Photo Credit: imakr
The following is a summary of “Assessing the Clinical and Functional Status of COPD Patients Using Speech Analysis During and After Exacerbation,” published in the January 2025 issue of Pulmonology by Mayr et al.
Researchers conducted a retrospective study using machine learning analysis of speech to classify the disease severity of chronic obstructive pulmonary disease (COPD).
They recruited non-consecutive patients with COPD from a single center to compare speech characteristics during and after acute COPD exacerbations. A set of spectral, prosodic, and temporal variability features were extracted and used as input for a support vector machine (SVM). The baseline for predicting patient state was an SVM model based on self-reported BORG and COPD Assessment Test (CAT) scores.
The results showed the speech analysis outperformed BORG and CAT scores in distinguishing between exacerbation status, achieving 84% accuracy in prediction for 50 patients with COPD (52% males, 22% GOLD II, 44% GOLD III, 32% GOLD IV, all group E). The CAT scores were linked to reading rhythm, while BORG scales correlated with articulation stability. Pulmonary function testing (PFT) was associated with speech pause rate and rhythm variability.
Investigators concluded that speech analysis might have the potential to serve as a viable technology for classifying COPD status, enabling novel approaches for remote disease monitoring.
