The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2447
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-10T00:01:50.768291Z
status: published
lens: p_space
sector: health
headline: Seeing the Gaps: Heatmaps, Metrics, and the Hidden Failures of Explainable AI in Dentomaxillofacial Radiology - A Systematic Review
dek: This systematic review aims to evaluate the techniques and reported patterns of heatmap-based visual explanations in deep learning (DL) systems for dental radiographic classification tasks. A literature search following PRISMA guidelines was conducted in PubMed, Scopus, IEEE Xplore Library, Oria.no and Google Scholar to retrieve studies using DL for dental classification tasks. Only articles with a visual explanation (heatmap) were selected. Risk of bias assessment was done with QUADAS-2, PROBAST-AI and CEBM. Th…
gain_title: (none)
problem_title: A systematic review of 136 dental radiograph AI studies found formal faithfulness testing of heatmap explanations was rarely done, so the heatmaps cannot be assumed to show how the model actually reasons.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: A systematic review of 136 dental radiograph AI studies found formal faithfulness testing of heatmap explanations was rarely done, so the heatmaps cannot be assumed to show how the model actually reasons.
problem_evidence: Formal faithfulness testing was rarely performed among the included studies. | explanations should not be assumed to accurately represent the model's underlying reasoning
quick_read: A systematic review of 136 studies on deep learning for dental radiograph classification examined the heatmaps researchers use to show what the AI is looking at. Grad-CAM was the most common technique, and the main reason for using heatmaps was to understand how the model makes decisions. Formal faithfulness testing was rarely performed, meaning few studies checked whether the heatmaps truly reflect the model's reasoning.

Some heatmaps matched established radiographic criteria, while others showed label-dependent patterns that sometimes emphasised irrelevant areas. Cropping images to the region of interest changed the visual explanations. Domain experts found the heatmaps plausible when they matched clinical knowledge, but the authors stress that plausibility is not the same as technical faithfulness.

The authors conclude the explanations remain insufficiently validated and call for evaluation metrics designed for dentomaxillofacial radiology. They also note an implausible heatmap does not necessarily mean the model has failed.
limitation: The review evaluated studies that were not primarily designed to assess visual explanations, which limits how directly their heatmap findings can be judged.
tag: Evidence-backed problem
key_points: The review covered 136 studies using deep learning for dental radiographic classification that included heatmap explanations. | Grad-CAM was the most commonly used heatmap technique. | The most common reason for using visual explanations was to understand the model's decision-making process. | Some heatmaps reflected established radiographic criteria; others showed label-dependent patterns that sometimes emphasised irrelevant areas. | Cropping to the region of interest influenced the visual explanations. | Formal faithfulness testing was rarely performed in the included studies. | The authors call for domain- and task-specific evaluation metrics for explainable AI in dentomaxillofacial radiology.
rundown: Searches followed PRISMA guidelines across PubMed, Scopus, IEEE Xplore Library, Oria.no and Google Scholar. Only studies using deep learning for dental classification tasks that included a heatmap visual explanation were selected. Risk of bias was assessed with QUADAS-2, PROBAST-AI and CEBM.

The authors analysed the heatmap technique, the reasons for including it, the explanations provided and the patterns seen. Heatmaps looked clinically plausible to domain experts when aligned with domain knowledge, but the review says that does not establish they faithfully represent model reasoning.

The authors say an implausible explanation does not necessarily indicate model failure, and recommend domain- and task-specific metrics for judging explainable AI in this field. No funding was received and the authors declared no competing interests.
sources:
- peer_reviewed | Dentomaxillofacial Radiology | https://doi.org/10.1093/dmfr/twag074 | 2026-11-07
prev: 0000000000000000000000000000000000000000000000000000000000000000

SHA-256 hash

34764f89d5c2c92f751f179243d5a3780ee21e46eabc4c696fdc9f07d1792f3a

Previous version’s hash

0000000000000000000000000000000000000000000000000000000000000000