机器学习在新生儿坏死性小肠结肠炎手术指征预测中的应用研究进展
Research Progress on the Application of Machine Learning in Predicting Surgical Indications for Necrotizing Enterocolitis in Neonates
摘要: 新生儿坏死性小肠结肠炎是早产儿重症监护中的急危重症，其中约20%~40%的患儿需接受手术治疗，但手术时机选择困难，目前临床决策依赖腹部X线、超声等影像学动态评估与经验性判断，缺乏统一量化预测工具。近年来，机器学习技术在NEC手术指征预测中得到广泛应用。本文系统综述机器学习在该领域的研究进展，分析对比现有模型的构建策略、算法特点与预测效能，总结其优势与不足，并探讨临床转化面临的挑战与未来方向，以期为机器学习在NEC手术预测中的进一步发展提供参考。
Abstract: Necrotizing enterocolitis (NEC) is an acute and critical disease in preterm infants under neonatal intensive care. Approximately 20%~40% of affected infants require surgical treatment, yet the selection of optimal surgical timing poses great challenges. At present, clinical decision-making depends on serial imaging evaluations including abdominal radiography and ultrasonography as well as empirical judgment, and standardized quantitative prediction tools are lacking. In recent years, machine learning techniques have been widely adopted for predicting surgical indications of NEC. This article systematically reviews research advances in machine learning in this field, analyzes and compares construction strategies, algorithm characteristics and predictive performance of existing models, summarizes their strengths and limitations, and discusses challenges and future directions for clinical translation, so as to provide a reference for further development of machine learning in surgical prediction of NEC.
文章引用：申桂源, 薛江. 机器学习在新生儿坏死性小肠结肠炎手术指征预测中的应用研究进展[J]. 临床医学进展, 2026, 16(9): 59-67. https://doi.org/10.12677/acm.2026.1693020

参考文献

[1] Jiang, S., Yan, W., Li, S., Zhang, L., Zhang, Y., Shah, P.S., et al. (2020) Mortality and Morbidity in Infants < 34 Weeks’ Gestation in 25 NICUs in China: A Prospective Cohort Study. Frontiers in Pediatrics, 8, Article ID: 33.
https://doi.org/10.3389/fped.2020.00033
[2] 杜京斌, 黄金狮. 新生儿坏死性小肠结肠炎的外科手术治疗现状[J]. 中国实用儿科杂志, 2024, 39(5): 334-338.
[3] Sitek, A., Seliga-Siwecka, J., Płotka, S., Grzeszczyk, M.K., Seliga, S., Włodarczyk, K., et al. (2023) Artificial Intelligence in the Diagnosis of Necrotising Enterocolitis in Newborns. Pediatric Research, 93, 376-381.
https://doi.org/10.1038/s41390-022-02322-2
[4] Maheshwari, A., Singh, R., Mishra, V., Cuna, A., Schwartz, D.M. and Chan, S. (2022) Imaging for Diagnosis and Assessment of Necrotizing Enterocolitis. Newborn, 1, 182-189.
https://doi.org/10.5005/jp-journals-11002-0002
[5] 姜齐, 张莉. 人工智能在新生儿坏死性小肠结肠炎辅助诊疗中的研究进展[J]. 中国当代儿科杂志, 2025, 27(10): 1281-1285.
[6] McElroy, S.J. and Lueschow, S.R. (2023) State of the Art Review on Machine Learning and Artificial Intelligence in the Study of Neonatal Necrotizing Enterocolitis. Frontiers in Pediatrics, 11, Article ID: 1182597.
https://doi.org/10.3389/fped.2023.1182597
[7] Duci, M., Verlato, G., Moschino, L., Uccheddu, F. and Fascetti-Leon, F. (2025) Advances in Artificial Intelligence and Machine Learning for Precision Medicine in Necrotizing Enterocolitis and Neonatal Sepsis: A State-of-the-Art Review. Children, 12, Article 498.
https://doi.org/10.3390/children12040498
[8] Kim, S.H., Oh, Y.J., Son, J., Jung, D., Kim, D., Ryu, S.R., et al. (2024) Machine Learning-Based Analysis for Prediction of Surgical Necrotizing Enterocolitis in Very Low Birth Weight Infants Using Perinatal Factors: A Nationwide Cohort Study. European Journal of Pediatrics, 183, 2743-2751.
https://doi.org/10.1007/s00431-024-05505-7
[9] Cho, H., Lee, E.H., Lee, K. and Heo, J.S. (2022) Machine Learning-Based Risk Factor Analysis of Necrotizing Enterocolitis in Very Low Birth Weight Infants. Scientific Reports, 12, Article No. 21407.
https://doi.org/10.1038/s41598-022-25746-6
[10] Hu, M., Ju, X., Zhang, X., Li, X., Zhang, Z., Chen, Z., et al. (2025) New Biomarkers to Predict the Need for Surgery of Necrotizing Enterocolitis: A Study Based on Abdominal X-Ray Radiomics and Machine Learning. BioMedical Engineering Online, 24, Article No. 144.
https://doi.org/10.1186/s12938-025-01466-6
[11] Li, Y., Wu, K., Yang, H., Wang, J., Chen, Q., Ding, X., et al. (2024) Surgical Prediction of Neonatal Necrotizing Enterocolitis Based on Radiomics and Clinical Information. Abdominal Radiology, 49, 1020-1030.
https://doi.org/10.1007/s00261-023-04157-9
[12] Weller, J.H., Scheese, D., Tragesser, C., Yi, P.H., Alaish, S.M. and Hackam, D.J. (2024) Artificial Intelligence Vs. Doctors: Diagnosing Necrotizing Enterocolitis on Abdominal Radiographs. Journal of Pediatric Surgery, 59, Article 161592.
https://doi.org/10.1016/j.jpedsurg.2024.06.001
[13] Cui, C., Qiu, L., Li, L., Chen, F., Liu, X., Sun, H., et al. (2024) A Time Series Algorithm to Predict Surgery in Neonatal Necrotizing Enterocolitis. BMC Medical Informatics and Decision Making, 24, Article No. 304.
https://doi.org/10.1186/s12911-024-02695-w
[14] Li, X., Zhang, L., Gao, H., Wang, Y., Huang, F., Li, D., et al. (2025) The Prediction Models for the Optimal Timing of Surgical Intervention for Necrotizing Enterocolitis: Nomogram vs. Five Machine Learning Models. Pediatric Surgery International, 41, Article No. 260.
https://doi.org/10.1007/s00383-025-06163-y
[15] Lure, A.C., Du, X., Black, E.W., Irons, R., Lemas, D.J., Taylor, J.A., et al. (2021) Using Machine Learning Analysis to Assist in Differentiating between Necrotizing Enterocolitis and Spontaneous Intestinal Perforation: A Novel Predictive Analytic Tool. Journal of Pediatric Surgery, 56, 1703-1710.
https://doi.org/10.1016/j.jpedsurg.2020.11.008
[16] Verhoeven, R., Kupers, T., Brunsch, C.L., Hulscher, J.B.F. and Kooi, E.M.W. (2024) Using Vital Signs for the Early Prediction of Necrotizing Enterocolitis in Preterm Neonates with Machine Learning. Children, 11, Article 1452.
https://doi.org/10.3390/children11121452
[17] Sun, D., Xie, C., Zhao, Y., Liao, J., Zhang, Y., Hua, K., et al. (2026) Transfer Learning Prediction of Surgical Necrotizing Enterocolitis in Preterm Infants without Pneumoperitoneum on Abdominal X-Ray. Translational Pediatrics, 15, 68-68.
https://doi.org/10.21037/tp-2025-1-867
[18] Gao, W., Pei, Y., Liang, H., Lv, J., Chen, J. and Zhong, W. (2021) Multimodal AI System for the Rapid Diagnosis and Surgical Prediction of Necrotizing Enterocolitis. IEEE Access, 9, 51050-51064.
https://doi.org/10.1109/access.2021.3069191
[19] Jin, X., Sun, W., Li, Y., Su, Y., Xu, L. and Zhu, X. (2025) Use of CatBoost Algorithm to Identify the Need for Surgery in Infants with Necrotizing Enterocolitis. Frontiers in Pediatrics, 13, Article ID: 1465278.
https://doi.org/10.3389/fped.2025.1465278
[20] Lundberg, S.M. and Lee, S. (2017) A Unified Approach to Interpreting Model Predictions. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, 4-9 December 2017, 4768-4777.
[21] Qi, G., Huang, S., Lai, D., Li, J., Zhao, Y., Shen, C., et al. (2022) An Improved Joint Non-Negative Matrix Factorization for Identifying Surgical Treatment Timing of Neonatal Necrotizing Enterocolitis. Bosnian Journal of Basic Medical Sciences, 22, 972-981.
https://doi.org/10.17305/bjbms.2022.7046
[22] Li, Y., Wu, K., Mou, Y., Zhong, C., Zhang, G., Tan, R., et al. (2025) Artificial Intelligence Aids Doctors in Diagnosing Necrotizing Enterocolitis and Predicting Surgery Using Abdominal Radiographs: A Multicenter Study. Quantitative Imaging in Medicine and Surgery, 15, 10722-10737.
https://doi.org/10.21037/qims-2024-2867
[23] Li, Y., Zhang, P., Wu, J., Wang, Y., Chen, Y., Sheng, S., et al. (2025) Machine Learning-Based Prediction of Surgical Intervention in Preterm Infants with Necrotizing Enterocolitis: A Retrospective Cohort Study. Children, 13, Article 21.
https://doi.org/10.3390/children13010021
[24] Bethell, G.S., Hall, N.J., Battersby, C., Knight, M. and Darlington, A. (2025) Surgeons and Neonatologists Views about Surgical Decision-Making in Necrotising Enterocolitis. Archives of Disease in Childhood-Fetal and Neonatal Edition, 110, 595-601.
https://doi.org/10.1136/archdischild-2025-328480
[25] Che, Z., Purushotham, S., Cho, K., Sontag, D. and Liu, Y. (2018) Recurrent Neural Networks for Multivariate Time Series with Missing Values. Scientific Reports, 8, Article No. 6085.
https://doi.org/10.1038/s41598-018-24271-9
[26] Chauhan, V.K., Thakur, A., O’Donoghue, O., Rohanian, O., Molaei, S. and Clifton, D.A. (2024) Continuous Patient State Attention Model for Addressing Irregularity in Electronic Health Records. BMC Medical Informatics and Decision Making, 24, Article No. 117.
https://doi.org/10.1186/s12911-024-02514-2
[27] Zeng, Z., Lin, M., Liu, Y., Yao, S. and Gong, X. (2025) HET-VQVAE: A Novel Encoder-Decoder Framework for Irregularly-Sampled Multivariate Time Series of Patients. Journal of Big Data, 12, Article No. 247.
https://doi.org/10.1186/s40537-025-01303-6

为你推荐