Modelling the impact of the disease on people with COPD – a comparison of feature selection methods

• Autor(a) principal: Cabral, Jorge Vaz Ramos Rodrigues de
• Data de Publicação: 2022
• Outros Autores: Macedo, Pedro, Marques, Alda, Afreixo, Vera
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://doi.org/10.34624/jshd.v4i1.29107

Lockdown due to The COVID-19 pandemic is likely to have influenced the daily life of people with chronic obstructive pulmonary disease. Criteria to choose the most appropriate methods to select features in datasets are unclear. We aimed to compare feature selection methods and describe the effect of the COVID-19 lockdown, sociodemographic and clinical features on the impact of the disease on people with COPD. A total of 42 participants with mean age 66.3 years (sd 7.8), 3 to 4 comorbidities (64.3%) and a median CAT score of 9.0 ([Q1,Q3]=[5.3,11.0]) were included, 24 (57.1%) of whom in the pre-lockdown group. The model obtained with 3 features selected by the entropy approach was at least not worse than the remaining. Our model suggests that lockdown had no influence in COPD impact but those with comorbidities but no emergencies tended to recover well from the pandemic.