A historical perspective of biomedical explainable AI research

[EN] The black-box nature of most artificial intelligence (AI) models encourages the development of explainability methods to engender trust into the AI decision-making process. Such methods can be broadly categorized into two main types: post hoc explanations and inherently interpretable algorithms...

Descripción completa

Detalles Bibliográficos
Autores: Malinverno, Luca, Barros, Vesna, Ghisoni, Francesco, Visonà, Giovanni, Kern, Roman, Nickel, Philip J., Ventura, Barbara Elvira, Simic, Ilija, Stryeck, Sarah, Manni, Francesca, Jean-Quartier, Claire, Genga, Laura, Schweikert, Gabriele, Lovric, Mario, Ferri Ramírez, César|||0000-0002-8975-1120
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/212440
Acceso en línea:https://riunet.upv.es/handle/10251/212440
Access Level:acceso abierto
Palabra clave:Artificial intelligence (AI)
Black-box
Explainability
Trust
Decision-making process
Post hoc explanations
Inherently interpretable algorithms
COVID-19
LENGUAJES Y SISTEMAS INFORMATICOS
Descripción
Sumario:[EN] The black-box nature of most artificial intelligence (AI) models encourages the development of explainability methods to engender trust into the AI decision-making process. Such methods can be broadly categorized into two main types: post hoc explanations and inherently interpretable algorithms. We aimed at analyzing the possible associations between COVID-19 and the push of explainable AI (XAI) to the forefront of biomed-ical research. We automatically extracted from the PubMed database biomedical XAI studies related to con-cepts of causality or explainability and manually labeled 1,603 papers with respect to XAI categories. To compare the trends pre-and post-COVID-19, we fit a change point detection model and evaluated significant changes in publication rates. We show that the advent of COVID-19 in the beginning of 2020 could be the driving factor behind an increased focus concerning XAI, playing a crucial role in accelerating an already evolving trend. Finally, we present a discussion with future societal use and impact of XAI technologies and potential future directions for those who pursue fostering clinical trust with interpretable machine learning models.

Similares en LA Referencia