Auditory Brainstem Response Threshold Estimation Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ABR testing for infants is time-consuming and incomplete due to the need for repeated stimuli and rejection of measurements with movement or vocalizations, leading to an incomplete diagnosis and additional clinic appointments.
Innovation Solution
A system and method using a fitted model to estimate hearing thresholds based on ABR response signals, where stimuli are presented, and the model is iteratively updated to reduce uncertainty, allowing for fewer presentation stimuli and improving diagnostic efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional ABR testing methods are used with repeated stimuli and averaging, then measurement precision is improved, but testing time and productivity deteriorate
Solution Approach 1:
The system performs preliminary actions by presenting a limited set of stimuli and using a fitted model to predict hearing thresholds across the full frequency range before completing traditional exhaustive testing. This preliminary estimation allows clinicians to identify likely hearing loss patterns early, reducing the need for extensive subsequent testing.
Solution Approach 2:
The system creates a fitted model that copies and generalizes from the limited ABR measurements obtained at specific frequencies to predict thresholds across the entire audible frequency spectrum. This mathematical copying approach allows inference of unmeasured frequencies from measured ones, significantly reducing testing requirements.
2Loss of information
If traditional ABR testing with many stimuli is used, then diagnostic completeness is improved, but loss of time increases
Solution Approach 1:
The system changes the approach from measuring all parameters (frequencies) directly to measuring a subset and using model fitting to infer the remaining parameters. By transforming the problem from direct measurement to parameter inference through mathematical modeling, the system maintains diagnostic completeness while reducing testing time.
Solution Approach 2:
The system performs partial action by testing only a subset of frequencies with a limited number of stimuli rather than exhaustively testing all frequencies. The fitted model compensates for the partial testing by predicting thresholds at untested frequencies, achieving adequate diagnostic information with reduced testing effort.
3Productivity
If fewer stimuli are presented to reduce testing time, then productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The fitted model acts as an intermediary between the limited ABR measurements and the predicted hearing thresholds across all frequencies. This mathematical intermediary processes the sparse measurements and generates comprehensive threshold estimates, bridging the gap between reduced data collection and maintained measurement accuracy.
Solution Approach 2:
The system transitions from direct one-to-one measurement (stimulus frequency to threshold frequency) to a many-to-many relationship through model fitting. The fitted model operates in the mathematical parameter space, allowing inference across the frequency dimension without requiring direct measurement at each frequency point.
Data Source
AI summary
Embodiments of the present disclosure provide methods, systems and non-transitory computer readable media of estimating hearing thresholds using auditory brainstem responses (ABR). An example method includes: presenting at least one stimulus to a subject; receiving first ABR signals responsive to the at least one stimulus; fitting a model to at least the first ABR signals to provide a fitted model; generating, using the fitted model, predicted hearing thresholds across a range of frequencies and uncertainty associated with the hearing thresholds; determining a next stimulus based, at least in part, on the uncertainty associated with the hearing thresholds; and presenting the next stimulus to the subject.