ECKO: Explainable Clinical Knowledge for Oncology

TL;DR

ECKO is a comprehensive, explainable knowledge graph integrating biomedical ontologies and data to support personalized oncology treatment decisions and enhance clinical understanding.

Contribution

The paper introduces ECKO, a novel knowledge graph that combines multiple biomedical ontologies and data sources for explainable, data-driven oncology applications.

Findings

Supports personalized drug recommendations with transparent explanations

Integrates 33 biomedical ontologies into a unified resource

Facilitates biomarker discovery and treatment optimization

Abstract

Personalized oncology aims to tailor treatment strategies to the unique molecular and clinical profiles of individual patients, moving beyond the traditional paradigm of treating the disease not the patient. Achieving this vision requires the integration and interpretation of vast, heterogeneous biomedical data within a meaningful scientific framework. Knowledge graphs, structured according to biomedical ontologies, offer a powerful approach to contextualize and interconnect diverse datasets, enabling more precise and informed clinical decision-making. We present ECKO (Explainable Clinical Knowledge for Oncology), a comprehensive knowledge graph that integrates 33 biomedical ontologies and aggregates data from multiple studies to create a unified resource optimized for data-driven clinical applications in oncology. Designed to support personalized drug recommendations, ECKO facilitates the identification of optimal therapeutic options by linking patient-specific molecular data to relevant pharmacological knowledge. It provides transparent, interpretable explanations for drug recommendations, fostering greater trust and understanding among clinicians and researchers. This resource represents a significant advancement toward explainable, scalable, and clinically actionable personalized medicine in oncology, with potential applications in biomarker discovery, treatment optimization, and translational research.