Dataset Information

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

ABSTRACT:

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.

SUBMITTER: de Andrade Rodrigues RS

PROVIDER: S-EPMC10411956 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

de Andrade Rodrigues Rafael Saraiva RS Heise Eduardo Ferreira José EFJ Hartmann Luis Felipe LF Rocha Guilherme Eduardo GE Olandoski Marcia M de Araújo Stefani Mariane Martins MM Latini Ana Carla Pereira ACP Soares Cleverson Teixeira CT Belone Andrea A Rosa Patrícia Sammarco PS de Andrade Pontes Maria Araci MA de Sá Gonçalves Heitor H Cruz Rossilene R Penna Maria Lúcia Fernandes MLF Carvalho Deborah Ribeiro DR Fava Vinicius Medeiros VM Bührer-Sékula Samira S Penna Gerson Oliveira GO Moro Claudia Maria Cabral CMC Nievola Julio Cesar JC Mira Marcelo Távora MT

Frontiers in medicine 20230726

<h4>Introduction</h4>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 c ...[more]

PMID: 37564037

Similar Datasets

Project description:BackgroundThe ILEP Nerve Function Impairment in Reaction (INFIR) is a cohort study designed to identify predictors of reactions and nerve function impairment in leprosy. The aim was to study correlations between clinical and histological diagnosis of reactions.Methodology/principal findingsThree hundred and three newly diagnosed patients with World Health Organization multibacillary (MB) leprosy from two centres in India were enrolled in the study. Skin biopsies taken at enrolment were assessed using a standardised proforma to collect data on the histological diagnosis of leprosy, leprosy reactions and the certainty level of the diagnosis. The pathologist diagnosed definite or probable Type 1 Reactions (T1R) in 113 of 265 biopsies from patients at risk of developing reactions whereas clinicians diagnosed skin only reactions in 39 patients and 19 with skin and nerve involvement. Patients with Borderline Tuberculoid (BT) leprosy had a clinical diagnosis rate of reactions of 43% and a histological diagnosis rate of 61%; for patients with Borderline Lepromatous (BL) leprosy the clinical and histological diagnosis rates were 53.7% and 46.2% respectively. The sensitivity and specificity of clinical diagnosis for T1R was 53.1% and 61.9% for BT patients and 61.1% and 71.0% for BL patients. Erythema Nodosum Leprosum (ENL) was diagnosed clinically in two patients but histologically in 13 patients. The Ridley-Jopling classification of patients (n = 303) was 42.8% BT, 27.4% BL, 9.4% Lepromatous Leprosy (LL), 13.0% Indeterminate and 7.4% with non-specific inflammation. This data shows that MB classification is very heterogeneous and encompasses patients with no detectable bacteria and high immunological activity through to patients with high bacterial loads.Conclusions/significanceLeprosy reactions may be under-diagnosed by clinicians and increasing biopsy rates would help in the diagnosis of reactions. Future studies should look at sub-clinical T1R and ENL and whether they have impact on clinical outcomes.

Project description:Background: Reactions in Leprosy are immune exacerbations that cause debilitating consequences like nerve damage and permanent deformities. Prediction of these reactional states using appropriate biomarkers would enable early treatment interventions to prevent nerve function impairment. The current study investigated whole transcriptomic expression profiles of Mycobacterium leprae (M. leprae) that differentiate leprosy cases in type 2 (Erythema Nodosum Leprosum) reactions with those without reactions in host skin tissue derived RNA. Methods: Post clinical examination, excisional skin biopsy specimens were collected from skin lesions of subjects with and without type 2 reaction. Total RNA was extracted following the Trizol protocol and bacterial RNA was enriched in the samples. A 2 x 400K gene expression array (whole genome tiling array) was designed with the probes having 60-mer oligonucleotides tiling every 10bp of the genome sequence of M. leprae (NC_011896.1). The array comprised 420288 features which include probes and Agilent controls. The quality of RNA was estimated using BioAnalyzer (Agilent Technologies) followed by labelling, reverse transcription, amplification and hybridization to the arrays. The hybridized slides were scanned on a G2600D scanner (Agilent Technologies). The data thus acquired is analysed using GeneSpring GX Version 12.1 software. Data was normalized and fold difference in expression was noted from 359,922 probes which include sense and antisense orientations of 179,961 probes. The differentially expressing M. leprae genomic regions between type 2 reactions and non reactional cases were noted. Results: Considering a statistical cut-off value of 0.6 for fold difference in expression between the test and the control samples, a set of 107 genes indicated statistically significant up-regulation with volcano plot p-values less than 0.05. Functional characterization revealed higher-expression of genes encoding transmembrane proteins (12), regulatory proteins (9), fatty acid biosynthesis (6), amino acid metabolism (13), nucleic acid metabolism (7), DNA replication and repair (7), Secretory proteins (2) Krebs Cycle (1), Glycolysis (1), Drug Efflux Protein (1),Stress Response Protein (1), Energy Metabolism (2), Pantothenate biosynthesis (1), Metalloproteins (3), Hydrolases (1) and Hypothetical Proteins (40). Additionally there are 157 genes that are down regulated in cases with reaction. Conclusion: Differential expression of genes in the human skin biopsy specimens among leprosy cases with type 2 reaction in contrast to those without reaction suggests the role of pathogen associated gene expression triggers with the aetiology of these reactions. As most of the transmembrane and cell wall proteins possess epitope and surface exposed domains, higher expression levels of genes encoding these proteins may have a possible role in enhancing host immune responses characteristic of type 2 reactions in leprosy.

Dataset Information

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

Introduction

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets