Prediction of the occurrence of leprosy reactions based on Bayesian networks.

Introduction: Leprosy reactions (LR) are severe episodes of intense activation of the host inflammatory response of uncertain etiology, today the leading cause of permanent nerve damage in leprosy patients. Several genetic and non-genetic risk factors for LR have been described; however, there are limited attempts to combine this information to estimate the risk of a leprosy patient developing LR. Here we present an artificial intelligence (AI)-based system that can assess LR risk using clinical, demographic, and genetic data. Methods: The study includes four datasets from different regions of Brazil, totalizing 1,450 leprosy patients followed prospectively for at least 2 years to assess the occurrence of LR. Data mining using WEKA software was performed following a two-step protocol to select the variables included in the AI system, based on Bayesian Networks, and developed using the NETICA software. Results: Analysis of the complete database resulted in a system able to estimate LR risk with 82.7% accuracy, 79.3% sensitivity, and 86.2% specificity. When using only databases for which host genetic information associated with LR was included, the performance increased to 87.7% accuracy, 85.7% sensitivity, and 89.4% specificity. Conclusion: We produced an easy-to-use, online, free-access system that identifies leprosy patients at risk of developing LR. Risk assessment of LR for individual patients may detect candidates for close monitoring, with a potentially positive impact on the prevention of permanent disabilities, the quality of life of the patients, and upon leprosy control programs.

Leprosy surveillance study in a highly endemic Brazilian area using leprosy specific serologic tests and IFNγ whole blood assay.

This surveillance study evaluated leprosy-serologic tests and the IFNγ whole-blood-assay/WBA as adjunct diagnostic tools. Previously diagnosed leprosy index cases, intradomiciliary, peridomiciliary contacts from a Brazilian endemic area were enrolled during domiciliary visits. Physical evaluation was performed by trained nurses and leprosy diagnosis confirmed by expert dermatologist. ELISA detected IgM anti-PGL-I, IgG anti-LID-1, and IgM/IgG anti-ND-O-LID antibodies. Heparinized WBA plasma stimulated with LID-1, 46f + LID-1, ML0276 + LID-1 (24 h, 37 °C, 5% CO2) was tested for human IFNγ (QuantiFERON®-TB Gold/QFT-G; Qiagen). The survey included 1731 participants: 44 leprosy index cases, 64 intradomiciliary, 1623 peridomiciliary contacts. Women represented 57.7%, median age was 32 years, 72.2% had BCG scar. Leprosy prevalence was higher in intradomiciliary (8.57%) versus peridomiciliary contacts (0.67%), p < 0.001. Among 23 suspects, five leprosy cases were confirmed: 4 multibacillary/MB and 1 paucibacillary/PB. Leprosy incidence was 0.30%: 1.56% in intradomiciliary versus 0.25% in peridomiciliary (p = 0.028). Seropositivity rates were 1.9% to PGL-I, 4.9% to LID-1, and 1.0% to ND-O-LID. LID-1 positivity was higher in all groups; incident cases were LID-1 seropositive. ND-O-LID positivity was higher in intra- versus peridomiciliary contacts (p = 0.022). IFNγ WBA (40 index cases, 19 suspects, 35 intradomiciliary, 74 peridomiciliary contacts) showed higher LID-1/WBA positivity in peridomiciliary contacts (p > 0.05); significant differences among groups were seen with 46f + LID-1 but 0276 + LID-1 induced higher IFNγ levels. Incident cases were LID-1 seropositive, while IFNγ-WBA had marginal diagnostic application. As seropositivity indicates exposed individuals at higher risk of disease development, the utility of serologic screening for surveillance and prophylactic measures remains to be demonstrated.

Description of leprosy classification at baseline among patients enrolled at the uniform multidrug therapy clinical trial for leprosy patients in Brazil.

The uniform multidrug therapy clinical trial, Brazil (U-MDT/CT-BR), database was used to describe and report the performance of available tools to classify 830 leprosy patients as paucibacillary (PB) and multibacillary (MB) at baseline. In a modified Ridley and Jopling (R&J) classification, considering clinical features, histopathological results of skin biopsies and the slit-skin smear bacterial load results were used as the gold standard method for classification. Anti-phenolic glycolipid-I (PGL-I) serology by ML Flow test, the slit skin smear bacterial load, and the number of skin lesions were evaluated. Considering the R&J classification system as gold standard, ML Flow tests correctly allocated 70% patients in the PB group and 87% in the MB group. The classification based on counting the number of skin lesions correctly allocated 46% PB patients and 99% MB leprosy cases. Slit skin smears properly classified 91% and 97% of PB and MB patients, respectively. Based on U-MDT/CT-BR results, classification of leprosy patients for treatment purposes is unnecessary because it does not impact clinical and laboratories outcomes. In this context, the identification of new biomarkers to detect patients at a higher risk to develop leprosy reactions or relapse remains an important research challenge.

HIV type 1 molecular epidemiology in pol and gp41 genes among naive patients from Mato Grosso do Sul State, central western Brazil.

Antiretroviral naive patients (n=49) were recruited in central western Brazil (Campo Grande City/Mato Grosso do Sul State, located across the Bolivia and Paraguay borders). HIV-1 protease (PR), reverse transcriptase (RT), and env gp41 HR1 fragments were sequenced. Genetic diversity was analyzed by REGA/phylogenetic analyses. Intersubtype recombinants were identified by SimPlot/phylogenetic trees. PR/RT resistance was analyzed by Calibrated Population Resistance/Stanford databases. T-20 resistance in gp41 was assessed by Stanford, Los Alamos, and other sources. Of HIV-1 subtypes 65.3% were B(PR)B(RT), 10.2% were C(PR)C(RT), and 8.2% were F1(PR)F1(RT). Intersubtype recombinants were 16.3%: four B/F1 and four B/C (two were "CRF31_BC-like"). The Pol-RT V75M mutation was detected in two homosexual partners; one patient had the T215S revertant mutation. T-20/gp41 resistance mutations were L44M (n=2) and V38A (n=1). The high percentage of non-B isolates (∼35%) highlights the importance of molecular surveillance studies in settings distant from the origin of the epidemic. Our data help elaborate the molecular epidemiological map of HIV-1 in Brazil.