非结构化数据在儿童脓毒症早期预测中的应用价值及进展
Application Value and Progress of Unstructured Data in Early Prediction of Pediatric Sepsis
DOI: 10.12677/acm.2025.153769, PDF,   
作者: 宋婉沁, 李 静*：重庆医科大学附属儿童医院重症医学科，国家儿童健康与疾病临床医学研究中心，儿童发育疾病研究教育部重点实验室，重庆市重点实验室，重庆；王浩林：重庆医科大学信息学院，重庆
关键词: 脓毒症；非结构化数据；早期诊断；预测模型；Sepsis； Unstructured-Data； Early Diagnosis； Predictive-Model
摘要: 儿童脓毒症是感染诱发的可导致器官功能障碍和死亡的急危重症，早期识别和诊断对于防治脓毒性休克和改善预后至关重要。根据临床标准，医生需要结合患儿的临床表现、病史、体格检查和实验室检查等综合判断并诊断。随着医疗信息化的不断发展，储存在电子病历中的数据被得到更多的关注和挖掘，除了结构化数据外，非结构化数据约占总数据的80%，有着更为丰富的信息，近年来逐渐开始运用于各种疾病的诊疗预测模型中，且在早期诊断、个性化治疗方案制定及预后评估等方面均取得了显著性的进展。本文旨在对非结构化数据在脓毒症早期预测模型中的运用前景及其挑战进行综述，为儿童脓毒症的早期诊断、个性化治疗和预后方面研究提供理论基础。
Abstract: Pediatric sepsis is an acute and critical illness induced by infection that can lead to organ dysfunction and death. Early recognition and diagnosis are crucial for preventing septic shock and improving prognosis. According to clinical standards, doctors need to comprehensively assess and diagnose pediatric sepsis by considering the child’s clinical manifestations, medical history, physical examination, and laboratory tests. With the continuous development of artificial intelligence, data stored in electronic health records (EHRs) has received increasing attention and exploration. In addition to structured data, unstructured data, which accounts for approximately 80% of the total data, contains richer information and has gradually been applied in predictive models for the diagnosis and treatment of various diseases in recent years. Unstructured data predictive models have increasingly become a research focus in the field of sepsis, achieving significant progress in early diagnosis, personalized treatment planning, and prognosis assessment. This article aims to review the application prospects and challenges of unstructured data in early predictive models for pediatric sepsis, providing a theoretical basis for research on early diagnosis, personalized treatment, and prognosis in pediatric sepsis.
文章引用：宋婉沁, 王浩林, 李静. 非结构化数据在儿童脓毒症早期预测中的应用价值及进展[J]. 临床医学进展, 2025, 15(3): 1501-1506. https://doi.org/10.12677/acm.2025.153769

参考文献

[1] Rudd, K.E., Johnson, S.C., Agesa, K.M., Shackelford, K.A., Tsoi, D., Kievlan, D.R., et al. (2020) Global, Regional, and National Sepsis Incidence and Mortality, 1990-2017: Analysis for the Global Burden of Disease Study. The Lancet, 395, 200-211. [Google Scholar] [CrossRef] [PubMed]
[2] Kissoon, N. and Uyeki, T.M. (2016) Sepsis and the Global Burden of Disease in Children. JAMA Pediatrics, 170, 107-108. [Google Scholar] [CrossRef] [PubMed]
[3] Bassat, Q., Blau, D.M., Ogbuanu, I.U., Samura, S., Kaluma, E., Bassey, I., et al. (2023) Causes of Death among Infants and Children in the Child Health and Mortality Prevention Surveillance (CHAMPS) Network. JAMA Network Open, 6, e2322494. [Google Scholar] [CrossRef] [PubMed]
[4] Marik, P.E. and Farkas, J.D. (2018) The Changing Paradigm of Sepsis: Early Diagnosis, Early Antibiotics, Early Pressors, and Early Adjuvant Treatment. Critical Care Medicine, 46, 1690-1692. [Google Scholar] [CrossRef] [PubMed]
[5] 王仲, 魏捷, 朱华栋, 等. 中国脓毒症早期预防与阻断急诊专家共识[J]. 中国急救医学, 2020, 40(7): 577-588.
[6] Kumar, A., Roberts, D., Wood, K.E., Light, B., Parrillo, J.E., Sharma, S., et al. (2006) Duration of Hypotension before Initiation of Effective Antimicrobial Therapy Is the Critical Determinant of Survival in Human Septic Shock. Critical Care Medicine, 34, 1589-1596. [Google Scholar] [CrossRef] [PubMed]
[7] Beam, A.L. and Kohane, I.S. (2018) Big Data and Machine Learning in Health Care. Journal of the American Medical Association, 319, 1317-1318. [Google Scholar] [CrossRef] [PubMed]
[8] Vincent, J.-L., Moreno, R., Takala, J., Willatts, S., De Mendonça, A., Bruining, H., et al. (1996) The SOFA (Sepsis-Related Organ Failure Assessment) Score to Describe Organ Dysfunction/Failure. Intensive Care Medicine, 22, 707-710. [Google Scholar] [CrossRef] [PubMed]
[9] Levy, M.M., Fink, M.P., Marshall, J.C., Abraham, E., Angus, D., et al. (2003) 2001 SCCM/ESICM/ACCP/ATS/SIS International Sepsis Definitions Conference. Intensive Care Medicine, 29, 530-538. [Google Scholar] [CrossRef] [PubMed]
[10] Tayefi, M., Ngo, P., Chomutare, T., Dalianis, H., Salvi, E., Budrionis, A., et al. (2021) Challenges and Opportunities beyond Structured Data in Analysis of Electronic Health Records. WIREs Computational Statistics, 13, e1549. [Google Scholar] [CrossRef] 
[11] Zhang, D., Yin, C., Zeng, J., Yuan, X. and Zhang, P. (2020) Combining Structured and Unstructured Data for Predictive Models: A Deep Learning Approach. BMC Medical Informatics and Decision Making, 20, 1-11. [Google Scholar] [CrossRef] [PubMed]
[12] 吴宗友, 白昆龙, 杨林蕊, 等. 电子病历文本挖掘研究综述[J]. 计算机研究与发展, 2021, 58(3): 513-527.
[13] Spasic, I. and Nenadic, G. (2020) Clinical Text Data in Machine Learning: Systematic Review. JMIR Medical Informatics, 8, e17984. [Google Scholar] [CrossRef] [PubMed]
[14] Goh, K.H., Wang, L., Yeow, A.Y.K., Poh, H., Li, K., Yeow, J.J.L., et al. (2021) Artificial Intelligence in Sepsis Early Prediction and Diagnosis Using Unstructured Data in Healthcare. Nature Communications, 12, Article No. 711. [Google Scholar] [CrossRef] [PubMed]
[15] Horng, S., Sontag, D.A., Halpern, Y., Jernite, Y., Shapiro, N.I. and Nathanson, L.A. (2017) Creating an Automated Trigger for Sepsis Clinical Decision Support at Emergency Department Triage Using Machine Learning. PLOS ONE, 12, e0174708. [Google Scholar] [CrossRef] [PubMed]
[16] Alsentzer, E., Murphy, J., Boag, W., Weng, W., Jindi, D., Naumann, T., et al. (2019) Publicly Available Clinical. Proceedings of the 2nd Clinical Natural Language Processing Workshop, Minneapolis, June 2019, 72-78. [Google Scholar] [CrossRef] 
[17] Amrollahi, F.P., Shashikumar, S., Razmi, F. and Nemati, S. (2021) Contextual Embeddings from Clinical Notes Improves Prediction of Sepsis. Intensive Care and Critical Care Medicine, 1-6. [Google Scholar] [CrossRef] 
[18] Barton, C., Chettipally, U., Zhou, Y., Jiang, Z., Lynn-Palevsky, A., Le, S., et al. (2019) Evaluation of a Machine Learning Algorithm for up to 48-Hour Advance Prediction of Sepsis Using Six Vital Signs. Computers in Biology and Medicine, 109, 79-84. [Google Scholar] [CrossRef] [PubMed]
[19] Mao, Q., Jay, M., Hoffman, J.L., Calvert, J., Barton, C., Shimabukuro, D., et al. (2018) Multicentre Validation of a Sepsis Prediction Algorithm Using Only Vital Sign Data in the Emergency Department, General Ward and ICU. BMJ Open, 8, e017833. [Google Scholar] [CrossRef] [PubMed]
[20] van Wyk, F., Khojandi, A. and Kamaleswaran, R. (2019) Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data: A Sepsis Case Study. IEEE Journal of Biomedical and Health Informatics, 23, 978-986. [Google Scholar] [CrossRef] [PubMed]
[21] Wang, D., Li, J., Sun, Y., Ding, X., Zhang, X., Liu, S., et al. (2021) A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients. Frontiers in Public Health, 9, Article 754348. [Google Scholar] [CrossRef] [PubMed]
[22] Apostolova, E. and Velez, T. (2017) Toward Automated Early Sepsis Alerting: Identifying Infection Patients from Nursing Notes. BioNLP 2017, Vancouver, August 2017, 257-262. [Google Scholar] [CrossRef] 
[23] Qin, F., Madan, V., Ratan, U., et al. (2021) Improving Early Sepsis Prediction with Multi Modal Learning.
[24] Solé-Ribalta, A., Launes, C., Felipe-Villalobos, A., Balaguer, M., Luaces, C., Garrido, R., et al. (2022) New Multivariable Prediction Model Pediatric Sepsis Recognition and Stratification (PESERS Score) Shows Excellent Discriminatory Capacity. Acta Paediatrica, 111, 1209-1219. [Google Scholar] [CrossRef] [PubMed]
[25] Chen, X., Zhang, R. and Tang, X.Y. (2021) Towards Real-Time Diagnosis for Pediatric Sepsis Using Graph Neural Network and Ensemble Methods. European Review for Medical & Pharmacological Sciences, 25, 4693-4701.
[26] 李少军. 基于大数据和机器学习开发儿童脓毒症诊断与预后模型的队列研究[D]: [博士学位论文]. 重庆: 重庆医科大学, 2023.

为你推荐