Research

Paper

AI LLM February 26, 2026

Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots

Authors

Dimitrios P. Panagoulias, Evangelia-Aikaterini Tsichrintzi, Georgios Savvidis, Evridiki Tsoureli-Nikita

Abstract

Human-in-the-loop validation is essential in safety-critical clinical AI, yet the transition between initial model inference and expert correction is rarely analyzed as a structured signal. We introduce a diagnostic alignment framework in which the AI-generated image based report is preserved as an immutable inference state and systematically compared with the physician-validated outcome. The inference pipeline integrates a vision-enabled large language model, BERT- based medical entity extraction, and a Sequential Language Model Inference (SLMI) step to enforce domain-consistent refinement prior to expert review. Evaluation on 21 dermatological cases (21 complete AI physician pairs) em- ployed a four-level concordance framework comprising exact primary match rate (PMR), semantic similarity-adjusted rate (AMR), cross-category alignment, and Comprehensive Concordance Rate (CCR). Exact agreement reached 71.4% and remained unchanged under semantic similarity (t = 0.60), while structured cross-category and differential overlap analysis yielded 100% comprehensive concordance (95% CI: [83.9%, 100%]). No cases demonstrated complete diagnostic divergence. These findings show that binary lexical evaluation substantially un- derestimates clinically meaningful alignment. Modeling expert validation as a structured transformation enables signal-aware quantification of correction dynamics and supports traceable, human aligned evaluation of image based clinical decision support systems.

Metadata

arXiv ID: 2602.22973
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-26
Fetched: 2026-02-27 04:35

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22973v1</id>\n    <title>Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots</title>\n    <updated>2026-02-26T13:11:58Z</updated>\n    <link href='https://arxiv.org/abs/2602.22973v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22973v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Human-in-the-loop validation is essential in safety-critical clinical AI, yet the transition between initial model inference and expert correction is rarely analyzed as a structured signal. We introduce a diagnostic alignment framework in which the AI-generated image based report is preserved as an immutable inference state and systematically compared with the physician-validated outcome. The inference pipeline integrates a vision-enabled large language model, BERT- based medical entity extraction, and a Sequential Language Model Inference (SLMI) step to enforce domain-consistent refinement prior to expert review. Evaluation on 21 dermatological cases (21 complete AI physician pairs) em- ployed a four-level concordance framework comprising exact primary match rate (PMR), semantic similarity-adjusted rate (AMR), cross-category alignment, and Comprehensive Concordance Rate (CCR). Exact agreement reached 71.4% and remained unchanged under semantic similarity (t = 0.60), while structured cross-category and differential overlap analysis yielded 100% comprehensive concordance (95% CI: [83.9%, 100%]). No cases demonstrated complete diagnostic divergence. These findings show that binary lexical evaluation substantially un- derestimates clinically meaningful alignment. Modeling expert validation as a structured transformation enables signal-aware quantification of correction dynamics and supports traceable, human aligned evaluation of image based clinical decision support systems.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-26T13:11:58Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Dimitrios P. Panagoulias</name>\n    </author>\n    <author>\n      <name>Evangelia-Aikaterini Tsichrintzi</name>\n    </author>\n    <author>\n      <name>Georgios Savvidis</name>\n    </author>\n    <author>\n      <name>Evridiki Tsoureli-Nikita</name>\n    </author>\n  </entry>"
}