scholarly journals Machine learning reveals that Mycobacterium tuberculosis genotypes and anatomic disease site impacts drug resistance and disease transmission among patients with proven extra-pulmonary tuberculosis

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Doctor B. Sibandze ◽  
Beki T. Magazi ◽  
Lesibana A. Malinga ◽  
Nontuthuko E. Maningi ◽  
Bong-Akee Shey ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Resistance ◽  
Mycobacterium Tuberculosis ◽  
Pulmonary Tuberculosis ◽  
Disease Transmission ◽  
Extra Pulmonary Tuberculosis ◽  
Disease Site ◽  
Extra Pulmonary

scholarly journals Machine-learning reveals that Mycobacterium tuberculosis genotypes and anatomic disease site impacts drug resistance and disease transmission among patients with proven extra-pulmonary tuberculosis

2020 ◽  
Author(s):  
Doctor Busizwe Sibandze ◽  
Beki Themba Magazi ◽  
Lesibana Anthony Malinga ◽  
Nontuthuko Excellent Maningi ◽  
Bong Akee Shey ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Resistance ◽  
Mycobacterium Tuberculosis ◽  
Disease Transmission ◽  
East Asian ◽  
Extrapulmonary Tuberculosis ◽  
Machine Learning Algorithms ◽  
East African ◽  
Development Of Resistance ◽  
Asian Lineage

Abstract Background: There is a general dearth of information on extrapulmonary tuberculosis (EPTB). Here, we investigated Mycobacterium tuberculosis (Mtb) drug resistance and transmission patterns in EPTB patients treated in the Tshwane metropolitan area, in South Africa.Methods: Consecutive Mtb culture-positive non-pulmonary samples from unique EPTB patients underwent mycobacterial genotyping and were assigned to phylogenetic lineages and transmission clusters based on spoligotypes. MTBDRplus assay was used to search mutations for isoniazid and rifampin resistance. Machine learning algorithms were used to identify clinically meaningful patterns in data. We computed odds ratio (OR), attributable risk (AR) and corresponding 95% confidence intervals (CI). Results: Of the 70 isolates examined, the largest cluster comprised 25 (36%) Mtb strains that belonged to the East Asian lineage. East Asian lineage was significantly more likely to occur within chains of transmission when compared to the Euro-American and East-African Indian lineages: OR= 10.11 (95% CI: 1.56-116). Lymphadenitis, meningitis and cutaneous TB, were significantly more likely to be associated with drug resistance: OR=12.69 (95% CI: 1.82-141.60) and AR = 0.25 (95% CI: 0.06-0.43) when compared with other EPTB sites, which suggests that poor rifampin penetration might be a contributing factor.Conclusions: The majority of Mtb strains circulating in the Tshwane metropolis belongs to East Asian, Euro-American and East-African Indian lineages. Each of these are likely to be clustered, suggesting on-going EPTB transmission. Since 25% of the drug resistance was attributable to sanctuary EPTB sites notorious for poor rifampin penetration, we hypothesize that poor anti-tuberculosis drug dosing might have a role in the development of resistance.

scholarly journals 1633. Improving the diagnosis of extra-pulmonary tuberculosis (EPTB): experience from north India

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S808-S808
Author(s):  
Anchal Sharma ◽  
Kusum Sharma ◽  
Manish Modi ◽  
Aman Sharma
Keyword(s):  
Mycobacterium Tuberculosis ◽  
Pulmonary Tuberculosis ◽  
Mycobacterium Tuberculosis Complex ◽  
Lamp Assay ◽  
Nucleic Acid Amplification ◽  
Rural Setting ◽  
Tuberculosis Complex ◽  
Extra Pulmonary Tuberculosis ◽  
Resource Poor ◽  
Extra Pulmonary

Abstract Background Rapid and accurate diagnosis of extra-pulmonary tuberculosis (EPTB) is imperative for early treatment and better patient outcome. Loop-mediated Isothermal Amplification (LAMP) is a promising nucleic-acid amplification assay. LAMP assay could be carried out in simple water bath under isothermal conditions in 60 minutes, and can be performed in any laboratory even in rural setting in resource poor endemic countries. We evaluated LAMP assay using two different target regions LAMP primers specific for Mycobacterium tuberculosis complex for the diagnosis of EPTB. Methods LAMP assay using 6 primers (each for IS6110 and IS1081) specific for Mycobacterium tuberculosis complex were performed on patients suspected of EPTB on various EPTB samples(CSF, Synovial fluid, Lymaphnode and tissue biopsies and various other samples) of 150 patients (50 confirmed, 100 suspected) Clinically suspected of EPTB and 100 non-TB control subjects. Results Overall LAMP test (using any of the two targets) had sensitivity and specificity of 96% and 100% for confirmed (50 culture positive) EPTB cases. In 100 clinically suspected but unconfirmed EPTB cases, LAMP was positive in 87 out of 100 cases (87%). Sensitivity of IS6110 LAMP, 1S1081 LAMP and IS6110 PCR for clinically suspected cases was 78 (78%), 84 (84%) and 70 (70%), respectively. In total 150 EPTB patients, the overall sensitivity of microscopy, culture, IS6110 PCR, IS6110 LAMP, 1081 LAMP and the LAMP test (if any of the two targets were used) were 4%, 33.3%, 74.6%, 82.66%, 87% and 92%, respectively. Specificity of all the tests was 100%. There were 8 cases which were missed by IS6110 LAMP and 2 cases by 1081 LAMP. Conclusion LAMP assay using two targets is a promising technique for rapid diagnosis of EPTB in 60 minutes especially in a resource poor setting who are still battling with this deadly disease. Disclosures All Authors: No reported disclosures

scholarly journals The silent pandemic in South Africa: Extra-pulmonary tuberculosis from head to heel

2021 ◽  
Vol 25 (1) ◽  
Author(s):  
Camilla E. Le Roux ◽  
Sucari S.C. Vlok
Keyword(s):  
South Africa ◽  
Mycobacterium Tuberculosis ◽  
Pulmonary Tuberculosis ◽  
Communicable Disease ◽  
Diagnostic Dilemma ◽  
Extra Pulmonary Tuberculosis ◽  
Immunodeficiency Virus ◽  
Normal Chest Radiograph ◽  
Normal Chest ◽  
Extra Pulmonary

Extra-pulmonary tuberculosis (EPTB), caused by Mycobacterium tuberculosis, is the leading cause of communicable disease-related deaths in people with human immunodeficiency virus (HIV) worldwide and in South Africa. Mycobacterium tuberculosis disseminates haematogenously from an active primary lung focus and may affect extra-pulmonary sites in up to 15% of patients. Extra-pulmonary TB may present with a normal chest radiograph, which often causes a significant diagnostic dilemma. This review describes the main sites of involvement in EPTB, which is illustrated by local imaging examples.

scholarly journals Gen X-Pert MTB/Rif Assay with the Ziehl Nielsen, and Florescence Microscopy Detection Rate of Urinary Tuberculosis Among Suspected and Pulmonary MTB Positive Patients Visiting University of Gondar Specialized Referral Hospital, Northwest Ethiopia.

2021 ◽  
Author(s):  
Dessie Eshetie ◽  
Minichil Worku ◽  
Abiye Tigabu ◽  
Melak Aynalem ◽  
Nega Berhane
Keyword(s):  
Mycobacterium Tuberculosis ◽  
Urinary Tract ◽  
Fluorescence Microscopy ◽  
Pulmonary Tuberculosis ◽  
Detection Rate ◽  
Extra Pulmonary Tuberculosis ◽  
Extra Pulmonary ◽  
Urinary Tuberculosis ◽  
Study Participants ◽  
Gen X

Abstract Background Tuberculosis is a bacterial infection caused by Mycobacterium tuberculosis remains a major global public health concern. Extra-pulmonary tuberculosis accounts for 15% of the global tuberculosis burden. Urinary tract tuberculosis is one of the most common and severe forms of extra-pulmonary tuberculosis in clinical practice. Diagnosis of urinary tract tuberculosis by Gen X-pert MTB/RIF assay from developing countries including Ethiopia is limited. Thus, this study was aimed to compare Gene X-pert MTB/RIF assay with the convectional diagnosis methods. Methods A hospital-based cross-sectional study was conducted among confirmed pulmonary tuberculosis and suspected for urinary tract tuberculosis patients at University of Gondar Specialized Referral Hospital from February 2020 to June 2020 G.C. Non-randomized purposive sampling technique was used to select study participants. To detect Mycobacterium tuberculosis, a urine sample was collected. Then, Ziehl Nielsen and fluorescence microscope, Gene X-pert Real-time PCR were performed to detect the Mycobacterium tuberculosis. Sociodemographic, clinical data, and laboratory data were collected and entered into EPI-Info version 3.5.3 and then transferred to SPSS version-20 for analysis. Descriptive statistics were summarized as percentages, means, and standard deviations. Results A total of 64 study participants were enrolled in this study, 64.2% (41/64) were males and 30% (19/64) were in the age group of 31–45 years. Moreover, 71.9% (46/64) and 57.8% (37/64) study participants were rural residences and illiterate respectively. Among the 64 study participants, 4.69% (3/64) were positive for urinary tuberculosis by Gene X-expert. However, 1.56% (1/64) was positive by fluorescence microscopy, and there was no urinary tuberculosis detected by Ziehl Nielsen examination method. Conclusion and recommendation: The prevalence of urinary tract Mycobacterium tuberculosis using Gene X-pert and fluorescence microscopy was 4.69% (3/64) and 1.56% (1/64), respectively. Gene X-pert has higher detection rate than the conventional methods. Therefore, it is better to develop a guideline on how to use Gen x-pert for the diagnosis for urinary tract tuberculosis in urine samples.

scholarly journals Accurate Integrated System to detect Pulmonary and Extra Pulmonary Tuberculosis using Machine Learning Algorithms

2021 ◽  
Vol 24 (68) ◽  
pp. 104-122
Author(s):  
Rupinder Kaur ◽  
Anurag Sharma
Keyword(s):  
Machine Learning ◽  
Pulmonary Tuberculosis ◽  
Decision Tree ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Integrated System ◽  
Machine Learning Algorithms ◽  
Validation Dataset ◽  
Extra Pulmonary Tuberculosis ◽  
Extra Pulmonary

Several studies have been reported the use of machine learning algorithms in the detection of Tuberculosis, but studies that discuss the detection of both types of TB, i.e., Pulmonary and Extra Pulmonary Tuberculosis, using machine learning algorithms are lacking. Therefore, an integrated system based on machine learning models has been proposed in this paper to assist doctors and radiologists in interpreting patients’ data to detect of PTB and EPTB. Three basic machine learning algorithms, Decision Tree, Naïve Bayes, SVM, have been used to predict and compare their performance. The clinical data and the image data are used as input to the models and these datasets have been collected from various hospitals of Jalandhar, Punjab, India. The dataset used to train the model comprises 200 patients’ data containing 90 PTB patients, 67 EPTB patients, and 43 patients having NO TB. The validation dataset contains 49 patients, which exhibited the best accuracy of 95% for classifying PTB and EPTB using Decision Tree, a machine learning algorithm.

Sign in / Sign up

Export Citation Format

Share Document