Article

From Black Box to Discovery Engine: A Geometric and Topological Framework for Interpreting Graph Neural Networks in Critical Care

2025-08-11

Abstract excerpt

Effective clinical decision-making in critical care depends on interpreting complex, high-dimensional patient data. However, many advanced AI models function as uninterpretable “black boxes,” limiting their trustworthiness and scientific value. This study introduces NETWISE, a geometric and topological framework designed not for mere prediction, but for building a validated patient similarity network to serve as a...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 2c3cd001-ef0b-5d1c-9819-bf7b4b3abd7b
DOI: 10.1101/2025.08.06.25333083

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

From Black Box to Discovery Engine: A Geometric and Topological Framework for Interpreting Graph Neural Networks in Critical CareDOI 10.1101/2025.08.06.25333083Read

InfEHR: Resolving Clinical Uncertainty through Deep Geometric Learning on Electronic Health RecordsSemantic proximity Read

CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation using Graph Neural NetworksSemantic proximity Read

Topology and redescriptions detect multiple alternative biological pathways from clinical phenotypes.Semantic proximity Read

Constructing cancer-specific patient similarity network with clinical significanceSemantic proximity Read

NetFlow: A Framework to Explore Topological Representations of High-Dimensional Biomedical DataSemantic proximity Read

SyndromeKGNM: A Framework for TCM Syndrome Biomarker Discovery via Knowledge Graph Completion and Network MedicineSemantic proximity Read

RarePathAI: Predictive Analytics to Identify Rare Diseases in Real-World DataSemantic proximity Read

Multilayered validation of graph attention autoencoder–derived drug repurposing candidates for COVID-19Semantic proximity Read

Novel graph attention autoencoder framework with multilayered validation identifies drug repurposing candidates for COVID-19 treatmentSemantic proximity Read

Clustering rare diseases within an ontology-enriched knowledge graphSemantic proximity Read

Multi-layer guilt-by-association-based drug repurposing by integrating clinical knowledge on biological heterogeneous networksSemantic proximity Read