Diagnosis of childhood febrile illness using a multi-class blood RNA molecular signature

The use of metagenomics to enhance diagnosis of encephalitis

INTRODUCTION

Encephalitis has a broad etiology, including infectious and auto-immune causes. In infectious encephalitis, the breadth of causative organisms results in incomplete testing and low diagnostic yields.Metagenomics sequences all DNA and RNA allowing untargeted detection of all organisms in a single specimen; this is of particular use in diagnosis of encephalitis with a broad etiology.

AREAS COVERED

We review the literature and discuss metagenomics workflows, host depletion and pathogen enrichment methods, bioinformatics analysis and potential analysis of the host transcriptome to aid diagnosis. We discuss the clinical use of metagenomics for diagnosis of neurological infection including time to result, cost, quality assurance, patient cohorts in whom metagenomics adds the most value, recommended specimen types, limitations and review published cases in which metagenomics has been used to diagnose encephalitis.

EXPERT OPINION

There is good evidence for the utility of metagenomics to diagnose infection in encephalitis. Due to infections with rare, unexpected or novel pathogens, metagenomics adds most value to diagnosis in immunocompromised patients and the greatest diagnostic yield is in brain biopsies. Technical advances are needed to reduce the complexity, cost and time to result which will enable wider adoption in clinical laboratories and use as a first-line test.

The application of machine learning in clinical microbiology and infectious diseases

With the development of artificial intelligence(AI) in computer science and statistics, it has been further applied to the medical field. These applications include the management of infectious diseases, in which machine learning has created inroads in clinical microbiology, radiology, genomics, and the analysis of electronic health record data. Especially, the role of machine learning in microbiology has gradually become prominent, and it is used in etiological diagnosis, prediction of antibiotic resistance, association between human microbiome characteristics and complex host diseases, prognosis judgment, and prevention and control of infectious diseases. Machine learning in the field of microbiology mainly adopts supervised learning and unsupervised learning, involving algorithms from classification and regression to clustering and dimensionality reduction. This Review explains crucial concepts in machine learning for unfamiliar readers, describes machine learning's current applications in clinical microbiology and infectious diseases, and summarizes important approaches clinicians must be aware of when evaluating research using machine learning.

A flexible framework for minimal biomarker signature discovery from clinical omics studies without library size normalisation

Application of transcriptomics, proteomics and metabolomics technologies to clinical cohorts has uncovered a variety of signatures for predicting disease. Many of these signatures require the full 'omics data for evaluation on unseen samples, either explicitly or implicitly through library size normalisation. Translation to low-cost point-of-care tests requires development of signatures which measure as few analytes as possible without relying on direct measurement of library size. To achieve this, we have developed a feature selection method (Forward Selection-Partial Least Squares) which generates minimal disease signatures from high-dimensional omics datasets with applicability to continuous, binary or multi-class outcomes. Through extensive benchmarking, we show that FS-PLS has comparable performance to commonly used signature discovery methods while delivering signatures which are an order of magnitude smaller. We show that FS-PLS can be used to select features predictive of library size, and that these features can be used to normalize unseen samples, meaning that the features in the complete model can be measured in isolation for making new predictions. By enabling discovery of small, high-performance signatures, FS-PLS addresses an important impediment for the further development of precision medical care.

Machine learning for early diagnosis of Kawasaki disease in acute febrile children: retrospective cross-sectional study in China

Early diagnosis of Kawasaki disease (KD) allows timely treatment to be initiated, thereby preventing coronary artery aneurysms in children. However, it is challenging due to the subjective nature of the diagnostic criteria. This study aims to develop a machine learning prediction model using routine blood tests to distinguish children with KD from other febrile illnesses in Chinese children within the first five days of fever onset. The retrospective cross-sectional data for this study was collected from the records of Guangzhou Women and Children's Medical Center, spanning January 1, 2020, to April 30, 2024. A retrospective analysis was performed using three machine learning models and five ensemble models based on this dataset. This study included 1,089 children with KD (mean age 32.8 ± 27.0 months; 34.5% female) and a control group of 81,697 children without KD (mean age 45.3 ± 33.6 months; 42.8% female). The supervised method, Xtreme Gradient Boosting (XGBoost), was applied. It was tested without feature selection, achieved an area under the ROC curve (AUC) of 0.9999, sensitivity of 0.9982, specificity of 0.9975, F1 score of 0.9979, accuracy of 0.9979, positive predictive value (PPV) of 0.9975, and negative predictive value (NPV) of 0.9982. The SHapley Additive exPlanations (SHAP) summary plot identified the top five significant features, which were the percentage of eosinophils (EO%), hematocrit (HCT), platelet crit (PCT), gender, and absolute basophil count (BA#). This study demonstrates that the application of the machine learning model, XGBoost, on routine blood test results can predict KD.

A 5-transcript signature for discriminating viral and bacterial etiology in pediatric pneumonia

Pneumonia stands as the primary cause of death among children under five, yet current diagnosis methods often result in inadequate or unnecessary treatments. Our research seeks to address this gap by identifying host transcriptomic biomarkers in the blood of children with definitive viral and bacterial pneumonia. We performed RNA sequencing on 192 prospectively collected whole blood samples, including 38 controls and 154 pneumonia cases, uncovering a 5-transcript signature (genes FAM20A, BAG3, TDRD9, MXRA7, and KLF14) that effectively distinguishes bacterial from viral pneumonia (area under the curve (AUC): 0.95 [0.88-1.00]). Initial validation using combined definitive and probable cases yielded an AUC of 0.87 [0.77-0.97], while full validation in a new prospective cohort of 32 patients achieved an AUC of 0.92 [0.83-1.00]. This robust signature holds significant potential to enhance diagnostics accuracy for pediatric pneumonia, reducing diagnostic delays and unnecessary treatments and potentially transforming clinical practice.

A diagnostic host-specific transcriptome response for Mycoplasma pneumoniae pneumonia to guide pediatric patient treatment

Mycoplasma pneumoniae causes atypical pneumonia in children and young adults. Its lack of a cell wall makes it resistant to beta-lactams, which are the first-line treatment for typical pneumonia. Current diagnostic tests are time-consuming and have low specificity, leading clinicians to administer empirical antibiotics. Using a LASSO regression simulation approach and blood microarray data from 107 children with pneumonia (including 30 M. pneumoniae) we identify eight different transcriptomic signatures, ranging from 3-10 transcripts, that differentiate mycoplasma pneumonia from other bacterial/viral pneumonias with high accuracy (AUC: 0.84-0.95). Additionally, we demonstrate that existing signatures for broadly distinguishing viral/bacterial infections and viral/bacterial pneumonias are ineffective in distinguishing M. pneumoniae from viral pneumonia. The new signatures are successfully validated in an independent RNAseq cohort of children with pneumonia, demonstrating their robustness. The high sensibility of these signatures presents a valuable opportunity to guide the treatment and management of M. pneumoniae pneumonia patients.

Role of diagnostic tests for sepsis in children: a review

Paediatric sepsis has a significant global impact and highly heterogeneous clinical presentation. The clinical pathway encompasses recognition, escalation and de-escalation. In each aspect, diagnostics have a fundamental influence over outcomes in children. Biomarkers can aid in creating a larger low-risk group of children from those in the clinical grey area who would otherwise receive antibiotics 'just in case'. Current biomarkers include C reactive protein and procalcitonin, which are limited in their clinical use to guide appropriate and rapid treatment. Biomarker discovery has focused on single biomarkers, which, so far, have not outperformed current biomarkers, as they fail to recognise the complexity of sepsis. The identification of multiple host biomarkers that may form a panel in a clinical test has the potential to recognise the complexity of sepsis and provide improved diagnostic performance. In this review, we discuss novel biomarkers and novel ways of using existing biomarkers in the assessment and management of sepsis along with the significant challenges in biomarker discovery at present. Validation of biomarkers is made less meaningful due to methodological heterogeneity, including variations in sepsis diagnosis, biomarker cut-off values and patient populations. Therefore, the utilisation of platform studies is necessary to improve the efficiency of biomarkers in clinical practice.

Plasma cell-free RNA signatures of inflammatory syndromes in children

Inflammatory syndromes, including those caused by infection, are a major cause of hospital admissions among children and are often misdiagnosed because of a lack of advanced molecular diagnostic tools. In this study, we explored the utility of circulating cell-free RNA (cfRNA) in plasma as an analyte for the differential diagnosis and characterization of pediatric inflammatory syndromes. We profiled cfRNA in 370 plasma samples from pediatric patients with a range of inflammatory conditions, including Kawasaki disease (KD), multisystem inflammatory syndrome in children (MIS-C), viral infections, and bacterial infections. We developed machine learning models based on these cfRNA profiles, which effectively differentiated KD from MIS-C-two conditions presenting with overlapping symptoms-with high performance [test area under the curve = 0.98]. We further extended this methodology into a multiclass machine learning framework that achieved 80% accuracy in distinguishing among KD, MIS-C, viral, and bacterial infections. We further demonstrated that cfRNA profiles can be used to quantify injury to specific tissues and organs, including the liver, heart, endothelium, nervous system, and the upper respiratory tract. Overall, this study identified cfRNA as a versatile analyte for the differential diagnosis and characterization of a wide range of pediatric inflammatory syndromes.

Integration and validation of host transcript signatures, including a novel 3-transcript tuberculosis signature, to enable one-step multiclass diagnosis of childhood febrile disease

BACKGROUND

Whole blood host transcript signatures show great potential for diagnosis of infectious and inflammatory illness, with most published signatures performing binary classification tasks. Barriers to clinical implementation include validation studies, and development of strategies that enable simultaneous, multiclass diagnosis of febrile illness based on gene expression.

METHODS

We validated five distinct diagnostic signatures for paediatric infectious diseases in parallel using a single NanoString nCounter® experiment. We included a novel 3-transcript signature for childhood tuberculosis, and four published signatures which differentiate bacterial infection, viral infection, or Kawasaki disease from other febrile illnesses. Signature performance was assessed using receiver operating characteristic curve statistics. We also explored conceptual frameworks for multiclass diagnostic signatures, including additional transcripts found to be significantly differentially expressed in previous studies. Relaxed, regularised logistic regression models were used to derive two novel multiclass signatures: a mixed One-vs-All model (MOVA), running multiple binomial models in parallel, and a full-multiclass model. In-sample performance of these models was compared using radar-plots and confusion matrix statistics.

RESULTS

Samples from 91 children were included in the study: 23 bacterial infections (DB), 20 viral infections (DV), 14 Kawasaki disease (KD), 18 tuberculosis disease (TB), and 16 healthy controls. The five signatures tested demonstrated cross-platform performance similar to their primary discovery-validation cohorts. The signatures could differentiate: KD from other diseases with area under ROC curve (AUC) of 0.897 [95% confidence interval: 0.822-0.972]; DB from DV with AUC of 0.825 [0.691-0.959] (signature-1) and 0.867 [0.753-0.982] (signature-2); TB from other diseases with AUC of 0.882 [0.787-0.977] (novel signature); TB from healthy children with AUC of 0.910 [0.808-1.000]. Application of signatures outside of their designed context reduced performance. In-sample error rates for the multiclass models were 13.3% for the MOVA model and 0.0% for the full-multiclass model. The MOVA model misclassified DB cases most frequently (18.7%) and TB cases least (2.7%).

CONCLUSIONS

Our study demonstrates the feasibility of NanoString technology for cross-platform validation of multiple transcriptomic signatures in parallel. This external cohort validated performance of all five signatures, including a novel sparse TB signature. Two exploratory multi-class models showed high potential accuracy across four distinct diagnostic groups.

A real-world multi-center RNA-seq benchmarking study using the Quartet and MAQC reference materials

Translating RNA-seq into clinical diagnostics requires ensuring the reliability and cross-laboratory consistency of detecting clinically relevant subtle differential expressions, such as those between different disease subtypes or stages. As part of the Quartet project, we present an RNA-seq benchmarking study across 45 laboratories using the Quartet and MAQC reference samples spiked with ERCC controls. Based on multiple types of 'ground truth', we systematically assess the real-world RNA-seq performance and investigate the influencing factors involved in 26 experimental processes and 140 bioinformatics pipelines. Here we show greater inter-laboratory variations in detecting subtle differential expressions among the Quartet samples. Experimental factors including mRNA enrichment and strandedness, and each bioinformatics step, emerge as primary sources of variations in gene expression. We underscore the profound influence of experimental execution, and provide best practice recommendations for experimental designs, strategies for filtering low-expression genes, and the optimal gene annotation and analysis pipelines. In summary, this study lays the foundation for developing and quality control of RNA-seq for clinical diagnostic purposes.

A computational framework to improve cross-platform implementation of transcriptomics signatures

The emergence of next-generation sequencing technologies and computational advances have expanded our understanding of gene expression regulation (i.e., the transcriptome). This has also led to an increased interest in using transcriptomic biomarkers to improve disease diagnosis and stratification, to assess prognosis and predict the response to treatment. Significant progress in identifying transcriptomic signatures for various clinical needs has been made, with large discovery studies accounting for challenges such as patient variability, unwanted batch effects, and data complexities; however, obstacles related to the technical aspects of cross-platform implementation still hinder the successful integration of transcriptomic technologies into standard diagnostic workflows. In this article, we discuss the challenges associated with integrating transcriptomic signatures derived using high-throughput technologies (such as RNA-sequencing) into clinical diagnostic tools using nucleic acid amplification (NAA) techniques. The novelty of the proposed approach lies in our aim to embed constraints related to cross-platform implementation in the process of signature discovery. These constraints could include technical limitations of amplification platform and chemistry, the maximal number of targets imposed by the chosen multiplexing strategy, and the genomic context of identified RNA biomarkers. Finally, we propose to build a computational framework that would integrate these constraints in combination with existing statistical and machine learning models used for signature identification. We envision that this could accelerate the integration of RNA signatures discovered by high-throughput technologies into NAA-based approaches suitable for clinical applications.

Enhancing APE1 detection through apurinic/apyrimidinic site inhibition of DNA polymerase: an innovative, highly sensitive approach

This study presents an innovative method for the highly sensitive detection of apurinic/apyrimidinic endonuclease 1 (APE1), a crucial biomarker and target for cancer diagnosis and treatment. The method is predicated on our discovery that the apurinic or apyrimidinic site (AP site) can inhibit the activity of Taq DNA polymerase. Subsequent experiments further led to the development of a new amplification method based on the digestion activity of Lambda exonuclease. This approach showed potential to detect trace amounts of APE1 in biological samples with high sensitivity.

The malarial blood transcriptome: translational applications

The blood transcriptome of malaria patients has been used extensively to elucidate the pathophysiological mechanisms and host immune responses to disease, identify candidate diagnostic and prognostic biomarkers, and reveal new therapeutic targets for drug discovery. This review gives a high-level overview of the three main translational applications of these studies (diagnostics, prognostics, and therapeutics) by summarising recent literature and outlining the main limitations and future directions of each application. It highlights the need for consistent and accurate definitions of disease states and subject groups and discusses how prognostic studies must distinguish clearly between analyses that attempt to predict future disease states and those which attempt to discriminate between current disease states (classification). Lastly it examines how many promising therapeutics fail due to the choice of imperfect animal models for pre-clinical testing and lack of appropriate validation studies in humans, and how future transcriptional studies may be utilised to overcome some of these limitations.

Raising AWaRe-ness of Antimicrobial Stewardship Challenges in Pediatric Emergency Care: Results from the PERFORM Study Assessing Consistency and Appropriateness of Antibiotic Prescribing Across Europe

BACKGROUND

Optimization of antimicrobial stewardship is key to tackling antimicrobial resistance, which is exacerbated by overprescription of antibiotics in pediatric emergency departments (EDs). We described patterns of empiric antibiotic use in European EDs and characterized appropriateness and consistency of prescribing.

METHODS

Between August 2016 and December 2019, febrile children attending EDs in 9 European countries with suspected infection were recruited into the PERFORM (Personalised Risk Assessment in Febrile Illness to Optimise Real-Life Management) study. Empiric systemic antibiotic use was determined in view of assigned final "bacterial" or "viral" phenotype. Antibiotics were classified according to the World Health Organization (WHO) AWaRe classification.

RESULTS

Of 2130 febrile episodes (excluding children with nonbacterial/nonviral phenotypes), 1549 (72.7%) were assigned a bacterial and 581 (27.3%) a viral phenotype. A total of 1318 of 1549 episodes (85.1%) with a bacterial and 269 of 581 (46.3%) with a viral phenotype received empiric systemic antibiotics (in the first 2 days of admission). Of those, the majority (87.8% in the bacterial and 87.0% in the viral group) received parenteral antibiotics. The top 3 antibiotics prescribed were third-generation cephalosporins, penicillins, and penicillin/β-lactamase inhibitor combinations. Of those treated with empiric systemic antibiotics in the viral group, 216 of 269 (80.3%) received ≥1 antibiotic in the "Watch" category.

CONCLUSIONS

Differentiating bacterial from viral etiology in febrile illness on initial ED presentation remains challenging, resulting in a substantial overprescription of antibiotics. A significant proportion of patients with a viral phenotype received systemic antibiotics, predominantly classified as WHO Watch. Rapid and accurate point-of-care tests in the ED differentiating between bacterial and viral etiology could significantly improve antimicrobial stewardship.