[1]杨 华a,孙天舒b,王 瑶c,等.人工智能辅助阅片与单纯人工阅片在女性阴道微生态系统形态学诊断中的比对研究[J].现代检验医学杂志,2023,38(01):169-174+198.[doi:10.3969/j.issn.1671-7414.2023.01.032]
　YANG Huaa,SUN Tian-shub,WANG Yaoc,et al.Comparative Study of Artificial Intelligence-assisted Analysis and Manual Visual Analysis in Gynecological Microbiome Diagnosis[J].Journal of Modern Laboratory Medicine,2023,38(01):169-174+198.[doi:10.3969/j.issn.1671-7414.2023.01.032]
点击复制

人工智能辅助阅片与单纯人工阅片在女性阴道微生态系统形态学诊断中的比对研究()
分享到：

《现代检验医学杂志》[ISSN:/CN:]

卷:
第38卷
期数:
2023年01期
页码:
169-174+198
栏目:
研究简报·实验技术
出版日期:
2023-01-15

文章信息/Info

Title:
Comparative Study of Artificial Intelligence-assisted Analysis and Manual Visual Analysis in Gynecological Microbiome Diagnosis
文章编号:
1671-7414（2023）01-169-07
作者:
杨 华a; 孙天舒b; 王 瑶c; 徐英春c; 孙宏莉c
（北京协和医院 a. 妇产科；b. 医学科学研究中心；c. 检验科，北京100730）
Author(s):
YANG Huaa;  SUN Tian-shub;  WANG Yaoc;  XU Ying-chunc;  SUN Hong-lic
(a. Department of Obstetrics and Gynecology；b. Medical Science Research Center；c. Department of Laboratory Medicine, Peking Union Medical College Hospital, Beijing 100730，China)
关键词:
阴道微生态; 形态学检测; 人工智能; 性能评估; 人工智能辅助阅片
分类号:
R446.19
DOI:
10.3969/j.issn.1671-7414.2023.01.032
文献标志码:
A
摘要:
目的 评估不同级别检验员对革兰染色涂片阴道微生态形态学评价的基线水平，分析检验员在电子阅片和镜下阅片的差异，探究使用人工智能分析系统独立进行微生态评价以及辅助检验员进行微生态评价的能力表现，评价人工智能分析系统在临床中的应用价值。方法 该研究样本来源于北京协和医院《中国女性人群下生殖道微生态菌群基线研究项目》，收集2021 年5 月～ 2021 年7 月女性阴道分泌物涂片共385 例，经革兰染色和图像采集后，分别进行检验员等级考核以及人工显微镜镜下阅片、人工电子阅片、人工智能（artificial intelligence, AI）独立阅片和AI 辅助检验员阅片。在确定镜下阅片金标准和电子阅片金标准之后，分析两种不同阅片方式在AV 评分和Nugent 评分的差异，比较不同级别检验员、AI，以及经AI 辅助后，在AV 评分和Nugent 评分上的能力表现。结果 镜下阅片和电子阅片在需氧菌性阴道炎（aerobic vaginitis，AV）和细菌性阴道病（bacterial vaginosis, BV）(含BV 中间型) 诊断的Kappa 一致性分析分别为0.91 和0.93（P ＜ 0.01）。AI 独立阅片在AV 和BV(含BV 中间型) 诊断的准确度分别为0.85 和0.92，灵敏度分别为0.86 和0.88，Kappa 值分别为0.62 和0.79。初级检验员在电子阅片下的AV 和BV(含BV 中间型) 诊断的准确度分别为0.85±0.02 和0.89±0.01，灵敏度分别为0.64±0.06 和0.84±0.07，Kappa 值分别为0.55±0.07 和0.72±0.04。高级检验员在电子阅片下的AV 和BV(含BV 中间型) 诊断的准确度分别为0.92±0.03 和0.91±0.03，灵敏度分别为0.87±0.02 和0.92±0.04，Kappa 值分别为0.78±0.07 和0.79±0.06。经AI 辅助诊断后，初级检验员AV 和BV(含BV中间型) 诊断的Kappa 值提升至0.77±0.04 和0.78±0.02，高级检验员AV 和BV(含BV 中间型) 诊断的Kappa 值提升至0.82±0.05 和0.85±0.01。结论 镜下阅片和电子阅片的一致性非常高，电子阅片或可替代镜下阅片成为一种新的阅片方式。AI 独立阅片诊断AV 和BV(含BV 中间型) 的能力优于普通检验员，比高级检验员略差。不同级别检验员经AI 辅助诊断后，AV 和BV(含BV 中间型) 的诊断能力均有提升，其中初级检验员提升明显，能力接近高级检验员的水平，且各检验员之间的偏差缩小明显。整体结果表明，使用人工智能Descartes-Image 妇科微生态辅助分析软件不仅能提升检验员诊断能力，还能减小检验员之间的偏差，使诊断结果不容易因为人为因素而出现较大波动，保证了结果的稳定性和可靠性。
Abstract:
Objective To evaluate the accuracy of morphological evaluation of vaginal microecology on Gram-stained vaginal smears by operators of differing levels of experience, determine differences between analyses using previously captured images versus live microscope images, explore the use of an artificial intelligence (AI) analysis system to independently conduct vaginal microecological evaluation, assist operators in vaginal microecological evaluation, and determine the application value of the AI analysis system in a clinical setting. Methods A total of 385 cases of female vaginal secretion smears from May 2021 to July 2021 were collected. After gram dyeing and image acquisition, the inspector’s grade assessment, manual microscope film reading, manual electronic film reading, AI independent film reading and AI auxiliary inspector film reading were conducted respectively.After determining the gold standard of microscopic viewing and the gold standard of image viewing, the differences in AV score and Nugent score of two different viewing methods were analyzed, and the performance of different operators, AI, and AI-assisted performance on AV and Nugent scores were compared. Results The Kappa concordance analysis of microscopic viewing and image viewing in the diagnosis of AV and BV (including BV intermediate) were 0.91 and 0.93, respectively (P ＜ 0.01). The accuracy of AI independent analysis in the diagnosis of AV and BV (including intermediate BV) were 0.85 and 0.92, sensitivity was 0.86 and 0.88 respectively, and the Kappa value was 0.62 and 0.79 respectively. The diagnostic accuracy of AV and BV (including intermediate BV) by junior operators using image viewing were 0.85±0.02 and 0.89±0.01, the sensitivity were 0.64±0.06 and 0.84±0.07, and the Kappa value were 0.55±0.07 and 0.72±0.04 respectively. The diagnostic accuracy of AV and BV (including intermediate BV) by senior operators using image viewing was 0.92 ± 0.03 and 0.91 ± 0.03, the sensitivity was 0.87 ± 0.02 and 0.92 ± 0.04 respectively, and the Kappa values was 0.78 ± 0.07 and 0.79±0.06 respectively. After AIassisted diagnosis, the Kappa values of AV and BV (including intermediate BV) diagnosed by junior operators were increased to 0.77±0.04 and 0.78±0.02, and the Kappa values of senior operators AV and BV (including intermediate BV) diagnosis were increased to 0.82±0.05 and 0.85±0.01. Conclusion The consistency between microscopic viewing and image viewing was very high, suggesting that image viewing could replace microscopic viewing as a new viewing method. The ability of AI to independently analyze and diagnose AV and BV (including intermediate BV) was better than that of junior operators, and slightly inferior to senior operators. With AI-assisted analysis, the diagnostic capabilities for AV and BV (including intermediate BV) among both junior and senior operators improved. The performance of junior operators improved significantly and nearly approached the performance of senior operators, significantly reducing the performance gap between junior and senior operators. The overall results indicated that the use of the Turing Microbial Gynecology Microbiome Auxiliary Analysis System not only improved the diagnostic ability of the operators, but also reduce the deviation between different operators thereby reducing fluctuations due to human factors and improving reliability of diagnosis.

参考文献/References:

[1] 国家卫生健康委员会. 中国卫生健康统计年鉴[M].北京：中国协和医科大学出版社, 2020：222.
National Health Commission. China Health Statistics Yearbook[M].Beijing：China Union Medical University Press, 2020：222.
[2] 中华医学会妇产科学分会感染性疾病协作组. 阴道微生态评价的临床应用专家共识[J]. 中华妇产科杂志, 2016, 51(10)：721-723.
Cooperative Group of Infectious Disease, Chinese Society of Obstetrics and Gynocology, Chinese Medical Association. Expert consensus on the clinical application of vaginal microecology test [J]. Chinese Journal of Obstetrics and Gynecology, 2016,51(10):721-723.
[3] 杨广全, 来忠梅. 阴道分泌物检查结果的影响因素分析[J]. 中外女性健康研究, 2016(11)：92, 94.
YANG Guangquan, LAI Zhongmei. Analysis of influencing factors of vaginal discharge examination results[J]. Women’s Health Research, 2016(11):92, 94.
[4] 李云, 冯伟, 王丕明, 等. 细菌性阴道病分泌物漏误诊相关因素分析[J]. 航空航天医学杂志, 2014,25(8)：1121-1122.
LI Yun, FENG Wei, WANG Peiming, et al. Analysis of factors related to missed and misdiagnosed secretion of bacterial vaginosis [J].Journal of Aerospace Medicine,2014, 25(8):1121-1122.
[5] 陈黔. 大型综合性医院检验科门诊工作存在的问题与对策[J]. 西南军医, 2007, 9(4)：100-101.
CHEN Qian. Problems and countermeasures in outpatient work of laboratory department in large general hospitals[J]. Journal of Military Surgeon in Southwest China, 2007, 9(4):100-101.
[6] WANG Zhongxiao, ZHANG Lei, ZHAO Min, et al.Deep neural networks offer morphologic classification and diagnosis of bacterial vaginosis zhongxiao[J]. J Clin Microbiol, 2021, 59(2):e02236-20.
[7] 王瑶, 孙宏莉, 赵颖, 等. 自动化镜检结合人工智能分析系统对阴道分泌物革兰染色涂片形态学的准确性评价[J]. 协和医学杂志, 2021, 12(4)：503-509.
WANG Yao, SUN Hongli, ZHAO Ying, et al. Accuracy assessment of the morphological analysis system with automated microscopy and artificial intelligence for gram-stained vaginal discharge smears [J]. Medical Journal of Peking Union Medical College Hospital,2021,12(4):503-509.
[8] 中华医学会妇产科学分会感染性疾病协作组. 细菌性阴道病诊治指南(2021 修订版)[J]. 中华妇产科杂志, 2021, 56(1)：3-6.
Cooperative Group of Infectious Disease,Chinese Society of Obstetrics and Gynecology,Chinese Medical Association. Guideline for diagnosis and treatment of bacterial vaginosis (2021 revised edition) [J].Chinese Journal of Obstetrics and Gynecology, 2021, 56(1): 3-6.
[9] DONDERS G G, VEREECKEN A, BOSMANS E, et al. Definition of a type of abnormal vaginal flora that is distinct from bacterial vaginosis: aerobic vaginitis[J].BJOG-An International Journal of Obstetrics and Gynaecology, 2002, 109(1): 34-43.
[10] 董梦婷, 王辰, 李会阳, 等. 基于革兰染色涂片结合临床特征的需氧菌性阴道炎联合诊断标准专家建议[J]. 中国实用妇科与产科杂志, 2021, 37(3)：327-335.
DONG Mengting, WANG Chen, XUE Huiyang, et al.Aerobic vaginitis diagnosis criteria combining gram stain with clinical features: an establishment and prospective validation study[J]. Chinese Journal of Practical Gynecology and Obstetrics, 2021, 37(3):327-335.

备注/Memo

备注/Memo:
作者简介：杨华（1982-），女, 医学博士，主治医师，研究方向：阴道微生态，E-mail:huasunny82@126.com。
通讯作者：孙宏莉（1971-），女，医学博士，副研究员，硕士生导师，主要研究方向：临床微生物检验，E-mail:sunhl2010@sina.com。
更新日期/Last Update: 2023-01-15