Diagnosis Of Tuberculosis Research Articles

Clinical spectrum of pediatric tuberculosis and early diagnosis by clinical, radiological, and CBNAAT in a Tertiary Care Teaching Hospital in South India

Background: In India, an estimated 220,000 children contract tuberculosis (TB) annually, yet the absence of a gold standard test hinders effective diagnosis and reporting of childhood TB. Objective: This study aimed to analyse the clinical profile of childhood tuberculosis, utilizing relevant laboratory investigations for early diagnosis. Methods: A cross-sectional observational study was conducted at a tertiary care hospital in South India from October 2019 to October 2021. Children under 18 with tuberculosis were included. Data on demographics, symptoms, family TB history, nutritional status, and clinical findings were collected. Laboratory tests included complete blood count, ESR, Mantoux test, chest X-rays, and sputum analyses for acid-fast bacilli (AFB). Results: Among 54 children, the most common age group was over 10 years (51.3%), with a male preponderance (53.3%). Pulmonary TB was diagnosed in 44.4% of cases, while 55.5% had extrapulmonary TB, predominantly pleural (40%). Fever (60.5%) and cough (42.7%) were the most common symptoms. The Mantoux test was reactive in 40.7% of patients, particularly among the undernourished. Chest X-rays indicated TB in 93.25% of pulmonary cases, while CBNAAT showed positive results in 10 cases, with a sensitivity of 18.8% and specificity of 81.25%. Conclusions: Diagnosing childhood TB remains complex, relying on symptom evaluation, clinical history, and laboratory tests. Despite advances in diagnostic methods, negative CBNAAT results do not exclude TB, highlighting the need for thorough clinical assessment and investigation.

Reactive arthritis in connective tissue diseases; one should be vigilant for joint tuberculosis.

The incidence of tuberculosis (TB) is increasing worldwide. Bone and joint TB are the most common types of extra-pulmonary TB, but can easily be misdiagnosed, since articular TB commonly mimics other joint diseases, including reactive and degenerative arthritis, and articular manifestations associated with systemic autoimmune diseases. Furthermore, patients with systemic auto-immune diseases are often more prone to mycobacterial infection. The diagnosis of joint TB can be made using a combination of the following methods: clinical evaluation, imaging, tuberculin skin test, interferon-gamma release assays, nucleic acid amplification tests, and Gene X-pert MTB/rifampicin assay.

Development and preliminary assessment of the iFIND TBR: all-in- one molecular diagnostic assay for rapid detection of Mycobacterium tuberculosis and rifampicin resistance

IntroductionEarly and accurate diagnosis of tuberculosis (TB) is crucial for initiating timely treatment and preventing new infections. In this study, we introduced the iFIND TBR assay, an automated all-in-one tuberculosis detection approach that simultaneously detect Mycobacterium tuberculosis (MTB) and rifampicin (RIF) resistance.MethodsThe limits of detection (LOD), sensitivity, specificity, and RIF-R rpoB mutation detection of the iFIND TBR were tested on Mycobacterium tuberculosis DNA or sputum samples spiked with known numbers of M.tuberculosis H37Rv. Frozen clinical samples from patients suspected of having TB were also tested.ResultsThe LOD of the iFIND TBR for MTB detection were 13.34 CFU/ml (95% CI, 11.71-16.47), and for RIF resistance was 109.79CFU/mL (95% CI, 95-138.19). The iFIND TBR assay accurately distinguish MTB strains from non-tuberculous mycobacteria (NTM) without any cross reactivity. Testing on 157 clinical sputum samples, compared with the bacteriologically TB standard, the overall sensitivity and specificity of the iFIND TBR was 100% (95%CI, 94.64, 100) and 85.29% (95% CI, 74.61, 92.72), respectively. When assessing RIF susceptibility, the iFIND TBR achieved a sensitivity of 98.15% (95% CI, 90.11–99.95) and a specificity of 85.71% (95% CI, 67.33–95.97), compared with phenotypic drug susceptibility testing. Discordant RIF susceptibility results were more frequently observed in samples exhibiting heteroresistance.DiscussionThese findings demonstrate that iFIND TBR assay performs well in detecting TB and RIF resistance, and shows promise as a point-of-care tool in resource-limited areas.

Changes in TB contact tracing during the COVID-19 pandemic. An Irish single centre experience

Abstract Contact tracing following the diagnosis of tuberculosis (TB) is a crucial process in the identification and treatment of both secondary TB cases and also infected contacts who may require treatment for latent TB infection. During the COVID-19 pandemic, Public Health and Respiratory teams in the St Vincent’s University Hospital (SVUH) TB clinic in Dublin, Ireland, noted anecdotally that there appeared to be fewer contacts screened by public health services per index active TB case identified. To investigate this, we performed a retrospective review of the TB contact tracing service in SVUH, examining and comparing contact tracing of active TB cases in the 3 years prior to the pandemic (2017-2019) and four years thereafter (2020-2023). Results from 2017-2019 calendar years, prior to the COVID-19 pandemic noted an average of 4.77 contacts per index TB case (total 107 index cases and 510 contacts). In comparison, our data from 2020-2022 noted an average of 3.03 contacts per index TB case (total 59 index cases and 179 contacts). As pandemic restrictions were lifted again, we found our 2023 data to be more comparable to that of pre-pandemic times, noting 4.54 contacts per index case (total 22 index cases and 100 contacts). The reduction in TB contacts per index cases noted during the COVID-19 pandemic may reflect work and lifestyle changes over that time, particularly an increase in remote work but also social distancing. It is interesting that as the population emerged from the isolation measures of the pandemic, contact numbers returned quickly to pre-pandemic levels. In line with global concerns, our data highlights the ongoing workload of TB contact tracing locally and the importance of resource allocation for these services. Key messages • Our Irish centre experienced a notable but temporary reduction in contacts requiring screening by public health services, per index active TB case, during the COVID-19 pandemic. • In line with global concerns, our data highlights the ongoing workload of TB contact tracing locally and the importance of resource allocation for these services.

High mortality rates among individuals misdiagnosed with tuberculosis: a matched retrospective cohort study of individuals diagnosed with tuberculosis in Brazil.

We conducted a matched retrospective cohort study comparing mortality among individuals receiving a false-positive tuberculosis diagnosis (n=3701) to individuals correctly diagnosed with TB (n=8595) in Brazil from 2007-2016. Over an average 5.4-year follow-up period, we estimated a mortality rate ratio of 1.95 (95% confidence interval: 1.80, 2.11) for individuals incorrectly diagnosed with TB compared to controls. The leading causes of death among the misdiagnosed were malignant neoplasms (40.9%) and respiratory system disorders (15.9%), conditions with symptoms similar to tuberculosis. Our findings highlight the need for improved follow-up care after identification of false-positive cases to increase survival for this high-risk population.

Factors Affecting the Early Diagnosis of Smear-positive Pulmonary Tuberculosis in Patients in Qom Province, Iran

Background and Objectives: According to the report of the World Health Organization (WHO), almost one-third of the world’s population is infected with tuberculosis (TB). The delay in TB diagnosis, in addition to increasing mortality, can increase the duration of disease transmission. This study aims to identify the factors affecting the early detection of smear-positive pulmonary TB in Patients in Qom Province, Iran. Methods: In this case-control study, 120 patients with smear-positive pulmonary TB (60 with a diagnosis delayed for more than three months and 60 with a timely diagnosis) diagnosed from 2018 to 2021 in Qom Province participated. To determine the factors effective in early diagnosis of pulmonary TB, the odds ratio of each factor was calculated, and logistic regression analysis was used for data analysis. Results: The prescription of the sputum test at the first visit had the most significant effect on the early diagnosis of pulmonary TB (odds ratio=161, P<0.001). The TB in patients who visited the clinics and those visited by general practitioners was diagnosed with a higher delay. The lack of knowledge of existing TB diagnosis and treatment services in health centers had increased the diagnosis delay by 2.3. Occupation, gender, and place of residence were not found to be effective factors. Conclusion: It seems that most doctors in Iran neglect to prescribe a sputum test for patients suspected of pulmonary TB and only prescribe chest x-rays. Training and informing doctors, private medical centers, and pharmacies in referring patients suspected of pulmonary TB to the health centers where the patients live can cause timely diagnosis of pulmonary TB.

HIV replication and tuberculosis risk among people living with HIV in Europe: A multicohort analysis, 1983-2015.

HIV replication leads to a change in lymphocyte phenotypes that impairs immune protection against opportunistic infections. We examined current HIV replication as an independent risk factor for tuberculosis (TB). We included people living with HIV from 25 European cohorts 1983-2015. Individuals <16 years or with previous TB were excluded. Person-time was calculated from enrolment (baseline) to the date of TB diagnosis or last follow-up information. We used adjusted Poisson regression and general additive regression models. We included 272,548 people with a median follow-up of 5.9 years (interquartile range [IQR] 2.3-10.9). At baseline, the median CD4 cell count was 355 cells/μL (IQR 193-540) and the median HIV-RNA level 22,000 copies/mL (IQR 1,300-103,000). During 1,923,441 person-years of follow-up, 5,956 (2.2%) people developed TB. Overall, TB incidence was 3.1 per 1,000 person-years (95% confidence interval [CI] 3.02-3.18) and was four times higher in patients with HIV-RNA levels of 10,000 compared with levels <400 copies/mL in any CD4 stratum. CD4 and HIV-RNA time-updated analyses showed that the association between HIV-RNA and TB incidence was independent of CD4. The TB incidence rate ratio for people born in TB-endemic countries compared with those born in Europe was 1.8 (95% CI 1.5-2.2). Our results indicate that ongoing HIV replication (suboptimal HIV control) is an important risk factor for TB, independent of CD4 count. Those at highest risk of TB are people from TB-endemic countries. Close monitoring and TB preventive therapy for people with suboptimal HIV control is important.

Molecular Indicator for Distinguishing Multi-drug-Resistant Tuberculosis from Drug Sensitivity Tuberculosis and Potential Medications for Treatment.

The issue of multi-drug-resistant tuberculosis (MDR-TB) presents a substantial challenge to global public health. Regrettably, the diagnosis of drug-resistant tuberculosis (DR-TB) frequently necessitates an extended period or more extensive laboratory resources. The swift identification of MDR-TB poses a particularly challenging endeavor. To identify the biomarkers indicative of multi-drug resistance, we conducted a screening of the GSE147689 dataset for differentially expressed genes (DEGs) and subsequently conducted a gene enrichment analysis. Our analysis identified a total of 117 DEGs, concentrated in pathways related to the immune response. Three machine learning methods, namely random forest, decision tree, and support vector machine recursive feature elimination (SVM-RFE), were implemented to identify the top 10 genes according to their feature importance scores. A4GALT and S1PR1, which were identified as common genes among the three methods, were selected as potential molecular markers for distinguishing between MDR-TB and drug-susceptible tuberculosis (DS-TB). These markers were subsequently validated using the GSE147690 dataset. The findings suggested that A4GALT exhibited area under the curve (AUC) values of 0.8571 and 0.7121 in the training and test datasets, respectively, for distinguishing between MDR-TB and DS-TB. S1PR1 demonstrated AUC values of 0.8163 and 0.5404 in the training and test datasets, respectively. When A4GALT and S1PR1 were combined, the AUC values in the training and test datasets were 0.881 and 0.7551, respectively. The relationship between hub genes and 28 immune cells infiltrating MDR-TB was investigated using single sample gene enrichment analysis (ssGSEA). The findings indicated that MDR-TB samples exhibited a higher proportion of type 1T helper cells and a lower proportion of activated dendritic cells in contrast to DS-TB samples. A negative correlation was observed between A4GALT and type 1T helper cells, whereas a positive correlation was found with activated dendritic cells. S1PR1 exhibited a positive correlation with type 1T helper cells and a negative correlation with activated dendritic cells. Furthermore, our study utilized connectivity map analysis to identify nine potential medications, including verapamil, for treating MDR-TB. In conclusion, our research identified two molecular indicators for the differentiation between MDR-TB and DS-TB and identified a total of nine potential medications for MDR-TB.

Contribution of TB-LAM Urine Test to Tuberculosis Diagnosis in HIV-infected Adult Patients in Burkina Faso

Aims: With the aim of improving the diagnosis of tuberculosis in patients living with HIV, we set out to evaluate the contribution of the TB-LAM urine test to the diagnosis of tuberculosis in PLWHA in Burkina Faso, in real life. Methodology: The study was conducted in the Infectious Diseases Departments of the Yalgado OUEDRAOGO (CHU-YO), Souro SANOU (CHU-SS) and Bogodogo (CHU-B) University Hospitals. These 03 centers are among the most important reference centers in Burkina Faso. This was a descriptive and analytical cross-sectional study with prospective data collection over 12 months, from January 1, 2023 to December 31, 2023, and involved PLWH inpatients and outpatients. Data were collected using the KoBoCollect v1.30.1 application and analyzed using STATA 16 software. Binary uni and multivariate logistic regression with a statistical significance level of 0.05 was used to identify associated factors. Results: A total of 113 patients were included in the study. The mean age was 43 ± 1.35 years, with a sex ratio of 0.85. The TB-LAM urine test was positive in 76 patients, for a positivity rate of 67.26%. The diagnosis of tuberculosis was confirmed by bacteriology in accordance with the national tuberculosis management protocol in 18/113 (15.93%) patients. Bacilloscopy and the Xpert test performed on all biological fluids, combined with the TB-LAM urine test, enabled the diagnosis of 81/113 (71.68%) patients in the study. Patients already on antiretroviral therapy (ORa=0.06 [0.06-0.73], p=0.02) were less likely to test positive for urinary TB-LAM, and those with unexplained asthenia (ORa=15.76 [1.19-20.66], p=0.03) were more likely to test positive. Conclusion: The TB-LAM urine test, combined with other tuberculosis diagnostic tools, increases the diagnostic yield of tuberculosis in PLWHA.

Diagnostic values of adenosine deaminase cytokines in fluid contributed to the detection of extrapulmonary tuberculosis

Tuberculosis (TB) is a serious global public health problem. Detecting the changes of adenosine deaminase (ADA), interleukin (IL)-1β, IL-2, tumor necrosis factor-α (TNF-α), interferon-γ (IFN-γ) released from macrophages and monocytes is greatly valuable in the diagnosis of TB. Hence, this study was designed to determine the optimal cut-off points of ADA, IL-1β, IL-2, TNF-α, and IFN-γ, allowing to differentiate pleural TB (PLTB), peritoneal TB (PTB), and meningeal TB (MTB). The study included 386 patients with pleural effusion, 47 patients with peritoneal effusion, and 134 patients with encephalitis and meningoencephalitis suspect of TB. ADA was determined by an enzyme kinetics method; cytokine concentration was measured by a test based on the competitive enzyme-linked immunosorbent assay principle. Sensitivity, specificity, and positive and negative predictive value were calculated and described. In the aspiration fluid, ADA activity was greatly different between PLTB, PTB, and MTB groups with values of 37.5 U/L, 30.5 U/L, and 8.1 U/L and sensitivity and specificity of 87.7% and 83.4%; 100% and 88.9%; 97.3% and 98.6%, respectively. Similar, IFN-γ concentrations were distinctively different between PLTB, PTB, and MTB patients (with values of 120 pg/mL, 200 pg/mL, and 30 pg/mL with sensitivity and specificity of 80.3% and 80.9%; 80.0% and 92.6%; 98.6% and 61.7%, respectively). The determination of ADA and IFN-γ levels in the aspiration fluid is potentially considered a highly sensitive and specific test for differentiating PLTB, PTB, and MTB.

The role and value of counsellors in the treatment journeys of people with tuberculosis and their families: Qualitative insights from the South Fly District of Papua New Guinea.

Combined education and counselling can contribute to person-centred care for tuberculosis (TB), improving uptake, adherence, and outcomes of treatment for TB disease and TB infection. Though strongly recommended by the World Health Organization for all people diagnosed with TB, education and counselling is not widely implemented in TB programs around the world. In 2016, a pilot TB education and counselling program, delivered by trained professionals and peers, was initiated to support people on TB treatment in the South Fly District of Papua New Guinea. This article reports on select findings from a qualitative study that examined the socio-cultural dimensions of TB, including treatment support such as education and counselling, in the South Fly District. An assessment on data collected during 128 semi-structured in-depth interviews of the role of counsellors on TB treatment journeys revealed strong participant support for the counsellors and the services they delivered, with particular emphasis on the emotional support provided to address fears and concerns related to TB diagnosis and treatment, and to support treatment adherence; valuable attributes of counsellors; their role as intermediaries between patients and health workers; their provision of biomedical knowledge of TB transmission and disease; and their assistance in addressing stigma and discrimination from family and community. Participants also noted how tackling the socio-structural issues that drive TB transmission in people's homes and communities were beyond the remit of counsellors' work. TB education and counselling should be an essential part of all TB services to provide support and encouragement for people to continue treatment to completion.

Challenges in diagnosing bovine tuberculosis through surveillance and characterization of Mycobacterium species in slaughtered cattle in Kolkata

BackgroundTuberculosis in cattle is caused by Mycobacterium tuberculosis complex (MTBC) species. Apart from MTBC, different Nontuberculous Mycobacteria (NTM) species have also been isolated from cattle. The presence of NTM infection in bovines makes the diagnosis of bovine tuberculosis (bTB) a cumbersome task. Therefore, a cross sectional study was conducted to isolate and characterize different Mycobacterium spp. from a slaughterhouse situated in Kolkata, a city in the eastern part of India.ResultsOut of 258 morbid samples, 98 isolates were found to be positive for bacterial growth, and 35% (n = 34) were positive for Mycobacterium. 94% of Mycobacterial cultural isolates were NTM (n = 32), and the rest (n = 2) were found to be MTBC. Species-level identification of the isolates by hsp65 sequencing revealed that out of 32 isolates, 24 were M. fortuitum, three were M. abscessus, two each were M. chelonae and M. parascrofulaceum, and one was M. novocastrense. A phylogenetic tree with partial hsp65 gene sequences was also constructed to determine the relatedness of the unknown isolates to the reference strains.ConclusionBoth NTM species and MTBCs were identified from TB-like lesions in cattle that were slaughtered at the Kolkata abattoir. This discovery may indicate that NTM contributes to the development of lesions in cattle. Also, we recommend implication of more specific diagnostic tests for bTB.

A dataset of Solicited Cough Sound for Tuberculosis Triage Testing

Cough is a common and commonly ignored symptom of lung disease. Cough is often perceived as difficult to quantify, frequently self-limiting, and non-specific. However, cough has a central role in the clinical detection of many lung diseases including tuberculosis (TB), which remains the leading infectious disease killer worldwide. TB screening currently relies on self-reported cough which fails to meet the World Health Organization (WHO) accuracy targets for a TB triage test. Artificial intelligence (AI) models based on cough sound have been developed for several respiratory conditions, with limited work being done in TB. To support the development of an accurate, point-of-care cough-based triage tool for TB, we have compiled a large multi-country database of cough sounds from individuals being evaluated for TB. The dataset includes more than 700,000 cough sounds from 2,143 individuals with detailed demographic, clinical and microbiologic diagnostic information. We aim to empower researchers in the development of cough sound analysis models to improve TB diagnosis, where innovative approaches are critically needed to end this long-standing pandemic.

Targeted next-generation sequencing - a promising approach in the diagnosis of Mycobacterium tuberculosis and drug resistance.

Targeted next-generation sequencing (tNGS) offers a high-throughput, culture-independent approach that delivers a comprehensive resistance profile in a significantly shorter turn-around time, making it promising in enhancing tuberculosis (TB) diagnosis and informing treatment decisions. This study aims to evaluate the performance of tNGS in the TB diagnosis and drug resistance detection of Mycobacterium tuberculosis (MTB) using MTB clinical isolates and bronchoalveolar lavage fluid (BALF) samples. A total of 143 MTB clinical isolates were assessed, tNGS, phenotypic antimicrobial susceptibility testing (AST), and AST based on whole genome sequencing (WGS) exhibited high concordance rates, averaging 95.10% and 97.05%. Among 158 BALF samples, culture, Xpert MTB/RIF, and tNGS reported 29, 70 and 111 positives, respectively. In the confirmed cases with etiological evidence (smears, cultures, or molecular test), the positive rate of tNGS (73/83, 87.95%) was higher than that of Xpert MTB (67/83, 80.72%). Additionally, 45% (27/60) of clinically diagnosed cases (with imaging or immunological evidence) were positive for tNGS. Further validation on the discrepant results between tNGS and Xpert MTB/RIF with droplet digital PCR (ddPCR) yielded 35 positives, tNGS detected all, and Xpert MTB/RIF only identified 6 positives. In conclusion, tNGS demonstrates robust and rapid performance in the identification of MTB and its associated drug resistance, and can be directly applied to clinical samples, positioning it as a promising approach for laboratory testing of tuberculosis.

Generalized tuberculosis with intestinal lesion in an adolescent. Case report

In the two recent decades a decrease in tuberculosis (TB) incidence has been observed worldwide, according to the World Health Organization, while the incidence of extrapulmonary TB, including TB of the intestine, is growing. Generally, diagnosis of TB in children and adolescents is difficult due to its subclinical course in a significant part of patients. A special diagnostic challenge is extrapulmonary TB, including abdominal TB. Abdominal TB has entered the top five most frequent manifestations of extrapulmonary TB along with TB of the peripheral lymph nodes, urogenital TB, bone and joint TB, and TB of the central nervous system. Lack of specific clinical signs of the disease results in late diagnosis of abdominal TB. We described a case of generalized TB with intestinal lesion in an adolescent. We detected mistakes in the follow-up of the female patient with double exposure to household TB, which resulted in late diagnosis of the disease. We demonstrated the challenges in diagnosing intestinal TB under the guise of appendicitis, which led to the development of complications – spilled peritonitis and abdominal abscess. The tactics of management of the female patient at high risk for developing bowel obstruction was represented. Interdisciplinary interactions with extrapulmonary TB specialists were accented for cases of generalized TB.

Analysis Neutrophil-to-Lymphocyte and Monocyte-to- Lymphocyte Ratios in Pediatric Respiratory Infections

Indonesia ranks third among countries with the highest tuberculosis (TB) cases worldwide. Pneumonia also stands as a leading cause of death among infants in developing nations. The delay in diagnosing and the challenges in distinguishing TB and pneumonia have significant impacts on elevated morbidity and mortality rates. Both Neutrophil-to-Lymphocyte Ratio (NLR) and Monocyte-to-Lymphocyte Ratio (MLR) serve as inflammatory biomarkers utilized for rapid and straightforward bacteremia evaluation. This study aimed to analyze the difference between NLR and MLR in diagnosing of TB and pneumonia in children. This study was retrospective cross-sectional research utilizing secondary data at the time of initial diagnosis by a clinician as TB or pneumonia. Subjects with TB and/or pneumonia were treated at Dr. Wahidin Sudirohusodo Hospital, Makassar from January 2017 to December 2021. The research sample consisted of 150 patients with pediatric patients with pneumonia. Statistical analyses involved the Kolmogorov-Smirnov test, Mann-Whitney U test, and Receiver Operating Characteristic (ROC). This study examined NLR and MLR as supportive biomarkers for diagnosing TB and pneumonia. The NLR (AUC 0.674) and MLR (AUC 0.63) values in TB subjects were reasonably good in distinguishing between TB diagnosis and healthy subjects. The NLR (AUC 0.77) and MLR (AUC 0.787) values were effective in distinguishing pneumonia diagnosis from healthy control with better sensitivity and specificity compared to TB subjects. However, NLR (AUC 0.401) and MLR (AUC 0.384) values were not recommended to distinguish pneumonia from tuberculosis due to low AUC and extremely low sensitivity and specificity. The NLR and MLR values cannot be used to differentiate TB and pneumonia in children due to their low sensitivity and specificity.

Machine learning algorithms to predict treatment success for patients with pulmonary tuberculosis.

Despite advancements in detection and treatment, tuberculosis (TB), an infectious illness caused by the Mycobacterium TB bacteria, continues to pose a serious threat to world health. The TB diagnosis phase includes a patient's medical history, physical examination, chest X-rays, and laboratory procedures, such as molecular testing and sputum culture. In artificial intelligence (AI), machine learning (ML) is an advanced study of statistical algorithms that can learn from historical data and generalize the results to unseen data. There are not many studies done on the ML algorithm that enables the prediction of treatment success for patients with pulmonary TB (PTB). The objective of this study is to identify an effective and predictive ML algorithm to evaluate the detection of treatment success in PTB patients and to compare the predictive performance of the ML models. In this retrospective study, a total of 1236 PTB patients who were given treatment under a randomized controlled clinical trial at the ICMR-National Institute for Research in Tuberculosis, Chennai, India were considered for data analysis. The multiple ML models were developed and tested to identify the best algorithm to predict the sputum culture conversion of TB patients during the treatment period. In this study, decision tree (DT), random forest (RF), support vector machine (SVM) and naïve bayes (NB) models were validated with high performance by achieving an area under the curve (AUC) of receiver operating characteristic (ROC) greater than 80%. The salient finding of the study is that the DT model was produced as a better algorithm with the highest accuracy (92.72%), an AUC (0.909), precision (95.90%), recall (95.60%) and F1-score (95.75%) among the ML models. This methodology may be used to study the precise ML model classification for predicting the treatment success of TB patients during the treatment period.

Does the Third Sputum Exam has an Added Value in the Diagnosis of Pulmonary Tuberculosis?

Abstract Introduction/Objective Introduction: Current practice of examining three sputum for the diagnosis of pulmonary tuberculosis (PTB) has tended to overburden the already scarce human resources in all-purpose laboratories, and to increase the turn- around- time for patients seeking treatment. Therefore, assessing the added value of the third sputum in the diagnosis of PTB in resource-limited country with less functional External Quality Assurance (EQA) system is critical. Methods/Case Report Materials and methods: Data on patients diagnosed with smear-positive PTB during 2012- 2016 was collected retrospectively from laboratory register of nine hospitals in Eritrea. The data was extracted and analyzed for incremental yield of three sputum samples. Results (if a Case Study enter NA) Results: Data from 2,484 microscopically confirmed acid-fast bacilli (AFB) smear positive PTB patients were reviewed. AFB was detected in the first sputum in 87.5% of patients, and 99.1% for the combined first and second sputum specimens. The incremental yield of the third sputum specimen as a diagnostic value was only 0.9%. No significant variation was detected by region, residence, gender or HIV. Background information Number of cases Percent Region Maekel 649 26.10% Anseba 293 11.80% Gash-Barka 815 32.80% Debub 297 12.00% Northern Red Sea 337 13.60% Southern Red Sea 93 3.70% Sex Male 1,251 50.40% Female 1,233 49.60% Residence Urban 1,296 52.20% Rural 1,188 47.80% Age group &amp;lt;15 35 1.40% 15 + 2,449 98.60% Total 2,484 100 Conclusion Conclusion: The added value of the third sputum is so minimal that its omission will reduce patient visits, workload and cost for patients and health services. Therefore, even countries like Eritrea, with limited EQA, should consider limiting the number of sputum examinations to improve quality.

Comprehensive Approach to TB Diagnosis Powered by Machine Learning in Endemic Countries

Abstract Introduction/Objective Tuberculosis (TB), a leading cause of mortality worldwide, is primarily diagnosed through methods that face numerous challenges, including lengthy result times and diagnostic inaccuracy, particularly in the context of drug-resistant strains and latent infections. This study proposes a novel approach that integrates multiple diagnostic modalities with machine learning to enhance TB diagnosis accuracy. Methods/Case Report The Machine learning model was tailored for the classification of radiological images, specifically CT scans, using original DICOM images to preserve valuable voxel information. The study involved a curated dataset of CT scans from Pakistan, TB-positive (smear+/Culture+ n=72; smear+/culture- n= 3; smear-/Culture+ n=16; smear-/Culture- n=14; clinical and radiological diagnosis only n= 12) and healthy (n=103) scans from COVID-CTSet were included in the training to assess the specificity of the model. Data preprocessing included noise reduction, histogram matching, and data augmentation techniques to ensure a robust training dataset. The methodology also incorporated using k-fold cross validation and a custom learning rate scheduling strategy to optimize the model’s training process. To further test its robustness, the model was evaluated by swapping random patches and analyzing 60 mm patches from the entire CT scan for local feature categorization. Results (if a Case Study enter NA) The model has demonstrated outstanding performance, with sensitivity and specificity exceeding 95% on our internal dataset (n=117) and aligning well with clinical, smear, culture, and anti-TB antibody findings. It also showed promising results on the external NIH TB Portal’s dataset (n= 1,460). The model is robust to variations in CT scanner image quality and noise profiles, maintaining strong generalization across datasets. Even when analyzing random 60mm patches, effectively classifying all local features Conclusion Our study enhances tuberculosis diagnostic methods in endemic regions by blending machine learning with conventional diagnostic techniques. This approach improves TB detection, particularly the early and accurate identification in areas impacted by drug-resistant strains and asymptomatic latent infections. By integrating radiological and clinico-pathological data, we aim to develop a comprehensive diagnostic score. Moving forward, we plan to further integrate this method into clinical decision support systems and adapt the approach to other infectious diseases.

Evaluating the significance of latent tuberculosis infection treatment in high‐incidence countries

Tuberculosis (TB) caused by Mycobacterium tuberculosis (Mtb) is a devastating and rapidly spreading disease. Despite years of scientific research and numerous efforts, it is still a major and resurgent health problem worldwide, with high mortality rates. Added to the concern is that TB persists as a latent infection, an occult face of TB, that becomes a potential reservoir for active tuberculosis. Since latent TB‐infected patients may eventually advance to the active form of TB, an accurate diagnosis and effective treatment of latent tuberculosis are essential for TB control. Latent tuberculosis infection (LTBI) treatment is a prominent component of TB control in low‐prevalence countries like the United States; however, its implication in high‐incidence countries like India is still challenging. Therefore, the present study aimed to evaluate the impact of implementing diagnosis and treatment of LTBI in high‐incidence countries using a mathematical model‐based approach. Through our model, we predicted the incidence rate based on the current treatment regimen in India for the year 2035, which is one of the milestones of WHO for a substantial reduction in TB incidence. We observed demographic variability in the effects of various parameters on the TB incidence rate. Finally, we formulated the putative treatment strategies to reduce the TB burden in high‐incidence scenarios. Further, we estimated the impact of these proposed treatment strategies on the drug‐resistant population in high‐incidence scenarios. The model predictions suggested molding the current treatment strategies and focused implementation of LTBI diagnosis and treatment in high‐incidence scenarios.