Search

The process of sleep stage identification is a labour-intensive task that involves the specialized interpretation of the polysomnographic signals captured from a patient’s overnight sleep session. Automating this task has proven to be challenging for data mining algorithms because of noise, complexity and the extreme size of data. In this paper we apply nonsmooth optimization to extract key features that lead to better accuracy. We develop a specific procedure for identifying K-complexes, a special type of brain wave crucial for distinguishing sleep stages. The procedure contains two steps. We first extract “easily classified” K-complexes, and then apply nonsmooth optimization methods to extract features from the remaining data and refine the results from the first step. Numerical experiments show that this procedure is efficient for detecting K-complexes. It is also found that most classification methods perform significantly better on the extracted features. [ABSTRACT FROM PUBLISHER]

The reported prevalence of interstitial lung disease in patients with rheumatoid arthritis has varied from 10% to 50%, yet less than 5% of patients with arthritis develop severe fibrosing interstitial lung disease. This suggests that subclinical disease may not always presage progressive disease. Bronchoalveolar lavage fluid from patients with rheumatoid arthritis and either clinically evident interstitial lung disease or subclinical disease was examined for the presence of factors with a putative role in the development of interstitial fibrosis. Patients with subclinical disease were identified by prospective radiographic and lung function screening of 93 patients with rheumatoid arthritis. Fourteen patients were identified in this manner and an association between subclinical disease and smoking history was noted. Eleven patients with established interstitial lung disease had increased neutrophils (p less than 0.05), collagenase, and type III procollagen N terminal peptide levels (p less than 0.01) in the bronchoalveolar lavage fluid. Preliminary characterisation of the bronchoalveolar lavage collagenase suggested that it originated from neutrophils. Ten patients with subclinical interstitial lung disease underwent bronchoalveolar lavage. Of these, one had increased neutrophils and two had increased collagenase concentrations--abnormalities associated with advanced interstitial lung disease and a poor prognosis. These results suggest that in arthritis patients with evidence of subclinical pulmonary interstitial disease bronchoalveolar lavage might be useful in identifying those who may require careful monitoring in the hope that early treatment will prevent severe fibrosis. [ABSTRACT FROM PUBLISHER]