| Title: | Machine Learning Approaches to Identify Discriminative Signatures of Volatile Organic Compounds (VOCs) from Bacteria and Fungi Using SPME-DART-MS |
| Author(s): | Arora M; Zambrzycki SC; Levy JM; Esper A; Frediani JK; Quave CL; Fernandez FM; Kamaleswaran R; |
| Address: | "School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA. Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA 30332, USA. School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, GA 30332, USA. Department of Otolaryngology-Head and Neck Surgery, Emory University School of Medicine, Atlanta, GA 30332, USA. Division of Pulmonary, Allergy, Critical Care, and Sleep Medicine, Emory University School of Medicine, Atlanta, GA 30332, USA. Emory Critical Care Center, Emory University School of Medicine, Atlanta, GA 30332, USA. Nell Hodgson Woodruff School of Nursing, Emory University, Atlanta, GA 30332, USA. Department of Dermatology, Emory University School of Medicine, Atlanta, GA 30332, USA. Center for the Study of Human Health, Emory College of Arts and Sciences, Atlanta, GA 30332, USA. Department of Emergency Medicine, Emory University School of Medicine, Atlanta, GA 30332, USA" |
| ISSN/ISBN: | 2218-1989 (Print) 2218-1989 (Electronic) 2218-1989 (Linking) |
| Abstract: | "Point-of-care screening tools are essential to expedite patient care and decrease reliance on slow diagnostic tools (e.g., microbial cultures) to identify pathogens and their associated antibiotic resistance. Analysis of volatile organic compounds (VOC) emitted from biological media has seen increased attention in recent years as a potential non-invasive diagnostic procedure. This work explores the use of solid phase micro-extraction (SPME) and ambient plasma ionization mass spectrometry (MS) to rapidly acquire VOC signatures of bacteria and fungi. The MS spectrum of each pathogen goes through a preprocessing and feature extraction pipeline. Various supervised and unsupervised machine learning (ML) classification algorithms are trained and evaluated on the extracted feature set. These are able to classify the type of pathogen as bacteria or fungi with high accuracy, while marked progress is also made in identifying specific strains of bacteria. This study presents a new approach for the identification of pathogens from VOC signatures collected using SPME and ambient ionization MS by training classifiers on just a few samples of data. This ambient plasma ionization and ML approach is robust, rapid, precise, and can potentially be used as a non-invasive clinical diagnostic tool for point-of-care applications" |
| Keywords: | Dart-ms K-means clustering Voc ambient plasma ionization imbalanced learning machine learning classification algorithms pathogen identification point-of-care devices solid phase micro-extraction; |
| Notes: | "PubMed-not-MEDLINEArora, Mehak Zambrzycki, Stephen C Levy, Joshua M Esper, Annette Frediani, Jennifer K Quave, Cassandra L Fernandez, Facundo M Kamaleswaran, Rishikesan eng R01 GM139967/GM/NIGMS NIH HHS/ UL1 TR002378/TR/NCATS NIH HHS/ R01GM139967 and UL1TR002378/NH/NIH HHS/ Switzerland 2022/03/25 Metabolites. 2022 Mar 8; 12(3):232. doi: 10.3390/metabo12030232" |
