Characterizing Vocal Hyperfunction Using Ecological Momentary Assessment of Relative Fundamental Frequency.
Ahsan J Cheema, Katherine L Marks, Hamzeh Ghasemzadeh and 3 others
PMID 39675944WHAT IT FOUND
Neck-sensor voice monitoring distinguished patients with phonotraumatic vocal hyperfunction from healthy controls in daily life, with better accuracy than in the lab.
It did not separate those with muscle tension dysphonia. The sensor also failed to track patients' self-reported vocal effort in real-world settings.
Key findings
01In-field accelerometer RFF values distinguished patients with phonotraumatic vocal hyperfunction (PVH) from controls with higher accuracy (81.3%) than in-lab measures (68.3%).
02RFF values from individual cycles failed to distinguish patients with non-phonotraumatic vocal hyperfunction (NPVH) from controls, though a machine learning model using multiple in-field tokens achieved greater-than-chance accuracy (62.5%).
03There was no clear relationship between RFF values and self-reported vocal effort in daily life, with regression models showing poor predictive power.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study relied on a specific /afa/ task, which may not reflect the vocal demands or effort of natural conversation. Sample sizes were unequal between PVH and NPVH groups, particularly in the NPVH control pool. Self-reported effort was measured on a continuous 0-100 scale, which may have introduced noise or overfitting in the regression models. The accelerometer-based RFF values showed bias compared to microphone-based standards, though internal comparisons were consistent. Participant adherence to hourly prompts and task execution was challenging in real-world environments.
Declared interests
The authors declared financial interests and personal relationships that may be considered potential competing interests, but the specific details of these declarations were truncated in the provided text.
The easy way to misread this
Do not interpret the successful classification of PVH patients as evidence that RFF measures can quantify vocal effort. The study explicitly found no clear relationship between RFF values and self-reported effort, meaning the sensor tracks vocal fold behavior but not the patient's subjective experience of strain.