机器学习在新生儿坏死性小肠结肠炎诊疗中的研究进展

崔承; 陈飞龙; 李禄全

doi:10.7499/j.issn.1008-8830.2302165

PDF(874 KB)

中国当代儿科杂志 ›› 2023, Vol. 25 ›› Issue (7) : 767-773. DOI: 10.7499/j.issn.1008-8830.2302165

综述

机器学习在新生儿坏死性小肠结肠炎诊疗中的研究进展

崔承¹, 陈飞龙^1,2, 李禄全¹

作者信息 +

Recent research on machine learning in the diagnosis and treatment of necrotizing enterocolitis in neonates

CUI Cheng, CHEN Fei-Long, LI Lu-Quan

Author information +

文章历史 +

摘要

新生儿坏死性小肠结肠炎（neonatal necrotizing enterocolitis，NEC）以血便、腹胀、呕吐等为主要表现，是导致新生儿死亡的主要原因之一，早期识别和诊断对该病预后极为重要。机器学习的兴起和发展为早期、快速、准确识别该病提供了可能。该文总结近年来机器学习在NEC应用中的算法，分析算法揭示的高危预测因子，评价机器学习在NEC病因回溯、定义、诊断方面的能力和特点，探讨机器学习在NEC未来应用中的挑战及前景。

Abstract

Necrotizing enterocolitis (NEC), with the main manifestations of bloody stool, abdominal distension, and vomiting, is one of the leading causes of death in neonates, and early identification and diagnosis are crucial for the prognosis of NEC. The emergence and development of machine learning has provided the potential for early, rapid, and accurate identification of this disease. This article summarizes the algorithms of machine learning recently used in NEC, analyzes the high-risk predictive factors revealed by these algorithms, evaluates the ability and characteristics of machine learning in the etiology, definition, and diagnosis of NEC, and discusses the challenges and prospects for the future application of machine learning in NEC.

导出引用

崔承, 陈飞龙, 李禄全. 机器学习在新生儿坏死性小肠结肠炎诊疗中的研究进展[J]. 中国当代儿科杂志. 2023, 25(7): 767-773 https://doi.org/10.7499/j.issn.1008-8830.2302165

CUI Cheng, CHEN Fei-Long, LI Lu-Quan. Recent research on machine learning in the diagnosis and treatment of necrotizing enterocolitis in neonates[J]. Chinese Journal of Contemporary Pediatrics. 2023, 25(7): 767-773 https://doi.org/10.7499/j.issn.1008-8830.2302165

参考文献

1 Kochanek KD, Xu MAJ, Arias E. Mortality in the United States, 2019[EB/OL]. (2020-12-22)[2023-02-19]. https://www.cdc.gov/nchs/products/databriefs/db395.htm.
2 中国医师协会新生儿科医师分会循证专业委员会. 新生儿坏死性小肠结肠炎临床诊疗指南(2020)[J]. 中国当代儿科杂志, 2021, 23(1): 1-11. PMID: 33476530. PMCID: PMC7818154. DOI: 10.7499/j.issn.1008-8830.2011145.
3 Battersby C, Santhalingam T, Costeloe K, et al. Incidence of neonatal necrotising enterocolitis in high-income countries: a systematic review[J]. Arch Dis Child Fetal Neonatal Ed, 2018, 103(2): F182-F189. PMID: 29317459. DOI: 10.1136/archdischild-2017-313880.
4 Patel RM, Ferguson J, McElroy SJ, et al. Defining necrotizing enterocolitis: current difficulties and future opportunities[J]. Pediatr Res, 2020, 88(Suppl 1): 10-15. PMID: 32855506. PMCID: PMC8096612. DOI: 10.1038/s41390-020-1074-4.
5 Kim JH, Sampath V, Canvasser J. Challenges in diagnosing necrotizing enterocolitis[J]. Pediatr Res, 2020, 88(Suppl 1): 16-20. PMID: 32855507. DOI: 10.1038/s41390-020-1090-4.
6 Sarker IH. Machine learning: algorithms, real-world applications and research directions[J]. SN Comput Sci, 2021, 2(3): 160. PMID: 33778771. PMCID: PMC7983091. DOI: 10.1007/s42979-021-00592-x.
7 Dada EG, Bassi JS, Chiroma H, et al. Machine learning for email spam filtering: review, approaches and open research problems[J]. Heliyon, 2019, 5(6): e01802. PMID: 31211254. PMCID: PMC6562150. DOI: 10.1016/j.heliyon.2019.e01802.
8 Huang B, Wei J, Tang Y, et al. Enterprise risk assessment based on machine learning[J]. Comput Intell Neurosci, 2021, 2021: 6049195. PMID: 34824579. PMCID: PMC8610684. DOI: 10.1155/2021/6049195.
9 Jayatilake SMDAC, Ganegoda GU. Involvement of machine learning tools in healthcare decision making[J]. J Healthc Eng, 2021, 2021: 6679512. PMID: 33575021. PMCID: PMC7857908. DOI: 10.1155/2021/6679512.
10 van Druten J, Sharif MS, Chan SS, et al. A deep learning based suggested model to detect necrotising enterocolitis in abdominal radiography images[C]//2019 International Conference on Computing, Electronics & Communications Engineering (iCCECE). Piscataway, NJ, USA: IEEE, 2019: 118-123.
11 Hyun S, Kaewprag P, Cooper C, et al. Exploration of critical care data by using unsupervised machine learning[J]. Comput Methods Programs Biomed, 2020, 194: 105507. PMID: 32403049. DOI: 10.1016/j.cmpb.2020.105507.
12 Viroonluecha P, Egea-Lopez E, Santa J. Evaluation of blood glucose level control in type 1 diabetic patients using deep reinforcement learning[J]. PLoS One, 2022, 17(9): e0274608. PMID: 36099285. PMCID: PMC9469983. DOI: 10.1371/journal.pone.0274608.
13 Handelman GS, Kok HK, Chandra RV, et al. Peering into the black box of artificial intelligence: evaluation metrics of machine learning methods[J]. AJR Am J Roentgenol, 2019, 212(1): 38-43. PMID: 30332290. DOI: 10.2214/AJR.18.20224.
14 Schober P, Vetter TR. Logistic regression in medical research[J]. Anesth Analg, 2021, 132(2): 365-366. PMID: 33449558. PMCID: PMC7785709. DOI: 10.1213/ANE.0000000000005247.
15 Cho H, Lee EH, Lee KS, et al. Machine learning-based risk factor analysis of necrotizing enterocolitis in very low birth weight infants[J]. Sci Rep, 2022, 12(1): 21407. PMID: 36496465. PMCID: PMC9741654. DOI: 10.1038/s41598-022-25746-6.
16 Chibwesha CJ, Zanolini A, Smid M, et al. Predictors and outcomes of low birth weight in Lusaka, Zambia[J]. Int J Gynaecol Obstet, 2016, 134(3): 309-314. PMID: 27365291. PMCID: PMC4987240. DOI: 10.1016/j.ijgo.2016.03.021.
17 Senaviratna NAMR, A Cooray TMJ. Diagnosing multicollinearity of logistic regression model[J]. Asian J Probab Stat, 2019, 5(2): 1-9. DOI: 10.9734/ajpas/2019/v5i230132.
18 Lavery MR, Acharya P, Sivo SA, et al. Number of predictors and multicollinearity: what are their effects on error and bias in regression?[J]. Commun Stat Simul Comput, 2019, 48(1): 27-38. DOI: 10.1080/03610918.2017.1371750.
19 Boateng EY, Abaye DA. A review of the logistic regression model with emphasis on medical research[J]. J Data Anal Inf Process, 2019, 7(4): 190-207. DOI: 10.4236/jdaip.2019.74012.
20 Jijo BT, Abdulazeez AM. Classification based on decision tree algorithm for machine learning[J]. J Appl Sci Technol Trends, 2021, 2(1): 20-28. DOI: 10.38094/jastt20165.
21 Patel HH, Prajapati P. Study and analysis of decision tree based classification algorithms[J]. Int J Comput Sci Eng, 2018, 6(10): 74-78. DOI: 10.26438/ijcse/v6i10.7478.
22 McTavish H, Zhong C, Achermann R, et al. Fast sparse decision tree optimization via reference ensembles[J]. Proc Conf AAAI Artif Intell, 2022, 36(9): 9604-9613. PMID: 36051654. PMCID: PMC9429834. DOI: 10.1609/aaai.v36i9.21194.
23 Lueschow SR, Boly TJ, Jasper E, et al. A critical evaluation of current definitions of necrotizing enterocolitis[J]. Pediatr Res, 2022, 91(3): 590-597. PMID: 34021272. DOI: 10.1038/s41390-021-01570-y.
24 Battersby C, Longford N, Costeloe K, et al. Development of a gestational age-specific case definition for neonatal necrotizing enterocolitis[J]. JAMA Pediatr, 2017, 171(3): 256-263. PMID: 28046187. DOI: 10.1001/jamapediatrics.2016.3633.
25 Vermont Oxford Network. 2019 Manual of operations: part 2 data definitions & infant data forms[EB/OL]. (2019-02)[2023-02-19]. https://vtoxford.zendesk.com/hc/en-us/articles/360013115393-2019-Manual-of-Operations-Part-2-Release-23-2-PDF.
26 Caplan MS, Underwood MA, Modi N, et al. Necrotizing enterocolitis: using regulatory science and drug development to improve outcomes[J]. J Pediatr, 2019, 212: 208-215.e1. PMID: 31235383. DOI: 10.1016/j.jpeds.2019.05.032.
27 Gephart SM, Gordon PV, Penn AH, et al. Changing the paradigm of defining, detecting, and diagnosing NEC: perspectives on Bell's stages and biomarkers for NEC[J]. Semin Pediatr Surg, 2018, 27(1): 3-10. PMID: 29275814. DOI: 10.1053/j.sempedsurg.2017.11.002.
28 Savargiv M, Masoumi B, Keyvanpour MR. A new random forest algorithm based on learning automata[J]. Comput Intell Neurosci, 2021, 2021: 5572781. PMID: 33854542. PMCID: PMC8019375. DOI: 10.1155/2021/5572781.
29 Ali J, Khan R, Ahmad N, et al. Random forests and decision trees[J]. Int J Comput Sci Issues, 2012, 9(5): 272-278.
30 Zhao Q, Shi Q, Zhu Q, et al. A mini-review of advances in intestinal flora and necrotizing enterocolitis[J]. Lett Appl Microbiol, 2022, 75(1): 2-9. PMID: 35138661. DOI: 10.1111/lam.13670.
31 Bode L. Human milk oligosaccharides in the prevention of necrotizing enterocolitis: a journey from in vitro and in vivo models to mother-infant cohort studies[J]. Front Pediatr, 2018, 6: 385. PMID: 30564564. PMCID: PMC6288465. DOI: 10.3389/fped.2018.00385.
32 Bering SB. Human milk oligosaccharides to prevent gut dysfunction and necrotizing enterocolitis in preterm neonates[J]. Nutrients, 2018, 10(10): 1461. PMID: 30297668. PMCID: PMC6213229. DOI: 10.3390/nu10101461.
33 Masi AC, Embleton ND, Lamb CA, et al. Human milk oligosaccharide DSLNT and gut microbiome in preterm infants predicts necrotising enterocolitis[J]. Gut, 2021, 70(12): 2273-2282. PMID: 33328245. PMCID: PMC9231288. DOI: 10.1136/gutjnl-2020-322771.
34 Hearst MA, Dumais ST, Osuna E, et al. Support vector machines[J]. IEEE Intell Syst Appl, 1998, 13(4): 18-28. DOI: 10.1109/5254.708428.
35 李振宇. 基于机器学习算法的早产儿坏死性小肠结肠炎预测模型的建立[D]. 长春: 吉林大学, 2022.
36 Martin CR. Definitions of necrotizing enterocolitis: what are we defining and is machine learning the answer?[J]. Pediatr Res, 2022, 91(3): 488-489. PMID: 34465874. DOI: 10.1038/s41390-021-01687-0.
37 Salimi A, Ziaii M, Amiri A, et al. Using a feature subset selection method and support vector machine to address curse of dimensionality and redundancy in Hyperion hyperspectral data classification[J]. Egypt J Remote Sens Space Sci, 2018, 21(1): 27-36. DOI: 10.1016/j.ejrs.2017.02.003.
38 Bentéjac C, Cs?rg? A, Martínez-Mu?oz G. A comparative analysis of gradient boosting algorithms[J]. Artif Intell Rev, 2021, 54(3): 1937-1967. DOI: 10.1007/s10462-020-09896-5.
39 Weller JHD. Predicting necrotizing enterocolitis in hospitalized neonates[D]. Baltimore, Maryland: Johns Hopkins University, 2022.
40 高文静, 梁会营, 钟微, 等. 基于机器学习的新生儿坏死性小肠结肠炎的鉴别诊断[J]. 中国数字医学, 2019, 14(3): 50-52. DOI: 10.3969/j.issn.1673-7571.2019.03.014.
41 Gao W, Pei Y, Liang H, et al. Multimodal AI system for the rapid diagnosis and surgical prediction of necrotizing enterocolitis[J]. IEEE Access, 2021, 9: 51050-51064. DOI: 10.1109/ACCESS.2021.3069191.
42 Kukreja H, Bharath N, Siddesh CS, et al. An introduction to artificial neural network[J]. Int J Adv Res Innov Ideas Educ, 2016, 1(5): 27-30.
43 Irles C, González-Pérez G, Carrera Mui?os S, et al. Estimation of neonatal intestinal perforation associated with necrotizing enterocolitis by machine learning reveals new key factors[J]. Int J Environ Res Public Health, 2018, 15(11): 2509. PMID: 30423965. PMCID: PMC6267340. DOI: 10.3390/ijerph15112509.
44 Son J, Kim D, Na JY, et al. Development of artificial neural networks for early prediction of intestinal perforation in preterm infants[J]. Sci Rep, 2022, 12(1): 12112. PMID: 35840701. PMCID: PMC9287325. DOI: 10.1038/s41598-022-16273-5.
45 Alzubaidi L, Zhang J, Humaidi AJ, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions[J]. J Big Data, 2021, 8(1): 53. PMID: 33816053. PMCID: PMC8010506. DOI: 10.1186/s40537-021-00444-8.
46 Lin YC, Salleb-Aouissi A, Hooven TA. Interpretable prediction of necrotizing enterocolitis from machine learning analysis of premature infant stool microbiota[J]. BMC Bioinformatics, 2022, 23(1): 104. PMID: 35337258. PMCID: PMC8953333. DOI: 10.1186/s12859-022-04618-w.
47 Vandenplas Y, Carnielli VP, Ksiazyk J, et al. Factors affecting early-life intestinal microbiota development[J]. Nutrition, 2020, 78: 110812. PMID: 32464473. DOI: 10.1016/j.nut.2020.110812.
48 Rai A. Explainable AI: from black box to glass box[J]. J Acad Mark Sci, 2020, 48(1): 137-141. DOI: 10.1007/s11747-019-00710-5.
49 Rigby MJ. Ethical dimensions of using artificial intelligence in health care[J]. AMA J Ethics, 2019, 21(2): E121-E124. DOI: 10.1001/amajethics.2019.121.
50 Cortez P, Embrechts MJ. Using sensitivity analysis and visualization techniques to open black box data mining models[J]. Inf Sci, 2013, 225: 1-17. DOI: 10.1016/j.ins.2012.10.039.
51 McCoy LG, Brenna CTA, Chen SS, et al. Believing in black boxes: machine learning for healthcare does not need explainability to be evidence-based[J]. J Clin Epidemiol, 2022, 142: 252-257. PMID: 34748907. DOI: 10.1016/j.jclinepi.2021.11.001.
52 Abdullah YI, Schuman JS, Shabsigh R, et al. Ethics of artificial intelligence in medicine and ophthalmology[J]. Asia Pac J Ophthalmol (Phila), 2021, 10(3): 289-298. PMID: 34383720. PMCID: PMC9167644. DOI: 10.1097/APO.0000000000000397.
53 刘艳红. 人工智能的可解释性与AI的法律责任问题研究[J]. 法制与社会发展, 2022, 28(1): 78-91.