Should AI models be explainable to clinicians?
In the high-stakes realm of critical care, where daily decisions are crucial and clear communication is paramount, comprehending the rationale behind Artificial Intelligence (AI)-driven decisions appears essential. While AI has the potential to improve decision-making, its complexity can hinder comprehension and adherence to its recommendations. "Explainable AI" (XAI) aims to bridge this gap, enhancing confidence among patients and doctors. It also helps to meet regulatory transparency requirements, offers actionable insights, and promotes fairness and safety. Yet, defining explainability and standardising assessments are ongoing challenges and balancing performance and explainability can be needed, even if XAI is a growing field.
Authors
- Zaineb Chelly Dagdia (ORCID: https://orcid.org/0000-0002-2551-6586)
- Karine Zeitouni (ORCID: https://orcid.org/0000-0002-5602-6942)
- G. Abgrall (ORCID: https://orcid.org/0000-0002-7150-6346)
- Andre L. Holder (ORCID: https://orcid.org/0000-0003-2635-3923)
- Xavier Monnet (ORCID: https://orcid.org/0000-0001-6820-2678)
Institutions
- Emory University (US)
- Inserm (FR)
- Université de Versailles Saint-Quentin-en-Yvelines (FR)
- Université Paris-Saclay (FR)
- Centre Hospitalier Universitaire de Grenoble (FR)
- Assistance Publique – Hôpitaux de Paris (FR)
- Hôpital Marie Lannelongue (FR)
- Hôpital Paris Saint-Joseph (FR)
- Université Gustave Eiffel (FR)
- Bicêtre Hospital (FR)
- Données et algorithmes pour une ville intelligente et durable (FR)
Publication Details
- Journal
- Critical Care
- Published
- 2024-09-12
- DOI
- https://doi.org/10.1186/s13054-024-05005-y
- Citations
- 117
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 40.64
Funders
- Fondation pour la Recherche Médicale
- Société de Réanimation de Langue Française