What question did this study set out to answer?

This work aims to automate the threshold estimation of auditory brainstem responses (ABR) using a novel deep learning framework.

May 3, 20260 citations

Dynamic Time Warping-Aware Transformer for Automated Auditory Brainstem Response Thresholding

A Dynamic Time Warping-Aware Series-Temporal Transformer for Automated Thresholding of Auditory Brainstem Responses.

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates accurate auditory brainstem response thresholding in humans and mice, suggesting improved clinical practice.

This work aims to automate the threshold estimation of auditory brainstem responses (ABR) using a novel deep learning framework.
Developed the Dynamic Time Warping-Aware Series-Temporal Transformer (DTWA-STformer) for ABR analysis.
Utilized three pre-recorded datasets: large-scale human datasets and a public mouse dataset.
Implemented a multi-class classifier for threshold prediction after extracting temporal representations.
Achieved exact-match/±10 dB accuracies of 92.08%/99.31% (Dataset I), 90.35%/98.75% (Dataset II), 73.45%/99.27% (mouse click ABRs), and 60.85%/98.82% (mouse tone-pip ABRs).
Outperformed existing state-of-the-art methods for threshold estimation across both human and mouse data.

Liu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

May 3, 20260 citations

A Dynamic Time Warping-Aware Series-Temporal Transformer for Automated Thresholding of Auditory Brainstem Responses.

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates accurate auditory brainstem response thresholding in humans and mice, suggesting improved clinical practice.

This work aims to automate the threshold estimation of auditory brainstem responses (ABR) using a novel deep learning framework.
Developed the Dynamic Time Warping-Aware Series-Temporal Transformer (DTWA-STformer) for ABR analysis.
Utilized three pre-recorded datasets: large-scale human datasets and a public mouse dataset.
Implemented a multi-class classifier for threshold prediction after extracting temporal representations.
Achieved exact-match/±10 dB accuracies of 92.08%/99.31% (Dataset I), 90.35%/98.75% (Dataset II), 73.45%/99.27% (mouse click ABRs), and 60.85%/98.82% (mouse tone-pip ABRs).
Outperformed existing state-of-the-art methods for threshold estimation across both human and mouse data.

Liu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark