机器学习在子宫内膜异位症诊断中的应用

doi:10.12280/gjszjk.20210297

摘要/Abstract

摘要：

机器学习是一种多学科交叉下产生的人工智能学科。在大数据时代,从数据挖掘的角度出发,应用机器学习方法,通过在繁复的数据中寻找隐含的信息与规律,是探索子宫内膜异位症（EMs）诊断和预测标准的新契机。利用机器学习挖掘EMs相关数据、构建诊断及预测模型具有可行性,但目前机器学习模型用于EMs辅助诊断尚处于研究阶段。从用于机器学习的EMs生物标志物、机器学习模型在EMs诊断中的应用和机器学习与传统统计学比较方面,讨论机器学习模型相较于传统统计学模型的应用优势,突显出机器学习在EMs诊断中应用的广阔前景。

关键词: 子宫内膜异位症, 诊断, 机器学习, 模型,统计学, 生物标记

Abstract:

Mechine learning is a new discipline of artificial intelligence with multidisciplinary integration. The machine learning methods can be used to search the hidden information and rules in complex data from the perspective of data mining in the era of big data, which is a new opportunity to explore the diagnosis and prediction standards of endometriosis (EMs). It is feasible to use machine learning to remine EMs data and build the diagnosis and prediction model. At present, the application of machine learning model in EMs auxiliary diagnosis is still at the research stage. This article discusses the application advantages of machine learning models compared to traditional statistical models from the aspects of EMs biomarkers for machine learning, the application of machine learning models in EMs diagnosis and the comparison of machine learning with traditional statistics, so as to show the broad prospects of machine learning in EMs diagnosis.

Key words: Endometriosis, Diagnosis, Machine learning, Models,statistical, Biomarkers

罗忆, 张丹丹. 机器学习在子宫内膜异位症诊断中的应用[J]. 国际生殖健康/计划生育, 2022, 41(1): 84-88.

LUO Yi, ZHANG Dan-dan. Application of Machine Learning in the Diagnosis of Endometriosis[J]. Journal of International Reproductive Health/Family Planning, 2022, 41(1): 84-88.

参考文献 31

[1]	Hirata T, Koga K, Kai K, et al. Clinical practice guidelines for the treatment of extragenital endometriosis in Japan, 2018[J]. J Obstet Gynaecol Res, 2020, 46(12):2474-2487. doi: 10.1111/jog.14522. doi: 10.1111/jog.14522 URL
[2]	Ghiasi M, Kulkarni MT, Missmer SA. Is Endometriosis More Common and More Severe Than It Was 30 Years Ago?[J]. J Minim Invasive Gynecol, 2020, 27(2):452-461. doi: 10.1016/j.jmig.2019.11.018. doi: 10.1016/j.jmig.2019.11.018 URL
[3]	中国医师协会妇产科医师分会子宫内膜异位症专业委员会, 中华医学会妇产科学分会子宫内膜异位症协作组. 子宫内膜异位症长期管理中国专家共识[J]. 中华妇产科杂志, 2018, 53(12):836-841. doi: 10.3760/cma.j.issn.0529-567x.2018.12.007. doi: 10.3760/cma.j.issn.0529-567x.2018.12.007
[4]	何清, 李宁, 罗文娟, 等. 大数据下的机器学习算法综述[J]. 模式识别与人工智能, 2014, 27(4):327-336. doi: 10.3969/j.issn.1003-6059.2014.04.007. doi: 10.3969/j.issn.1003-6059.2014.04.007
[5]	Lee KS, Ahn KH. Application of Artificial Intelligence in Early Diagnosis of Spontaneous Preterm Labor and Birth[J]. Diagnostics (Basel), 2020, 10(9):733. doi: 10.3390/diagnostics10090733. doi: 10.3390/diagnostics10090733
[6]	Kawakami E, Tabata J, Yanaihara N, et al. Application of Artificial Intelligence for Preoperative Diagnostic and Prognostic Prediction in Epithelial Ovarian Cancer Based on Blood Biomarkers[J]. Clin Cancer Res, 2019, 25(10):3006-3015. doi: 10.1158/1078-0432.CCR-18-3378. doi: 10.1158/1078-0432.CCR-18-3378 pmid: 30979733
[7]	Matta K, Vigneau E, Cariou V, et al. Associations between persistent organic pollutants and endometriosis: A multipollutant assessment using machine learning algorithms[J]. Environ Pollut, 2020, 260:114066. doi: 10.1016/j.envpol.2020.114066. doi: 10.1016/j.envpol.2020.114066 URL
[8]	Matsuo K, Purushotham S, Jiang B, et al. Survival outcome prediction in cervical cancer: Cox models vs deep-learning model[J]. Am J Obstet Gynecol, 2019, 220(4):381.e1-e14. doi: 10.1016/j.ajog.2018.12.030. doi: 10.1016/j.ajog.2018.12.030
[9]	Barnett-Itzhaki Z, Elbaz M, Butterman R, et al. Machine learning vs. classic statistics for the prediction of IVF outcomes[J]. J Assist Reprod Genet, 2020, 37(10):2405-2412. doi: 10.1007/s10815-020-01908-1. doi: 10.1007/s10815-020-01908-1 URL
[10]	Venkatesh KK, Strauss RA, Grotegut CA, et al. Machine Learning and Statistical Models to Predict Postpartum Hemorrhage[J]. Obstet Gynecol, 2020, 135(4):935-944. doi: 10.1097/AOG.0000000000 doi: 10.1097/AOG.0000000000003759 pmid: 32168227
	003759. pmid: 32168227
[11]	Ye Y, Xiong Y, Zhou Q, et al. Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study[J]. J Diabetes Res, 2020, 2020:4168340. doi: 10.1155/2020/4168340. doi: 10.1155/2020/4168340
[12]	Muyldermans M, Cornillie FJ, Koninckx PR. CA125 and endometriosis[J]. Hum Reprod Update, 1995, 1(2):173-187. doi: 10.1093/humupd/1.2.173. doi: 10.1093/humupd/1.2.173 pmid: 15726771
[13]	Shen A, Xu S, Ma Y, et al. Diagnostic value of serum CA125, CA19-9 and CA15-3 in endometriosis: A meta-analysis[J]. J Int Med Res, 2015, 43(5):599-609. doi: 10.1177/0300060515583076. doi: 10.1177/0300060515583076 URL
[14]	Parlatan U, Inanc MT, Ozgor BY, et al. Raman spectroscopy as a non-invasive diagnostic technique for endometriosis[J]. Sci Rep, 2019, 9(1):19795. doi: 10.1038/s41598-019-56308-y. doi: 10.1038/s41598-019-56308-y pmid: 31875014
[15]	袁家英, 张建华, 刘华. 基于智能算法的子宫内膜异位症辅助诊断模型的建立[J]. 医学信息, 2015, 28(28):53-54. doi: 10.3969/j.issn.1006-1959.2015.28.068. doi: 10.3969/j.issn.1006-1959.2015.28.068
[16]	Knific T, Fishman D, Vogler A, et al. Multiplex analysis of 40 cytokines do not allow separation between endometriosis patients and controls[J]. Sci Rep, 2019, 9(1):16738. doi: 10.1038/s41598-019-52899-8. doi: 10.1038/s41598-019-52899-8 URL
[17]	Wang L, Zheng W, Yu JK, et al. Artificial neural networks combined with surface-enhanced laser desorption/ionization mass spectra distinguish endometriosis from healthy population[J]. Fertil Steril, 2007, 88(6):1700-1702. doi: 10.1016/j.fertnstert.2007.01.055. doi: 10.1016/j.fertnstert.2007.01.055 URL
[18]	Wang L, Zheng W, Mu L, et al. Identifying biomarkers of endometriosis using serum protein fingerprinting and artificial neural networks[J]. Int J Gynaecol Obstet, 2008, 101(3):253-258. doi: 10.1016/j.ijgo.2008.01.018. doi: 10.1016/j.ijgo.2008.01.018 URL
[19]	Wang L, Zheng W, Ding XY, et al. Identification biomarkers of eutopic endometrium in endometriosis using artificial neural networks and protein fingerprinting[J]. Fertil Steril, 2010, 93(7):2460-2462. doi: 10.1016/j.fertnstert.2009.08.061. doi: 10.1016/j.fertnstert.2009.08.061 URL
[20]	Li B, Wang S, Duan H, et al. Discovery of gene module acting on ubiquitin-mediated proteolysis pathway by co-expression network analysis for endometriosis[J]. Reprod Biomed Online, 2021, 42(2):429-441. doi: 10.1016/j.rbmo.2020.10.005. doi: 10.1016/j.rbmo.2020.10.005 URL
[21]	Akter S, Xu D, Nagel SC, et al. GenomeForest: An Ensemble Machine Learning Classifier for Endometriosis[J]. AMIA Jt Summits Transl Sci Proc, 2020, 2020:33-42.
[22]	Akter S, Xu D, Nagel SC, et al. Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data[J]. Front Genet, 2019, 10:766. doi: 10.3389/fgene.2019.00766. doi: 10.3389/fgene.2019.00766 URL
[23]	Moustafa S, Burn M, Mamillapalli R, et al. Accurate diagnosis of endometriosis using serum microRNAs[J]. Am J Obstet Gynecol, 2020, 223(4): 557.e1-e11. doi: 10.1016/j.ajog.2020.02.050. doi: 10.1016/j.ajog.2020.02.050
[24]	Zhu H, Bao J, Liu S, et al. Null genotypes of GSTM1 and GSTT1 and endometriosis risk: a meta-analysis of 25 case-control studies[J]. PLoS One, 2014, 9(9):e106761. doi: 10.1371/journal.pone.0106761. doi: 10.1371/journal.pone.0106761 URL
[25]	Crestani A, Abdel Wahab C, Arfi A, et al. A short anogenital distance on MRI is a marker of endometriosis[J]. Hum Reprod Open, 2021, 2021(1):hoab003. doi: 10.1093/hropen/hoab003. doi: 10.1093/hropen/hoab003
[26]	Missmer SA, Chavarro JE, Malspeis S, et al. A prospective study of dietary fat consumption and endometriosis risk[J]. Hum Reprod, 2010, 25(6):1528-1535. doi: 10.1093/humrep/deq044. doi: 10.1093/humrep/deq044 URL
[27]	Harris HR, Wieser F, Vitonis AF, et al. Early life abuse and risk of endometriosis[J]. Hum Reprod, 2018, 33(9):1657-1668. doi: 10.1093/humrep/dey248. doi: 10.1093/humrep/dey248 URL
[28]	Bouaziz J, Mashiach R, Cohen S, et al. How Artificial Intelligence Can Improve Our Understanding of the Genes Associated with Endometriosis: Natural Language Processing of the PubMed Database[J]. Biomed Res Int, 2018, 2018:6217812. doi: 10.1155/2018/6217812. doi: 10.1155/2018/6217812 pmid: 29750165
[29]	Perrotta AR, Borrelli GM, Martins CO, et al. The Vaginal Microbiome as a Tool to Predict rASRM Stage of Disease in Endometriosis: a Pilot Study[J]. Reprod Sci, 2020, 27(4):1064-1073. doi: 10.1007/s43032-019-00113-5. doi: 10.1007/s43032-019-00113-5 pmid: 32046455
[30]	Guerriero S, Pascual M, Ajossa S, et al. Artificial intelligence (AI) in the detection of rectosigmoid deep endometriosis[J]. Eur J Obstet Gynecol Reprod Biol, 2021, 261:29-33. doi: 10.1016/j.ejogrb.2021. 04.012. doi: 10.1016/j.ejogrb.2021.04.012 pmid: 33873085
[31]	Loring M, Kabelac Z, Munir U, et al. Novel Technology to Capture Objective Data from Patients′ Recovery from Laparoscopic Endometriosis Surgery[J]. J Minim Invasive Gynecol, 2021, 28(2):325-331. doi: 10.1016/j.jmig.2020.06.011. doi: 10.1016/j.jmig.2020.06.011 URL