Bibliographic record
Abstract
Recent mobile and automated audiometry technologies have allowed for the democratization of hearing healthcare and enables non-experts to deliver hearing tests.The problem remains that a large number of such users are not trained to interpret audiograms.In this work, we outline the development of an intelligent audiogram classification system.More specifically, we present how a training dataset was collected, the development of the classification system relying on supervised learning, as well as other tools designed for the analysis of audiograms in large databases.Using a dedicated annotation tool developed specifically for this study, the Rapid Audiogram Annotation Environment, we collected hundreds of audiogram annotations from three licensed audiologists.Our analysis demonstrates that inter-rater reliability is substantial or better for classification of hearing loss configuration, symmetry, and severity, in spite of the subjective nature of the classification task.Furthermore, our results suggest that the agreement nonexistent for the identification of audiometric notches or potentially unreliable thresholds.The system proposed here achieves a performance comparable to the state of the art, but is significantly more flexible.Finally, we demonstrate qualitatively that a method based on density estimation with Gaussian mixture models is useful for the detection of potential reliability issues in audiograms.iiiFirst and foremost, I would like to express my gratitude to my research advisor, Prof. James Green, for his guidance, his support during the difficult times, and for his unwavering patience.I thank him for continuously pushing me to take an extra step out of my comfort zone so that I can see a little farther and a little clearer.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".