The most robust and economical method for laboratory diagnosis of tuberculosis (TB) is to identify mycobacteria acid-fast bacilli (AFB) under acid-fast staining, despite its disadvantages of low sensitivity and labor intensity. In recent years, artificial intelligence (AI) has been used in TB-smear microscopy to assist medical technologists with routine AFB smear microscopy. In this study, we evaluated the performance of a TB automated system consisting of a microscopic scanner and recognition program powered by artificial intelligence and machine learning. This AI-based system can detect AFB and classify the level from 0 to 4+. A total of 5930 smears were evaluated on the performance of this automatic system in identifying AFB in daily lab practice. At the first stage, 120 images were analyzed per smear, and the accuracy, sensitivity, and specificity were 91.3%, 60.0%, and 95.7%, respectively. In the second stage, 200 images were analyzed per smear, and the accuracy, sensitivity, and specificity were increased to 93.7%, 77.4%, and 96.6%. After removing disqualifying smears caused by poor staining quality and smear preparation, the accuracy, sensitivity, and specificity were improved to 95.2%, 85.7%, and 96.9%, respectively. Furthermore, the automated system recovered 85 positive smears initially identified as negative by manual screening. Our results suggested that the automated TB system could achieve higher sensitivity and laboratory efficiency than manual microscopy under the quality control of smear preparation. Automated TB smear screening systems can serve as a screening tool at the first screen before manual microcopy.
Rapidly growing mycobacteria (RGM) has gained increasing clinical importance, and treatment is challenging due to diverse drug resistance. The minimum inhibitory concentrations (MIC) of 13 antimicrobial agents using modified broth microdilution and E-test were determined for 32 clinical isolates of RGM, including Mycobacterium abscessus (22 isolates) and Mycobacterium fortuitum (10 isolates). Our results showed high rates of resistance to available antimicrobial agents. Amikacin remained highly susceptible (87.5%). Clarithromycin was active against the isolates of M. abscessus (95.5%), and M. fortuitum (50%), but 36.4% and 20% had inducible macrolide resistance, respectively. Rates of susceptibility to tigecycline were 68.2–70%, and linezolid 45.5–50%, respectively. The quinolones (ciprofloxacin and moxifloxacin) showed better in vitro activity against M. fortuitum isolates (50% susceptibility) than the M. abscessus isolates (31.8% susceptibility). The susceptibilities to other conventional anti-mycobacterial agents were poor. The MICs of E-test were higher than broth microdilution and may result in reports of false resistance. In conclusion, the implementation of the modified broth microdilution plates into the routine clinical laboratory workflow to provide antimicrobial susceptibility early, allows for the timely selection of appropriate treatment of RGM infections to improve outcome.
Mycobacterium tuberculosis complex (MTBC) infection is an important public health concern in Taiwan. In addition to pulmonary tuberculosis (PTB), MTBC can also cause genitourinary tuberculosis (GUTB). This study aimed to examine the role of laboratory data and the values that can be calculated from them for the early detection of GUTB. Patients admitted from 2011 to 2020 were retrospectively recruited to analyze their associated clinical data. Statistical significance was analyzed using the chi-square test and univariate analysis for different variables. A receiver operating characteristic (ROC) curve analysis was used to evaluate the performances of the examined laboratory data and their calculated items, including the neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR), neutrophil-to-monocyte-plus-lymphocyte ratio (NMLR), and platelet-to-lymphocyte ratio (PLR), in diagnosing PTB or GUTB. A p-value of <0.05 was considered significant. The ROC curve showed that the discriminative power of the neutrophil count, NLR, and MLR was within the acceptable level between patients with both PTB and GUTB and those with GUTB alone (area under the curve [AUC] values = 0.738, 0.779, and 0.725; p = 0.024, 0.008, and 0.033, respectively). The discriminative power of monocytes and the MLR was within the acceptable level (AUC = 0.782 and 0.778; p = 0.008 and 0.010, respectively). Meanwhile, the neutrophil and lymphocyte counts, NLR, NMLR, and PLR had good discriminative power (AUC = 0.916, 0.896, 0.898, 0.920, and 0.800; p < 0.001, <0.001, <0.001, <0.001, and 0.005, respectively) between patients with GUTB and those with PTB alone. In conclusion, the neutrophil count, lymphocyte count, NLR, NMLR, and PLR can be used as potential markers for distinguishing PTB from GUTB.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.