Segmentation and classification of capnograms: application in respiratory variability analysis.

Variability analysis of respiratory waveforms has been shown to provide key insights into respiratory physiology and has been used successfully to predict clinical outcomes. The current standard for quality assessment of the capnogram signal relies on a visual analysis performed by an expert in order to identify waveform artifacts. Automated processing of capnograms is desirable in order to extract clinically useful features over extended periods of time in a patient monitoring environment. However, the proper interpretation of capnogram derived features depends upon the quality of the underlying waveform. In addition, the comparison of capnogram datasets across studies requires a more practical approach than a visual analysis and selection of high-quality breath data. This paper describes a system that automatically extracts breath-by-breath features from capnograms and estimates the quality of individual breaths derived from them. Segmented capnogram breaths were presented to expert annotators, who labeled the individual physiological breaths into normal and multiple abnormal breath types. All abnormal breath types were aggregated into the abnormal class for the purpose of this manuscript, with respiratory variability analysis as the end-application. A database of 11,526 breaths from over 300 patients was created, comprising around 35% abnormal breaths. Several simple classifiers were trained through a stratified repeated ten-fold cross-validation and tested on an unseen portion of the labeled breath database, using a subset of 15 features derived from each breath curve. Decision Tree, K-Nearest Neighbors (KNN) and Naive Bayes classifiers were close in terms of performance (AUC of 90%, 89% and 88% respectively), while using 7, 4 and 5 breath features, respectively. When compared to airflow derived timings, the 95% confidence interval on the mean difference in interbreath intervals was ± 0.18 s. This breath classification system provides a fast and robust pre-processing of continuous respiratory waveforms, thereby ensuring reliable variability analysis of breath-by-breath parameter time series.

Disordered eating cognitions and behaviours among slimming organization competition winners.

BACKGROUND: Long-term success in weight loss treatments for obesity is elusive. The most widely used approach after diet books is slimming clubs. A percentage of members achieve dramatic and lasting weight losses. The study aimed to evaluate the prevalence of binge eating and unhealthy eating-related thought patterns among a group of highly successful weight losers. METHODS: Sixty-five slimming competition winners self reported their weight history and eating habits in a semi-structured questionnaire. The Eating Disorders Examination Questionnaire (EDE-Q) and the Emotional Eating Scale (EES) were also administered. RESULTS: Despite substantial weight loss (mean = 38%, SD = 10%) and widespread maintenance of losses, participants evidenced high levels of dietary restraint and weight, shape and eating overconcern. Emotional eating levels were significantly higher than those seen in noneating disordered populations on two of three subscales. Seventy-one per cent also reported bingeing in the past 3 months. CONCLUSIONS: Commercial slimming organizations should engage with broader psychological and behavioural features of obesity, including bingeing and eating-related cognitive patterns.