EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Clinical XAI: A Tutorial on Concepts, Methods, and Modalities from Linear Models to LLMs

Munib Mesinovic, Tingting Zhu

ACM Computing Surveys · 30.11.2026 · 58 (15) · 1-36

DOI: 10.1145/3816420 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 21.08.2026. Verfasst von Munib Mesinovic und 1 weiteren Autor:innen. Die Arbeit nennt 224 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Explainable AI (XAI) in clinical risk prediction helps make applied machine learning models transparent and clinically accountable. This tutorial covers recent progress across EHR, text, imaging, genomics, and multimodal data, with a later focus on emerging large language model (LLM) systems. We aimed to standardise terminology and distinguish terms such as interpretability, explanation, fairness, bias, trust, and transparency. We also provide a decision map linking methods to evaluation requirements. We survey explainable clinical AI studies (2019–2024) and propose a scheme that distinguishes alignment with knowledge (AK), expert review (ER), decision impact (DI), workflow integration (WI), and patient-facing (PF) assessment. We find that SHAP with tree ensembles is the most popular method in tabular EHRs, attention and CAM methods are common in imaging, and saliency-plus enrichment testing in genomics. A minority of papers report clinician-involved validation, and reporting of rater agreement, calibration, and subgroup effects is inconsistent. We, thus, propose a tiered, modality-agnostic framework, comprising AK+ER as the minimum standard, followed by DI (accuracy, time, confidence), and then WI (usage, outcomes), and provide design checklists, metrics, and pitfalls. Our aim is a roadmap, grounded in clinical practice, for developing, stress-testing, and deploying XAI in risk prediction.

Zitieren

APA

Mesinovic, M., & Zhu, T. (2026). Clinical XAI: A Tutorial on Concepts, Methods, and Modalities from Linear Models to LLMs. ACM Computing Surveys, 58(15), 1-36. https://doi.org/10.1145/3816420

Vancouver

Mesinovic M, Zhu T. Clinical XAI: A Tutorial on Concepts, Methods, and Modalities from Linear Models to LLMs. ACM Computing Surveys. 2026;58(15):1-36. doi:10.1145/3816420

BibTeX
@article{Mesinovic2026,
  author = {Mesinovic, Munib and Zhu, Tingting},
  title = {Clinical XAI: A Tutorial on Concepts, Methods, and Modalities from Linear Models to LLMs},
  journal = {ACM Computing Surveys},
  year = {2026},
  volume = {58},
  number = {15},
  pages = {1--36},
  doi = {10.1145/3816420}
}
Kostenlos starten →