A wheeze recognition algorithm for practical implementation in children.

BACKGROUND: The detection of wheezes as an exacerbation sign is important in certain respiratory diseases. However, few highly accurate clinical methods are available for automatic detection of wheezes in children. This study aimed to develop a wheeze detection algorithm for practical implementation in children. METHODS: A wheeze recognition algorithm was developed based on wheezes features following the Computerized Respiratory Sound Analysis guidelines. Wheezes can be detected by auscultation with a stethoscope and using an automatic computerized lung sound analysis. Lung sounds were recorded for 30 s in 214 children aged 2 months to 12 years and 11 months in a pediatric consultation room. Files containing recorded lung sounds were assessed by two specialist physicians and divided into two groups: 65 were designated as "wheeze" files, and 149 were designated as "no-wheeze" files. All lung sound judgments were agreed between two specialist physicians. We compared wheeze recognition between the specialist physicians and using the wheeze recognition algorithm and calculated the sensitivity, specificity, positive predictive value, and negative predictive value for all recorded sound files to evaluate the influence of age on the wheeze detection sensitivity. RESULTS: The detection of wheezes was not influenced by age. In all files, wheezes were differentiated from noise using the wheeze recognition algorithm. The sensitivity, specificity, positive predictive value, and negative predictive value of the wheeze recognition algorithm were 100%, 95.7%, 90.3%, and 100%, respectively. CONCLUSIONS: The wheeze recognition algorithm could identify wheezes in sound files and therefore may be useful in the practical implementation of respiratory illness management at home using properly developed devices.

Wheeze sound characteristics are associated with nighttime sleep disturbances in younger children.

BACKGROUND: Wheezing is a typical symptom of respiratory conditions. Few objective methods are available for predicting sleep disturbance in young children with wheezing. OBJECTIVE: We investigated whether wheezing characteristics, detected by lung-sound analysis, were associated with risk of sleep disturbance. METHODS: We recorded the lung sounds of 66 young children (4-59 months) every morning, for the entire duration of a wheezing episode. On lung-sound analysis, wheezing was displayed as horizontal bars of intensity with corresponding sharp peaks of power. The sharp peak of power was defined as a wheeze band. Wheezing characteristics (e.g., number, frequency, duration, and frequency of maximum intensity of wheeze bands) were analyzed using lung-sound analysis. Patients were divided into 3 groups based on sleep disturbance on the first night after wheezing was recorded: mild group (no sleep disturbance and disappearance of wheezing within 2 days), moderate group (no sleep disturbance but disappearance of wheezing after 3 or more days), and severe group (sleep disturbance and disappearance of wheezing after 3 or more days). Wheezing characteristics on the first morning were compared among the 3 groups based on sleep disturbance on the first night. RESULTS: The highest frequency, the frequency of maximum intensity, and the number of wheeze bands per 30 seconds were significantly higher in the severe group than in the mild group (p < 0.005, p < 0.005, p < 0.001, respectively). The number of wheeze bands per 30 seconds was a predictor of nighttime sleep disturbance, with a cutoff value of 11.1. The sensitivity, specificity, and positive- and negative-predictive values were 100%, 65%, 32%, and 100% (p < 0.001), respectively, with an area under the curve of 0.86 ± 0.05. CONCLUSIONS: The number of wheeze bands per 30 seconds on lung-sound analysis was a useful indicator of risk of prolonged exacerbation.