Host Diagnostic Biomarkers of Infection in the ICU: Where Are We and Where Are We Going?

MicroRNA Expression Profile in Patients Admitted to ICU as Novel and Reliable Approach for Diagnostic and Therapeutic Purposes

The ability to detect early metabolic changes in patients who have an increased mortality risk in the intensive care units (ICUs) could increase the likelihood of predicting recovery patterns and assist in disease management. Markers that can predict the disease progression of patients in the ICU might also be beneficial for improving their medical profile. Although biomarkers have been used in the ICU more frequently in recent years, the clinical use of most of them is limited. A wide range of biological processes are influenced by microRNAs (miRNAs) that modulate the translation and stability of specific mRNAs. Studies suggest that miRNAs may serve as a diagnostic and therapeutic biomarker in ICUs by profiling miRNA dysregulation in patient samples. To improve the predictive value of biomarkers for ICU patients, researchers have proposed both investigating miRNAs as novel biomarkers and combining them with other clinical biomarkers. Herein, we discuss recent approaches to the diagnosis and prognosis of patients admitted to an ICU, highlighting the use of miRNAs as novel and robust biomarkers for this purpose. In addition, we discuss emerging approaches to biomarker development and ways to improve the quality of biomarkers so that patients in ICU get the best outcomes possible.

Clinical usefulness of a host signature based on TRAIL, IP10, and CRP (MeMed BV) as infection biomarkers in intensive care units' patients. A retrospective observational study

INTRODUCTION

Infection complications are common in intensive care unit patients, and early detection remains a diagnostic challenge. Procalcitonin (PCT) and C-reactive protein (CRP) are commonly used biomarkers. A novel diagnostic approach focuses on the host immune response. One of the approaches, the MMBV index, is based on measuring in a blood sample three parameters: (i) tumor necrosis factor-related apoptosis-inducing ligand (TRAIL), (ii) interferon-γ-induced protein-10 (IP10), and (iii) CRP. This study aimed to evaluate the usefulness of MMBV as an infection biomarker in an ICU cohort.

PATIENTS AND METHODS

Forty-six patients treated in the University Clinical Center in Gdansk ICU were enrolled in the study, and their clinical data were retrospectively analyzed. In total, 91 MMBV results were analyzed.

RESULTS

Most of the patients had high MMBV values, suggesting bacterial etiology. A weak correlation between PCT and MMBV was observed, and no correlation between parameter changes was noted. There was a correlation between CRP/MMBV and between changes in CRP / changes in MMBV.

CONCLUSION

It seems that MMBV is not valuable for ICU patients neither in diagnosing nor monitoring infection. Higher MMBV values may predict unfavorable treatment outcomes.

Bacterial Infections in Intensive Care Units: Epidemiological and Microbiological Aspects

Intensive care units constitute a critical setting for the management of infections. The patients' fragilities and spread of multidrug-resistant microorganisms lead to relevant difficulties in the patients' care. Recent epidemiological surveys documented the Gram-negative bacteria supremacy among intensive care unit (ICU) infection aetiologies, accounting for numerous multidrug-resistant isolates. Regarding this specific setting, clinical microbiology support holds a crucial role in the definition of diagnostic algorithms. Eventually, the complete patient evaluation requires integrating local epidemiological knowledge into the best practice and the standardization of antimicrobial stewardship programs. Clinical laboratories usually receive respiratory tract and blood samples from ICU patients, which express a significant predisposition to severe infections. Therefore, conventional or rapid diagnostic workflows should be modified depending on patients' urgency and preliminary colonization data. Additionally, it is essential to complete each microbiological report with rapid phenotypic minimum inhibitory concentration (MIC) values and information about resistance markers. Microbiologists also help in the eventual integration of ultimate genome analysis techniques into complicated diagnostic workflows. Herein, we want to emphasize the role of the microbiologist in the decisional process of critical patient management.

Procalcitonin for the diagnosis of postoperative bacterial infection after adult cardiac surgery: a systematic review and meta-analysis

BACKGROUND AND AIMS

Patients undergoing cardiac surgery are subject to infectious complications that adversely affect outcomes. Rapid identification is essential for adequate treatment. Procalcitonin (PCT) is a noninvasive blood test that could serve this purpose, however its validity in the cardiac surgery population is still debated. We therefore performed a systematic review and meta-analysis to estimate the accuracy of PCT for the diagnosis of postoperative bacterial infection after cardiac surgery.

METHODS

We included studies on adult cardiac surgery patients, providing estimates of test accuracy. Search was performed on PubMed, EmBase and WebOfScience on April 12th, 2023 and rerun on September 15th, 2023, limited to the last 10 years. Study quality was assessed with the QUADAS-2 tool. The pooled measures of performance and diagnostic accuracy, and corresponding 95% Confidence Intervals (CI), were calculated using a bivariate regression model. Due to the variation in reported thresholds, we used a multiple-thresholds within a study random effects model for meta-analysis (diagmeta R-package).

RESULTS

Eleven studies were included in the systematic review, and 10 (2984 patients) in the meta-analysis. All studies were single-center with observational design, five of which with retrospective data collection. Quality assessment highlighted various issues, mainly concerning lack of prespecified thresholds for the index test in all studies. Results of bivariate model analysis using multiple thresholds within a study identified the optimal threshold at 3 ng/mL, with a mean sensitivity of 0.67 (0.47-0.82), mean specificity of 0.73 (95% CI 0.65-0.79), and AUC of 0.75 (IC95% 0.29-0.95). Given its importance for practice, we also evaluated PCT's predictive capability. We found that positive predictive value is at most close to 50%, also with a high prevalence (30%), and the negative predictive value was always > 90% when prevalence was < 20%.

CONCLUSIONS

These results suggest that PCT may be used to help rule out infection after cardiac surgery. The optimal threshold of 3 ng/mL identified in this work should be confirmed with large, well-designed randomized trials that evaluate the test's impact on health outcomes and on the use of antibiotic therapy. PROSPERO Registration number CRD42023415773. Registered 22 April 2023.

Pneumonia in the first week after polytrauma is associated with reduced blood levels of soluble herpes virus entry mediator

Background

Pneumonia develops frequently after major surgery and polytrauma and thus in the presence of systemic inflammatory response syndrome (SIRS) and organ dysfunction. Immune checkpoints balance self-tolerance and immune activation. Altered checkpoint blood levels were reported for sepsis. We analyzed associations of pneumonia incidence in the presence of SIRS during the first week of critical illness and trends in checkpoint blood levels.

Materials and methods

Patients were studied from day two to six after admission to a surgical intensive care unit (ICU). Blood was sampled and physician experts retrospectively adjudicated upon the presence of SIRS and Sepsis-1/2 every eight hours. We measured the daily levels of immune checkpoints and inflammatory markers by bead arrays for polytrauma patients developing pneumonia. Immune checkpoint time series were additionally determined for clinically highly similar polytrauma controls remaining infection-free during follow-up. We performed cluster analyses. Immune checkpoint time trends in cases and controls were compared with hierarchical linear models. For patients with surgical trauma and with and without sepsis, selected immune checkpoints were determined in study baseline samples.

Results

In polytrauma patients with post-injury pneumonia, eleven immune checkpoints dominated subcluster 3 that separated subclusters 1 and 2 of myeloid markers from subcluster 4 of endothelial activation, tissue inflammation, and adaptive immunity markers. Immune checkpoint blood levels were more stable in polytrauma cases than controls, where they trended towards an increase in subcluster A and a decrease in subcluster B. Herpes virus entry mediator (HVEM) levels (subcluster A) were lower in cases throughout. In unselected surgical patients, sepsis was not associated with altered HVEM levels at the study baseline.

Conclusion

Pneumonia development after polytrauma until ICU-day six was associated with decreased blood levels of HVEM. HVEM signaling may reduce pneumonia risk by strengthening myeloid antimicrobial defense and dampening lymphoid-mediated tissue damage. Future investigations into the role of HVEM in pneumonia and sepsis development and as a predictive biomarker should consider the etiology of critical illness and the site of infection.

The diagnostic likelihood ratio function and modified test for trend: Identifying, evaluating, and validating nontraditional biomarkers in case-control studies

The ROC curve and its associated summary statistic, the AUC, are used to identify informative diagnostic biomarkers under the assumption that risk of disease is a monotone function of the biomarker. We refer to biomarkers that meet this assumption as traditional, and those that do not as nontraditional. Nontraditional biomarkers most often arise when both low and high biomarker values are associated with an outcome of interest, such as blood pressure with medical complications or leukocyte count with ICU prognosis. Since nontraditional biomarkers do not meet the assumptions for ROC-based analyses, we propose using the discrete diagnostic likelihood ratio (DLR) function to evaluate a wider class of informative biomarkers. We obtain the DLR function using the multinomial logistic regression (MLR) model to improve upon existing estimation techniques, and implement a likelihood ratio test to identify candidate informative traditional and nontraditional biomarkers. We propose a modification of the Cochran-Armitage test for trend that separates biomarkers deemed informative into traditional and nontraditional categories. The statistical properties of the likelihood ratio test and modified test for trend are explored under simulation. Together, these methods achieve the identification, evaluation, and validation of biomarkers from early discovery research. Finally, we show that incorporating covariates into the MLR model results in a covariate-adjusted DLR function that is useful for integrating multiple sources of information in clinical decision making. The methods are applied to gene expression data from subjects with high grade serous ovarian cancer, where stage, early stage vs late stage, is the outcome of interest.

Metabolomic profiling of bacterial biofilm: trends, challenges, and an emerging antibiofilm target

Biofilm-related infections substantially contribute to bacterial illnesses, with estimates indicating that at least 80% of such diseases are linked to biofilms. Biofilms exhibit unique metabolic patterns that set them apart from their planktonic counterparts, resulting in significant metabolic reprogramming during biofilm formation. Differential glycolytic enzymes suggest that central metabolic processes are markedly different in biofilms and planktonic cells. The glycolytic enzyme glyceraldehyde-3-phosphate dehydrogenase (GAPDH) is highly expressed in Staphylococcus aureus biofilm progenitors, indicating that changes in glycolysis activity play a role in biofilm development. Notably, an important consideration is a correlation between elevated cyclic di-guanylate monophosphate (c-di-GMP) activity and biofilm formation in various bacteria. C-di-GMP plays a critical role in maintaining the persistence of Pseudomonas aeruginosa biofilms by regulating alginate production, a significant biofilm matrix component. Furthermore, it has been demonstrated that S. aureus biofilm development is initiated by several tricarboxylic acid (TCA) intermediates in a FnbA-dependent manner. Finally, Glucose 6-phosphatase (G6P) boosts the phosphorylation of histidine-containing protein (HPr) by increasing the activity of HPr kinase, enhancing its interaction with CcpA, and resulting in biofilm development through polysaccharide intercellular adhesion (PIA) accumulation and icaADBC transcription. Therefore, studying the metabolic changes associated with biofilm development is crucial for understanding the complex mechanisms involved in biofilm formation and identifying potential targets for intervention. Accordingly, this review aims to provide a comprehensive overview of recent advances in metabolomic profiling of biofilms, including emerging trends, prevailing challenges, and the identification of potential targets for anti-biofilm strategies.

Evaluation of the Diagnostic Value of Cell Population Data in Sepsis in Comparison to Localized Infection, Chronic Inflammation, and Noninfectious Inflammation Cases

INTRODUCTION

Sepsis, defined as an increase of 2 points or more in the sequential organ failure assessment score, is a life-threatening organ dysfunction caused by the dysregulated host response to infection. Volume-conductivity-scatter (VCS) parameters of cell counters which are known as cell population data (CPD) have been suggested to be beneficial in diagnosing sepsis. We aimed to evaluate the diagnostic value of CPD parameters in sepsis in comparison to nonsystemic infection cases (NSI) and non-infectious acute and chronic inflammatory conditions.

MATERIALS AND METHODS

We prospectively included four groups of patients" data: sepsis (n = 66), localized infection (pneumonia, n = 59), chronic inflammation (rheumatoid arthritis, n = 92) and noninfectious inflammation (coronary artery bypass graft operation, n = 56) groups, according to their clinical status and laboratory results. Samples for cell counting and serum markers were collected on the same day of culture collection. VCS parameters were measured by Unicel DxH800 Coulter Cellular Analyzer (Beckman Coulter, USA).

RESULTS

Mean neutrophil volume (MN-V-NE), was highest in the sepsis group [155(149-168)] compared to the localized infection [148(140-158)], chronic inflammation [144.5(142-149)] and noninfectious inflammation [149(145.2-153.7)] (P = 0.001, P < 0.001, P < 0.001, respectively). Neutrophil volume SD (SD-V-NE) was higher in the sepsis [21(18.8-23.7)], significantly differentiating sepsis from other groups. The area under curves of procalcitonin and hs-C-reactive protein were 0.846 and 0.837, respectively, in the receiver-operating characteristic curves (ROC) . CPD combinations, (SD-V NE + SD-V LY + SD-V MO), (SD-V NE + SD-V MO), and (MN-V NE + SD-V NE + SD-C LY + SD-V MO) had greater AUC values than procalcitonin's.

CONCLUSION

VCS parameters might be promising for differentiating sepsis and non-sepsis cases. Additionally, obtaining these data routinely makes their prospects promising without any additional cost and time.

Diagnosing sepsis in the ICU: Comparison of a gene expression signature to pre-existing biomarkers

PURPOSE

We aimed to identify a gene signature that discriminates between sepsis and aseptic inflammation in patients administered antibiotics in the intensive care unit and compare it to commonly utilised sepsis biomarkers.

METHODS

91 patients commenced on antibiotics were retrospectively diagnosed as having: (i) blood culture positive sepsis; (ii) blood culture negative sepsis; or (iii) aseptic inflammation. Bloods were collected after <24 h of antibiotic commencement for both gene expression sequencing analysis and measurement of previously identified biomarkers.

RESULTS

53 differentially expressed genes were identified that accurately discriminated between blood culture positive sepsis and aseptic inflammation in a cohort of patients given antibiotics [aROC 0.97 (95% CI, 0.95-0.99)]. This gene signature was validated in a publicly available database. The gene signature outperformed previously identified sepsis biomarkers including C-reactive protein [aROC 0.72 (95% CI, 0.57-0.87)], NT-Pro B-type Natriuretic Peptide [aROC 0.84 (95% CI, 0.73-0.96)], and Septicyte™ LAB [aROC 0.8 (95% CI, 0.68-0.93)], but was comparable to Procalcitonin [aROC 0.96 (95% CI, 0.9-1)].

CONCLUSIONS

A gene expression signature was identified that accurately discriminates between sepsis and aseptic inflammation in patients given antibiotics in the intensive care unit.

Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection

OBJECTIVES

Early recognition and timely intervention for urosepsis are key to reducing morbidity and mortality. Blood culture has low sensitivity, and a long turnaround time makes meeting the needs of clinical diagnosis difficult. This study aimed to use biomarkers to build a machine learning model for early prediction of urosepsis.

METHODS

Through retrospective analysis, we screened 157 patients with urosepsis and 417 patients with urinary tract infection. Laboratory data of the study participants were collected, including data on biomarkers, such as procalcitonin, D-dimer, and C-reactive protein. We split the data into training (80%) and validation datasets (20%) and determined the average model prediction accuracy through cross-validation.

RESULTS

In total, 26 variables were initially screened and 18 were statistically significant. The influence of the 18 variables was sorted using three ranking methods to further determine the best combination of variables. The Gini importance ranking method was found to be suitable for variable filtering. The accuracy rates of the six machine learning models in predicting urosepsis were all higher than 80%, and the performance of the artificial neural network (ANN) was the best among all. When the ANN included the eight biomarkers with the highest influence ranking, its model had the best prediction performance, with an accuracy rate of 92.9% and an area under the receiver operating characteristic curve of 0.946.

CONCLUSIONS

Urosepsis can be predicted using only the top eight biomarkers determined by the ranking method. This data-driven predictive model will enable clinicians to make quick and accurate diagnoses.

Biomarkers as Prognostic Predictors and Therapeutic Guide in Critically Ill Patients: Clinical Evidence

A biomarker is a molecule that can be measured in a biological sample in an objective, systematic, and precise way, whose levels indicate whether a process is normal or pathological. Knowing the most important biomarkers and their characteristics is the key to precision medicine in intensive and perioperative care. Biomarkers can be used to diagnose, in assessment of disease severity, to stratify risk, to predict and guide clinical decisions, and to guide treatments and response to them. In this review, we will analyze what characteristics a biomarker should have and how to ensure its usefulness, and we will review the biomarkers that in our opinion can make their knowledge more useful to the reader in their clinical practice, with a future perspective. These biomarkers, in our opinion, are lactate, C-Reactive Protein, Troponins T and I, Brain Natriuretic Peptides, Procalcitonin, MR-ProAdrenomedullin and BioAdrenomedullin, Neutrophil/lymphocyte ratio and lymphopenia, Proenkephalin, NefroCheck, Neutrophil gelatinase-associated lipocalin (NGAL), Interleukin 6, Urokinase-type soluble plasminogen activator receptor (suPAR), Presepsin, Pancreatic Stone Protein (PSP), and Dipeptidyl peptidase 3 (DPP3). Finally, we propose an approach to the perioperative evaluation of high-risk patients and critically ill patients in the Intensive Care Unit (ICU) based on biomarkers.

Deep Learning of Dual Plasma Fingerprints for High-Performance Infection Classification

Infection classification is the key for choosing the proper treatment plans. Early determination of the causative agents is critical for disease control. Host responses analysis can detect variform and sensitive host inflammatory responses to ascertain the presence and type of the infection. However, traditional host-derived inflammatory indicators are insufficient for clinical infection classification. Fingerprints-based omic analysis has attracted increasing attention globally for analyzing the complex host systemic immune response. A single type of fingerprints is not applicable for infection classification (area under curve (AUC) of 0.550-0.617). Herein, an infection classification platform based on deep learning of dual plasma fingerprints (DPFs-DL) is developed. The DPFs with high reproducibility (coefficient of variation <15%) are obtained at low sample consumption (550 nL native plasma) using inorganic nanoparticle and organic matrix assisted laser desorption/ionization mass spectrometry. A classifier (DPFs-DL) for viral versus bacterial infection discrimination (AUC of 0.775) and coronavirus disease 2019 (COVID-2019) diagnosis (AUC of 0.917) is also built. Furthermore, a metabolic biomarker panel of two differentially regulated metabolites, which may serve as potential biomarkers for COVID-19 management (AUC of 0.677-0.883), is constructed. This study will contribute to the development of precision clinical care for infectious diseases.

A Robust and Generalizable Immune-Related Signature for Sepsis Diagnostics

High-throughput sequencing can detect tens of thousands of genes in parallel, providing opportunities for improving the diagnostic accuracy of multiple diseases including sepsis, which is an aggressive inflammatory response to infection that can cause organ failure and death. Early screening of sepsis is essential in clinic, but no effective diagnostic biomarkers are available yet. Here, we present a novel method, Recurrent Logistic Regression, to identify diagnostic biomarkers for sepsis from the blood transcriptome data. A panel including five immune-related genes, LRRN3, IL2RB, FCER1A, TLR5, and S100A12, are determined as diagnostic biomarkers (LIFTS) for sepsis. LIFTS discriminates patients with sepsis from normal controls in high accuracy (AUROC = 0.9959 on average; IC = [0.9722-1.0]) on nine validation cohorts across three independent platforms, which outperforms existing markers. Our analysis determined an accurate prediction model and reproducible transcriptome biomarkers that can lay a foundation for clinical diagnostic tests and biological mechanistic studies.

Evaluation of a Multivalent Transcriptomic Metric for Diagnosing Surgical Sepsis and Estimating Mortality Among Critically Ill Patients

Importance

Rapid and accurate discrimination of sepsis and its potential severity currently require multiple assays with slow processing times that are often inconclusive in discerning sepsis from sterile inflammation.

Objective

To analyze a whole-blood, multivalent, host-messenger RNA expression metric for estimating the likelihood of bacterial infection and 30-day mortality and compare performance of the metric with that of other diagnostic and prognostic biomarkers and clinical parameters.

Design, Setting, and Participants

This prospective diagnostic and prognostic study was performed in the surgical intensive care unit (ICU) of a single, academic health science center. The analysis included 200 critically ill adult patients admitted with suspected sepsis (cohort A) or those at high risk for developing sepsis (cohort B) between July 1, 2020, and July 30, 2021.

Exposures

Whole-blood sample measurements of a custom 29-messenger RNA transcriptomic metric classifier for likelihood of bacterial infection (IMX-BVN-3) or 30-day mortality (severity) (IMX-SEV-3) in a clinical-diagnostic laboratory setting using an analysis platform (510[k]-cleared nCounter FLEX; NanoString, Inc), compared with measurement of procalcitonin and interleukin 6 (IL-6) plasma levels, and maximum 24-hour sequential organ failure assessment (SOFA) scores.

Main Outcomes and Measures

Estimated sepsis and 30-day mortality performance.

Results

Among the 200 patients included (124 men [62.0%] and 76 women [38.0%]; median age, 62.5 [IQR, 47.0-72.0] years), the IMX-BVN-3 bacterial infection classifier had an area under the receiver operating characteristics curve (AUROC) of 0.84 (95% CI, 0.77-0.90) for discriminating bacterial infection at ICU admission, similar to procalcitonin (0.85 [95% CI, 0.79-0.90]; P = .79) and significantly better than IL-6 (0.67 [95% CI, 0.58-0.75]; P < .001). For estimating 30-day mortality, the IMX-SEV-3 metric had an AUROC of 0.81 (95% CI, 0.66-0.95), which was significantly better than IL-6 levels (0.57 [95% CI, 0.37-0.77]; P = .006), marginally better than procalcitonin levels (0.65 [95% CI, 0.50-0.79]; P = .06), and similar to the SOFA score (0.76 [95% CI, 0.62-0.91]; P = .48). Combining IMX-BVN-3 and IMX-SEV-3 with procalcitonin or IL-6 levels or SOFA scores did not significantly improve performance. Among patients with sepsis, IMX-BVN-3 scores decreased over time, reflecting the resolution of sepsis. In 11 individuals at high risk (cohort B) who subsequently developed sepsis during their hospital course, IMX-BVN-3 bacterial infection scores did not decline over time and peaked on the day of documented infection.

Conclusions and Relevance

In this diagnostic and prognostic study, a novel, multivalent, transcriptomic metric accurately estimated the presence of bacterial infection and risk for 30-day mortality in patients admitted to a surgical ICU. The performance of this single transcriptomic metric was equivalent to or better than multiple alternative diagnostic and prognostic metrics when measured at admission and provided additional information when measured over time.

Key Signature Genes of Early Terminal Granulocytic Differentiation Distinguish Sepsis From Systemic Inflammatory Response Syndrome on Intensive Care Unit Admission

Infection can induce granulopoiesis. This process potentially contributes to blood gene classifiers of sepsis in systemic inflammatory response syndrome (SIRS) patients. This study aimed to identify signature genes of blood granulocytes from patients with sepsis and SIRS on intensive care unit (ICU) admission. CD15+ cells encompassing all stages of terminal granulocytic differentiation were analyzed. CD15 transcriptomes from patients with sepsis and SIRS on ICU admission and presurgical controls (discovery cohort) were subjected to differential gene expression and pathway enrichment analyses. Differential gene expression was validated by bead array in independent sepsis and SIRS patients (validation cohort). Blood counts of granulocyte precursors were determined by flow cytometry in an extension of the validation cohort. Despite similar transcriptional CD15 responses in sepsis and SIRS, enrichment of canonical pathways known to decline at the metamyelocyte stage (mitochondrial, lysosome, cell cycle, and proteasome) was associated with sepsis but not SIRS. Twelve of 30 validated genes, from 100 selected for changes in response to sepsis rather than SIRS, were endo-lysosomal. Revisiting the discovery transcriptomes revealed an elevated expression of promyelocyte-restricted azurophilic granule genes in sepsis and myelocyte-restricted specific granule genes in sepsis followed by SIRS. Blood counts of promyelocytes and myelocytes were higher in sepsis than in SIRS. Sepsis-induced granulopoiesis and signature genes of early terminal granulocytic differentiation thus provide a rationale for classifiers of sepsis in patients with SIRS on ICU admission. Yet, the distinction of this process from noninfectious tissue injury-induced granulopoiesis remains to be investigated.

Therapeutic Drug Monitoring of Antibiotic Drugs: The Role of the Clinical Laboratory

BACKGROUND

Therapeutic drug monitoring (TDM) of anti-infective drugs is an increasingly complex field, given that in addition to the patient and drug as 2 usual determinants, its success is driven by the pathogen. Pharmacodynamics is related both to the patient (toxicity) and bacterium (efficacy or antibiotic susceptibility). The specifics of TDM of antimicrobial drugs stress the need for multidisciplinary knowledge and expertise, as in any other field. The role and the responsibility of the laboratory in this interplay are both central and multifaceted. This narrative review highlights the role of the clinical laboratory in the TDM process.

METHODS

A literature search was conducted in PubMed and Google Scholar, focusing on the past 5 years (studies published since 2016) to limit redundancy with previously published review articles. Furthermore, the references cited in identified publications of interest were screened for additional relevant studies and articles.

RESULTS

The authors addressed microbiological methods to determine antibiotic susceptibility, immunochemical and chromatographic methods to measure drug concentrations (primarily in blood samples), and endogenous clinical laboratory biomarkers to monitor treatment efficacy and toxicity. The advantages and disadvantages of these methods are critically discussed, along with existing gaps and future perspectives on strategies to provide clinicians with as reliable and useful results as possible.

CONCLUSIONS

Although interest in the field has been the driver for certain progress in analytical technology and quality in recent years, laboratory professionals and commercial providers persistently encounter numerous unresolved challenges. The main tasks that need tackling include broadly and continuously available, easily operated, and cost-effective tests that offer short turnaround times, combined with reliable and easy-to-interpret results. Various fields of research are currently addressing these features.

Does COVID-19 Clinical Status Associate with Outcome Severity? An Unsupervised Machine Learning Approach for Knowledge Extraction

Since the beginning of the COVID-19 pandemic, 195 million people have been infected and 4.2 million have died from the disease or its side effects. Physicians, healthcare scientists and medical staff continuously try to deal with overloaded hospital admissions, while in parallel, they try to identify meaningful correlations between the severity of infected patients with their symptoms, comorbidities and biomarkers. Artificial intelligence (AI) and machine learning (ML) have been used recently in many areas related to COVID-19 healthcare. The main goal is to manage effectively the wide variety of issues related to COVID-19 and its consequences. The existing applications of ML to COVID-19 healthcare are based on supervised classifications which require a labeled training dataset, serving as reference point for learning, as well as predefined classes. However, the existing knowledge about COVID-19 and its consequences is still not solid and the points of common agreement among different scientific communities are still unclear. Therefore, this study aimed to follow an unsupervised clustering approach, where prior knowledge is not required (tabula rasa). More specifically, 268 hospitalized patients at the First Propaedeutic Department of Internal Medicine of AHEPA University Hospital of Thessaloniki were assessed in terms of 40 clinical variables (numerical and categorical), leading to a high-dimensionality dataset. Dimensionality reduction was performed by applying a principal component analysis (PCA) on the numerical part of the dataset and a multiple correspondence analysis (MCA) on the categorical part of the dataset. Then, the Bayesian information criterion (BIC) was applied to Gaussian mixture models (GMM) in order to identify the optimal number of clusters under which the best grouping of patients occurs. The proposed methodology identified four clusters of patients with similar clinical characteristics. The analysis revealed a cluster of asymptomatic patients that resulted in death at a rate of 23.8%. This striking result forces us to reconsider the relationship between the severity of COVID-19 clinical symptoms and the patient's mortality.

Diagnostic Challenges in Sepsis

Purpose of Review

Sepsis is a leading cause of death worldwide. Groundbreaking international collaborative efforts have culminated in the widely accepted surviving sepsis guidelines, with iterative improvements in management strategies and definitions providing important advances in care for patients. Key to the diagnosis of sepsis is identification of infection, and whilst the diagnostic criteria for sepsis is now clear, the diagnosis of infection remains a challenge and there is often discordance between clinician assessments for infection.

Recent Findings

We review the utility of common biochemical, microbiological and radiological tools employed by clinicians to diagnose infection and explore the difficulty of making a diagnosis of infection in severe inflammatory states through illustrative case reports. Finally, we discuss some of the novel and emerging approaches in diagnosis of infection and sepsis.

Summary

While prompt diagnosis and treatment of sepsis is essential to improve outcomes in sepsis, there remains no single tool to reliably identify or exclude infection. This contributes to unnecessary antimicrobial use that is harmful to individuals and populations. There is therefore a pressing need for novel solutions. Machine learning approaches using multiple diagnostic and clinical inputs may offer a potential solution but as yet these approaches remain experimental.

Artificial intelligence approach towards assessment of condition of COVID-19 patients - Identification of predictive biomarkers associated with severity of clinical condition and disease progression

BACKGROUND AND OBJECTIVES

Although ML has been studied for different epidemiological and clinical issues as well as for survival prediction of COVID-19, there is a noticeable shortage of literature dealing with ML usage in prediction of disease severity changes through the course of the disease. In that way, predicting disease progression from mild towards moderate, severe and critical condition, would help not only to respond in a timely manner to prevent lethal results, but also to minimize the number of patients in hospitals where this is not necessary.

METHODS

We present a methodology for the classification of patients into 4 distinct categories of the clinical condition of COVID-19 disease. Classification of patients is based on the values of blood biomarkers that were assessed by Gradient boosting regressor and which were selected as biomarkers that have the greatest influence in the classification of patients with COVID-19.

RESULTS

The results show that among several tested algorithms, XGBoost classifier achieved best results with an average accuracy of 94% and an average F1-score of 94.3%. We have also extracted 10 best features from blood analysis that are strongly associated with patient condition and based on those features we can predict the severity of the clinical condition.

CONCLUSIONS

The main advantage of our system is that it is a decision tree-based algorithm which is easier to interpret, instead of the use of black box models, which are not appealing in medical practice.

Exploring Inflammatory Status in Febrile Seizures Associated with Urinary Tract Infections: A Two-Step Cluster Approach

BACKGROUND

Urinary tract infections (UTIs) are considered common facilitating factors, along with other infections, in triggering febrile seizures (FS). The main purpose of our study was to identify specific inflammatory patterns of UTI cases from other infections in a specific cluster, using a combination of inflammatory biomarkers to differentiate UTIs from other bacterial diseases triggering FS.

METHOD

This prospective study included a number of 136 patients with 197 distinct FS events, from patients hospitalized in the Pediatric Clinical Hospital Sibiu, among which 10.2% were diagnosed with UTIs.

RESULTS

In one-third of the patients with UTIs (20 cases), the symptoms were limited to fever and FS. Using two-step cluster analysis, a distinct UTI inflammatory pattern has emerged: highest platelet values (PLT), median value 331 × 103/mm3 and intermediate C-reactive protein (CRP), median value 15 mg/dL, platelet distribution width (PDW), median value 9.65%, platelet-large cell ratio (P-LCR), median value 14.45%, mean platelet volume (MPV), median value 8.60 fL and neutrophil-to-lymphocyte values (NLR), median value 3.64. Furthermore, higher PDW (median value 12.25%), P-LCR (median value 28.55%), MPV (median value 10.40 fL), CRP (median value 74.00 mg/dL) and NLR values (median value 4.11) were associated mainly (85.7%) with bacterial lower respiratory infections. UTIs were highly unlikely in these patients with significantly increased CRP values and normal values of platelet indices.

CONCLUSIONS

Considering the nonspecific clinical picture of UTIs at an early age, to optimize the management of FS, a fast diagnosis of UTI is mandatory. The analysis of the inflammatory biomarker clusters (rather than individual parameters) correlated with urine leukocyte and nitrite stick evaluation for specific age groups could help in identifying even oligosymptomatic UTIs patients. The study limitation (20 UTI cases) recommends future multicentric trials on larger datasets to validate the model.

Deep Learning for Identification of Acute Illness and Facial Cues of Illness

Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves the assessment of patients' health status, as shown in genetic syndromes and acute coronary syndrome. It is unknown if the inclusion of clinical gestalt improves ML-based classification of acutely ill patients. As in previous research in ML analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt. Objective: To assess whether a deep learning algorithm trained on a dataset of simulated and augmented facial photographs reflecting acutely ill patients can distinguish between healthy and LPS-infused, acutely ill individuals. Methods: Photographs from twenty-six volunteers whose facial features were manipulated to resemble a state of acute illness were used to extract features of illness and generate a synthetic dataset of acutely ill photographs, using a neural transfer convolutional neural network (NT-CNN) for data augmentation. Then, four distinct CNNs were trained on different parts of the facial photographs and concatenated into one final, stacked CNN which classified individuals as healthy or acutely ill. Finally, the stacked CNN was validated in an external dataset of volunteers injected with lipopolysaccharide (LPS). Results: In the external validation set, the four individual feature models distinguished acutely ill patients with sensitivities ranging from 10.5% (95% CI, 1.3-33.1% for the skin model) to 89.4% (66.9-98.7%, for the nose model). Specificity ranged from 42.1% (20.3-66.5%) for the nose model and 94.7% (73.9-99.9%) for skin. The stacked model combining all four facial features achieved an area under the receiver characteristic operating curve (AUROC) of 0.67 (0.62-0.71) and distinguished acutely ill patients with a sensitivity of 100% (82.35-100.00%) and specificity of 42.11% (20.25-66.50%). Conclusion: A deep learning algorithm trained on a synthetic, augmented dataset of facial photographs distinguished between healthy and simulated acutely ill individuals, demonstrating that synthetically generated data can be used to develop algorithms for health conditions in which large datasets are difficult to obtain. These results support the potential of facial feature analysis algorithms to support the diagnosis of acute illness.

Independent Validation of Sepsis Index for Sepsis Screening in the Emergency Department

(1) Background: The early detection of sepsis is still challenging, and there is an urgent need for biomarkers that could identify patients at a high risk of developing it. We recently developed an index, namely the Sepsis Index (SI), based on the combination of two CBC parameters: monocyte distribution width (MDW) and mean monocyte volume (MMV). In this study, we sought to independently validate the performance of SI as a tool for the early detection of patients at a high risk of sepsis in the Emergency Department (ED). (2) Methods: We enrolled all consecutive patients attending the ED with a request of the CBC. MDW and MMV were measured on samples collected in K3-EDTA tubes on the UniCel DxH 900 haematology analyser. SI was calculated based on the MDW and MMV. (3) Results: We enrolled a total of 703 patients stratified into four subgroups according to the Sepsis-2 criteria: control (498), infection (105), SIRS (52) and sepsis (48). The sepsis subgroup displayed the highest MDW (median 27.5, IQR 24.6–32.9) and SI (median 1.15, IQR 1.05–1.29) values. The ROC curve analysis for the prediction of sepsis showed a good and comparable diagnostic accuracy of the MDW and SI. However, the SI displayed an increased specificity, positive predictive value and positive likelihood ratio in comparison to MDW alone. (4) Conclusions: SI improves the diagnostic accuracy of MDW for sepsis screening.

Diagnosis and prediction of COVID-19 severity: can biochemical tests and machine learning be used as prognostic indicators?

OBJECTIVE

This study aimed to implement and evaluate machine learning based-models to predict COVID-19' diagnosis and disease severity.

METHODS

COVID-19 test samples (positive or negative results) from patients who attended a single hospital were evaluated. Patients diagnosed with COVID-19 were categorised according to the severity of the disease. Data were submitted to exploratory analysis (principal component analysis, PCA) to detect outlier samples, recognise patterns, and identify important variables. Based on patients' laboratory tests results, machine learning models were implemented to predict disease positivity and severity. Artificial neural networks (ANN), decision trees (DT), partial least squares discriminant analysis (PLS-DA), and K nearest neighbour algorithm (KNN) models were used. The four models were validated based on the accuracy (area under the ROC curve).

RESULTS

The first subset of data had 5,643 patient samples (5,086 negatives and 557 positives for COVID-19). The second subset included 557 COVID-19 positive patients. The ANN, DT, PLS-DA, and KNN models allowed the classification of negative and positive samples with >84% accuracy. It was also possible to classify patients with severe and non-severe disease with an accuracy >86%. The following were associated with the prediction of COVID-19 diagnosis and severity: hyperferritinaemia, hypocalcaemia, pulmonary hypoxia, hypoxemia, metabolic and respiratory acidosis, low urinary pH, and high levels of lactate dehydrogenase.

CONCLUSION

Our analysis shows that all the models could assist in the diagnosis and prediction of COVID-19 severity.