Discovery of urinary biosignatures for tuberculosis and nontuberculous mycobacteria classification using metabolomics and machine learning
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Discovery of urinary biosignatures for tuberculosis and nontuberculous mycobacteria classification using metabolomics and machine learning. / Anh, Nguyen Ky; Phat, Nguyen Ky; Thu, Nguyen Quang; Tien, Nguyen Tran Nam; Eunsu, Cho; Kim, Ho-Sook; Nguyen, Duc Ninh; Kim, Dong Hyun; Long, Nguyen Phuoc; Oh, Jee Youn.
In: Scientific Reports, Vol. 14, No. 1, 03.07.2024, p. 15312.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Discovery of urinary biosignatures for tuberculosis and nontuberculous mycobacteria classification using metabolomics and machine learning
AU - Anh, Nguyen Ky
AU - Phat, Nguyen Ky
AU - Thu, Nguyen Quang
AU - Tien, Nguyen Tran Nam
AU - Eunsu, Cho
AU - Kim, Ho-Sook
AU - Nguyen, Duc Ninh
AU - Kim, Dong Hyun
AU - Long, Nguyen Phuoc
AU - Oh, Jee Youn
N1 - © 2024. The Author(s).
PY - 2024/7/3
Y1 - 2024/7/3
N2 - Nontuberculous mycobacteria (NTM) infection diagnosis remains a challenge due to its overlapping clinical symptoms with tuberculosis (TB), leading to inappropriate treatment. Herein, we employed noninvasive metabolic phenotyping coupled with comprehensive statistical modeling to discover potential biomarkers for the differential diagnosis of NTM infection versus TB. Urine samples from 19 NTM and 35 TB patients were collected, and untargeted metabolomics was performed using rapid liquid chromatography-mass spectrometry. The urine metabolome was analyzed using a combination of univariate and multivariate statistical approaches, incorporating machine learning. Univariate analysis revealed significant alterations in amino acids, especially tryptophan metabolism, in NTM infection compared to TB. Specifically, NTM infection was associated with upregulated levels of methionine but downregulated levels of glutarate, valine, 3-hydroxyanthranilate, and tryptophan. Five machine learning models were used to classify NTM and TB. Notably, the random forest model demonstrated excellent performance [area under the receiver operating characteristic (ROC) curve greater than 0.8] in distinguishing NTM from TB. Six potential biomarkers for NTM infection diagnosis, including methionine, valine, glutarate, 3-hydroxyanthranilate, corticosterone, and indole-3-carboxyaldehyde, were revealed from univariate ROC analysis and machine learning models. Altogether, our study suggested new noninvasive biomarkers and laid a foundation for applying machine learning to NTM differential diagnosis.
AB - Nontuberculous mycobacteria (NTM) infection diagnosis remains a challenge due to its overlapping clinical symptoms with tuberculosis (TB), leading to inappropriate treatment. Herein, we employed noninvasive metabolic phenotyping coupled with comprehensive statistical modeling to discover potential biomarkers for the differential diagnosis of NTM infection versus TB. Urine samples from 19 NTM and 35 TB patients were collected, and untargeted metabolomics was performed using rapid liquid chromatography-mass spectrometry. The urine metabolome was analyzed using a combination of univariate and multivariate statistical approaches, incorporating machine learning. Univariate analysis revealed significant alterations in amino acids, especially tryptophan metabolism, in NTM infection compared to TB. Specifically, NTM infection was associated with upregulated levels of methionine but downregulated levels of glutarate, valine, 3-hydroxyanthranilate, and tryptophan. Five machine learning models were used to classify NTM and TB. Notably, the random forest model demonstrated excellent performance [area under the receiver operating characteristic (ROC) curve greater than 0.8] in distinguishing NTM from TB. Six potential biomarkers for NTM infection diagnosis, including methionine, valine, glutarate, 3-hydroxyanthranilate, corticosterone, and indole-3-carboxyaldehyde, were revealed from univariate ROC analysis and machine learning models. Altogether, our study suggested new noninvasive biomarkers and laid a foundation for applying machine learning to NTM differential diagnosis.
KW - Humans
KW - Machine Learning
KW - Metabolomics/methods
KW - Male
KW - Biomarkers/urine
KW - Female
KW - Middle Aged
KW - Tuberculosis/urine
KW - Mycobacterium Infections, Nontuberculous/urine
KW - Nontuberculous Mycobacteria
KW - Aged
KW - Adult
KW - Metabolome
KW - ROC Curve
KW - Diagnosis, Differential
U2 - 10.1038/s41598-024-66113-x
DO - 10.1038/s41598-024-66113-x
M3 - Journal article
C2 - 38961191
VL - 14
SP - 15312
JO - Scientific Reports
JF - Scientific Reports
SN - 2045-2322
IS - 1
ER -
ID: 398545253