1976 research outputs found
Sort by
Clinical Text Classification for Tuberculosis Diagnosis Using Natural Language Processing and Deep Learning Model with Statistical Feature Selection Technique
Full text linkIn the medical field, various deep learning (DL) algorithms have been effec�tively used to extract valuable information from unstructured clinical text data, potentially
leading to more effective outcomes. This study utilized clinical text data to classify clinical case reports into tuberculosis (TB) and non-tuberculosis (non-TB) groups using natural lan�guage processing (NLP), a pre-processing technique, and DL models. Methods: This study used 1743 open-source respiratory disease clinical text data, labeled via fuzzy matching with ICD-10 codes to create a labeled dataset. Two tokenization methods preprocessed the
clinical text data, and three models were evaluated: the existing Text-CNN, the proposed Text-CNN with t-test, and Bio_ClinicalBERT. Performance was assessed using multiple metrics and validated on 228 baseline screening clinical case text data collected from ICMR–NIRT to demonstrate effective TB classification. Results: The proposed model achieved the best results in both the test and validation datasets. On the test dataset, it attained a precision of 88.19%, a recall of 90.71%, an F1-score of 89.44%, and an AUC of 0.91. Simi�larly, on the validation dataset, it achieved 100% precision, 98.85% recall, 99.42% F1-score,
and an AUC of 0.982, demonstrating its effectiveness in TB classification. Conclusions: This study highlights the effectiveness of DL models in classifying TB cases from clinical notes. The proposed model outperformed the other two models. The TF-IDF and t-test showed statistically significant feature selection and enhanced model interpretability and efficiency, demonstrating the potential of NLP and DL in automating TB diagnosis in
clinical decision settings
Low-complexity automated nucleic acid amplification tests for extrapulmonary tuberculosis and rifampicin resistance in adults and adolescents (Review)
Full text linkLow-complexity automated nucleic acid amplification tests (LC-aNAATs) are molecular World Health Organization (WHO)-recommended rapid diagnostic tests widely used for simultaneous detection of Mycobacterium tuberculosis complex and rifampicin resistance in sputum. To extend our previous review on extrapulmonary tuberculosis, we performed this update to inform a WHO policy update
Direct targeted next-generation sequencing for diagnosis of drug-resistant tuberculosis from clinical samples – An update
No full textTimely detection of drug resistance is a pre-requisite to tuberculosis management globally. While phenotypic drug susceptibility testing (pDST) by liquid or solid
method takes time, current genotypic DST assays can be performed directly from clinical specimens but target only a limited number of resistance variants. Targeted Next Generation Sequencing (tNGS) is a rapid, cost-effective method using direct sample to perform the sequencing than compared to whole genome sequencing (WGS) which requires culture. tNGS provides comprehensive drug resistance profiling with turnaround time of 3–4 days when done directly from clinical samples. For respiratory samples with rifampicin resistance, tNGS could be used for the rapid detection of additional drug resistance including newer and repurposed drugs like Bedaquiline, Delamanid, Pretomanid, Linezolid and Clofazimine for which no rapid molecular tests are currently available. A variety of clinical samples can be used and there are wide choices available for DNA extraction. The targets for tNGS could be amplified using commercial kits or in house primers. tNGS could be
performed using different platforms like Illumina, Oxford Nanopore Technology and/or Ion torrent and diverse bio-informatic pipeline options. Positioning of a tNGS
with portability system in the current TB diagnostic algorithm and its use in the clinical management of patients’ needs further evaluation and efforts
Recovery of Mycobacterium tuberculosis Complex Isolates Including Pre–Extensively Drug-Resistant Strains From Cattle at a Slaughterhouse in Chennai, India
Full text linkIndia has the highest global burden of human tuberculosis (TB) and the largest cattle herd with endemic bovine TB (bTB). However, the extent of cross-species transmission and the zoonotic spillover risk, including drug-resistant
Mycobacterium tuberculosis complex (MTBC) strains circulating in cattle, remain uncharacterized
Role of Neutrophil to Lymphocyte Ratio and Platelet to Lymphocyte Ratio as Predictors of Preeclampsia
Full text linkPreeclampsia affects 10 million women each year, accounting for 76,000maternal deaths. Since the one and only effective treatment is deliveryof the fetus, it has therefore lead to iatrogenic preterm deliveries andthus causing 500,000 neonatal deaths each year. Preeclampsia also affects neonatal morbidity to a great extent by causing intrauterine growth restriction, oligohydramnios, iatrogenic low birth weight preterm babies,allof which babies require intensive care. In western countries,incidence is2‐7% out of which 0.1% of them progress to develop seizures, known as eclampsia. To study the efficacy of neutrophil to lymphocyte ratio and platelet to lymphocyte ratio in predicting preeclampsia at early second trimester. (13‐20 weeks). To study and compare neutrophil to lymphocyte ratio and platelet to lymphocyte ratio measured at 13‐20 weeks (before the development of disease) among normotensive, non‐severe preeclampsia and severe preeclampsia women. Case control study. 300 Neutrophil and lymphocyte levels are measured using automated cellcounter and the corresponding ratios are measured. Allenrolled patientsare regularly followed up in OPD in their second and third trimesters.Patients who developed preeclampsia are taken as CASES. 5ml venoussample is taken for those who developed disease. Out of 300 women, 68women developed preeclampsia (52 non severe and 16 severepreeclampsia respectively) and 232 were normotensive. NLR and PLRhave shown promising results in many studies on early prediction of preeclampsia. These markers are a part of routine antenatal investigation profile, they are very simple, rapid, non‐invasive and easily availablepredictor tool developed so far in the early prediction of the diseas
Effectiveness of food supplement on treatment outcomes and quality of life in pulmonary tuberculosis: Phased implementation approach
Full text linkBy encouraging treatment adherence and lowering mortality, dietary supplements can serve as adjuvant therapy for the success of medical interventions. We determined the effect of
locally accessible food supplements on treatment outcomes, and health-related quality of life in patients with pulmonary tuberculosis initiating anti-tuberculosis treatment (ATT) in
Odisha, India
Development and Validation of a SimpleHigh-pressure Liquid Chromatography-Ultraviolet Detection Method for Simultaneous Quantitation of First-LineAnti-Tuberculosis Drugs in Formulations of Fixed-Dose Combination
Full text linkThe current treatment protocol for drug-sensitive tuberculosis involves all four first-line anti-tuberculosis drugs: rifampicin, isoniazid, pyrazinamide and ethambutol hydrochloride in a single tablet, known as fixed-dose combination tablets. However, the analytical methods are scanty to test all these drugs simultaneously in a single run without any pre-sample process or using a simple method suitable for resource-limited settings. In this method, 50 mM potassium phosphate buffer containing 0.2% triethylamine (without pH adjustment) added with acetonitrile (98:2, v/v) was served as mobile phase A, while mobile phase B was 100% acetonitrile. All four drugs were separated within 10.3 min using a gradient mobile phase program in a C18 column (150 mm × 4.6 mm; 5 μm) and detected at two ultraviolet wavelengths (238 nm for rifampicin, isoniazid and pyrazinamide, and 210 nm for ethambutol hydrochloride). The method was selective, sensitive and linear with a correlation coefficient >0.999 with the acceptable precision and accuracy (<2% relative standard deviation) for all four drugs. In conclusion, the method is simple and it does not require any pH adjustment of the buffer/mobile phase, and within 11 min, the separation of all four drugs can be achieved. Overall, the method is suitable for quality testing of fixed-dose combination tablets in limited-resource settings
Estimating and Explaining the Differences in Health Care Seeking by Symptom Burden Among Persons With Presumptive Tuberculosis: Findings From a Population-Based Tuberculosis Prevalence Survey in a High-Burden Setting in India
Full text linkThere is a lack of research evidence on the quantitative relationship between symptom burden and health care
seeking among individuals with presumptive tuberculosis (TB)
A systematic review and meta-analysis of circulating serum and plasma microRNAs in TB diagnosis
Full text linkTuberculosis (TB) ranks as the second leading cause of death globally among all infectious diseases. This problem is likely due to the lack of biomarkers to differentiate the heterogeneous spectrum of infection. Therefore,the first step in solving this problem is to identify biomarkers to distinguish the different disease states of an individual and treat them accordingly. Circulating microRNA (miRNA) biomarkers are promising candidates for various diseases. In fact, we are yet to conceptualize how miRNA expression influences and predicts TB disease outcomes. Thus, this systematic review and meta-analysis aimed to assess the diagnostic efficacy of circulating miRNAs in Latent TB (LTB) and Active Pulmonary TB (PTB)
The Predicted Potential Impact of COVID-19 Pandemic on Tuberculosis Epidemic in Tamil Nadu, South India
Full text linkObjective: To estimate the prevalence and incidence of TB before and during the COVID-19
pandemic in Tamil Nadu, south India. Methods: In the present study, the effect of COVID-19 epidemiology
on the TB epidemic was assessed by the SEIR (Susceptible-Exposed-Infected-Recovered),
a compartmental epidemiological model. The model input parameters on compartments of TB and
incidence of COVID-19 were collected from the published literature. Based on the data collected,
point prevalence and incidence of TB per 100,000 population is calculated with and without COVID-
19. A prediction was conducted up to 2025, trend analysis was performed, and a trend chi-square
test and chi-square test of independence were used to test the difference between the prevalence
with and without COVID-19. R software 2000 (R 4.0.0) was used for analysis. Results: The TB
prevalence without and with COVID-19 decreases from 289 in 2020 to 271 in 2025 and from 289 in
2020 to 269 in 2025, respectively. Similarly, the incidence of TB was decreasing from 144 in 2020 to
135 in 2025 without COVID-19 and 143 in 2020 to 134 in 2025 with COVID-19. Though the TB burden
is decreasing over the years, the trend was not statistically significant (p > 0.05). With respect to
the district level, the prevalence and incidence of TB with and without COVID-19 is also found to be decreasing over the years. It was also found that the difference in the prevalence and incidence of TB with and without COVID-19 was not statically significant. Conclusion: The results of our
study shows that there was an annual decline of around 2% from 2020 to 2025 in the trend of the prevalence and incidence of TB with and without COVID-19. Overall, there is a reduction, but it was not significant, and there is no significant effect of COVID-19 on TB in Tamil Nadu