Produção Docente
URI Permanente para esta coleção
Navegar
Navegando Produção Docente por Assunto "accuracy"
Agora exibindo 1 - 1 de 1
Resultados por página
Opções de Ordenação
- ItemArtificial neural network models to support the diagnosis of pleural tuberculosis in adult patients(INT J TUBERC LUNG DIS, 2013) Seixas, J. M.; Faria, J.; Filho, J. B. O. Souza; Vieira, A. F. M.; Kritski, A.; Trajman, A.BACKGROUND: 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.