical University, Kunming 650000, China

Received:2019-03-18 Online:2019-08-27 Published:2019-08-27

摘要/Abstract

摘要： 目的评估基于人工智能的辅助诊断在先天性房间隔缺损（atrial septal defect,ASD）筛查中的应用价值。方法 2014年9月至2018年9月,在先心病筛查中对10 142名0 ~ 14岁儿童进行人工听诊及基于人工智能的辅助诊断。人工智能对已确诊ASD的儿童采集标准部位心音,通过去噪和提取特征信息学习,实现心音和ASD对应的辅助诊断;在筛查中随机分为人工听诊组（n = 6 280）和人工智能组（n = 3 762）,比较ASD的发现率;在确诊的162例患儿中比较人工听诊和人工智能诊断的准确率。结果人工智能共学习6 253个ASD患儿和6 544个正常儿童心音周期;采用学习所得辅助诊断技术听诊3 762名儿童,诊断率（4.5‰）与人工听诊（1.9‰）相比差异无统计学意义（P > 0.05）;对162例确诊患儿进行人工智能辅助诊断,准确率为69.1%。结论基于人工智能的辅助诊断在先天性ASD筛查中是一个有效的辅助手段。

关键词: 先天性房间隔缺损, 先心病筛查, 人工智能

Abstract: Objective To evaluate the value of artificial intelligence （AI）-based auxiliary diagnosis in the screening of congenital atrial septal defect（ASD）. Methods From September 2014 to September 2018, 10,142 children aged 0 ~ 14 years were enrolled in a diagnosis of congenital heart disease （CHD） by artificial auscultation and AI-based diagnosis. Heart sounds of standard parts in children with confirmed atrial septal defect were collected by AI, and the denoising and extracting characteristic information were conducted to realize the auxiliary diagnosis corresponding to heart sound and atrial septal defect. During the screening, patients were randomly divided into artificial auscultation group （n = 6,280） and AI group （n = 3,762）. The detection rate of atrial septal defect was compared in the two groups and the accuracy of artificial auscultation and AI diagnosis was compared among the 162 diagnosed children. Results A total of 6,253 children with atrial septal defect and 6,544 normal children′s heart sound cycle were detected by AI. Auscultation of 3,762 children was conducted with AI and there was no significant difference between the detection rate of auscultation with AI （4.5‰） and that with manual stethoscope （1.9‰）（P > 0.05）. AI-assisted diagnosis was performed on 162 confirmed patients with an accuracy rate of 69.1%. Conclusion AI-based assisted diagnosis is an effective adjunct in the screening of congenital atrial septal defect.

Key words: congenital atrial septal defect, screening, artificial intelligence

杨宏波, 潘家华, 王威廉, 郭涛, 张戈军, 唐永研, 许虹莉. 基于人工智能的辅助诊断在先天性房间隔缺损筛查中的应用研究[J]. 实用医学杂志, 2019, 35(16): 2637-2640.

YANG Hongbo, PAN Jiahua, WANG Weilian, GUO Tao, ZHANG Gejun, TANG Yongyan, XU Hongli. Application of artificial intelligence-based auxiliary diagnosis in screening of congenital atrial septal defect[J]. The Journal of Practical Medicine, 2019, 35(16): 2637-2640.

参考文献 23

[1]	STLOUIS J D, KUROSAW A H, JONAS R A, et al.The World database for pediatric and congenital heart surgery: The dawn of a new era of global communication and quality improvement in congenital heart disease[J]. World J Pediatr Congenit Heart Surg, 2017,8(5):597-599.
[2]	MATTHEWS T J, MACDORMAN M F,THOMA M E.Infantmortality,statistics from the 2013 period linked birth/infant death data set[J]. Natl Vital Stat Rep, 2015, 64: 1-30.
[3]	BHARDWAJ R, RAI S K, YADAV A K, et al.Epidemiology of congenital heart disease in India[J]. Congenit Heart Dis. 2015, 10(5):437-446.
[4]	HOFFMAN JIE.The global burden of congenital heart disease[J]. Cardiovasc J Afr, 2013, 24(4):141-145.
[5]	LARA D A, LOPEZ K N.Public health research in congenital heart disease[J]. Congenit Heart Dis, 2014, 9(6):549-558.
[6]	DOLK H, LOANE M, GARNE E.The prevalence of congenital anomalies in Europe[J]. Adv Exp Med Biol, 2010, 686:349-364.
[7]	Ministry of Health of the People's Republic of China. The Chinese national report on birth defects. [EB/OL]. (2012-9-13)[2019-5-27]. http:// www.gov.cn/fwxx//jk/2012-09/13/content_2223559.htm
[8]	ZHANG Y F, ZENG X L, ZHAO E F, et al.Diagnostic value of fetal echocardiography for congenital heart disease: A systematic review and meta-analysis[J]. Medicine (Baltimore), 2015, 94(42):e1759.
[9]	邢素霞, 陈天华. 基于DSP的心音信号采集与分析[J]. 生物医学工程学杂志, 2011, 28(2):273-276.
[10]	HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. proc[J]. Proc Math Phy Eng Sci, 1998, 454(1971):903-995.
[11]	钟丽莎, 万江中, 黄志伟,等. 基于GMM的心音信号生物识别方法研究[J]. 中国医疗器械杂志, 2013,37(2):92-95, 99.
[12]	董柱, 刘莹, 曹一秋, 等. 3D打印技术在先天性心脏病个性化诊治中的应用[J]. 实用医学杂志, 2018,34(15):2481-2484.
[13]	LIU Q G, SUN J, XIAO X W, et al.Birth defects data from surveillance hospitals in Dalian city, China, 2006-2010[J]. J Matern Fetal Neonatal Med, 2016, 29(22):3615-3621.
[14]	HO T C, OUYANG H, LU Y, et al.Postprocedural outcomes of rural children undergoing correction of congenital heart lesions in Yunnan province[J]. China. Pediatr Cardiol, 2011, 32:811-814.
[15]	WU L, LI B, XIA J, et al.Prevalence of congenital heart defect in Guangdong province[J]. BMC Public Health, 2014, 14:152.
[16]	ZHANG X, LI S, WU S, et al.Prevalence of birth defects and risk-factor analysis from a population-based survey in Inner Mongolia, China[J]. BMC Pediatr, 2012, 12(1):125.
[17]	FORRESTER M B, MERZ R D.Descriptive epidemiology of selected congenital heart defects, Hawaii[J]. Paediatr Perinat Epidemiol, 2004, 18:415-424.
[18]	LIN A E, KRIKOV S, RIEHLE-COLARUSSO T, et al.Laterality defects in the national birth defects prevention study (1998-2007): Birth prevalence and descriptive epidemiology[J]. Am J Med Genet A, 2014, 164A(10):2581-2591.
[19]	BRAVO-VALENZUELA N J, PEIXOTO A B, ARAUJO JÚNIOR E. Prenatal diagnosis of congenital heart disease: A review of current knowledge[J]. Indian Heart J, 2018, 70(1):150-164.
[20]	LINDINGER A, SCHWEDLER G, HENSE H W.Prevalence of congenital heart defects in newborns in Germany: Results of the first registration year of the PAN Study (July 2006 to June 2007)[J]. Klin Padiatr, 2010, 222:321-326.
[21]	WU M H, CHEN H C, LU C W, et al.Prevalence of congenital heart disease at live birth in Taiwan[J]. J Pediatr, 2010, 156:782-785.
[22]	PRADAT P, FRANCANNET C, HARRIS J A, et al.The epidemiology of cardiovascular defects, part I: A study based on data from three large registries of congenital malformations[J]. Pediatr Cardiol, 2003, 24:195-221.
[23]	TURAN S, TURAN O M, DESAI A, et al.First-trimester fetal cardiac examination using spatiotemporal image correlation, tomographic ultrasound and color Doppler imaging for the diagnosis of complex congenital heart disease in high-risk patients.[J]. Ultrasound Obstet Gynecol, 2014, 44(5):562-567.

基于人工智能的辅助诊断在先天性房间隔缺损筛查中的应用研究

Application of artificial intelligence-based auxiliary diagnosis in screening of congenital atrial septal defect

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 23

相关文章 0

编辑推荐

Metrics

本文评价