Leveraging knowledge for explainable AI in personalized cancer treatment: challenges and future directions

Integrating multi-modal patient data to support personalized medicine has gained a lot of interest across different health domains over the past decade. Addressing this challenge requires the development and implementation of an informed, evidence-based AI-driven decision-support system continuously maintained and updated to align with the latest clinical guidelines. A key challenge to ensure its real-life adoption lies in translating the outcomes of complex AI-driven data integration and modeling into a form easily understood by the clinical audience. To ensure explainability, knowledge graphs have emerged as data models integrating multi-omics data sources and representing them as interconnected networks. Knowledge graphs offer a framework which AI models can progressively refine, highlighting the most influential features and relationships facilitating transparency of complex interactions and interdependencies. In this perspective we present major components and challenges upon developing a knowledge-based explainable AI system. Additionally, we showcase a current effort undertaken by the Knowledge at the Tips of your Fingers (KATY) consortium to develop the infrastructure for an explainable system supporting best treatment decision for a renal cancer patient.

Authors

Institutions

Publication Details

Journal
Frontiers in Digital Health
Published
2025-09-29
DOI
https://doi.org/10.3389/fdgth.2025.1637195
Citations
2
Primary Topic
Bioinformatics and Genomic Networks
Type
article
Field-Weighted Citation Impact
1.61

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Leveraging knowledge for explainable AI in personalized cancer treatment: challenges and future directions

Delphine Pflieger, Patrícia Eugénio, Dimitrios Varvaras, Steven McGinn et al.
2 citations
Frontiers in Digital Health
Bioinformatics and Genomic Networks
1.61
article

Leveraging knowledge for explainable AI in personalized cancer treatment: challenges and future directions

Delphine Pflieger, Patrícia Eugénio, Dimitrios Varvaras, Steven McGinn, Yuri Gordienko, In Hwa Um, Francisco Lupiáñez‐Villanueva, Javier A. Alfaro, Laura Balbi, Paolo Garagnani, Emilia Daghir‐Wojtkowiak, Riccardo Leoni, Nikolaus Forgó, Roberta Bernardini, Ana Roca‐Umbert, Stéphane Gazut, Francesco Bonchi, Piyush Borole, Georges Bedran, Laurent Guyon, Maria Gazouli, Aleksander Pałkowski, Fabio Massimo Zanzotto, Marta Contreiras Silva, Assilah Bouzit, Pavlos Golnas, Jean‐Alexandre Long, Cátia Pesquita, Marie-Catherine Wagner, Francesco Maiorino, Elisa Zago, Saverio Gravina, Christophe Battail, Mario Reyes de los Mozos, Hector Katifelis, Stefan Nicholas Symeonides, Elena Verzoni, Sergii Stirenko, Georg Wölflein, Giuseppe Procopio, Septi Mariani, Liangwei Yin, Armando Stellato, David J. Harrison, Valentina Guadalupi, Maurizio Mattei, Francesco Torino, Håkan Axelson, Pierluigi Bove, Juan Caubet, Florian Jeanneret, Mario Roselli, Daniel Faria, Rosella Cicconi, Carla Montesano, Ajitha Rajan, Kyriakos Souliotis, Nikolas Dovrolis, Liana Bevilacqua, Mark Stares, Ted R. Hupp, Odile Filhol-Cochet, Chiara Cipriani, Susana Nunes, Katarzyna Barud, Pauline Bazelle, Yamir Moreno, Dmitri Koroliouk, Ashwin Adrian Kallor, Peter Thorpe, Alexander Laird, Frans Folkvord, Sarah Schoch, Luciano Xumerle, Davide Venditti, Rohit Kumar, Manuel Fiorelli, Francisco Serrano, Michał Waleron, Saskia Kaltenbrunner, Anne Boland, Christina Golna, J Descotes, Jean‐François Deleuze, Michele Mastromattei, Aria Nourbaksh, Camille Ducki, Etienne Bardet, Damien Alouges, Elodine Coquelet, Apolline Bacquet, Simona Brezar, Heiko Poth, Andraz Krajnc, Sandra Türk
article en
2 citations

Abstract

Integrating multi-modal patient data to support personalized medicine has gained a lot of interest across different health domains over the past decade. Addressing this challenge requires the development and implementation of an informed, evidence-based AI-driven decision-support system continuously maintained and updated to align with the latest clinical guidelines. A key challenge to ensure its real-life adoption lies in translating the outcomes of complex AI-driven data integration and modeling into a form easily understood by the clinical audience. To ensure explainability, knowledge graphs have emerged as data models integrating multi-omics data sources and representing them as interconnected networks. Knowledge graphs offer a framework which AI models can progressively refine, highlighting the most influential features and relationships facilitating transparency of complex interactions and interdependencies. In this perspective we present major components and challenges upon developing a knowledge-based explainable AI system. Additionally, we showcase a current effort undertaken by the Knowledge at the Tips of your Fingers (KATY) consortium to develop the infrastructure for an explainable system supporting best treatment decision for a renal cancer patient.

Frontiers in Digital HealthVol. 7
University of Rome Tor Vergata (IT), University of Vienna (AT), NHS Lothian (GB), Universitat Oberta de Catalunya (ES), University of Lisbon (PT), Inserm (FR), University of St Andrews (GB), Lund University (SE), National and Kapodistrian University of Athens (GR), National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” (UA), Universidad de Zaragoza (ES), Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR), Université Paris-Saclay (FR), Western General Hospital (GB), Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute (DE), Centre Hospitalier Universitaire de Grenoble (FR), Edinburgh Cancer Research (GB), CEA Grenoble (FR), University of Gdańsk (PL), Centre National de Recherche en Génomique Humaine (FR), Centre Tecnologic de Telecomunicacions de Catalunya (ES), Predict (France) (FR), University Mental Health Research Institute (GR), MassTech (United States) (US), CEA Paris-Saclay (FR), Kranj School Centre (SI), Fondazione IRCCS Istituto Nazionale dei Tumori (IT), Université Grenoble Alpes (FR), University of Edinburgh (GB)
European Commission, Infrastruktura PL-Grid, Horizon 2020 Framework Programme, Academic Computer Centre Cyfronet, AGH University of Science and Technology
Openalex Percentile: Top 15%
Bioinformatics and Genomic Networks
1.61
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.