Rapid, antibiotic incubation-free determination of tuberculosis drug resistance using machine learning and Raman spectroscopy

• 成果类型: Article
• 署名作者: Li, Babatunde Ogunlade a Loza F. Tadesse bcde Hongquan; Vu, Nhat; Banaei, Niaz; Barczak, Amy K.; Saleh, j Amr A. E.; Prakash, Manu; Dionne, Jennifer A.; Murphy, Catherine
• 署名单位: Stanford University; Stanford University; Massachusetts Institute of Technology (MIT); Massachusetts Institute of Technology (MIT); Massachusetts Institute of Technology (MIT); Stanford University; Stanford University; Harvard University; Harvard University Medical Affiliates; Massachusetts General Hospital; Harvard University; Harvard Medical School; Egyptian Knowledge Bank (EKB); Cairo University; Stanford University
• 刊物名称: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
• ISSN/ISSBN: 0027-14179
• DOI: 10.1073/pnas.2315670121
• 发表日期: 2024-06-18
• 页码: 10-10
• 关键词: identification; sers; diagnostics; infection; bacteria; size

摘要

Tuberculosis (TB) is the world's deadliest infectious disease, with over 1.5 million deaths and 10 million new cases reported anually. The causative organism Mycobacterium tuberculosis (Mtb) can take nearly 40 d to culture, a required step to determine the pathogen's antibiotic susceptibility. Both rapid identification and rapid antibiotic susceptibility testing of Mtb are essential for effective patient treatment and combating antimicrobial resistance. Here, we demonstrate a rapid, culture-free, and antibiotic incubation-free drug susceptibility test for TB using Raman spectroscopy and machine learning. We collect few-to-single-cell Raman spectra from over 25,000 cells of the Mtb complex strain Bacillus Calmette-Guerin (BCG) resistant to one of the four mainstay anti-TB drugs, isoniazid, rifampicin, moxifloxacin, and amikacin, as well as a pan-susceptible wildtype strain. By training a neural network on this data, we classify the antibiotic resistance profile of each strain, both on dried samples and on patient sputum samples. On dried samples, we achieve >98% resistant versus susceptible classification accuracy across all five BCG strains. In patient sputum samples, we achieve similar to 79% average classification accuracy. We develop a feature recognition algorithm in order to verify that our machine learning model is using biologically relevant spectral features to assess the resistance profiles of our mycobacterial strains. Finally, we demonstrate how this approach can be deployed in resource-limited settings by developing a low-cost, portable Raman microscope that costs <$5,000. We show how this instrument and our machine learning model enable combined microscopy and spectroscopy for accurate few-to-single-cell drug susceptibility testing of BCG.