Importance:Ventilator-associated pneumonia (VAP) is one of the most common complications after cardiac surgery in children with congenital heart disease (CHD).Early prediction of the incidence of VAP is important for ...Importance:Ventilator-associated pneumonia (VAP) is one of the most common complications after cardiac surgery in children with congenital heart disease (CHD).Early prediction of the incidence of VAP is important for clinical prevention and treatment.Objective:To determine the value of serum C-reactive protein (CRP) levels and the Pediatric Risk of Mortality Ⅲ (PRISM Ⅲ) score in predicting the risk of postoperative VAP in pediatric patients with CHD.Methods:We performed a retrospective review of clinical data of 481 pediatric patients with CHD who were admitted to our pediatric intensive care unit.These patients received mechanical ventilation for 48 hours or longer after corrective Surgery.On the basis of their clinical manifestations and laboratory results,patients were separated into two groups of those with VAP and those without VAP.CRP levels were measured and PRISM Ⅲ scores were collected within 12 hours of admission to the pediatric intensive care unit.The Pearson correlation coefficient was used to evaluate the association of CRP levels and the PRISM score with the occurrence of postoperative VAP.A linear regression model was constructed to obtain a joint function and receiver operating curves were used to assess the predictive value.Results:CRP levels and the PRISM Ⅲ score in the VAP group were significantly higher than those in the non-VAP group (P < 0.05).Receiver operating curves suggested that using CRP + the PRISM Ⅲ score to predict the incidence of VAP after congenial heart surgery was more accurate than using either of them alone (CRP + the PRISM Ⅲ score:sensitivity:53.2%,specificity:85.7%).When CRP + the PRISM Ⅲ score was greater than 45.460,patients were more likely to have VAP.Interpretation:Although using CRP levels plus the PRISM Ⅲ score to predict the incidence of VAP after congenial heart surgery is more accurate than using either of them alone,its predictive value is still limited.展开更多
目的基于机器学习方法构建重症患儿院际转运风险预测模型,识别出影响转运预后的关键性医学特征,提高转运的成功率。方法前瞻性的选取2020年1月至2021年1月期间湖南省儿童医院转运中心通过院际转运的收住重症监护病房的重症患儿为研究对...目的基于机器学习方法构建重症患儿院际转运风险预测模型,识别出影响转运预后的关键性医学特征,提高转运的成功率。方法前瞻性的选取2020年1月至2021年1月期间湖南省儿童医院转运中心通过院际转运的收住重症监护病房的重症患儿为研究对象,对其重症医学特征数据和第三代儿童死亡风险(pediatric risk of mortality,PRISMⅢ)评分系统的相关数据进行收集和处理,基于逻辑回归、决策树模型、Relief算法3种机器学习模型构建风险预测模型,利用反向传播神经网络构建转诊结局预测模型对风险预测模型所选医学特征进行验证和分析,探寻影响院际转运风险的关键医学特征。结果在纳入的549例转诊患儿中,新生儿222例(40.44%),非新生儿327例(59.56%),院内死亡50例,病死率为9.11%。对所收集的151项重症患儿医学特征数据进行数据处理,三种模型各自选取影响转诊结局的前15项重要的特征,共有34项入选。其中决策树模型所选特征与PRISMⅢ指标的重叠度为72.7%,高于逻辑回归的36.4%和Relief算法的27.3%,且训练预测精确率为0.94,也高于纳入所有特征训练精确率0.90,表明决策树模型是一种具有良好临床实用性的预测模型。在决策树入选的前15项重要特征中,通过量化特征的小提琴图对转诊结局影响的大小排序为:碱剩余、总胆红素、钙离子、总耗时、动脉氧分压、血液(包括白细胞、血小板、凝血酶原时间/凝血活酶时间)、二氧化碳分压、血糖、收缩压、心率、器官衰竭、乳酸、毛细血管再充盈时间、体温、发绀,其中有8项重要特征与PRISMⅢ的指标重叠,分别是收缩压、心率、体温、瞳孔反射、神志状态、酸中毒、动脉氧分压、二氧化碳分压、血液、血糖。利用决策树分别对新生儿和非新生儿两个数据集选择有高度影响的前15个医学特征,共有19项特征入选,其中新生儿与非新生儿的重要特征之间有8个差异项和11个重叠项。结论机器学习模型可作为预测重症患儿院际转运风险的可靠工具。决策树模型具有较佳的性能,有助于识别影响院际转运风险的关键医学特征,提高重症患儿院际转运的成功率。展开更多
目的探讨脓毒症患儿相关标志物水平与小儿危重病例评分(PCIS)及小儿死亡危险因素评分(PRISMⅢ)的相关性。方法回顾性分析2020年5月—2022年5月在本院儿童重症监护病房收治的99例脓毒症患儿的临床资料,分析90例存活组和9例死亡组患儿白...目的探讨脓毒症患儿相关标志物水平与小儿危重病例评分(PCIS)及小儿死亡危险因素评分(PRISMⅢ)的相关性。方法回顾性分析2020年5月—2022年5月在本院儿童重症监护病房收治的99例脓毒症患儿的临床资料,分析90例存活组和9例死亡组患儿白细胞计数(WBC)、中性粒细胞与淋巴细胞比值(NLR)、48 h NLR、NLR变化率、平均血小板体积(MPV)、血小板体积分布宽度(PDW)和PCIS、PRISMⅢ评分的相关性;绘制受试者工作特征(ROC)曲线并计算曲线下面积(AUC),比较NLR、NLR变化率、MPV、PDW对患者的28 d全因死亡风险预测价值。结果与存活组比较,死亡组48 h NLR、NLR变化率、MPV、PDW水平及PRISMⅢ分数均较存活组升高,PCIS分数降低(P<0.05)。48 h NLR、NLR变化率、MPV、PDW与PRISMⅢ分数成正相关性(r值为0.117~0.265,P<0.05);而48 h NLR、NLR变化率与PCIS分数成负相关性(r值分别为-0.323、-0.342,P<0.05)。各指标评价脓毒症患儿预后的曲线下面积(AUC)从高到低依次为MPV、48 h NLR、PRISMⅢ分数、PCIS分数、PDW、NLR变化率。结论MPV和48 h NLR可能是评估脓毒症患儿病情严重程度和预测疾病预后的潜在指标。展开更多
目的了解危重患儿的营养状况，探讨营养状况与病情严重程度及预后的相关性，为临床对危重患儿进行合理的营养支持提供一定理论依据。方法采集2010．11-2011．01期间入住北京儿童医院儿童加强监护病房（pediatric intensive care unit，P...目的了解危重患儿的营养状况，探讨营养状况与病情严重程度及预后的相关性，为临床对危重患儿进行合理的营养支持提供一定理论依据。方法采集2010．11-2011．01期间入住北京儿童医院儿童加强监护病房（pediatric intensive care unit，PICU）的所有患儿作为研究对象。采用前瞻性研究方法，对人组患儿的身长、体质量等人体参数进行测量及营养评估。收集基础疾病、危重病例评分、住院时间、机械通气时间等临床资料。结果196例患儿中，营养不良共43例，营养不良现患率为21．9％。营养不良组的儿童死亡危险评分大于营养正常组（P〈0．05）；机械通气使用率高于营养正常组（P〈0．05）；营养正常组患儿28d存活率高于营养不良组（P＜0．05）。结论PICU入院患儿中营养不良的患病率为21．9％。营养不良组患儿儿童死亡危险评分、机械通气使用率高于营养正常组，28d存活率低于与营养正常组，提示营养不良与疾病严重程度和预后相关。展开更多
文摘Importance:Ventilator-associated pneumonia (VAP) is one of the most common complications after cardiac surgery in children with congenital heart disease (CHD).Early prediction of the incidence of VAP is important for clinical prevention and treatment.Objective:To determine the value of serum C-reactive protein (CRP) levels and the Pediatric Risk of Mortality Ⅲ (PRISM Ⅲ) score in predicting the risk of postoperative VAP in pediatric patients with CHD.Methods:We performed a retrospective review of clinical data of 481 pediatric patients with CHD who were admitted to our pediatric intensive care unit.These patients received mechanical ventilation for 48 hours or longer after corrective Surgery.On the basis of their clinical manifestations and laboratory results,patients were separated into two groups of those with VAP and those without VAP.CRP levels were measured and PRISM Ⅲ scores were collected within 12 hours of admission to the pediatric intensive care unit.The Pearson correlation coefficient was used to evaluate the association of CRP levels and the PRISM score with the occurrence of postoperative VAP.A linear regression model was constructed to obtain a joint function and receiver operating curves were used to assess the predictive value.Results:CRP levels and the PRISM Ⅲ score in the VAP group were significantly higher than those in the non-VAP group (P < 0.05).Receiver operating curves suggested that using CRP + the PRISM Ⅲ score to predict the incidence of VAP after congenial heart surgery was more accurate than using either of them alone (CRP + the PRISM Ⅲ score:sensitivity:53.2%,specificity:85.7%).When CRP + the PRISM Ⅲ score was greater than 45.460,patients were more likely to have VAP.Interpretation:Although using CRP levels plus the PRISM Ⅲ score to predict the incidence of VAP after congenial heart surgery is more accurate than using either of them alone,its predictive value is still limited.
文摘目的基于机器学习方法构建重症患儿院际转运风险预测模型,识别出影响转运预后的关键性医学特征,提高转运的成功率。方法前瞻性的选取2020年1月至2021年1月期间湖南省儿童医院转运中心通过院际转运的收住重症监护病房的重症患儿为研究对象,对其重症医学特征数据和第三代儿童死亡风险(pediatric risk of mortality,PRISMⅢ)评分系统的相关数据进行收集和处理,基于逻辑回归、决策树模型、Relief算法3种机器学习模型构建风险预测模型,利用反向传播神经网络构建转诊结局预测模型对风险预测模型所选医学特征进行验证和分析,探寻影响院际转运风险的关键医学特征。结果在纳入的549例转诊患儿中,新生儿222例(40.44%),非新生儿327例(59.56%),院内死亡50例,病死率为9.11%。对所收集的151项重症患儿医学特征数据进行数据处理,三种模型各自选取影响转诊结局的前15项重要的特征,共有34项入选。其中决策树模型所选特征与PRISMⅢ指标的重叠度为72.7%,高于逻辑回归的36.4%和Relief算法的27.3%,且训练预测精确率为0.94,也高于纳入所有特征训练精确率0.90,表明决策树模型是一种具有良好临床实用性的预测模型。在决策树入选的前15项重要特征中,通过量化特征的小提琴图对转诊结局影响的大小排序为:碱剩余、总胆红素、钙离子、总耗时、动脉氧分压、血液(包括白细胞、血小板、凝血酶原时间/凝血活酶时间)、二氧化碳分压、血糖、收缩压、心率、器官衰竭、乳酸、毛细血管再充盈时间、体温、发绀,其中有8项重要特征与PRISMⅢ的指标重叠,分别是收缩压、心率、体温、瞳孔反射、神志状态、酸中毒、动脉氧分压、二氧化碳分压、血液、血糖。利用决策树分别对新生儿和非新生儿两个数据集选择有高度影响的前15个医学特征,共有19项特征入选,其中新生儿与非新生儿的重要特征之间有8个差异项和11个重叠项。结论机器学习模型可作为预测重症患儿院际转运风险的可靠工具。决策树模型具有较佳的性能,有助于识别影响院际转运风险的关键医学特征,提高重症患儿院际转运的成功率。
文摘目的探讨脓毒症患儿相关标志物水平与小儿危重病例评分(PCIS)及小儿死亡危险因素评分(PRISMⅢ)的相关性。方法回顾性分析2020年5月—2022年5月在本院儿童重症监护病房收治的99例脓毒症患儿的临床资料,分析90例存活组和9例死亡组患儿白细胞计数(WBC)、中性粒细胞与淋巴细胞比值(NLR)、48 h NLR、NLR变化率、平均血小板体积(MPV)、血小板体积分布宽度(PDW)和PCIS、PRISMⅢ评分的相关性;绘制受试者工作特征(ROC)曲线并计算曲线下面积(AUC),比较NLR、NLR变化率、MPV、PDW对患者的28 d全因死亡风险预测价值。结果与存活组比较,死亡组48 h NLR、NLR变化率、MPV、PDW水平及PRISMⅢ分数均较存活组升高,PCIS分数降低(P<0.05)。48 h NLR、NLR变化率、MPV、PDW与PRISMⅢ分数成正相关性(r值为0.117~0.265,P<0.05);而48 h NLR、NLR变化率与PCIS分数成负相关性(r值分别为-0.323、-0.342,P<0.05)。各指标评价脓毒症患儿预后的曲线下面积(AUC)从高到低依次为MPV、48 h NLR、PRISMⅢ分数、PCIS分数、PDW、NLR变化率。结论MPV和48 h NLR可能是评估脓毒症患儿病情严重程度和预测疾病预后的潜在指标。
文摘目的了解危重患儿的营养状况，探讨营养状况与病情严重程度及预后的相关性，为临床对危重患儿进行合理的营养支持提供一定理论依据。方法采集2010．11-2011．01期间入住北京儿童医院儿童加强监护病房（pediatric intensive care unit，PICU）的所有患儿作为研究对象。采用前瞻性研究方法，对人组患儿的身长、体质量等人体参数进行测量及营养评估。收集基础疾病、危重病例评分、住院时间、机械通气时间等临床资料。结果196例患儿中，营养不良共43例，营养不良现患率为21．9％。营养不良组的儿童死亡危险评分大于营养正常组（P〈0．05）；机械通气使用率高于营养正常组（P〈0．05）；营养正常组患儿28d存活率高于营养不良组（P＜0．05）。结论PICU入院患儿中营养不良的患病率为21．9％。营养不良组患儿儿童死亡危险评分、机械通气使用率高于营养正常组，28d存活率低于与营养正常组，提示营养不良与疾病严重程度和预后相关。
