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.

Trends of drug resistance in M. tuberculosis in a reference laboratory in Central India: Forging ahead towards TB elimination.

PURPOSE: The National Tuberculosis Elimination Programme (NTEP) of the Government of India has strived to control tuberculosis (TB) in the country through various interventions. Understanding the trends of resistance patterns may provide insights into the effectiveness of TB control activities in the country. METHODS: A total of 31,144 clinical samples were received from 2013 to 2022 from presumptive drug-resistant TB patients. All the specimens were decontaminated and subjected to the line probe assay for detection of resistance to rifampicin and isoniazid. Mycobacterium tuberculosis (MTB) was detected in 28,814 samples. Autoregressive integrated moving average model (ARIMA) was fitted to assess the trend over time. RESULTS: A decreasing trend in multi-drug resistant TB from 19 % in 2013 to 4 % in 2022 was seen. A decreasing trend in rifampicin monoresistance from 11.2 % in 2013 to 1.5 % in 2022 was seen, though there was an increase in resistance in 2017. No significant decreasing trends were seen in the proportion of isoniazid monoresistance from 8.3 % in 2013 to 7 % in 2022. CONCLUSION: The findings are encouraging, and to a considerable extent, affirm that India is well on track with regard to the goal of TB elimination.

Undernourished Household Contacts Are at Increased Risk of Tuberculosis (TB) Disease, but not TB Infection-a Multicenter Prospective Cohort Analysis.

Undernutrition is the leading risk factor for tuberculosis (TB) globally and in India. This multicenter prospective cohort analysis from India suggests that undernutrition is associated with increased risk of TB disease but not TB infection among household contacts of persons with TB.

Impact of Undernutrition on Tuberculosis Treatment Outcomes in India: A Multicenter, Prospective, Cohort Analysis.

BACKGROUND: Undernutrition is the leading risk factor for tuberculosis (TB) globally. Its impact on treatment outcomes is poorly defined. METHODS: We conducted a prospective cohort analysis of adults with drug-sensitive pulmonary TB at 5 sites from 2015-2019. Using multivariable Poisson regression, we assessed associations between unfavorable outcomes and nutritional status based on body mass index (BMI) nutritional status at treatment initiation, BMI prior to TB disease, stunting, and stagnant or declining BMI after 2 months of TB treatment. Unfavorable outcome was defined as a composite of treatment failure, death, or relapse within 6 months of treatment completion. RESULTS: Severe undernutrition (BMI <16 kg/m2) at treatment initiation and severe undernutrition before the onset of TB disease were both associated with unfavorable outcomes (adjusted incidence rate ratio [aIRR], 2.05; 95% confidence interval [CI], 1.42-2.91 and aIRR, 2.20; 95% CI, 1.16-3.94, respectively). Additionally, lack of BMI increase after treatment initiation was associated with increased unfavorable outcomes (aIRR, 1.81; 95% CI, 1.27-2.61). Severe stunting (height-for-age z score <-3) was associated with unfavorable outcomes (aIRR, 1.52; 95% CI, 1.00-2.24). Severe undernutrition at treatment initiation and lack of BMI increase during treatment were associated with a 4- and 5-fold higher rate of death, respectively. CONCLUSIONS: Premorbid undernutrition, undernutrition at treatment initiation, lack of BMI increase after intensive therapy, and severe stunting are associated with unfavorable TB treatment outcomes. These data highlight the need to address this widely prevalent TB comorbidity. Nutritional assessment should be integrated into standard TB care.

Role of a Putative Alkylhydroperoxidase Rv2159c in the Oxidative Stress Response and Virulence of Mycobacterium tuberculosis.

Mycobacterium tuberculosis, which causes tuberculosis, is one of the leading infectious agents worldwide with a high rate of mortality. Following aerosol inhalation, M. tuberculosis primarily infects the alveolar macrophages, which results in a host immune response that gradually activates various antimicrobial mechanisms, including the production of reactive oxygen species (ROS), within the phagocytes to neutralize the bacteria. OxyR is the master regulator of oxidative stress response in several bacterial species. However, due to the absence of a functional oxyR locus in M. tuberculosis, the peroxidase stress is controlled by alkylhydroperoxidases. M. tuberculosis expresses alkylhydroperoxide reductase to counteract the toxic effects of ROS. In the current study, we report the functional characterization of an orthologue of alkylhydroperoxidase family member, Rv2159c, a conserved protein with putative peroxidase activity, during stress response and virulence of M. tuberculosis. We generated a gene knockout mutant of M. tuberculosis Rv2159c (MtbΔ2159) by specialized transduction. The MtbΔ2159 was sensitive to oxidative stress and exposure to toxic transition metals. In a human monocyte (THP-1) cell infection model, MtbΔ2159 showed reduced uptake and intracellular survival and increased expression of pro-inflammatory molecules, including IL-1ß, IP-10, and MIP-1α, compared to the wild type M. tuberculosis and Rv2159c-complemented MtbΔ2159 strains. Similarly, in a guinea pig model of pulmonary infection, MtbΔ2159 displayed growth attenuation in the lungs, compared to the wild type M. tuberculosis and Rv2159c-complemented MtbΔ2159 strains. Our study suggests that Rv2159c has a significant role in maintaining the cellular homeostasis during stress and virulence of M. tuberculosis.

Bayesian structural equation modeling for post treatment health related quality of life among tuberculosis patients.

BACKGROUND: The use of Bayesian Structural Equation Model (BSEM) to evaluate the impact of TB on self-reported health related quality of life (HRQoL) of TB patients has been not studied. OBJECTIVE: To identify the factors that contribute to the HRQoL of TB patients using BSEM. METHODS: This is a latent variable modeling with Bayesian approach using secondary data. HRQoL data collected after one year from newly diagnosed 436 TB patients who were registered and successfully completed treatment at Government health facilities in Tiruvallur district, south India under the National TB Elimination Programme (NTEP) were used for this analysis. In this study, the four independent latent variables such as physical well-being (PW = PW1-7), mental well-being (MW = MW1-7), social well-being (SW = SW1-4) and habits were considered. The BSEM was constructed using Markov Chain Monte Carlo algorithm for identifying the factors that contribute to the HRQoL of TB patients who completed treatment. RESULTS: Bayesian estimates were obtained using 46,300 observations after convergence and the standardized structural regression estimate of PW, MW, SW on HRQoL were 0.377 (p<0.001), 0.543 (p<0.001) and 0.208 (p<0.001) respectively. The latent variables PW, MW and SW were significantly associated with HRQoL of TB patients. The age was found to be significantly negatively associated with HRQoL of TB patients. CONCLUSIONS: The current study demonstrated the application of BSEM in evaluating HRQoL. This methodology may be used to study precise estimates of HRQoL of TB patients in different time points.

Distribution and growth rate of COVID-19 outbreak in Tamil Nadu: A log-linear regression approach.

BACKGROUND: Most of the countries are affected with the pandemic outbreak of the coronavirus infection. Understanding the severity and distribution in various regions will help in planning the controlling measures. OBJECTIVES: The objective was to assess the distribution and growth rate of COVID-19 infection in Tamil Nadu, India. METHODS: The data on the number of infections of COVID-19 have been obtained from the media reports released by the Government of Tamil Nadu. The data contain information on the incidence of the disease for the first 41 days of the outbreak started on March 7, 2020. Log-linear model has been used to estimate the progression of the COVID-19 infection in Tamil Nadu. Separate models were employed to model the growth rate and decay rate of the disease. Spatial Poisson regression was used to identify the high-risk areas in the state. RESULTS: : The models estimated the doubling time for the number of cases in growth phase as 3.96 (95% confidence interval [CI]: 2.70, 9.42) days and halving time in the decay phase as 12.08 (95% CI: 6.79, 54.78) days. The estimated median reproduction numbers were 1.88 (min = 1.09, max = 2.51) and 0.76 (min = 0.56, max = 0.99) in the growth and decay phases, respectively. The spatial Poisson regression identified 11 districts as high risk. CONCLUSION: The results indicate that the outbreak is showing decay in the number of infections of the disease which highlights the effectiveness of controlling measures.

4-month moxifloxacin containing regimens in the treatment of patients with sputum-positive pulmonary tuberculosis in South India - a randomised clinical trial.

BACKGROUND: Shortening tuberculosis (TB) treatment duration is a research priority. We tested the efficacy and safety of 3- and 4-month regimens containing moxifloxacin in a randomised clinical trial in pulmonary TB (PTB) patients in South India. METHODS: New, sputum-positive, adult, HIV-negative, non-diabetic PTB patients were randomised to 3- or 4-month moxifloxacin regimens [moxifloxacin (M), isoniazid (H), rifampicin (R), pyrazinamide (Z) and ethambutol (E)] or to a control regimen (2H3 R3 Z3 E3 /4R3 H3 ) [C]. The 4 test regimens were 3R7 H7 Z7 E7 M7 [M3], 2R7 H7 Z7 E7 M7 /2R7 H7 M7 [M4], 2R7 H7 Z7 E7 M7 /2R3 H3 M3 [M4-I] or 2R7 H7 Z7 E7 M7 /2R3 H3 E3 M3 [M4-IE]. Treatment was directly observed. Clinical and bacteriological assessments were done monthly during treatment and for 24 months post-treatment. The primary end point was TB recurrence post-treatment. RESULTS: Of 1371 patients, randomised, modified intention-to-treat (ITT) analysis was done in 1329 and per-protocol (PP) analysis in 1223 patients. Regimen M3 was terminated due to high TB recurrence rates. 'Favourable' response at end of treatment was 96-100% in the moxifloxacin regimens and 93% in the control  regimen. Among these, the TB recurrence occurred in 4.1% in the M4 regimen and in 4.5% in the control regimen and demonstrated equivalence within a 5% margin (95% CI -3.68, 4.55). Similar findings were observed in modified ITT analysis. The TB recurrence rates in the M4-I and M4-IE regimens did not show equivalence with the control regimen. Sixteen (1.4%) of 1087 patients in the moxifloxacin regimens required treatment modification. CONCLUSION: The 4-month daily moxifloxacin regimen [M4] was found to be equivalent and as safe as the 6-month thrice-weekly control regimen.

CONTEXTE: La réduction de la durée du traitement de la tuberculose (TB) est une priorité de recherche. Nous avons testé l'efficacité et la sécurité de schémas thérapeutiques contenant de la moxifloxacine pendant 3 et 4 mois dans un essai clinique randomisé chez des patients atteints de TB pulmonaire (PTB) dans le sud de l'Inde. MÉTHODES: De nouveaux patients PTB, adultes, non diabétiques, positifs pour les expectorations, VIH négatifs ont été randomisés pour des schémas thérapeutiques contenant de la moxifloxacine pendant 3 mois ou 4 mois [moxifloxacine (M), isoniazide (H), rifampicine (R), pyrazinamide (Z), l'éthambutol (E)] ou pour un régime témoin (2H3 R3 Z3 E3 /4R3 H3 ) [C]. Les 4 régimes de l'essai étaient 3R7 H7 Z7 E7 M7 [M3], 2R7 H7 Z7 E7 M7 /2R7 H7 M7 [M4], 2R7 H7 Z7 E7 M7 /2R3 H3 M3 [M4-I] ou 2R7 H7 Z7 E7 M7 /2R3 H3 E3 M3 [M4-IE]. Le traitement a été directement observé. Les évaluations cliniques et bactériologiques ont été effectuées mensuellement au cours du traitement et durant 24 mois après le traitement. Le critère d'évaluation principal était la récidive de la TB après le traitement. RÉSULTATS: Des 1.371 patients randomisés, une analyse en intention de traiter (ITT) modifiée a été effectuée sur 1.329 et une analyse par protocole (PP) sur 1.223 patients. Le régime M3 a été interrompu en raison de taux élevés de récidive de la TB. La réponse «favorable¼ à la fin du traitement était de 96 à 100% dans les bras moxifloxacine et 93% dans le bras témoin. Parmi ceux-ci, la récidive de la TB est survenue chez 4,1% dans le schéma M4 et chez 4,5% dans le schéma témoin et a démontré une équivalence dans une marge de 5% (IC95%: −3,68, 4,55). Des résultats similaires ont été observés dans l'analyse ITT modifiée. Les taux de récidive de la TB dans les schémas M4-I et M4-IE n'ont pas montré d'équivalence avec le schéma témoin. 16 (1,4%) des 1.087 patients dans les régimes à moxifloxacine ont nécessité une modification du traitement. CONCLUSION: Le régime quotidien de moxifloxacine pendant 4 mois [M4] s'est avéré équivalent et aussi sûr que le régime témoin de trois fois par semaine pendant 6 mois.

Recurrence of tuberculosis among newly diagnosed sputum positive pulmonary tuberculosis patients treated under the Revised National Tuberculosis Control Programme, India: A multi-centric prospective study.

INTRODUCTION: There is lack of information on the proportion of new smear-positive pulmonary tuberculosis (PTB) patients treated with a 6-month thrice-weekly regimen under Revised National Tuberculosis Control Programme (RNTCP) who develop recurrent TB after successful treatment outcome. OBJECTIVE: To estimate TB recurrence among newly diagnosed PTB patients who have successfully completed treatment and to document endogenous reactivation or re-infection. Risk factors for unfavourable outcomes to treatment and TB recurrence were determined. METHODOLOGY: Adult (aged ≥ 18 yrs) new smear positive PTB patients initiated on treatment under RNTCP were enrolled from sites in Tamil Nadu, Karnataka, Delhi, Maharashtra, Madhya Pradesh and Kerala. Those declared "treatment success" at the end of treatment were followed up with 2 sputum examinations each at 3, 6 and 12 months after treatment completion. MIRU-VNTR genotyping was done to identify endogenous re-activation or exogenous re-infection at TB recurrence. TB recurrence was expressed as rate per 100 person-years (with 95% confidence interval [95%CI]). Regression models were used to identify the risk factors for unfavourable response to treatment and TB recurrence. RESULTS: Of the1577 new smear positive PTB patients enrolled, 1565 were analysed. The overall cure rate was 77% (1207/1565) and treatment success was 77% (1210 /1565). The cure rate varied from 65% to 86%. There were 158 of 1210 patients who had TB recurrence after treatment success. The pooled TB recurrence estimate was 10.9% [95%CI: 0.2-21.6] and TB recurrence rate per 100 person-years was 12.7 [95% CI: 0.4-25]. TB recurrence per 100 person-years varied from 5.4 to 30.5. Endogenous reactivation was observed in 56 (93%) of 60 patients for whom genotyping was done. Male gender was associated with TB recurrence. CONCLUSION: A substantial proportion of new smear positive PTB patients successfully treated with 6 -month thrice-weekly regimen have TB recurrence under program settings.

Prevalence of nephropathy in type 1 diabetes in the Arab world: A systematic review and meta-analysis.

The aim of this study was to conduct a systematic review and meta-analysis and determine the prevalence of diabetic nephropathy (DN) among Arab patients with T1D. A systematic literature search was conducted using 4 different literature databases (PubMed, ScienceDirect, Web of Science, and Embase) to capture all relevant data about Arab patients with T1D that had DN. Meta-analysis and systematic review were performed using the random effect model, and the heterogeneity of the studies was assessed using the Q-test, I2, and Tau-squared statistics. Publication bias was assessed using the funnel-plot test. Our search strategy captured 372 studies in only 10 out of the 22 Arab countries in a period of 48 years (1969-2017); of which, 41 met our inclusion criteria for full article analysis, of those, 15 were eligible for meta-analysis. We estimated the prevalence of DN among Arab people with T1D to be 18.2% (95% confidence interval 13.1%-24.8%). In conclusion, DN prevalence is underexplored among Arab patients with T1D and represents a significant risk for the well-being of Arab patients with T1D. Therefore, there is an urgent need for comprehensive epidemiological studies for DN among Arab patients with T1D.

Comparison of different treatments for isoniazid-resistant tuberculosis: an individual patient data meta-analysis.

BACKGROUND: Isoniazid-resistant, rifampicin-susceptible (INH-R) tuberculosis is the most common form of drug resistance, and is associated with failure, relapse, and acquired rifampicin resistance if treated with first-line anti-tuberculosis drugs. The aim of the study was to compare success, mortality, and acquired rifampicin resistance in patients with INH-R pulmonary tuberculosis given different durations of rifampicin, ethambutol, and pyrazinamide (REZ); a fluoroquinolone plus 6 months or more of REZ; and streptomycin plus a core regimen of REZ. METHODS: Studies with regimens and outcomes known for individual patients with INH-R tuberculosis were eligible, irrespective of the number of patients if randomised trials, or with at least 20 participants if a cohort study. Studies were identified from two relevant systematic reviews, an updated search of one of the systematic reviews (for papers published between April 1, 2015, and Feb 10, 2016), and personal communications. Individual patient data were obtained from authors of eligible studies. The individual patient data meta-analysis was performed with propensity score matched logistic regression to estimate adjusted odds ratios (aOR) and risk differences of treatment success (cure or treatment completion), death during treatment, and acquired rifampicin resistance. Outcomes were measured across different treatment regimens to assess the effects of: different durations of REZ (≤6 months vs >6 months); addition of a fluoroquinolone to REZ (fluoroquinolone plus 6 months or more of REZ vs 6 months or more of REZ); and addition of streptomycin to REZ (streptomycin plus 6 months of rifampicin and ethambutol and 1-3 months of pyrazinamide vs 6 months or more of REZ). The overall quality of the evidence was assessed using GRADE methodology. FINDINGS: Individual patient data were requested for 57 cohort studies and 17 randomised trials including 8089 patients with INH-R tuberculosis. We received 33 datasets with 6424 patients, of which 3923 patients in 23 studies received regimens related to the study objectives. Compared with a daily regimen of 6 months of (H)REZ (REZ with or without isoniazid), extending the duration to 8-9 months had similar outcomes; as such, 6 months or more of (H)REZ was used for subsequent comparisons. Addition of a fluoroquinolone to 6 months or more of (H)REZ was associated with significantly greater treatment success (aOR 2·8, 95% CI 1·1-7·3), but no significant effect on mortality (aOR 0·7, 0·4-1·1) or acquired rifampicin resistance (aOR 0·1, 0·0-1·2). Compared with 6 months or more of (H)REZ, the standardised retreatment regimen (2 months of streptomycin, 3 months of pyrazinamide, and 8 months of isoniazid, rifampicin, and ethambutol) was associated with significantly worse treatment success (aOR 0·4, 0·2-0·7). The quality of the evidence was very low for all outcomes and treatment regimens assessed, owing to the observational nature of most of the data, the diverse settings, and the imprecision of estimates. INTERPRETATION: In patients with INH-R tuberculosis, compared with treatment with at least 6 months of daily REZ, addition of a fluoroquinolone was associated with better treatment success, whereas addition of streptomycin was associated with less treatment success; however, the quality of the evidence was very low. These results support the conduct of randomised trials to identify the optimum regimen for this important and common form of drug-resistant tuberculosis. FUNDING: World Health Organization and Canadian Institutes of Health Research.

Randomized clinical trial of thrice-weekly 4-month moxifloxacin or gatifloxacin containing regimens in the treatment of new sputum positive pulmonary tuberculosis patients.

BACKGROUND: Shortening tuberculosis (TB) treatment duration is a research priority. This paper presents data from a prematurely terminated randomized clinical trial, of 4-month moxifloxacin or gatifloxacin regimens, in South India. METHODS: Newly diagnosed, sputum-positive HIV-negative pulmonary TB patients were randomly allocated to receive gatifloxacin or moxifloxacin, along with isoniazid and rifampicin for 4 months with pyrazinamide for first 2 months (G or M) or isoniazid and rifampicin for 6 months with ethambutol and pyrazinamide for first 2 months (C). All regimens were administered thrice-weekly. Clinical and bacteriological assessments were done monthly during treatment and for 24 months post-treatment. The Data and Safety Monitoring Board recommended termination of the trial due to high TB recurrence rates in the G and M regimens. RESULTS: Of 416 patients in intent-to-treat analysis, 6 (5%) of 124, 2 (2%) of 110 and 2 (2%) of 137 patients with drug-susceptible TB in the G, M and C arms respectively had unfavorable response at the end of treatment; during the next 24 months, 17 (15%) of 115, 11 (11%) of 104 and 8 (6%) of 132 patients respectively, had TB recurrence. Of 38 drug-resistant patients 1 of 8 and 3 of 26 in the G and C arms respectively had unfavourable response at the end of treatment; and TB recurrence occurred in 2 of 7 and 2 of 23 patients, respectively. The differences in TB recurrence rates between the G and C arms was statistically significant (p = 0.02). Gastro-intestinal symptoms occurred in 23%, 22% and 9% of patients in the G, M and C arms respectively, but most reactions were mild and manageable with symptomatic measures; 1% required regimen modification. CONCLUSIONS: 4-month thrice-weekly regimens of gatifloxacin or moxifloxacin with isoniazid, rifampicin and pyrazinamide, were inferior to standard 6-month treatment, in patients with newly diagnosed sputum positive pulmonary TB. TRIAL REGISTRATION: Clinical Trials Registry of India CTRI/2012/10/003060.

Efficacy and safety of once-daily nevirapine- or efavirenz-based antiretroviral therapy in HIV-associated tuberculosis: a randomized clinical trial.

BACKGROUND: Nevirapine (NVP) can be safely and effectively administered once-daily but has not been assessed in human immunodeficiency virus (HIV)-infected patients with tuberculosis (TB). We studied the safety and efficacy of once-daily NVP, compared with efavirenz (EFV; standard therapy); both drugs were administered in combination with 2 nucleoside reverse-transcriptase inhibitors. METHODS: An open-label, noninferiority, randomized controlled clinical trial was conducted at 3 sites in southern India. HIV-infected patients with TB were treated with a standard short-course anti-TB regimen (2EHRZ(3)/4RH(3); [2 months of Ethambutol, Isoniazid, Rifampicin, Pyrazinamide / 4 months of Isoniazid and Rifampicin] thrice weekly) and randomized to receive once-daily EFV at a dose of 600 mg or NVP at a dose of 400 mg (after 14 days of 200 mg administered once daily) with didanosine 250/400 mg and lamivudine 300 mg after 2 months. Sputum smears and mycobacterial cultures were performed every month. CD4+ cell count, viral load, and liver function test results were monitored periodically. Primary outcome was a composite of death, virological failure, default, or serious adverse event (SAE) at 24 weeks. Both intent-to-treat and per protocol analyses were done, and planned interim analyses were performed. RESULTS: A total of 116 patients (75% [87 patients] of whom had pulmonary TB), with a mean age of 36 years, a median CD4+ cell count of 84 cells/mm(3), and a median viral load of 310 000 copies/mL, were randomized. At 24 weeks, 50 of 59 patients in the EFV group and 37 of 57 patients in the NVP group had virological suppression (P = .024). There were no deaths, 1 SAE, and 5 treatment failures in the EFV arm, compared with 5 deaths, 2 SAEs, and 10 treatment failures in the NVP arm. The trial was halted by the data and safety monitoring board at the second interim analysis. Favorable TB treatment outcomes were observed in 93% of the patients in the EFV arm and 84% of the patients in the NVP arm (P = .058). CONCLUSIONS: Compared with a regimen of didanosine, lamivudine, and EFV, a regimen of once-daily didanosine, lamivudine, and NVP was inferior and was associated with more frequent virologic failure and death. Clinical Trials Registration. NCT00332306.