Machine Learning Algorithms Identify Pathogen-Specific Biomarkers of Clinical and Metabolomic Characteristics in Septic Patients with Bacterial Infections

Sepsis is a high-mortality disease that is infected by bacteria, but pathogens in individual patients are difficult to diagnosis. Metabolomic changes triggered by microbial activity provide us with the possibility of accurately identifying infection. We adopted machine learning methods for training different classifiers with a clinical-metabolomic database from sepsis cases to identify the pathogen of sepsis. Records of clinical indicators and concentration of metabolites were obtained for each patient upon their arrival at the hospital. Machine learning algorithms were used in 100 patients with clear infection and corresponding 29 controls to select specific biosignatures to discriminate microorganism in septic patients. The sensitivity, specificity, and AUC value of clinical and metabolomic characteristics in predicting diagnostic outcomes were determined at admission. Our analyses demonstrate that the biosignatures selected by machine learning algorithms could have diagnostic value on the identification of infected patients and Gram-positive from Gram-negative; related AUC values were 0.94 ± 0.054 and 0.80 ± 0.085, respectively. Pathway and blood disease enrichment analyses of clinical and metabolomic biomarkers among infected patients showed that sepsis disease was accompanied by abnormal nitrogen metabolism, cell respiratory disorder, and renal or intestinal failure. The panel of selected clinical and metabolomic characteristics might be powerful biomarkers to discriminate patients with sepsis.

Clinical Impact of a Rapid Streptococcal Antigen Test on Antibiotic Use in Adult Patients

INTRODUCTION

Adult pharyngitis is rarely attributable to group A streptococci. Utilization of a rapid streptococcal antigen test (RADT) may improve appropriate prescribing for bacterial pharyngitis.

METHODS

Clinic 1 performed RADTs with subsequent Group A DNA probe test (GADNA) from November 2014-March 2015 and November 2015-March 2016 while Clinic 2 was the control clinic, then implemented the RADT with a GADNA from November 2015-March 2016. All GADNA results were obtained for each clinic from October 2013-March 2016.

RESULTS

At Clinic 1, 22.2% versus 8.5% of patients received inappropriately prescribed antibiotics for a GADNA or RADT result, respectively (p=0.048). For Clinic 2, 51.1% compared to 21.4% of patients were inappropriately prescribed antibiotic for a GADNA or RADT result, respectively (p=0.038). Overall, the total GADNA without RADT testing or RADTs with subsequent GADNA testing, 41.6% versus 11% of patients were inappropriately prescribed antibiotics, respectively (p=<0.0001).

CONCLUSION

Utilizing the RADT prevented unnecessary prescribing of antibiotics in adults.

Narrow-Spectrum Antibacterial Agents

While broad spectrum antibiotics play an invaluable role in the treatment of bacterial infections, there are some drawbacks to their use, namely selection for and spread of resistance across multiple bacterial species, and the detrimental effect they can have upon the host microbiome. If the causitive agent of the infection is known, the use of narrow-spectrum antibacterial agents has the potential to mitigate some of these issues. This review outlines the advantages and challenges of narrow-spectrum antibacterial agents, discusses the progress that has been made toward developing diagnostics to enable their use, and describes some of the narrow-spectrum antibacterial agents currently being investigated against some of the most clinically important bacteria including Clostridium difficile, Mycobacterium tuberculosis and several ESKAPE pathogens.

Clinical Impact and Provider Acceptability of Real-Time Antimicrobial Stewardship Decision Support for Rapid Diagnostics in Children With Positive Blood Culture Results

BACKGROUND

Rapid diagnostic technologies for infectious diseases have the potential to improve clinical outcomes, but guideline-recommended antimicrobial stewardship (AS) strategies are not currently optimized for rapid intervention. We evaluated the clinical impact and provider acceptability of implementing real-time AS decision support for children with positive blood culture results according to the FilmArray blood culture identification panel (BCID [BioFire Diagnostics]) at Children's Hospital Colorado.

METHODS

A pre-post quasi-experimental design was used to compare the outcomes of 100 postintervention children with positive blood culture results matched with 200 preintervention control children. Causative organisms in the preintervention group were identified using conventional microbiologic techniques and communicated to providers by a microbiology technologist. Postintervention organisms were identified by the BCID and communicated by an AS provider in real time with interpretation and antimicrobial recommendations. The primary outcome was time to optimal antimicrobial therapy (time from blood culture collection to start of predetermined pathogen-specific regimen or antimicrobial discontinuation for contaminants) compared by a log-rank test and Kaplan-Meier analysis. Provider acceptability of the intervention was assessed via E-mailed surveys.

RESULTS

The median time to optimal therapy decreased from 60.2 hours before intervention to 26.7 hours after intervention (P = .001). Among children with blood cultures that contained true pathogens, the time to effective antimicrobial therapy decreased from 6.9 to 3.4 hours (P = .03). Unnecessary antibiotic initiation for children with a culture that contained organisms considered to be contaminants decreased from 76% to 26% (P < .001). Providers reported a change in management as a result of BCID results in 73% of the cases and a mean overall satisfaction rating of 4.8 on a 5-point Likert scale.

CONCLUSIONS

Real-time AS decision support for rapid diagnostics is associated with improved antimicrobial use and high satisfaction ratings by providers.

Respiratory Infections

The majority of respiratory tract infections (RTIs) are community acquired and are the single most common cause of physician office visits and among the most common causes of hospitalizations. The morbidity and mortality associated with RTIs are significant and the financial and social burden high due to lost time at work and school. The scope of clinical symptoms can significantly overlap among the respiratory pathogens, and the severity of disease can vary depending on patient age, underlying disease, and immune status, thereby leading to inaccurate presumptions about disease etiology. The rapid and accurate diagnosis of the causative agent of RTIs improves patient care, reduces morbidity and mortality, promotes effective hospital bed utilization and antibiotic stewardship, and reduces length of stay. This chapter focuses on the clinical utility, advantages, and disadvantages of viral and bacterial tests cleared by the Food and Drug Administration (FDA), and new promising technologies for the detection of bacterial agents of pneumonia currently in development or in US FDA clinical trials are briefly reviewed.

Emerging technologies for hybridization based single nucleotide polymorphism detection

Detection of single nucleotide polymorphisms (SNPs) is a crucial challenge in the development of a novel generation of diagnostic tools. Accurate detection of SNPs can prove elusive, as the impact of a single variable nucleotide on the properties of a target sequence is limited, even if this sequence consists of only a few nucleotides. New, accurate and facile strategies for the detection of point mutations are therefore absolutely necessary for the increased adoption of point-of-care molecular diagnostics. Currently, PCR and sequencing are mostly applied for diagnosing SNPs. However these methods have serious drawbacks as routine diagnostic tools because of their labour intensity and cost. Several new, more suitable methods can be applied to enable sensitive detection of mutations based on specially designed hybridization probes, mutation recognizing enzymes and thermal denaturation. Here, an overview is presented of the most recent advances in the field of fast and sensitive SNP detection assays with strong potential for integration in point-of-care tests.

Differences in hospital- and ventilator-associated pneumonia due to Staphylococcus aureus (methicillin-susceptible and methicillin-resistant) between Europe and Latin America: a comparison of the EUVAP and LATINVAP study cohorts

PURPOSE

A comparison is made of epidemiological variables (demographic and clinical characteristics) and outcomes in patients with hospital-acquired pneumonia (HAP) or ventilator-associated pneumonia (VAP) caused by methicillin-susceptible and methicillin-resistant Staphylococcus aureus (MSSA and MRSA) in the Latin American VAP (LATINVAP) vs. the European Union VAP (EUVAP) cohorts of patients admitted to intensive care units (ICUs).

METHODS

The EUVAP project was a prospective, multicenter observational study reporting 827 patients with HAP/VAP in 27 ICUs from 9 European countries. The LATINVAP project was a multicenter prospective observational study, with an identical design, performed in 17 ICUs from 4 Latin American countries involving 99 patients who developed HAP/VAP. Episodes of VAP/HAP caused by S. aureus, MSSA, and MRSA were compared in both cohorts.

RESULTS

Forty-five patients had S. aureus HAP/VAP in the EUVAP cohort vs. 11 patients in the LATINVAP cohort. More patients had MRSA in the LATINVAP study than in the EUVAP (45% vs. 33%). ICU mortality among patients with MSSA HAP/VAP in EUVAP was 10% vs. 50% for LATINVAP (OR=9.75, p=0.01). Fifteen patients in the EUVAP cohort developed MRSA HAP/VAP as opposed to 5 in LATINVAP. In the EUVAP study there was an ICU mortality rate of 33.3%. In the LATINVAP cohort, the ICU mortality rate was 60% (OR for death=3.0; 95%CI 0.24-44.7).

CONCLUSION

MRSA pneumonia was associated with poorer outcomes in comparison with MSSA. Our study suggests significant variability among European and Latin American ICU practices that may influence clinical outcomes. Furthermore, patients with pneumonia in Latin America have different outcomes.

The crisis of no new antibiotics--what is the way forward?

Antibiotic use not only underpins modern medicine, but has brought huge changes to the world, especially in expectations of survival of children into adulthood. The theme of World Health Day, 2011, was "antimicrobial resistance: no action today and no cure tomorrow". The demise of antibacterial drug discovery brings the spectre of untreatable infections. To prevent this crisis immediate action is needed and a new initiative, Antibiotic Action, has been launched. By bringing together communities who need these drugs with academia, health-care professionals, and pharmaceutical companies, this initiative aims to strengthen and enhance academic-industrial partnerships, bring about revision of costly and laborious processes of licensing and regulation of new antibiotics, and address the economics of antimicrobial drugs (cost of use vs profit). A global alliance for antibiotic drug discovery and development would provide a platform for these initiatives.