PG-GECR: A provenance-gated hybrid expert system for auditable otoscopic classification and human-supervised referral
Array · 2026-12 · 32 · 101296
DOI: 10.1016/j.array.2026.101296 ↗At a glance
Journal article in Array, 2026-12. Written by Ankit Kumar Singh and 2 co-authors. 56 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Otoscopic artificial-intelligence studies can be distorted by duplicate images, acquisition-domain shortcuts, small minority classes, and overconfident predictions. This minor revision evaluates PG-GECR as a provenance-gated hybrid expert system for auditable image-level classification and an exploratory selective-referral rule. To align the evidentiary claim with provenance governance, the expert-only ROI branch is now designated the primary classifier; the 37 pseudo-labelled additions and their ROI fusion are retained only as exploratory training sensitivity because their incremental classification benefit was not statistically established. On 104 expert-labelled test images, the expert-only ROI classifier achieved 0.788 accuracy, 0.688 balanced accuracy, 0.677 macro F1, 0.862 macro AUC, and 0.598 MCC. CSOM recall remained 0.286 (2/7; exact 95% CI 0.037-0.710), while high ASOM discrimination remained inseparable from JPEG-ASOM acquisition confounding. A new post-review referral ablation isolated the conditional-latent branch: at the locked ROI threshold, ROI-only confidence/entropy gating retained 70/104 images at 88.6% accuracy and captured 63.6% of observed errors; adding latent-branch agreement/confidence/entropy retained 54/104 images at 94.4% accuracy and captured 86.4% of errors. At matched 51.9% coverage, ROI-only retention achieved 88.9% accuracy and 72.7% error capture versus 94.4% and 86.4% with latent consensus; these post hoc image-level findings are exploratory and do not establish clinical safety, particularly because neither of the two retained CSOM images under the full gate was correctly classified. A global 64-bit perceptual-hash audit of all 2,922 exact-unique auxiliary images found no cross-label near-duplicate component at Hamming distance
Cite
APA
Singh, A. K., Raghuvanshi, A. S., & Mehta, R. (2026). PG-GECR: A provenance-gated hybrid expert system for auditable otoscopic classification and human-supervised referral. Array, 32, 101296. https://doi.org/10.1016/j.array.2026.101296
Vancouver
Singh AK, Raghuvanshi AS, Mehta R. PG-GECR: A provenance-gated hybrid expert system for auditable otoscopic classification and human-supervised referral. Array. 2026;32:101296. doi:10.1016/j.array.2026.101296
BibTeX
@article{Singh2026,
author = {Singh, Ankit Kumar and Raghuvanshi, Ajay Singh and Mehta, Rupa},
title = {PG-GECR: A provenance-gated hybrid expert system for auditable otoscopic classification and human-supervised referral},
journal = {Array},
year = {2026},
volume = {32},
pages = {101296},
doi = {10.1016/j.array.2026.101296}
}
EUVIMED