COPD severity classification using principal component and cluster analysis on HRV parameters

Chronic obstructive pulmonary disease severity analysis using deep learning on multi-channel lung sounds

“…Though the use of image processing requires much computation power, they achieved a low classification accuracy. Several studies They identified five COPD severities with higher accuracy rates than 88% using principal component analysis and cluster analysis [11]. Whereas HRV measurements are decisive features for cardiac disorders, they act as supportive diagnostics, not a definitive diagnostic tool for respiratory diseases.…”

“…Newandee et al proposed a method that was based on heart rate variability (HRV) measurements to diagnose COPD. They classified COPD and non-COPD subjects using principal component analysis and clustering algorithms [11]. Altan et al proposed a nonlinear method to quantize consecutive differences of the data points on lung sounds.…”

“…However, spirometric measurements and physical examination assessments can be misleading since their high dependency on the medical device and staff. Whereas some studies directly focused on clinical data, a limited number of them used clinical data as additional features[10,11].Kanwade and Bairagi analyzed EMG signals related to chest movements, along with breathing. They received clinical data as additional features.…”

Nighttime features derived from topic models for classification of patients with COPD

“…In the encoding step, we processed each sensor data sequence Sn assigning a symbol to each 1-min data sample. METs data were encoded with the symbols S, VL, L and MV using the thresholds and intensity categories (IC) proposed by the American College of Sports Medicine [13]: very light intensity (VL), < 2.0 METs; light intensity (L), 2.0 to 2.9 METs; moderate-to-vigorous intensity (MV), ≥ 3.0 METs. Epochs marked by the activity monitor as sleeping and with METs < 2.0 formed a separate category named sleeping (S).…”

“…Arpaia et al [12] proposed a method based on particle swarm optimization to predict the condition of a subject with COPD from clinical parameters monitored monthly for one year. Newandee et al [13] applied cluster analysis to identify the most severe patients with COPD in a mixture of healthy and COPD population for which heart rate, blood pressure, and respiration signals were recorded. Results demonstrated that these two groups could be differentiated with 99.0% accuracy.…”