Dataset Information

Investigating Unfavorable Factors That Impede MALDI-TOF-Based AI in Predicting Antibiotic Resistance.

ABSTRACT: The combination of Matrix-Assisted Laser Desorption/Ionization Time-of-Flight (MALDI-TOF) spectra data and artificial intelligence (AI) has been introduced for rapid prediction on antibiotic susceptibility testing (AST) of Staphylococcus aureus. Based on the AI predictive probability, cases with probabilities between the low and high cut-offs are defined as being in the "grey zone". We aimed to investigate the underlying reasons of unconfident (grey zone) or wrong predictive AST. In total, 479 S. aureus isolates were collected and analyzed by MALDI-TOF, and AST prediction and standard AST were obtained in a tertiary medical center. The predictions were categorized as correct-prediction group, wrong-prediction group, and grey-zone group. We analyzed the association between the predictive results and the demographic data, spectral data, and strain types. For methicillin-resistant S. aureus (MRSA), a larger cefoxitin zone size was found in the wrong-prediction group. Multilocus sequence typing of the MRSA isolates in the grey-zone group revealed that uncommon strain types comprised 80%. Of the methicillin-susceptible S. aureus (MSSA) isolates in the grey-zone group, the majority (60%) comprised over 10 different strain types. In predicting AST based on MALDI-TOF AI, uncommon strains and high diversity contribute to suboptimal predictive performance.

SUBMITTER: Wang HY

PROVIDER: S-EPMC8871102 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Investigating Unfavorable Factors That Impede MALDI-TOF-Based AI in Predicting Antibiotic Resistance.

Wang Hsin-Yao HY Liu Yu-Hsin YH Tseng Yi-Ju YJ Chung Chia-Ru CR Lin Ting-Wei TW Yu Jia-Ruei JR Huang Yhu-Chering YC Lu Jang-Jih JJ

Diagnostics (Basel, Switzerland) 20220205 2

The combination of Matrix-Assisted Laser Desorption/Ionization Time-of-Flight (MALDI-TOF) spectra data and artificial intelligence (AI) has been introduced for rapid prediction on antibiotic susceptibility testing (AST) of <i>Staphylococcus aureus</i>. Based on the AI predictive probability, cases with probabilities between the low and high cut-offs are defined as being in the "grey zone". We aimed to investigate the underlying reasons of unconfident (grey zone) or wrong predictive AST. In total ...[more]

PMID: 35204505

Similar Datasets

Project description:Lactational mastitis constitutes one of the main causes of undesired weaning, depriving the mother-infant pair from the benefits of breastfeeding; therefore, this condition should be considered a relevant public health issue. The role of specific microorganisms remains unclear since human milk cultures and antibiotic susceptibility testing (AST) are not routinely performed, despite the fact that this would be key to ensure an early and effective diagnosis and treatment. The objective of this study was to describe the culturable microbial diversity in 647 milk samples from breastfeeding women with clinical symptoms of mastitis by Matrix-Assisted Laser Desorption Ionization Time-of-Flight Mass Spectrometry (MALDI-TOF) VITEK MS technology and to analyze the antimicrobial susceptibility profiles of a collection of isolates from these samples by the VITEK 2 AST system. Staphylococcus epidermidis was the most common species isolated from mastitis samples (87.6%), while Staphylococcus aureus was detected in 22.1%. Streptococci constituted the second (68.6%) most prevalent bacterial group, with Streptococcus mitis/oralis, Streptococcus salivarius, and Streptococcus parasanguinis detected with frequencies of 40.8, 36.8, and 14.4%, respectively. The antibiotic susceptibility profiles of 642 staphylococcal isolates indicated a remarkable resistance to benzylpenicillin (88.3%) and erythromycin (67.3%) with differences between species. A high percentage of Staphylococcus isolates were resistant to at least one antibiotic (Staphylococcus hominis, 100%; S. epidermidis, 98.2%; S. aureus, 92.9%; Staphylococcus lugdunensis, 90.5%) and the percentage of multidrug-resistance (MDR) isolates was noticeable (S. hominis, 81%; S. epidermidis, 64.4%; S. aureus, 11.5%; S. lugdunensis, 10.5%). In relation to streptococcal isolates (n = 524), AST revealed high or moderate percentages of resistance to erythromycin (68.7%), benzylpenicillin (63.7%), ampicillin (51.5%), and tetracycline (30.8%). Antibiotic resistance to at least one antibiotic was detected in 97.6% of S. parasanguinis, 92.6% of S. salivarius, 83.3% of S. mitis/oralis, and 72.4% of Streptococcus vestibularis isolates. A significant number of MDR streptococcal isolates was also found (S. parasanguinis, 51.2%; S. salivarius, 39.3%; S. mitis/oralis, 34.6%; and S. vestibularis, 19%). The results highlight the important role of coagulase-negative staphylococci and streptococci as human mastitis-causing agents. Moreover, the high rates of antimicrobial resistance among these microorganisms must be contemplated as an issue of clinical relevance in relation to treatment options.

Project description:Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used in clinical microbiology laboratories for bacterial identification but its use for detection of antimicrobial resistance (AMR) remains limited. Here, we used MALDI-TOF MS with artificial intelligence (AI) approaches to successfully predict AMR in Pseudomonas aeruginosa, a priority pathogen with complex AMR mechanisms. The highest performance was achieved for modern β-lactam/β-lactamase inhibitor drugs, namely, ceftazidime/avibactam and ceftolozane/tazobactam. For these drugs, the model demonstrated area under the receiver operating characteristic curve (AUROC) of 0.869 and 0.856, specificity of 0.925 and 0.897, and sensitivity of 0.731 and 0.714, respectively. As part of this work, we developed dynamic binning, a feature engineering technique that effectively reduces the high-dimensional feature set and has wide-ranging applicability to MALDI-TOF MS data. Compared to conventional feature engineering approaches, the dynamic binning method yielded highest performance in 7 of 10 antimicrobials. Moreover, we showcased the efficacy of transfer learning in enhancing the AUROC performance for 8 of 11 antimicrobials. By assessing the contribution of features to the model's prediction, we identified proteins that may contribute to AMR mechanisms. Our findings demonstrate the potential of combining AI with MALDI-TOF MS as a rapid AMR diagnostic tool for Pseudomonas aeruginosa.IMPORTANCEPseudomonas aeruginosa is a key bacterial pathogen that causes significant global morbidity and mortality. Antimicrobial resistance (AMR) emerges rapidly in P. aeruginosa and is driven by complex mechanisms. Drug-resistant P. aeruginosa is a major challenge in clinical settings due to limited treatment options. Early detection of AMR can guide antibiotic choices, improve patient outcomes, and avoid unnecessary antibiotic use. Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used for rapid species identification in clinical microbiology. In this study, we repurposed mass spectra generated by MALDI-TOF and used them as inputs for artificial intelligence approaches to successfully predict AMR in P. aeruginosa for multiple key antibiotic classes. This work represents an important advance toward using MALDI-TOF as a rapid AMR diagnostic for P. aeruginosa in clinical settings.

Dataset Information

Investigating Unfavorable Factors That Impede MALDI-TOF-Based AI in Predicting Antibiotic Resistance.

Publications

Investigating Unfavorable Factors That Impede MALDI-TOF-Based AI in Predicting Antibiotic Resistance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets