Machine-Learning Model for Prediction of Cefepime Susceptibility in Escherichia coli from Whole-Genome Sequencing Data

Rapid inference of antibiotic resistance and susceptibility for Klebsiella pneumoniae by clinical shotgun metagenomic sequencing

OBJECTIVES

The study aimed to develop a genotypic antimicrobial resistance testing method for Klebsiella pneumoniae using metagenomic sequencing data.

METHODS

We utilized Lasso regression on assembled genomes to identify genetic resistance determinants for six antibiotics (Gentamicin, Tobramycin, Imipenem, Meropenem, Ceftazidime, Trimethoprim/Sulfamethoxazole). The genetic features were weighted, grouped into clusters to establish classifier models. Origin species of detected antibiotic resistant gene (ARG) was determined by novel strategy integrating "possible species," "gene copy number calculation" and "species-specific kmers." The performance of the method was evaluated on retrospective case studies.

RESULTS

Our study employed machine learning on 3928 K. pneumoniae isolates, yielding stable models with AUCs > 0.9 for various antibiotics. GenseqAMR, a read-based software, exhibited high accuracy (AUC 0.926-0.956) for short-read datasets. The integration of a species-specific kmer strategy significantly improved ARG-species attribution to an average accuracy of 96.67%. In a retrospective study of 191 K. pneumoniae-positive clinical specimens (0.68-93.39% genome coverage), GenseqAMR predicted 84.23% of AST results on average. It demonstrated 88.76-96.26% accuracy for resistance prediction, offering genotypic AST results with a shorter turnaround time (mean ± SD: 18.34 ± 0.87 hours) than traditional culture-based AST (60.15 ± 21.58 hours). Furthermore, a retrospective clinical case study involving 63 cases showed that GenseqAMR could lead to changes in clinical treatment for 24 (38.10%) cases, with 95.83% (23/24) of these changes deemed beneficial.

CONCLUSIONS

In conclusion, GenseqAMR is a promising tool for quick and accurate AMR prediction in Klebsiella pneumoniae, with the potential to improve patient outcomes through timely adjustments in antibiotic treatment.

The real-world impact of the BioFire FilmArray blood culture identification 2 panel on antimicrobial stewardship among patients with bloodstream infections in intensive care units with a high burden of drug-resistant pathogens

BACKGROUND

The increasing prevalence of drug-resistant pathogens leads to delays in adequate antimicrobial treatment in intensive care units (ICU). The real-world influence of the BioFire FilmArray Blood Culture Identification 2 (BCID2) panel on pathogen identification, diagnostic concordance with conventional culture methods, and antimicrobial stewardship in the ICU remains unexplored.

METHODS

This retrospective observational study, conducted from July 2021 to August 2023, involved adult ICU patients with positive blood cultures who underwent BCID2 testing. The concordance between BCID2 and conventional culture results was examined, and its impact on antimicrobial stewardship was assessed through a comprehensive retrospective review of patient records by intensivists.

RESULTS

A total of 129 blood specimens from 113 patients were analysed. Among these patients, a high proportion of drug-resistant strains were noted, including carbapenem-resistant Klebsiella pneumoniae (CRKP) (57.1%), carbapenem-resistant Acinetobacter calcoaceticus-baumannii complex (100%), methicillin-resistant Staphylococcus aureus (MRSA) (70%), and vancomycin-resistant Enterococcus faecium (VRE) (100%). The time from blood culture collection to obtaining BCID2 results was significantly shorter than conventional culture (46.2 h vs. 86.9 h, p < 0.001). BCID2 demonstrated 100% concordance in genotype-phenotype correlation in antimicrobial resistance (AMR) for CRKP, carbapenem-resistant Escherichia coli, MRSA, and VRE. A total of 40.5% of patients received inadequate empirical antimicrobial treatment. The antimicrobial regimen was adjusted or confirmed in 55.4% of patients following the BCID2 results.

CONCLUSIONS

In the context of a high burden of drug-resistant pathogens, BCID2 demonstrated rapid pathogen and AMR detection, with a noticeable impact on antimicrobial stewardship in BSI in the ICU.

Status check: next-generation sequencing for infectious-disease diagnostics

Next-generation sequencing (NGS) applications for the diagnostics of infectious diseases has demonstrated great potential with three distinct approaches: whole-genome sequencing (WGS), targeted NGS (tNGS), and metagenomic NGS (mNGS, also known as clinical metagenomics). These approaches provide several advantages over traditional microbiologic methods, though challenges still exist.

Machine learning and feature extraction for rapid antimicrobial resistance prediction of Acinetobacter baumannii from whole-genome sequencing data

Background

Whole-genome sequencing (WGS) has contributed significantly to advancements in machine learning methods for predicting antimicrobial resistance (AMR). However, the comparisons of different methods for AMR prediction without requiring prior knowledge of resistance remains to be conducted.

Methods

We aimed to predict the minimum inhibitory concentrations (MICs) of 13 antimicrobial agents against Acinetobacter baumannii using three machine learning algorithms (random forest, support vector machine, and XGBoost) combined with k-mer features extracted from WGS data.

Results

A cohort of 339 isolates was used for model construction. The average essential agreement and category agreement of the best models exceeded 90.90% (95%CI, 89.03-92.77%) and 95.29% (95%CI, 94.91-95.67%), respectively; the exceptions being levofloxacin, minocycline and imipenem. The very major error rates ranged from 0.0 to 5.71%. We applied feature selection pipelines to extract the top-ranked 11-mers to optimise training time and computing resources. This approach slightly improved the prediction performance and enabled us to obtain prediction results within 10 min. Notably, when employing these top-ranked 11-mers in an independent test dataset (120 isolates), we achieved an average accuracy of 0.96.

Conclusion

Our study is the first to demonstrate that AMR prediction for A. baumannii using machine learning methods based on k-mer features has competitive performance over traditional workflows; hence, sequence-based AMR prediction and its application could be further promoted. The k-mer-based workflow developed in this study demonstrated high recall/sensitivity and specificity, making it a dependable tool for MIC prediction in clinical settings.

The Use of Machine Learning for Image Analysis Artificial Intelligence in Clinical Microbiology

The growing transition to digital microbiology in clinical laboratories creates the opportunity to interpret images using software. Software analysis tools can be designed to use human-curated knowledge and expert rules, but more novel artificial intelligence (AI) approaches such as machine learning (ML) are being integrated into clinical microbiology practice. These image analysis AI (IAAI) tools are beginning to penetrate routine clinical microbiology practice, and their scope and impact on routine clinical microbiology practice will continue to grow. This review separates the IAAI applications into 2 broad classification categories: (i) rare event detection/classification or (ii) score-based/categorical classification. Rare event detection can be used for screening purposes or for final identification of a microbe including microscopic detection of mycobacteria in a primary specimen, detection of bacterial colonies growing on nutrient agar, or detection of parasites in a stool preparation or blood smear. Score-based image analysis can be applied to a scoring system that classifies images in toto as its output interpretation and examples include application of the Nugent score for diagnosing bacterial vaginosis and interpretation of urine cultures. The benefits, challenges, development, and implementation strategies of IAAI tools are explored. In conclusion, IAAI is beginning to impact the routine practice of clinical microbiology, and its use can enhance the efficiency and quality of clinical microbiology practice. Although the future of IAAI is promising, currently IAAI only augments human effort and is not a replacement for human expertise.