Graph–Neurosymbolic Neural Networks for Trustworthy Clinical Decision Support

Oluwatobi Noah Akande, Amil Misra, Abidemi Adeniyi, Qurrat Ul Ain Mughal, Dagogo Godwin Orifama
Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, PMLR 319:244-263, 2026.

Abstract

We propose a Graph–Neurosymbolic Framework for Trustworthy Clinical Decision Support that integrates graph-based neural learning with formal symbolic medical reasoning. Patients and clinical entities are represented as a heterogeneous clinical graph; domain knowledge encoded as first-order logic and Horn-clause rules explicitly constrains graph construction, neural message passing, and inference. The framework is evaluated on MIMIC-IV and eICU-CRD, demonstrating competitive predictive performance while substantially reducing clinical rule violations, producing high-fidelity rule-consistent explanations, and exhibiting improved robustness under distribution shift across institutions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v319-akande26a, title = {Graph–Neurosymbolic Neural Networks for Trustworthy Clinical Decision Support}, author = {Akande, Oluwatobi Noah and Misra, Amil and Adeniyi, Abidemi and Mughal, Qurrat Ul Ain and Orifama, Dagogo Godwin}, booktitle = {Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments}, pages = {244--263}, year = {2026}, editor = {Folorunso, Sakinat and Ogundokun, Roseline and Oladipo, Francisca}, volume = {319}, series = {Proceedings of Machine Learning Research}, month = {11--14 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v319/main/assets/akande26a/akande26a.pdf}, url = {https://proceedings.mlr.press/v319/akande26a.html}, abstract = {We propose a Graph–Neurosymbolic Framework for Trustworthy Clinical Decision Support that integrates graph-based neural learning with formal symbolic medical reasoning. Patients and clinical entities are represented as a heterogeneous clinical graph; domain knowledge encoded as first-order logic and Horn-clause rules explicitly constrains graph construction, neural message passing, and inference. The framework is evaluated on MIMIC-IV and eICU-CRD, demonstrating competitive predictive performance while substantially reducing clinical rule violations, producing high-fidelity rule-consistent explanations, and exhibiting improved robustness under distribution shift across institutions.} }
Endnote
%0 Conference Paper %T Graph–Neurosymbolic Neural Networks for Trustworthy Clinical Decision Support %A Oluwatobi Noah Akande %A Amil Misra %A Abidemi Adeniyi %A Qurrat Ul Ain Mughal %A Dagogo Godwin Orifama %B Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments %C Proceedings of Machine Learning Research %D 2026 %E Sakinat Folorunso %E Roseline Ogundokun %E Francisca Oladipo %F pmlr-v319-akande26a %I PMLR %P 244--263 %U https://proceedings.mlr.press/v319/akande26a.html %V 319 %X We propose a Graph–Neurosymbolic Framework for Trustworthy Clinical Decision Support that integrates graph-based neural learning with formal symbolic medical reasoning. Patients and clinical entities are represented as a heterogeneous clinical graph; domain knowledge encoded as first-order logic and Horn-clause rules explicitly constrains graph construction, neural message passing, and inference. The framework is evaluated on MIMIC-IV and eICU-CRD, demonstrating competitive predictive performance while substantially reducing clinical rule violations, producing high-fidelity rule-consistent explanations, and exhibiting improved robustness under distribution shift across institutions.
APA
Akande, O.N., Misra, A., Adeniyi, A., Mughal, Q.U.A. & Orifama, D.G.. (2026). Graph–Neurosymbolic Neural Networks for Trustworthy Clinical Decision Support. Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, in Proceedings of Machine Learning Research 319:244-263 Available from https://proceedings.mlr.press/v319/akande26a.html.

Related Material