Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin
ABSTRACT Enterococcus faecium is a clinically important pathogen that can cause significant morbidity and death. In this study, we aimed to develop a machine learning (ML) algorithm-based rapid susceptibility method to distinguish vancomycin-resistant E. faecium (VREfm) and vancomycin-susceptible E....
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Society for Microbiology
2021-12-01
|
| Series: | Microbiology Spectrum |
| Subjects: | |
| Online Access: | https://journals.asm.org/doi/10.1128/Spectrum.00913-21 |
| _version_ | 1798015808575635456 |
|---|---|
| author | Hsin-Yao Wang Chia-Ru Chung Chao-Jung Chen Ko-Pei Lu Yi-Ju Tseng Tzu-Hao Chang Min-Hsien Wu Wan-Ting Huang Ting-Wei Lin Tsui-Ping Liu Tzong-Yi Lee Jorng-Tzong Horng Jang-Jih Lu |
| author_facet | Hsin-Yao Wang Chia-Ru Chung Chao-Jung Chen Ko-Pei Lu Yi-Ju Tseng Tzu-Hao Chang Min-Hsien Wu Wan-Ting Huang Ting-Wei Lin Tsui-Ping Liu Tzong-Yi Lee Jorng-Tzong Horng Jang-Jih Lu |
| author_sort | Hsin-Yao Wang |
| collection | DOAJ |
| description | ABSTRACT Enterococcus faecium is a clinically important pathogen that can cause significant morbidity and death. In this study, we aimed to develop a machine learning (ML) algorithm-based rapid susceptibility method to distinguish vancomycin-resistant E. faecium (VREfm) and vancomycin-susceptible E. faecium (VSEfm) strains. A predictive model was developed and validated to distinguish VREfm and VSEfm strains by analyzing the matrix-assisted laser desorption ionization–time of flight (MALDI-TOF) mass spectrometry (MS) spectra of unique E. faecium isolates from different specimen types. The algorithm used 5,717 mass spectra, including 2,795 VREfm and 2,922 VSEfm mass spectra, and was externally validated with 2,280 mass spectra of isolates (1,222 VREfm and 1,058 VSEfm strains). A random forest-based algorithm demonstrated overall good classification performances for the isolates from the specimens, with mean accuracy, sensitivity, and specificity of 0.78, 0.79, and 0.77, respectively, with 10-fold cross-validation, timewise validation, and external validation. Furthermore, the algorithm provided rapid results, which would allow susceptibility prediction prior to the availability of phenotypic susceptibility results. In conclusion, an ML algorithm designed using mass spectra obtained from the routine workflow may be able to rapidly differentiate VREfm strains from VSEfm strains; however, susceptibility results must be confirmed by routine methods, given the demonstrated performance of the assay. IMPORTANCE A modified binning method was incorporated to cluster MS shifting ions into a set of representative peaks based on a large-scale MS data set of clinical VREfm and VSEfm isolates, including 2,795 VREfm and 2,922 VSEfm isolates. Predictions with the algorithm were significantly more accurate than empirical antibiotic use, the accuracy of which was 0.50, based on the local epidemiology. The algorithm improved the accuracy of antibiotic administration, compared to empirical antibiotic prescription. An ML algorithm designed using MALDI-TOF MS spectra obtained from the routine workflow accurately differentiated VREfm strains from VSEfm strains, especially in blood and sterile body fluid samples, and can be applied to facilitate the rapid and accurate clinical testing of pathogens. |
| first_indexed | 2024-04-11T15:40:41Z |
| format | Article |
| id | doaj.art-ba1dfd8def6b4a558456b9b31a386683 |
| institution | Directory Open Access Journal |
| issn | 2165-0497 |
| language | English |
| last_indexed | 2024-04-11T15:40:41Z |
| publishDate | 2021-12-01 |
| publisher | American Society for Microbiology |
| record_format | Article |
| series | Microbiology Spectrum |
| spelling | doaj.art-ba1dfd8def6b4a558456b9b31a3866832022-12-22T04:15:50ZengAmerican Society for MicrobiologyMicrobiology Spectrum2165-04972021-12-019310.1128/Spectrum.00913-21Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to VancomycinHsin-Yao Wang0Chia-Ru Chung1Chao-Jung Chen2Ko-Pei Lu3Yi-Ju Tseng4Tzu-Hao Chang5Min-Hsien Wu6Wan-Ting Huang7Ting-Wei Lin8Tsui-Ping Liu9Tzong-Yi Lee10Jorng-Tzong Horng11Jang-Jih Lu12Department of Information Management, National Central University, Taoyuan City, TaiwanDepartment of Computer Science and Information Engineering, National Central University, Taoyuan City, TaiwanGraduate Institute of Integrated Medicine, China Medical University, Taichung, TaiwanGraduate Program in Biomedical Information, Yuan-Ze University, Taoyuan City, TaiwanDepartment of Information Management, National Central University, Taoyuan City, TaiwanGraduate Institute of Biomedical Informatics, Taipei Medical University, Taipei City, TaiwanDepartment of Information Management, National Central University, Taoyuan City, TaiwanDepartment of Pathology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, TaiwanDepartment of Information Management, National Central University, Taoyuan City, TaiwanDepartment of Information Management, National Central University, Taoyuan City, TaiwanSchool of Life and Health Sciences, The Chinese University of Hong Kong, Shenzhen, ChinaDepartment of Information Management, National Central University, Taoyuan City, TaiwanDepartment of Information Management, National Central University, Taoyuan City, TaiwanABSTRACT Enterococcus faecium is a clinically important pathogen that can cause significant morbidity and death. In this study, we aimed to develop a machine learning (ML) algorithm-based rapid susceptibility method to distinguish vancomycin-resistant E. faecium (VREfm) and vancomycin-susceptible E. faecium (VSEfm) strains. A predictive model was developed and validated to distinguish VREfm and VSEfm strains by analyzing the matrix-assisted laser desorption ionization–time of flight (MALDI-TOF) mass spectrometry (MS) spectra of unique E. faecium isolates from different specimen types. The algorithm used 5,717 mass spectra, including 2,795 VREfm and 2,922 VSEfm mass spectra, and was externally validated with 2,280 mass spectra of isolates (1,222 VREfm and 1,058 VSEfm strains). A random forest-based algorithm demonstrated overall good classification performances for the isolates from the specimens, with mean accuracy, sensitivity, and specificity of 0.78, 0.79, and 0.77, respectively, with 10-fold cross-validation, timewise validation, and external validation. Furthermore, the algorithm provided rapid results, which would allow susceptibility prediction prior to the availability of phenotypic susceptibility results. In conclusion, an ML algorithm designed using mass spectra obtained from the routine workflow may be able to rapidly differentiate VREfm strains from VSEfm strains; however, susceptibility results must be confirmed by routine methods, given the demonstrated performance of the assay. IMPORTANCE A modified binning method was incorporated to cluster MS shifting ions into a set of representative peaks based on a large-scale MS data set of clinical VREfm and VSEfm isolates, including 2,795 VREfm and 2,922 VSEfm isolates. Predictions with the algorithm were significantly more accurate than empirical antibiotic use, the accuracy of which was 0.50, based on the local epidemiology. The algorithm improved the accuracy of antibiotic administration, compared to empirical antibiotic prescription. An ML algorithm designed using MALDI-TOF MS spectra obtained from the routine workflow accurately differentiated VREfm strains from VSEfm strains, especially in blood and sterile body fluid samples, and can be applied to facilitate the rapid and accurate clinical testing of pathogens.https://journals.asm.org/doi/10.1128/Spectrum.00913-21vancomycin-resistant Enterococcus faeciumantibacterial drug resistancematrix-assisted laser desorption ionization–time of flight (MALDI-TOF) mass spectrometrymachine learningrapid detectionEnterococcus faecium |
| spellingShingle | Hsin-Yao Wang Chia-Ru Chung Chao-Jung Chen Ko-Pei Lu Yi-Ju Tseng Tzu-Hao Chang Min-Hsien Wu Wan-Ting Huang Ting-Wei Lin Tsui-Ping Liu Tzong-Yi Lee Jorng-Tzong Horng Jang-Jih Lu Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin Microbiology Spectrum vancomycin-resistant Enterococcus faecium antibacterial drug resistance matrix-assisted laser desorption ionization–time of flight (MALDI-TOF) mass spectrometry machine learning rapid detection Enterococcus faecium |
| title | Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin |
| title_full | Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin |
| title_fullStr | Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin |
| title_full_unstemmed | Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin |
| title_short | Clinically Applicable System for Rapidly Predicting Enterococcus faecium Susceptibility to Vancomycin |
| title_sort | clinically applicable system for rapidly predicting enterococcus faecium susceptibility to vancomycin |
| topic | vancomycin-resistant Enterococcus faecium antibacterial drug resistance matrix-assisted laser desorption ionization–time of flight (MALDI-TOF) mass spectrometry machine learning rapid detection Enterococcus faecium |
| url | https://journals.asm.org/doi/10.1128/Spectrum.00913-21 |
| work_keys_str_mv | AT hsinyaowang clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT chiaruchung clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT chaojungchen clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT kopeilu clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT yijutseng clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT tzuhaochang clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT minhsienwu clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT wantinghuang clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT tingweilin clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT tsuipingliu clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT tzongyilee clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT jorngtzonghorng clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin AT jangjihlu clinicallyapplicablesystemforrapidlypredictingenterococcusfaeciumsusceptibilitytovancomycin |