Ana Torres, Brima Musa Younis, Samuel Tesema, Jose Carlos Solana, Javier Moreno, Antonio J Martín-Galiano, Ahmed Mudawi Musa, Fabiana Alves, Eugenia Carrillo
{"title":"Unsupervised machine learning identifies biomarkers of disease progression in post-kala-azar dermal leishmaniasis in Sudan.","authors":"Ana Torres, Brima Musa Younis, Samuel Tesema, Jose Carlos Solana, Javier Moreno, Antonio J Martín-Galiano, Ahmed Mudawi Musa, Fabiana Alves, Eugenia Carrillo","doi":"10.1371/journal.pntd.0012924","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Post-kala-azar dermal leishmaniasis (PKDL) appears as a rash in some individuals who have recovered from visceral leishmaniasis caused by Leishmania donovani. Today, basic knowledge of this neglected disease and how to predict its progression remain largely unknown.</p><p><strong>Methods and findings: </strong>This study addresses the use of several biochemical, haematological and immunological variables, independently or through unsupervised machine learning (ML), to predict PKDL progression risk. In 110 patients from Sudan, 31 such factors were assessed in relation to PKDL disease state at the time of diagnosis: progressive (worsening) versus stable. To identify key factors associated with PKDL worsening, we used both a conventional statistical approach and multivariate analysis through unsupervised ML. The independent use of these variables had limited power to predict skin lesion severity in a baseline examination. In contrast, the unsupervised ML approach identified a set of 10 non-redundant variables that was linked to a 3.1 times higher risk of developing progressive PKDL. Three of these clustering factors (low albumin level, low haematocrit and low IFN-γ production in PBMCs after Leishmania antigen stimulation) were remarkable in patients with progressive disease. Dimensionality re-establishment identified 11 further significantly modified factors that are also important to understand the worsening phenotype. Our results indicate that the combination of anaemia and a weak Th1 immunological response is likely the main physiological mechanism that leads to progressive PKDL.</p><p><strong>Conclusions: </strong>A combination of 14 biochemical variables identified by unsupervised ML was able to detect a worsening PKDL state in Sudanese patients. This approach could prove instrumental to train future supervised algorithms based on larger patient cohorts both for a more precise diagnosis and to gain insight into fundamental aspects of this complication of visceral leishmaniasis.</p>","PeriodicalId":49000,"journal":{"name":"PLoS Neglected Tropical Diseases","volume":"19 3","pages":"e0012924"},"PeriodicalIF":3.4000,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11932480/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"PLoS Neglected Tropical Diseases","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1371/journal.pntd.0012924","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"PARASITOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Post-kala-azar dermal leishmaniasis (PKDL) appears as a rash in some individuals who have recovered from visceral leishmaniasis caused by Leishmania donovani. Today, basic knowledge of this neglected disease and how to predict its progression remain largely unknown.
Methods and findings: This study addresses the use of several biochemical, haematological and immunological variables, independently or through unsupervised machine learning (ML), to predict PKDL progression risk. In 110 patients from Sudan, 31 such factors were assessed in relation to PKDL disease state at the time of diagnosis: progressive (worsening) versus stable. To identify key factors associated with PKDL worsening, we used both a conventional statistical approach and multivariate analysis through unsupervised ML. The independent use of these variables had limited power to predict skin lesion severity in a baseline examination. In contrast, the unsupervised ML approach identified a set of 10 non-redundant variables that was linked to a 3.1 times higher risk of developing progressive PKDL. Three of these clustering factors (low albumin level, low haematocrit and low IFN-γ production in PBMCs after Leishmania antigen stimulation) were remarkable in patients with progressive disease. Dimensionality re-establishment identified 11 further significantly modified factors that are also important to understand the worsening phenotype. Our results indicate that the combination of anaemia and a weak Th1 immunological response is likely the main physiological mechanism that leads to progressive PKDL.
Conclusions: A combination of 14 biochemical variables identified by unsupervised ML was able to detect a worsening PKDL state in Sudanese patients. This approach could prove instrumental to train future supervised algorithms based on larger patient cohorts both for a more precise diagnosis and to gain insight into fundamental aspects of this complication of visceral leishmaniasis.
期刊介绍:
PLOS Neglected Tropical Diseases publishes research devoted to the pathology, epidemiology, prevention, treatment and control of the neglected tropical diseases (NTDs), as well as relevant public policy.
The NTDs are defined as a group of poverty-promoting chronic infectious diseases, which primarily occur in rural areas and poor urban areas of low-income and middle-income countries. Their impact on child health and development, pregnancy, and worker productivity, as well as their stigmatizing features limit economic stability.
All aspects of these diseases are considered, including:
Pathogenesis
Clinical features
Pharmacology and treatment
Diagnosis
Epidemiology
Vector biology
Vaccinology and prevention
Demographic, ecological and social determinants
Public health and policy aspects (including cost-effectiveness analyses).