Artificial neural network models to support the diagnosis of pleural tuberculosis in adult patients

Página do item simplificado
dc.contributor.authorSeixas, J. M.
dc.contributor.authorFaria, J.
dc.contributor.authorFilho, J. B. O. Souza
dc.contributor.authorVieira, A. F. M.
dc.contributor.authorKritski, A.
dc.contributor.authorTrajman, A.
dc.date.accessioned2025-01-03T12:08:59Z
dc.date.available2025-01-03T12:08:59Z
dc.date.issued2013
dc.description.abstractBACKGROUND: Clinicians in countries with high tu- berculosis (TB) prevalence often treat pleural TB based on clinical grounds, as the availability and sensitivity of diagnostic tests are poor. OBJECTIVE: To evaluate the role of artificial neural net- works (ANN) as an aid for the non-invasive diagnosis of pleural TB. These tools can be used in simple computer devices (tablets) without remote internet connection. METHODS: The clinical history and human immuno- deficiency virus (HIV) status of 137 patients were pro- spectively entered in a database. Both non-linear ANN and the linear Fisher discriminant were used to calculate performance indexes based on clinical grounds. The same procedure was performed including pleural fluid test results (smear, culture, adenosine deaminase, serology and nucleic acid amplification test). The gold standard was any positive test for TB. RESULTS: In pre-test modelling, the neural model reached >90% accuracy (Fisher discriminant 74.5%). Under pre-test conditions, ANN had better accuracy compared to each test considered separately. CONCLUSIONS: ANN are highly reliable for diagnos- ing pleural TB based on clinical grounds and HIV status only, and are useful even in remote conditions lacking access to sophisticated medical or computer infrastruc- ture. In other better-equipped scenarios, these tools should be evaluated as substitutes for thoracocentesis and pleural biopsy.
dc.identifier.citationSeixas JM, Faria J, Souza Filho JB, Vieira AF, Kritski A, Trajman A. Artificial neural network models to support the diagnosis of pleural tuberculosis in adult patients. Int J Tuberc Lung Dis. 2013 May;17(5):682-6. doi: 10.5588/ijtld.12.0829.
dc.identifier.otherDOI: 10.5588/ijtld.12.0829
dc.identifier.urihttps://dspace.inc.saude.gov.br/handle/123456789/730
dc.language.isoen
dc.publisherINT J TUBERC LUNG DIS
dc.subjectPleurisyen
dc.subjectaccuracyen
dc.subjectartificial intelligenceen
dc.subjecttuberculosisen
dc.subjectdiagnosis.en
dc.titleArtificial neural network models to support the diagnosis of pleural tuberculosis in adult patients
dc.typeArticle
Arquivos
Original bundle
Agora exibindo 1 - 1 de 1
thumbnail.default.alt
Nome:
Seixas JM et al_INT J TUBERC LUNG DIS.pdf
Tamanho:
97.45 KB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
License bundle
Agora exibindo 1 - 1 de 1
thumbnail.default.placeholder
Nome:
license.txt
Tamanho:
1.71 KB
Formato:
Item-specific license agreed to upon submission
Descrição:
Baixar
Coleções
Produção Docente