ABSTRACT
Objective: To develop a classification framework based on random forest (RF) modeling to outline the declarative memory profile of patients with panic disorder (PD) compared to a healthy control sample. Methods: We developed RF models to classify the declarative memory profile of PD patients in comparison to a healthy control sample using the Rey Auditory Verbal Learning Test (RAVLT). For this study, a total of 299 patients with PD living in the city of Rio de Janeiro (70.9% females, age 39.9 ± 7.3 years old) were recruited through clinician referrals or self/family referrals. Results: Our RF models successfully predicted declarative memory profiles in patients with PD based on RAVLT scores (lowest area under the curve [AUC] of 0.979, for classification; highest root mean squared percentage [RMSPE] of 17.2%, for regression) using relatively bias-free clinical data, such as sex, age, and body mass index (BMI). Conclusions: Our findings also suggested that BMI, used as a proxy for diet and exercises habits, plays an important role in declarative memory. Our framework can be extended and used as a prospective tool to classify and examine associations between clinical features and declarative memory in PD patients.
ABSTRACT
INTRODUÇÃO: A Tomografia por Impedância Elétrica (TIE) é um método de imageamento de baixo custo, não invasivo, portátil e livre de radiacão ionizante, que é capaz de mapear a distribuicão das propriedades elétricas de tecidos biológicos. Apesar da baixa resolucão das imagens reconstruídas, quando comparadas a outras técnicas de imageamento tomográfico, tem-se observado uma série de aplicacões clínicas nas quais a EIT é utilizada para monitorar a atividade de determinados tecidos do corpo humano. A maioria dos sistemas de EIT comerciais tem sido pautada no paradigma originalmente proposto de uma configuracão multiportas. Este trabalho apresenta um algoritmo de reconstrucão de imagem para um sistema alternativo de EIT que usa uma configuracão multiterminais. MÉTODOS: O algoritmo é baseado na associacão entre o plano tomográfico do volume condutor e um sistema eletrostático análogo. Para avaliar o algoritmo, imagens de EIT foram reconstruídas a partir de dados obtidos experimentalmente em tanque com solucão salina, sendo as mesmas quantificadas por meio de métricas estabelecidas para este propósito. RESULTADOS: Quantitativamente, as imagens reconstruídas com o algoritmo proposto apresentaram um erro de posicão de ±10%, resolucão e deformacão decrescentes do centro para a borda e oscilacão em torno de 60% do meio. CONCLUSÃO: Uma vez que o algoritmo não possui nenhum processo de filtragem, os resultados foram considerados satisfatórios e encorajadores para trabalhos futuros visando melhorias.
INTRODUCTION: Electrical Impedance Tomography (EIT) is a low cost, non-invasive, portable and free of ionizing radiation method for imaging the distribution of the electric properties of biological tissues. Despite the low resolution of the reconstructed images when compared with other tomographic techniques, there is a range of clinical applications in which the EIT has been used to monitor the activity of certain body tissues. Most of commercial EIT systems are based on the original paradigm defined as a multiport configuration. This paper presents an algorithm developed to reconstruct images for an alternative multiterminal-based EIT system. METHODS: The algorithm is based on the association between the tomographic plane of the conductor volume and an analogous electrostatic system. To evaluate the algorithm, EIT images were reconstructed using data obtained experimentally in a saline solution tank, which were quantified by some metrics established for this purpose. RESULTS: Quantitatively, EIT images reconstructed by the proposed algorithm presented a position error around ±10%, resolution and shape deformation decreasing from center to the edge, and ringing around 60% of the medium. CONCLUSION: Taking into account that no filtering was used in the algorithm, the results can be considered satisfactory and encourage future works aiming further improvement.