{
  "id": 529,
  "url": "https://arxiv.org/abs/2606.27973v1",
  "title": "From Black-Box to Clinical Insight: A Multi-Stage Explainable Framework for Speech-Based Cognitive Impairment Detection",
  "summary": "Speech-based cognitive impairment detection offers a noninvasive, accessible alternative to costly biomarker assays, yet transformer-based models remain clinically uninterpretable. We propose a multi-stage explainability framework that translates black-box transformer predictions into clinically grounded narratives by integrating SHapley Additive exPlanations (SHAP)-based token attribution, theory-informed linguistic features, and a four-stage LLM reasoning pipeline using LLaMA-3.1-70B-Instruct.",
  "authors": "Yasaman Haghbin, Sina Rashidi, Ali Zolnour, Fatemeh Taherinezhad, Ali Fartoot, Hossein Azadmaleki et al.",
  "category": "research",
  "topics": "healthcare,transparency",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-26T11:21:42.000Z",
  "fetched_at": "2026-07-14T14:14:37.246Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/529",
  "original_url": "https://arxiv.org/abs/2606.27973v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}