Advanced analytical techniques are gaining popularity in addressing complex classification type decision problems in many fields including healthcare and medicine. In this exemplary study, using digitized signal data, we developed predictive models employing three machine learning methods to diagnose an asthma patient based solely on the sounds acquired from the chest of the patient in a clinical laboratory. Although, the performances varied slightly, ensemble models (i.e., Random Forest and AdaBoost combined with Random Forest) achieved about 90% accuracy on predicting asthma patients, compared to artificial neural networks models that achieved about 80% predictive accuracy. Our results show that noninvasive, computerized lung sound analysis that rely on low-cost microphones and an embedded real-time microprocessor system would help physicians to make faster and better diagnostic decisions, especially in situations where x-ray and CT-scans are not reachable or not available. This study is a testament to the improving capabilities of analytic techniques in support of better decision making, especially in situations constraint by limited resources.

This study was conducted with randomized controlled and experimental design to examine the effect of breathing exercise on daytime sleepiness and fatigue on patients with obstructive sleep apnea syndrome. The first application was performed by teaching patients in the intervention group breathing exercises including diaphragmatic and pursed lip breathing via the face-to-face interview technique. Then, the researcher applied breathing exercises in the same patient group every morning/evening for 10–15 min and a total of 20–30 min for eight weeks via the online interview method. The data were collected via a questionnaire, Epworth sleepiness scale (ESS), and Piper Fatigue Scale (PFS). Chi-square, Student’s t, Mann Whitney U, paired sample t-test, analysis of variance (ANOVA) and generalized estimating equations were used to assess the data. It was determined that PFS total mean score of the intervention group which was 6.15 ± 1.65 before the application decreased to 5.34 ± 1.94 in the eighth week (p > 0.05) and PFS total mean score of the control group which was 5.59 ± 1.76 before the application increased to 5.77 ± 1.81 in the eighth week (p > 0.05). ESS total mean score of the intervention group which was 12.13 ± 4.34 at the baseline decreased to 9.13 ± 4.71 in the eighth week (p > 0.05) and ESS total mean score of the control group which was 10.37 ± 2.77 at the baseline increased to 10.5 ± 2.85 in the eighth week (p > 0.05). It was concluded that breathing exercise performed in the intervention group decreased the fatigue and daytime sleepiness mean scores of the patients at the end of the fourth and eighth week. In addition, the group-time interaction was significant, which was associated with the intervention group.