Speech Signal Parameters as Biomarkers for Remote Monitoring of Patients with Chronic Heart Failure.
Level 3 - non-randomized controlled study
Non-randomized prospective cohort study with a healthy control group.
PubMed 41531354 · doi:10.18087/cardio.2025.12.n3038
What was done
Researchers analyzed acoustic and prosodic speech parameters in 55 patients with chronic heart failure (CHF) during acute exacerbation, re-evaluating 38 of these patients after treatment during remission. Results were compared against a control group of 57 apparently healthy individuals using Praat software to measure fundamental frequency parameters, jitter, shimmer, harmonic-to-noise ratio, and voiced frame ratios.
What was found
Patients with CHF before treatment demonstrated voice frequency and amplitude instability compared to healthy controls. Following treatment, Jitter (local) significantly decreased (p=0.012) and no longer differed significantly from healthy controls. The Bowley skew index significantly increased (p=0.041), approaching control values (p=0.068). In contrast, Shimmer (dda) and Shimmer (apq3) indexes did not show significant improvement and remained significantly different from controls. Specific baseline and post-treatment numerical acoustic values were not reported in the abstract.
Why it matters
Certain speech signal characteristics, particularly jitter and pitch asymmetry, fluctuate with clinical status in CHF and normalize with clinical improvement, suggesting potential utility as non-invasive biomarkers for remote post-discharge monitoring.
Limits
The abstract does not report baseline demographic characteristics, CHF etiology, ejection fraction, or specific medical regimens. Sample size was modest with substantial attrition between exacerbation (n=55) and remission (n=38). Exact quantitative baseline and follow-up values for acoustic parameters are omitted, and clinical diagnostic accuracy metrics (e.g., sensitivity, specificity) were not evaluated.