A carregar...
Publicação
Algoritmos de Classificação Multiclasse via SVM para Apoio ao Diagnóstico a partir de Dados do Teste de Esforço Cardiopulmonar (CPET)
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.61 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
O Teste de Esforço Cardiopulmonar (CPET) é uma ferramenta vital para o diagnóstico
funcional, mas a aplicação de modelos de aprendizagem automática é frequentemente
limitada pela escassez de séries temporais completas para diversas condições clínicas.
Esta dissertação aborda esta lacuna, partindo de um framework de classificação baseado
em Support Vector Machines (SVM) e na Transformada Wavelet Discreta (DWT),
originalmente desenvolvido para três classes (Insuficiência Cardíaca (IC), Síndrome
Metabólica (SM) e Saudáveis (S)).
O objetivo central foi expandir esta metodologia para um cenário mais complexo de
cinco classes, através da geração de Dados Semi-Sintéticos para os grupos de Limitação
Pulmonar (LP) e Limitação Musculoesquelética (LM), guiada por parâmetros estatísticos
de pacientes reais. Subsequentemente, para validar a eficácia da Transformada
Wavelet Discreta (Discrete Wavelet Transform) (DWT) neste novo contexto, foi conduzida
uma análise comparativa, avaliando o desempenho do modelo contra três métodos
alternativos de extração de características: a Transformada de Fourier de Curto Tempo
(Short-Time Fourier Transform) (STFT), a Transformada Wavelet por Pacotes (Wavelet
Packet Transform) (WPT) e a Decomposição por Modos Empíricos (Empirical Mode Decomposition)
(EMD). Todos os modelos foram avaliados sob um protocolo experimental
consistente para garantir uma comparação justa.
Os resultados da análise comparativa foram consistentes. O modelo SVM-Linear-MW5,
que utiliza a DWT, alcançou uma acurácia de 93.60% e um F1-Score de 84.14%, um
desempenho que se destacou em relação ao das outras transformadas. A análise demonstrou
que a STFT foi a alternativa mais competitiva (F1-Score de 74.25%), enquanto
a WPT e a EMD não se mostraram tão eficazes para este problema.
Este trabalho conclui que a combinação de dados semi-sintéticos com a extração
de características via DWT é uma abordagem viável para a expansão de modelos de
diagnóstico. A metodologia de referência foi expandida para cinco classes e, na análise
comparativa realizada, a sua abordagem de processamento de sinal obteve o desempenho
mais elevado entre as técnicas testadas, o que estabelece um baseline sólido para
futuras investigações na área, incluindo a otimização de Hiperparâmetros.
Cardiopulmonary Exercise Testing (CPET) is a vital tool for functional diagnosis, yet the application of machine learning models is often limited by the scarcity of complete time-series across clinical conditions. This dissertation addresses that gap by extending a classification framework based on Support Vector Machines (SVM) and the Discrete Wavelet Transform (DWT), originally developed for three classes (Heart Failure, Metabolic Syndrome, and Healthy). The central goal was to scale this methodology to a five-class scenario by generating semi-synthetic data for Pulmonary Limitation and Musculoskeletal Limitation, guided by summary statistics from real patients. To assess the effectiveness of DWT in this expanded setting, a comparative study was conducted against three alternative featureextraction methods: Short-Time Fourier Transform (STFT), Wavelet Packet Transform (WPT), and Empirical Mode Decomposition (EMD). All models were evaluated under a consistent experimental protocol to ensure fair comparison. Results were consistent: the SVM-Linear-MW5 model, using DWT-based features, achieved 93.60% accuracy and an F1-score of 84.14%, outperforming the alternatives. STFT was the most competitive contender (F1-score of 74.25%), while WPT and EMD were less effective for this problem. This work concludes that combining semi-synthetic data with DWT-based feature extraction is a viable path to expand diagnostic models. The reference methodology was successfully extended to five classes and set a strong baseline for future research, including hyperparameter optimisation.
Cardiopulmonary Exercise Testing (CPET) is a vital tool for functional diagnosis, yet the application of machine learning models is often limited by the scarcity of complete time-series across clinical conditions. This dissertation addresses that gap by extending a classification framework based on Support Vector Machines (SVM) and the Discrete Wavelet Transform (DWT), originally developed for three classes (Heart Failure, Metabolic Syndrome, and Healthy). The central goal was to scale this methodology to a five-class scenario by generating semi-synthetic data for Pulmonary Limitation and Musculoskeletal Limitation, guided by summary statistics from real patients. To assess the effectiveness of DWT in this expanded setting, a comparative study was conducted against three alternative featureextraction methods: Short-Time Fourier Transform (STFT), Wavelet Packet Transform (WPT), and Empirical Mode Decomposition (EMD). All models were evaluated under a consistent experimental protocol to ensure fair comparison. Results were consistent: the SVM-Linear-MW5 model, using DWT-based features, achieved 93.60% accuracy and an F1-score of 84.14%, outperforming the alternatives. STFT was the most competitive contender (F1-score of 74.25%), while WPT and EMD were less effective for this problem. This work concludes that combining semi-synthetic data with DWT-based feature extraction is a viable path to expand diagnostic models. The reference methodology was successfully extended to five classes and set a strong baseline for future research, including hyperparameter optimisation.
Descrição
Palavras-chave
Teste de esforço cardiopulmonar (CPET) Support vector machines (SVM) Transformada Wavelet Geração de dados semi-sintéticos Séries temporais fisiológicas Decisão clínica