Derivation of a clinical-based model to detect invasive bacterial infections in febrile infants.
Derivation of a clinical-based model to detect invasive bacterial infections in febrile infants.
复制标题
DOI：
10.1002/jhm.12956
复制
发表时间：
2022-11
影响因子：
2.6
通讯作者：
Fiscella, Kevin A.
中科院分区：
文献类型：
--
作者：
Yaeger, Jeffrey P.;Jones, Jeremiah;Ertefaie, Ashkan;Caserta, Mary T.;Fiscella, Kevin A.
发热的婴儿有感染侵袭性细菌感染（IBI）（即菌血症和细菌性脑膜炎）的风险，如果未被诊断，可能会产生毁灭性的后果。目前的IBI预测模型依赖于血清生物标志物，这些生物标志物可能无法提供及时的结果，并且可能难以在低资源环境中获得。推导出基于临床的发热婴儿IBI预测模型。这是一项对2011年1月至2018年12月期间被送往两个儿科急诊科的婴儿进行的横断面研究。入选标准为0-90天，体温≥38°C，记录的胎龄，发热持续时间和疾病持续时间。为了检测IBI，我们使用了回归和集成机器学习模型以及基于证据的预测因素（即性别，年龄，慢性疾病，胎龄，外观，最高温度，发热持续时间，疾病持续时间，咳嗽状态和尿路炎症）。我们将IBI婴儿的权重提高了8倍，并使用了10倍交叉验证以避免过度拟合。我们计算了受试者工作特征曲线（AUC）下的面积，优先考虑高灵敏度，以确定最佳临界点，以估计灵敏度和特异性。在2,311例发热婴儿中，39例（1.7%）有IBI。中位年龄为54天（IQR 35-71）。AUC为0.819（95% CI 0.762，0.868）。预测模型的敏感性为0.974（0.800，1.00），特异性为0.530（0.484，0.575）。研究结果表明，基于临床的模型可以检测发热婴儿的IBI，其表现与基于血清生物标志物的模型相似。该模型可以通过使临床医生在任何情况下估计IBI风险来改善健康公平性。未来的研究应前瞻性地验证多个研究中心的结果，并按年龄调查性能。
Febrile infants are at risk for invasive bacterial infections (IBIs) (i.e. bacteremia and bacterial meningitis) which, when undiagnosed, may have devastating consequences. Current IBI predictive models rely on serum biomarkers which may not provide timely results and may be difficult to obtain in low-resource settings. To derive a clinical-based IBI predictive model for febrile infants.. This is a cross-sectional study of infants brought to two pediatric emergency departments from January 2011-December 2018. Inclusion criteria were age 0–90 days, temperature ≥38°C, and documented gestational age, fever duration and illness duration. To detect IBIs, we used regression and ensemble machine learning models and evidence-based predictors (i.e. sex, age, chronic medical condition, gestational age, appearance, maximum temperature, fever duration, illness duration, cough status, and urinary tract inflammation). We up-weighted infants with IBIs 8-fold and used 10-fold cross-validation to avoid overfitting. We calculated area-under-the-receiver operating characteristic curve (AUC), prioritizing a high sensitivity to identify the optimal cut-point to estimate sensitivity and specificity. Of 2,311 febrile infants, 39 had an IBI (1.7%). Median age was 54 days (IQR 35–71). The AUC was 0.819 (95% CI 0.762, 0.868). The predictive model achieved a sensitivity of 0.974 (0.800, 1.00) and specificity of 0.530 (0.484, 0.575). Findings suggest a clinical-based model can detect IBIs in febrile infants, performing similarly to serum biomarker-based models. This model may improve health equity by enabling clinicians to estimate IBI risk in any setting. Future studies should prospectively validate findings across multiple sites and investigate performance by age.
登录
查看更多内容
影响因子：
5.1
作者：
DAGAN, R;POWELL, KR;MENEGUS, MA
通讯作者：
MENEGUS, MA
影响因子：
8
作者：
Levine, DA;Platt, SL;Kuppermann, N
通讯作者：
Kuppermann, N
影响因子：
8
作者：
Pantell, Robert H.;Roberts, Kenneth B.;Woods, Charles R., Jr.
通讯作者：
Woods, Charles R., Jr.
影响因子：
--
作者：
Pantell, Robert H;Roberts, Kenneth B;Pantell, Matthew S
通讯作者：
Pantell, Matthew S
DOI：
10.1007/978-3-030-50420-5_41
发表时间：
2020-05-22
期刊：
Computational Science – ICCS 2020
影响因子：
--
作者：
Mnich K;Kitlas Golińska A;Polewko-Klim A;Rudnicki WR
通讯作者：
Rudnicki WR