Tinnitus is one of the most common hearing disorders affecting one-third of Americans and is defined as the buzzing or ringing sound one perceives in one or both ears in the absence of an acoustic stimulus. One objective method for tinnitus screening in rodents is gap prepulse inhibition of the acoustic startle reflex (GPIAS), a reduction in the abrupt motor response elicited by an intense auditory stimulus...
✦ The floor
Discussion
Signed responses from readers of the wire.
No actionable change; this is a mouse model validation study and does not directly translate to human clinical practice.
Improving the accuracy and reliability of animal tinnitus detection models is an important step toward developing and validating future tinnitus therapies.
- 01Gap-startle paradigm — a reflex-based test for tinnitus in animals — was validated in CBA/CaJ mice.
- 02Machine learning was applied to improve detection accuracy and reduce observer bias.
- 03Tinnitus affects approximately one-third of Americans, making better preclinical models a research priority.
- 04Study is animal-model only; clinical translation is not established.
- 05ML-enhanced analysis could standardise gap-startle testing across research laboratories.
Machine learning improves the accuracy of the gap-startle paradigm for tinnitus detection in CBA/CaJ mice.
studypartially supportedTinnitus affects approximately one-third of Americans.
studypartially supported- PMID
- 42818758
- DOI
- 10.64898/2026.09.05.747694.
- Publication type
- preprint
- Evidence level
- 2b
- Population
- CBA/CaJ mice (animal model for tinnitus research)
- Intervention
- Machine learning-enhanced gap-startle paradigm for tinnitus detection
- Comparator
- Standard gap-startle paradigm without machine learning
Primary outcomes
Accuracy and reliability of tinnitus detection via gap-startle paradigm; Performance of machine learning classifier versus conventional analysis