Value of CRP, PCT, and NLR in Prediction of Severity and Prognosis of Patients With Bloodstream Infections and Sepsis

Definitions of sepsis and septic shock were last revised in 2001. Considerable advances have since been made into the pathobiology (changes in organ function, morphology, cell biology, biochemistry, immunology, and circulation), management, and epidemiology of sepsis, suggesting the need for reexamination.

Purpose Early clinical recognition of sepsis can be challenging. With the advancement of machine learning, promising real-time models to predict sepsis have emerged. We assessed their performance by carrying out a systematic review and meta-analysis. Methods A systematic search was performed in PubMed, Embase.com and Scopus. Studies targeting sepsis, severe sepsis or septic shock in any hospital setting were eligible for inclusion. The index test was any supervised machine learning model for real-time prediction of these conditions. Quality of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology, with a tailored Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) checklist to evaluate risk of bias. Models with a reported area under the curve of the receiver operating characteristic (AUROC) metric were meta-analyzed to identify strongest contributors to model performance. Results After screening, a total of 28 papers were eligible for synthesis, from which 130 models were extracted. The majority of papers were developed in the intensive care unit (ICU, n = 15; 54%), followed by hospital wards (n = 7; 25%), the emergency department (ED, n = 4; 14%) and all of these settings (n = 2; 7%). For the prediction of sepsis, diagnostic test accuracy assessed by the AUROC ranged from 0.68–0.99 in the ICU, to 0.96–0.98 in-hospital and 0.87 to 0.97 in the ED. Varying sepsis definitions limit pooling of the performance across studies. Only three papers clinically implemented models with mixed results. In the multivariate analysis, temperature, lab values, and model type contributed most to model performance. Conclusion This systematic review and meta-analysis show that on retrospective data, individual machine learning models can accurately predict sepsis onset ahead of time. Although they present alternatives to traditional scoring systems, between-study heterogeneity limits the assessment of pooled results. Systematic reporting and clinical implementation studies are needed to bridge the gap between bytes and bedside. Electronic supplementary material The online version of this article (10.1007/s00134-019-05872-y) contains supplementary material, which is available to authorized users.

Introduction Sepsis biomarkers can have important diagnostic, therapeutic, and prognostic functions. In a previous review, we identified 3370 references reporting on 178 different biomarkers related to sepsis. In the present review, we evaluate the progress in the research of sepsis biomarkers. Methods Using the same methodology as in our previous review, we searched the PubMed database from 2009 until September 2019 using the terms “Biomarker” AND “Sepsis.” There were no restrictions by age or language, and all studies, clinical and experimental, were included. Results We retrieved a total of 5367 new references since our previous review. We identified 258 biomarkers, 80 of which were new compared to our previous list. The majority of biomarkers have been evaluated in fewer than 5 studies, with 81 (31%) being assessed in just a single study. Apart from studies of C-reactive protein (CRP) or procalcitonin (PCT), only 26 biomarkers have been assessed in clinical studies with more than 300 participants. Forty biomarkers have been compared to PCT and/or CRP for their diagnostic value; 9 were shown to have a better diagnostic value for sepsis than either or both of these biomarkers. Forty-four biomarkers have been evaluated for a role in answering a specific clinical question rather than for their general diagnostic or prognostic properties in sepsis. Conclusions The number of biomarkers being identified is still increasing although at a slower rate than in the past. Most of the biomarkers have not been well-studied; in particular, the clinical role of these biomarkers needs to be better evaluated.