Research on algorithms for identifying the severity of pediatric patients with ARDS based on noninvasive parameters
-
摘要: 目的:现阶段儿科ICU诊断急性呼吸窘迫综合征 (ARDS) 主要依赖于氧合指数, 也就是PaO2/FiO2, 而动脉血氧分压 (PaO2) 必须通过血气分析获得, 但是血气分析是一个有创、不连续的监测手段。本文研究无创参数SpO2/FiO2和PaO2/FiO2以及OSI和OI之间的关系, 探索使用无创参数辨识ARDS患儿疾病严重程度的可能性。方法:本研究利用MIMIC-III数据库, 获取患者相关生理参数, 将患儿人群随机分为训练集和测试集, 在训练集上利用广义线性回归模型, 分别建立S/F与P/F、Lg (S/F) 与Lg (P/F)、OSI与OI之间的线性回归模型, 在测试集上研究3种模型对于重度ARDS、中度ARDS、轻度ARDS的辨识效果。结果:在训练集分别建立了S/F-P/F、Lg (S/F) -Lg (P/F)、OSI-OI3种模型的线性回归方程, 对于S/F-P/F、Lg (S/F) -Lg (P/F) 两种模型分别确定了P/F在100、200、300处对应的S/F阈值, 对于OSI-OI模型确定了OI在4、8、16处的对应的OSI阈值。在测试集上使用对应阈值对ARDS疾病严重程度进行辨识, 获得了3种模型的辨识敏感性、特异性、准确率、AUC值。结论:通过以上研究可知, 相较于S/F-P/F、Lg (S/F) -Lg (P/F) 模型, OSI-OI模型对于患儿ARDS疾病严重程度有较好的辨识能力, 在患儿血气分析结果缺失的情况下, 可以考虑使用无创参数OSI代替PaO2/FiO2, 作为ARDS患儿病情诊断的辅助手段。Abstract: Objective: At present, pediatric ICU diagnosis of acute respiratory distress syndrome (ARDS) mainly depends on the oxygenation index (PaO2/FiO2), and arterial oxygen partial pressure (PaO2) must be obtained through blood gas analysis, but blood gas analysis is an invasive, discontinuous Monitoring means.This article studies the relationship between non-invasive parameters SpO2/FiO2-PaO2/FiO2 and OSI-OI, and explores the possibility of using non-invasive parameters to identify the severity of disease in children with ARDS.Method: In this study, MIMIC-III database was used to obtain patient-related physiological parameters.The children were randomly divided into training set and test set.Generalized linear regression model was used on the training set to establish S/F and P/F and Lg, respectively./F) Linear regression model between Lg (P/F), OSI and OI.The effect of the three models on the detection of severe ARDS, moderate ARDS, and mild ARDS was studied on the test set.Result: In the training set, the linear regression equations of S/F-P/F, Lg (S/F) -Lg (P/F), and OSI-OI were established respectively for S/FP/F and Lg (S/F).The Lg (P/F) models respectively determine the corresponding S/F thresholds at 100, 200, and 300 for the P/F, and the corresponding OSI thresholds at 4, 8, and 16 for the OSI-OI model.The corresponding thresholds were used to identify the severity of ARDS disease on the test set.The sensitivity, specificity, accuracy, and AUC values of the three models were obtained.Conclusion: The above study shows that the OSI-OI model has better ability to identify the severity of ARDS disease in children compared with the S/F-P/F and Lg (S/F) -Lg (P/F) models.In the absence of blood gas analysis results in children, noninvasive parameters OSI can be used instead of PaO2/FiO2 as an aid in the diagnosis of children with ARDS.
-
[1] Rezoagli E, Fumagalli R, Bellani G.Definition and epidemiology of acute respiratory distress syndrome[J].Ann Transl Med, 2017, 5 (14):282.
[2] The Pediatric Acute Lung Injury Consensus Conference Group.Pediatric acute respiratory distress syndrome:consensus recommendations from the Pediatric Acute Lung Injury Consensus Conference[J].Pediatr Crit Care Med, 2015, 16 (5):428.
[3] Cheifetz IM.Year in Review 2015:Pediatric ARDS[J].Respir Care, 2016, 61 (7):980-985.
[4] Bernard GR, Artigas A, Brigham KL, et al.Report of the American-European consensus conference on ARDS:definitions, mechanisms, relevant outcomes and clinical trial coordination.The Consensus Committee[J].Intensive Care Med, 1994, 20 (3):225-232.
[5] 尹文, 李俊杰, 张斌, 等.急性呼吸窘迫综合征诊疗新进展[J].临床急诊杂志, 2017, 18 (2):81-85.
[6] 赵惠军, 杨鹏程, 王亚林.基于无创参数SpO2/FiO2辨识ARDS患者疾病程度的研究[J].医疗卫生装备, 2018, 39 (3):6-9, 14.
[7] Brown SM, Grissom CK, Moss M, et al.Non-linear imputation of PaO2/FIO2, from SpO2/FIO2, among patients with Acute Respiratory Distress Syndrome[J].Chest, 2016, 150 (2):307-313.
[8] Bilan N, Dastranji A, Ghalehgolab BA.Comparison of the spo2/fio2ratio and the pao2/fio2ratio in patients with acute lung injury or acute respiratory distress syndrome[J].Chest, 2007, 132 (2):410-417.
[9] 杨鹏程, 王春飞, 张广, 等.基于多种方法评估ARDS病情严重程度及预后的现状与展望[J].军事医学, 2017, 41 (12):1021-1024, 1026.
[10] Khemani RG, Patel NR, Rd BR, et al.Comparison of the pulse oximetric saturation/fraction of inspired oxygen ratio and the PaO2/fraction of inspired oxygen ratio in children[J].Chest, 2009, 135 (3):662.
[11] Thomas NJ, Shaffer ML, Willson DF, et al.Defining acute lung disease in children with the oxygenation saturation index[J].Pediatr Crit Care Med, 2010, 11 (1):12.
[12] Desprez K, Mcneil JB, Wang C, et al.Oxygenation Saturation Index Predicts Clinical Outcomes in ARDS[J].Chest, 2017, 152 (6):1151-1158.
[13] Hammond BG, Garcia-Filion P, Kang P, et al.Identifying an Oxygenation Index Threshold for Increased Mortality in Acute Respiratory Failure[J].Respir Care, 2017, 62 (10):1375.
[14] Johnson AE, Pollard TJ, Shen L, et al.MIMIC-III, a freely accessible critical care database[J].Sci Data, 2016, 3:160035.
[15] Ferguson ND, Fan E, Camporota L, et al.The Berlin definition of ARDS:an expanded rationale, justification, and supplementary material[J].Intensive Care Med, 2012, 38 (10):1573-1582.
[16] Lindsey JK, Jones B.Choosing among generalized linear models applied to medical data[J].Stat Med, 1998, 17 (1):59.
[17] Khemani RG, Thomas NJ, Venkatachalam V, et al.Comparison of SpO2 to PaO2 based markers of lung disease severity for children with acute lung injury[J].Crit Care Med, 2012, 40 (4):1309-1316.
[18] Ray S, Rogers L, Pagel C, et al.PaO2/FIO2 Ratio Derived From the SpO2/FIO2 Ratio to Improve Mortality Prediction Using the Pediatric Index of Mortality-3 Score in Transported Intensive Care Admissions[J].Pediatr Crit Care Med, 2017, 18:1.
[19] Pandharipande PP, Shintani AK, Hagerman HE, et al.Derivation and validation of Spo2/Fio2ratio to impute for Pao2/Fio2ratio in the respiratory component of the Sequential Organ Failure Assessment score[J].Crit Care Med, 2009, 37 (4):1317-1321.
[20] Khemani RG, Thomas NJ, Venkatachalam V, et al.Comparison of SpO2 to PaO2 based markers of lung disease severity for children with acute lung injury[J].Crit Care Med, 2012, 40 (4):1309-1316.
[21] ARDS Definition Task Force, Ranieri VM, Rubenfeld GD, et al.Acute respiratory distress syndrome:the Berlin Definition[J].JAMA, 2012, 307 (23):2526-2533.
计量
- 文章访问数: 66
- PDF下载数: 45
- 施引文献: 0