SLPOtherEar and hearing2020

Dynamically Masked Audiograms With Machine Learning Audiometry.

Katherine L Heisey, Alexandra M Walker, Kevin Xie and 2 others

PMID 33136643

WHAT IT FOUND

In 29 participants, automated masked hearing tests agreed closely with manual audiograms and were faster, especially with asymmetric hearing loss; the masking noise was usually undetected and not distracting.

Key findings

01For participants with highly asymmetric hearing loss, 90% of automated masked audiogram thresholds were expected to fall within 5–9 dB of manual audiogram thresholds.

02Automated masked audiograms estimated thresholds for both ears an average of 13.1 minutes faster than manual audiograms in participants whose hearing losses required masking.

03No masking failures were noted in 6200 tone deliveries.

STILL TO COME

How it was doneWhat they found

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.

Already have one?

What it does not show

Only 29 participants were tested, and two right ears were excluded because of a temporary equipment malfunction. Manual audiograms were performed by a student audiologist, so the speed comparison may not match an experienced clinician. No participant had an air-bone gap that required additional air-conduction masking, so that clinical scenario was not tested. The automated masked test used supra-aural headphones and a fixed 40 dB masking rule based on average interaural attenuation, not individual attenuation or insert earphones. The current implementation used 100 tone presentations per ear and a static 1.5-second response window, while test stopping criteria are still under research.

Declared interests

The supplied article text does not include a conflicts-of-interest statement. The supplied publication types indicate NIH and U.S. government research support.

The easy way to misread this

Do not conclude that this automated test can replace manual audiograms in all clinics. It was tested in only 29 participants, did not include patients with air-bone gaps requiring additional air-conduction masking, and manual testing was performed by a student audiologist.

Read it on PubMed →