Direct prediction of ceftazidime-resistant Stenotrophomonas maltophilia from routine MALDI-TOF mass spectra using machine learning

Article Infectious Diseases

Machine learning based on routine laboratory indicators promoting the discrimination between active tuberculosis and latent tuberculosis infection

Ying Luo et al.

Summary: In this study, a diagnostic model with promising value was successfully developed using machine learning based on routine laboratory indicators to differentiate active tuberculosis from latent tuberculosis infection. The model showed high sensitivity and specificity and was validated independently.

JOURNAL OF INFECTION (2022)

Add to Collection

Article Biochemical Research Methods

Rapid detection of KPC-producing Klebsiella pneumoniae in China based on MALDI-TOF MS

Yun Huang et al.

Summary: The study successfully identified KPC-Kp in Chinese clinical isolates using MALDI-TOF MS, with the 4521 m/z peak closely related to the ST11 gene. This approach has potential applications in drug resistance analysis and infection control without additional costs or expertise.

JOURNAL OF MICROBIOLOGICAL METHODS (2022)

Add to Collection

Article Biochemistry & Molecular Biology

Direct antimicrobial resistance prediction from clinical MALDI-TOF mass spectra using machine learning

Caroline Weis et al.

Summary: A machine learning approach has been developed to predict antimicrobial resistance from clinical isolates' mass spectra profiles, which can significantly accelerate the determination of antimicrobial resistance and change clinical management.

NATURE MEDICINE (2022)

Add to Collection

Article Microbiology

Rapid Identification of Methicillin-Resistant Staphylococcus aureus Using MALDI-TOF MS and Machine Learning from over 20,000 Clinical Isolates

Jiaxin Yu et al.

Summary: This study proposes a machine learning model based on MALDI-TOF MS for rapid MRSA prediction. The model was evaluated and validated on a prospective test and four external clinical sites. It can be easily integrated into current clinical workflows and help support proper antibiotic treatments.

MICROBIOLOGY SPECTRUM (2022)

Add to Collection

Article Microbiology

Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin

Hsin-Yao Wang et al.

Summary: The study developed a machine learning algorithm-based rapid susceptibility method to distinguish between vancomycin-resistant and vancomycin-susceptible Enterococcus faecium strains. The algorithm showed good classification performances and provided rapid results for predicting susceptibility prior to phenotypic susceptibility results becoming available. This method accurately differentiated VREfm strains from VSEfm strains and can improve the accuracy of antibiotic administration in clinical testing of pathogens.

MICROBIOLOGY SPECTRUM (2021)

Add to Collection

Article Microbiology

Evaluation of the Vitek 2, Phoenix, and MicroScan for Antimicrobial Susceptibility Testing of Stenotrophomonas maltophilia

Ayesha Khan et al.

Summary: This study evaluated the performance of different systems in detecting drug resistance of Stenotrophomonas maltophilia and found inconsistencies in the agreement among different systems under different drugs and corresponding CLSI breakpoints, with the presence of significant errors.

JOURNAL OF CLINICAL MICROBIOLOGY (2021)

Add to Collection

Review Infectious Diseases