[Risk Factors and a Prediction Model for Frequent Acute Exacerbations of Chronic Obstructive Pulmonary Disease].

Objective To identify the risk factors of patients with frequent acute exacerbations of chronic obstructive pulmonary disease (AECOPD) and construct a prediction model based on the clinical data,providing a theoretical basis for the clinical prevention and treatment. Methods A total of 25 638 COPD patients admitted to the Department of Respiratory and Critical Care Medicine,the Third People's Hospital of Chengdu from January 1,2013 to May 1,2023 were selected.Among them,11 315 patients were included according to the inclusion and exclusion criteria,and their clinical characteristics were analyzed.Multivariate Logistic regression was carried out to identify the risk factors for frequent AECOPD.A nomogram model was utilized to quantify the risk of acute exacerbation,and the performance of the prediction model was assessed based on the area under the receiver operating characteristic (ROC) curve. Results In the patients with frequent AECOPD,male percentage (P<0.001),age (P<0.001),urban residence (P<0.001),smoking (P<0.001),length of stay (P<0.001),total cost (P<0.001),antibiotic cost (P<0.001),diabetes (P=0.003),respiratory failure (P<0.001),heart disease (P<0.001),application of systemic glucocorticoids (P<0.001),white blood cell count (P<0.001),neutrophil percentage (P<0.001),C-reactive protein (P<0.001),total cholesterol (P<0.001),and brain natriuretic peptide (BNP) (P<0.001) were all higher than those in the patients with infrequent AECOPD.Multivariate Logistic regression analysis revealed that age,urban residence,smoking,diabetes,heart disease,Pseudomonas aeruginosa infection,application of systemic glucocorticoids,antibiotics,respiratory failure,and elevated white blood cell count,total cholesterol,and BNP were independent risk factors for hospitalization due to frequent AECOPD.A nomogram model of hospitalization due to frequent AECOPD was constructed according to risk factors.The ROC curve was established to evaluate the performance of the model,which showed the area under the ROC curve of 0.899 (95%CI=0.892-0.905),the sensitivity of 85.30%,and the specificity of 79.80%. Conclusion Frequent AECOPD is associated with smoking,heart disease,application of systemic glucocorticoids,Pseudomonas aeruginosa infection,age,low body mass index,and elevated BNP.Predicting the risks of hospitalization due to frequent AECOPD by the established model can provide theoretical support for the treatment and risk factor management of the patients.

Building intelligent communication systems for handicapped aphasiacs.

This paper presents an intelligent system allowing handicapped aphasiacs to perform basic communication tasks. It has the following three key features: (1) A 6-sensor data glove measures the finger gestures of a patient in terms of the bending degrees of his fingers. (2) A finger language recognition subsystem recognizes language components from the finger gestures. It employs multiple regression analysis to automatically extract proper finger features so that the recognition model can be fast and correctly constructed by a radial basis function neural network. (3) A coordinate-indexed virtual keyboard allows the users to directly access the letters on the keyboard at a practical speed. The system serves as a viable tool for natural and affordable communication for handicapped aphasiacs through continuous finger language input.