Search

Introduction: This study aims to create an artificial intelligence (AI) based machine learning (ML) model capable of predicting a spirometric obstructive pattern using variables with the highest predictive power derived from an active case-finding program for COPD in primary care., Material and Methods: A total of 1190 smokers, aged 30-80 years old with no prior history of respiratory disease, underwent spirometry with bronchodilation. The sample was analyzed using AI tools. Based on an exploratory data analysis (EDA), independent variables (according to mutual information analysis) were trained using a gradient boosting algorithm (GBT) and validated through cross-validation., Results: With an area under the curve close to unity, the model predicted a spirometric obstructive pattern using variables with the highest predictive power: FEV1_theoretical_pre values. Sensitivity: 93%. Positive predictive value: 94%. Specificity: 97%. Negative predictive value: 96%. Accuracy: 95%. Precision: 94%., Conclusion: An ML model can predict the presence of an obstructive pattern in spirometry in a primary care smoking population with no prior diagnosis of respiratory disease using the FEV1_theoretical_pre values with an accuracy and precision exceeding 90%. Further studies including clinical data and strategies for integrating AI into clinical workflow are needed., (© 2024 Sociedad Española de Neumología y Cirugía Torácica (SEPAR). Published by Elsevier España, S.L.U.)

Background: Several descriptive cohort studies of patients affected by COVID-19 have been published., Objective: To describe the characteristics of patients with SARS-CoV-2 infection who were admitted to Hospital Universitario la Plana, Castellón, Spain., Methods: Retrospective, observational cohort study that included 18-year-old or older patients who were consecutively admitted with SARS-CoV2 confirmed infection. Demographic characteristics, comorbidities, clinical symptoms, laboratory results and radiological tests are described., Results: The study included 255 patients with a mean age of 70 years; 54.9 % were males. Most common comorbidities were high blood pressure (58 %), dyslipidemia (42.4 %), diabetes (25.5 %) and obesity (24.3 %). Median number of days from the onset of clinical symptoms prior to hospital admission was seven. Most common manifestations prior to admission were fever (74.5 %), dry cough (61.2 %), malaise (51.8 %) and dyspnea (51.0 %); 19 patients (7.4 %) were admitted to the intensive care unit, where mortality was 50 %; overall mortality was 16.9 %., Conclusions: Our cohort reflects similar characteristics to those of other European series. Mortality was lower than that in similar studies., (Copyright: © 2020 Permanyer.)