analiza aiqbench
NEURON addresses the critical barrier of explainability in clinical AI by integrating neuro-symbolic methods with SNOMED CT ontologies and LLMs to generate trustworthy, human-aligned interpretations for high-stakes medical decisions. This approach successfully bridges raw data gaps while improving predictive accuracy on Acute Heart Failure mortality prediction compared to standard feature attribution techniques. The system represents a significant engineering step toward deploying reliable AI in connected health environments where narrative transparency is non-negotiable.
NEURON: A Neuro-symbolic System for Grounded Clinical Explainability
arXiv:2605.01189v3 Announce Type: replace Abstract: Clinical AI adoption is hindered by the black-box/grey-box nature of high-performing models, which lack the ontological grounding and narrative transparency required for professional-level explainability. We present NEURON, a neuro-symbolic system designed to enhance both predictive reliability and clinical interpretability. NEURON integrates SNOMED CT ontology-informed structural representations with machine learning models to bridge the gap between raw data and medical nomenclature. To facilitate human-aligned interaction, the system utilizes a Retrieval-Augmented Generation (RAG) grounded Large Language Model (LLM) layer to synthesize SHAP feature attributions and patient-specific clinical notes into coherent, natural-language explanations. Validated on the MIMIC-IV dataset for Acute Heart Failure mortality prediction, NEURON improved the AUC from 0.71-0.74 to 0.74-0.77 and substantially outperformed SHAP-based explanations in human-aligned metrics (0.807 vs. 0.558). Our results demonstrate that NEURON offers a robust, scalable engineering solution for deploying trustworthy, human-centered connected health applications.
Abstract:Clinical AI adoption is hindered by the black-box/grey-box nature of high-performing models, which lack the ontological grounding and narrative transparency required for professional-level explainability. We present NEURON, a neuro-symbolic system designed to enhance both predictive reliability and clinical interpretability. NEURON integrates SNOMED CT ontology-informed structural representations with machine learning models to bridge the gap between raw data and medical nomenclature. To facilitate human-aligned interaction, the system utilizes a Retrieval-Augmented Generation (RAG) grounded Large Language Model (LLM) layer to synthesize SHAP feature attributions and patient-specific clinical notes into coherent, natural-language explanations. Validated on the MIMIC-IV dataset for Acute Heart Failure mortality prediction, NEURON improved the AUC from 0.71-0.74 to 0.74-0.77 and substantially outperformed SHAP-based explanations in human-aligned metrics (0.807 vs. 0.558). Our results demonstrate that NEURON offers a robust, scalable engineering solution for deploying trustworthy, human-centered connected health applications.
Artificial Intelligence (cs.AI)
arXiv:2605.01189 [cs.AI]
(or arXiv:2605.01189v3 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.01189 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 230 cuvinte
Subiecte conexe
Neuro-Symbolic Participation Governance for Verifiable AI Agents in Open Digital Twin Ecosystems
arXiv · 5 aug. 2026
Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective
arXiv · 2 sept. 2026
Academia is for Ambition — Alex Zhang, MIT
Latent Space · 2 oct. 2026
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
arXiv · 28 iul. 2026