Machine learning algorithms using national registry data to predict loss to follow-up during tuberculosis treatment.

BACKGROUND: Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN). METHODS: We performed a retrospective study of all TB cases reported to SINAN between 2015 and 2022; excluding children (< 18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we splitted our data into training (~ 80% data) and test (~ 20%) sets, and then compared the model metrics using the test data set. RESULTS: Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring systems exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity and sensitivity. A user-friendly web calculator app was developed ( https://tbprediction.herokuapp.com/ ) to facilitate implementation. CONCLUSIONS: Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement utilizing schooling level, sex, age, prior TB status, and substance use (drug, alcohol, and/or tobacco). This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.

An integrative multi-omics approach to characterize interactions between tuberculosis and diabetes mellitus.

Tuberculosis-diabetes mellitus (TB-DM) is linked to a distinct inflammatory profile, which can be assessed using multi-omics analyses. Here, a machine learning algorithm was applied to multi-platform data, including cytokines and gene expression in peripheral blood and eicosanoids in urine, in a Brazilian multi-center TB cohort. There were four clinical groups: TB-DM(n = 24), TB only(n = 28), DM(HbA1c ≥ 6.5%) only(n = 11), and a control group of close TB contacts who did not have TB or DM(n = 13). After cross-validation, baseline expression or abundance of MMP-28, LTE-4, 11-dTxB2, PGDM, FBXO6, SECTM1, and LINCO2009 differentiated the four patient groups. A distinct multi-omic-derived, dimensionally reduced, signature was associated with TB, regardless of glycemic status. SECTM1 and FBXO6 mRNA levels were positively correlated with sputum acid-fast bacilli grade in TB-DM. Values of the biomarkers decreased during the course of anti-TB therapy. Our study identified several markers associated with the pathophysiology of TB-DM that could be evaluated in future mechanistic investigations.

Machine learning algorithms using national registry data to predict loss to follow- up during tuberculosis treatment.

Background: Identifying patients at increased risk of loss to follow-up (LTFU) is key to developing strategies to optimize the clinical management of tuberculosis (TB). The use of national registry data in prediction models may be a useful tool to inform healthcare workers about risk of LTFU. Here we developed a score to predict the risk of LTFU during anti-TB treatment (ATT) in a nationwide cohort of cases using clinical data reported to the Brazilian Notifiable Disease Information System (SINAN). Methods: We performed a retrospective study of all TB cases reported to SINAN between 2015-2022; excluding children (<18 years-old), vulnerable groups or drug-resistant TB. For the score, data before treatment initiation were used. We trained and internally validated three different prediction scoring systems, based on Logistic Regression, Random Forest, and Light Gradient Boosting. Before applying our models we split our data into train (~80% data) and test (~20%), and then we compare model metrics using a test data set. Results: Of the 243,726 cases included, 41,373 experienced LTFU whereas 202,353 were successfully treated and cured. The groups were different with regards to several clinical and sociodemographic characteristics. The directly observed treatment (DOT) was unbalanced between the groups with lower prevalence in those who were LTFU. Three models were developed to predict LTFU using 8 features (prior TB, drug use, age, sex, HIV infection and schooling level) with different score composition approaches. Those prediction scoring system exhibited an area under the curve (AUC) ranging between 0.71 and 0.72. The Light Gradient Boosting technique resulted in the best prediction performance, weighting specificity, and sensibility. A user-friendly web calculator app was created (https://tbprediction.herokuapp.com/) to facilitate implementation. Conclusions: Our nationwide risk score predicts the risk of LTFU during ATT in Brazilian adults prior to treatment commencement. This is a potential tool to assist in decision-making strategies to guide resource allocation, DOT indications, and improve TB treatment adherence.

Prevalence and Clinical Profiling of Dysglycemia and HIV Infection in Persons With Pulmonary Tuberculosis in Brazil.

BACKGROUND: There are scarce data on the prevalence and disease presentation of HIV in patients with tuberculosis (TB) and dysglycemia (diabetes [DM] and prediabetes [PDM]), especially in TB-endemic countries. METHODS: We assessed the baseline epidemiological and clinical characteristics of patients with culture-confirmed pulmonary TB, enrolled in a multicenter prospective cohort in Brazil (RePORT-Brazil) during 2015-2019. Dysglycemia was defined by elevated glycated hemoglobin and stratified as PDM or DM. Additionally, we used data from TB cases obtained through the Brazilian National Notifiable Diseases Information System (SINAN), during 2015-2019. In SINAN, diagnosis of diabetes was based on self-report. Logistic regression models were performed to test independent associations between HIV, dysglycemia status, and other baseline characteristics in both cohorts. RESULTS: In the RePORT-Brazil cohort, the prevalence of DM and of PDM was 23.7 and 37.8%, respectively. Furthermore, the prevalence of HIV was 21.4% in the group of persons with TB-dysglycemia and 20.5% in that of patients with TBDM. In the SINAN cohort, the prevalence of DM was 9.2%, and among the TBDM group the prevalence of HIV was 4.1%. Logistic regressions demonstrated that aging was independently associated with PDM or DM in both the RePORT-Brazil and SINAN cohorts. In RePORT-Brazil, illicit drug use was associated with PDM, whereas a higher body mass index (BMI) was associated with DM occurrence. Of note, HIV was not associated with an increased risk of PDM or DM in patients with pulmonary TB in both cohorts. Moreover, in both cohorts, the TBDM-HIV group presented with a lower proportion of positive sputum smear and a higher frequency of tobacco and alcohol users. CONCLUSION: There is a high prevalence of dysglycemia in patients with pulmonary TB in Brazil, regardless of the HIV status. This reinforces the idea that DM should be systematically screened in persons with TB. Presence of HIV does not substantially impact clinical presentation in persons with TBDM, although it is associated with more frequent use of recreational drugs and smear negative sputum samples during TB screening.

Treinamento muscular inspiratório na doença pulmonar obstrutiva crônica: impacto na qualidade de vida, intolerância ao esforço e dispnéia / Inspiratory muscle training in chronic obstructive pulmonary disease: impact on quality of life, exercise intolerance, and dyspnea

O treinamento muscular inspiratório (TMI) tem demonstrado efeitos positivos na melhora da função muscular inspiratória, porém seus efeitos sobre a intolerância ao esforço e a qualidade de vida ainda precisam ser esclarecidos. Este estudo visou avaliar...

Inspiratory muscle training (IMT) has shown beneficial effects concerning inspiratory muscle function, but its effects on exercise intolerance and quality of life are not clearly established...

In house reverse line hybridization assay for rapid detection of susceptibility to rifampicin in isolates of Mycobacterium tuberculosis.

We developed a Reverse Hybridization Assay (RHA) slightly modified from the Rifoligotyping assay and analyzed the presence of mutations in a specific region of rpoB gene in 157 isolates (90 rifampin-resistant and 67 rifampin sensitive) of Mycobacterium tuberculosis from patients attended in South and Southeast region of Brazil. Comparing to standardized drug susceptibility testing results, the sensitivity and specificity of the RHA was respectively 93% (95% IC: 86.6%-97.2%) and 100% respectively. Additionally, a high agreement (kappa coefficient 95%) between the RHA assay and sequencing was obtained. Among the 90 rifampicin-resistant isolates, RHA identified point mutations in the following codons: 42 isolates (46.6%) in 531; 29 isolates (32.2%) in 526, 6 isolates (6.7%) in 516, 3 isolates (3.3%) in 522, 2 isolates (2.2%) in 515, 514, 513 and 1 isolate (1.1%) in 511, 524 and 525. Mutations in different codons were simultaneously identified in 8 isolates (8.9%). The RHA used in the present study had a high accuracy and can be rapidly performed. However, more reproducible hybridization conditions should be looked for to increase reliability of mutant probe interpretation.