Rapid diagnosis of latent and active pulmonary tuberculosis by autofluorescence spectroscopy of blood plasma combined with artificial neural network algorithm

• Published in: Photodiagnosis and photodynamic therapy Vol. 50; p. 104426
• Main Authors: Yue, Fengjiao, Li, Si, Wu, Lijuan, Chen, Xuerong, Zhu, Jianhua
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.12.2024; Elsevier
• Subjects: Adult; Algorithms; Artificial neural network; Autofluorescence spectroscopy; Blood plasma; Female; Humans; Latent Tuberculosis - diagnosis; Linear discriminant analysis; Male; Middle Aged; Neural Networks, Computer; Principal component analysis; Pulmonary tuberculosis; Spectrometry, Fluorescence - methods; Tuberculosis, Pulmonary - blood; Tuberculosis, Pulmonary - diagnosis; Autofluorescence spectroscopy; Artificial neural network; Linear discriminant analysis; Pulmonary tuberculosis; Blood plasma; Principal component analysis
• ISSN: 1572-1000; 1873-1597; 1873-1597
• DOI: 10.1016/j.pdpdt.2024.104426

•A rapid, accurate, label-free and non-invasive diagnosis method of pulmonary tuberculosis (TB) has been developed by using plasma autofluorescence spectroscopy and Machine Learning algorithm.•It is the first time that the autofluorescence spectroscopy combined with optimized three-classification Artificial Neural Network (ANN) model for distinguishing the active TB patients, latent TB infected individuals from healthy people.•Compared with traditional Principal component analysis (PCA) and Linear discriminant analysis (LDA) method, the three-layer ANN model achieves much better classification accuracy of 96.3 %, it can be developed as a promising diagnostic tool for the early screening of pulmonary TB disease. The existing clinical diagnostic methods of pulmonary tuberculosis (TB) usually have some of the following limitations, such as time-consuming, invasive, radioactive, insufficiently sensitive and accurate. This study demonstrates the possibility of using blood plasma autofluorescence spectroscopy and Artificial Neural Network (ANN) algorithm for the rapid and accurate diagnosis of latent and active pulmonary TB from healthy subjects. The fluorescence spectra of blood plasma from 18 healthy volunteers, 12 individuals with latent TB infections and 80 active TB patients are measured and analyzed. By optimizing the ANN structure and activation functions, the ANN three-classification model achieves average classification accuracy of 96.3 %, and the accuracy of healthy persons, latent TB infections and active TB patients are 100 %, 83.3 % and 97.5 %, respectively, which is much better than the results of traditional Principal component analysis (PCA) and Linear discriminant analysis (LDA) method. To the best of our knowledge, this is the first research work of differentiating latent, active pulmonary TB cases from healthy samples with autofluorescence spectroscopy. As a rapid, accurate, safe, label-free, non-invasive and cost-effective technique, it can be developed as a promising diagnostic tool for the screening of pulmonary TB disease in the early stage. [Display omitted]