机器学习在新生儿败血症早期识别和护理中的研究进展

doi:10.3761/j.issn.2096-7446.2023.06.006

摘要/Abstract

摘要： 机器学习算法是指研究分析数据,从而获得数据间的规律,并利用规律对未知数据进行预测的算法。电子病历中包括反映患者疾病相关的海量数据信息,这为机器学习在医疗护理领域的实践提供了数据基础。该文综述了机器学习在新生儿败血症早期识别和护理领域的应用现状,从电子病历数据库中获取包括患儿人口统计学特征、生命体征、抗生素使用情况、病原学特征和整个新生儿住院期间的治疗等数据,通过机器学习算法研发预测模型,以期为护理工作者针对新生儿败血症实现早期识别、尽早实施护理计划、提供护理干预给予参考。机器学习建模可用于新生儿败血症的早期识别和诊断,临床推广还有待于多中心大规模数据基础上应用前瞻性研究方法进一步证实其准确性和广泛适应性。

关键词: 机器学习, 新生儿败血症, 预测模型, 危重病护理

Abstract: Machine learning algorithms are algorithms that study and analyze data to obtain regularities among the data and use the regularities to predict unknown data. Electronic medical records contain a large amount of data information about patients' diseases,which provides the data basis for the practice of machine learning in the field of medical and nursing. This article reviewed the application status of machine learning in the early identification and nursing of neonatal sepsis,including obtaining data such as demographic characteristics,vital signs,antibiotic use,etiological characteristics and treatment of the entire hospitalization period from the electronic medical record database,and developing predictive models through machine learning algorithms,in order to provide reference for clinic nurses to realize early identification of neonatal sepsis,implement nursing plans as early as possible,and provide nursing interventions. Machine learning modeling can be used for early identification and diagnosis of neonatal sepsis. Its accuracy and wide adaptability need to be further confirmed by prospective studies based on multi-center large-scale data.

Key words: Machine Learning, Neonatal Sepsis, Prediction Model, Critical Care Nursing

束礼梅, 李秋芳, 顾慧敏, 徐鑫芬, 江川. 机器学习在新生儿败血症早期识别和护理中的研究进展[J]. 中华急危重症护理杂志, 2023, 4(6): 515-518.

SHU Limei, LI Qiufang, GU Huimin, XU Xinfen, JIANG Chuan. Research progress of machine learning in the early identification and nursing of neonatal sepsis[J]. Chinese Journal of Emergency and Critical Care Nursing, 2023, 4(6): 515-518.

参考文献

[1] Wang Y,Zhu Y,Xue Q,et al.Predicting chronic pain in postoperative breast cancer patients with multiple machine learning and deep learning models[J]. J Clin Anesth,2021,74:110423.
[2] Strom JB,Sengupta PP.Predicting preclinical heart failure progression:the rise of machine-learning for population health[J]. JACC Cardiovasc Imaging,2022,15(2):209-211.
[3] Shane AL,Sánchez PJ,Stoll BJ.Neonatal sepsis[J]. Lancet,2017,390(10104):1770-1780.
[4] GBD Mortality and Causes of Death Collaborators. Global,regional,and national life expectancy,all-cause mortality,and cause-specific mortality for 249 causes of death,1980-2015:a systematic analysis for the Global Burden of Disease Study 2015[J]. Lancet,2016,388(10053):1459-1544.
[5] Kim F,Polin RA,Hooven TA.Neonatal sepsis[J]. BMJ,2020,371:m3672.
[6] 中华医学会儿科学分会新生儿学组,中国医师协会新生儿科医师分会感染专业委员会. 新生儿败血症诊断及治疗专家共识(2019年版)[J]. 中华儿科杂志,2019(4):252-257.
The Neonatology Group of Pediatric Branch of Chinese Medical Association,Infectious Diseases Professional Committee of Neonatology Branch of Chinese Medical Doctor Association. Expert consensus on the diagnosis and management of neonatal sepsis(version2019)[J]. Chin J Pediatr,2019(4):252-257.
[7] Roy MP,Bhatt M,Maurya V,et al.Changing trend in bacterial etiology and antibiotic resistance in sepsis of intramural neonates at a tertiary care hospital[J]. J Postgrad Med,2017,63(3):162-168.
[8] Machado FR,Salomão R,Rigato O,et al.Late recognition and illness severity are determinants of early death in severe septic patients[J]. Clinics(Sao Paulo),2013,68(5):586-591.
[9] Greco M,Caruso PF,Cecconi M.Artificial intelligence in the intensive care unit[J]. Semin Respir Crit Care Med,2021,42(1):2-9.
[10] 吴静洁,杨丽黎. 机器学习在构建高血压风险模型中的研究进展[J]. 护理与康复,2021,20(2):33-36.
Wu JJ,Yang LL.Research progress of machine learning in constructing hypertension risk models[J]. J Nurs Rehabil,2021,20(2):33-36.
[11] 杨荣根,王博,龚乐君. 基于CRF和深度学习的病历实体识别的研究[J]. 南京师范大学学报(工程技术版),2022,22(1):81-85.
Yang RG,Wang B,Gong LJ.Research on medical record entity recognition based on CRF and Bi-LSTM-CRF[J]. J Nanjing Norm Univ Eng Technol Ed,2022,22(1):81-85.
[12] Johnson A,Yang F,Gollarahalli S,et al.Use of mobile health apps and wearable technology to assess changes and predict pain during treatment of acute pain in sickle cell disease:feasibility study[J]. JMIR Mhealth Uhealth, 2019,7(12):e13671.
[13] Pepito JA,Locsin R.Can nurses remain relevant in a technologically advanced future?[J]. Int J Nurs Sci,2019,6(1):106-110.
[14] Carroll W.Artificial intelligence,nurses and the quadruple aim[J]. Online J Nurs Inform,2018,22(2):3-1.
[15] Joseph J,Moore ZEH,Patton D,et al.The impact of implementing speech recognition technology on the accuracy and efficiency(time to complete）clinical documentation by nurses:a systematic review[J]. J Clin Nurs,2020,29(13/14):2125-2137.
[16] Lindberg DS,Prosperi M,Bjarnadottir RI,et al.Identification of important factors in an inpatient fall risk prediction model to improve the quality of care using EHR and electronic administrative data:a machine-learning approach[J]. Int J Med Inform,2020,143:104272.
[17] 曲超然,王青,韩琳,等. 机器学习算法在压力性损伤管理中的应用进展[J]. 中华护理杂志,2021,56(2):212-217.
Qu CR,Wang Q,Han L,et al.A literature review on the application of machine learning algorithms in pressure injury management[J]. Chin J Nurs,2021,56(2):212-217.
[18] Polin RA,Committee on Fetus and Newborn. Management of neonates with suspected or proven early-onset bacterial sepsis[J]. Pediatrics,2012,129(5):1006-1015.
[19] 中国妇幼保健协会新生儿保健专业委员会,中国医师协会新生儿科医师分会. 母婴同室早发感染高危新生儿临床管理专家共识[J]. 中华围产医学杂志,2021,24(8):567-575.
Neonatal Health Professional Committee of China Maternal and Child Health Association,Neonatologist Branch of Chinese Medical Doctor Association. Expert consensus on clinical management of newborns at high-risk of early-onset infection at rooming-in ward[J]. Chin J Perinat Med,2021,24(8):567-575.
[20] López-Martínez F,Núñez-Valdez ER,Lorduy Gomez J,et al.A neural network approach to predict early neonatal sepsis[J]. Comput Electr Eng,2019,76:379-388.
[21] 吴芳芳,余瑛,宋华芳. 新生儿早发型和晚发型败血症的高危因素调查[J]. 中国妇幼保健,2020,35(12):2300-2303.
Wu FF,Yu Y,Song HF.Investigation on high-risk factors of early-onset sepsis and late-onset sepsis in neonates[J]. Matern Child Heal Care China,2020,35(12):2300-2303.
[22] Mani S,Ozdas A,Aliferis C,et al.Medical decision support using machine learning for early detection of late-onset neonatal sepsis[J]. J Am Med Inform Assoc,2014,21(2):326-336.
[23] Roland D,Madar J,Connolly G.The newborn early warning (NEW）system:development of an at-risk infant intervention system[J]. Infant,2010,6(4):116.
[24] 梁曼,冯晓慧,沈静. 母婴同室新生儿常见感染性疾病早期预警评估表的效度研究[J]. 四川医学,2021,42(2):109-112.
Liang M,Feng XH,Shen J.Validity of early warning assessment for common infectious diseases of mother-newborns[J]. Sichuan Med J,2021,42(2):109-112.
[25] Back JS,Jin YJ,Jin TX,et al.Development and validation of an automated sepsis risk assessment system[J]. Res Nurs Health,2016,39(5):317-327.