analiza aiqbench
MedGate-Fusion demonstrates a practical application of transformer-based embeddings to synthesize unstructured clinical narratives with structured biomarkers for prospective stroke risk prediction. By employing dictionary-based redaction to mitigate target leakage, the study addresses critical data integrity challenges inherent in integrating electronic health record text with physiological markers. This work advances the field of medical AI by validating multi-modal architectures on large-scale primary care datasets for long-term outcome stratification.
MedGate-Fusion: Integrating First-Encounter Semantic Narratives and Physiological Biomarkers for Prospective Stroke Risk Stratification
arXiv:2609.25272v1 Announce Type: new Abstract: Prospective stroke risk stratification in primary care is challenging because early risk signals are distributed across routine biomarkers and unstructured clinical narratives. We propose MedGate-Fusion, a multi-modal gated architecture that integrates transformer-based embeddings of first-encounter narratives with ten routinely recorded risk markers. We used electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Starting from 808,921 encounter-level observations, we constructed a first-encounter cohort and retained 102,736 unique patient records with non-empty narratives and sufficient data to evaluate a five-year stroke outcome. To reduce explicit target leakage from diagnostic mentions in notes, we applied dictionary-based redaction of stroke-related terms prior to semantic encoding.
Abstract:Prospective stroke risk stratification in primary care is challenging because early risk signals are distributed across routine biomarkers and unstructured clinical narratives. We propose MedGate-Fusion, a multi-modal gated architecture that integrates transformer-based embeddings of first-encounter narratives with ten routinely recorded risk markers. We used electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Starting from 808,921 encounter-level observations, we constructed a first-encounter cohort and retained 102,736 unique patient records with non-empty narratives and sufficient data to evaluate a five-year stroke outcome. To reduce explicit target leakage from diagnostic mentions in notes, we applied dictionary-based redaction of stroke-related terms prior to semantic encoding.
7 pages,2 tables, 2 figures. Submitted to EMBC 2026
Artificial Intelligence (cs.AI)
arXiv:2609.25272 [cs.AI]
(or arXiv:2609.25272v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.25272 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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 · 209 cuvinte
Subiecte conexe
Salesforce after Dreamforce: How the CRM giant can grow beyond its own interface
SiliconANGLE · 19 sept. 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · 2 oct. 2026
The payload: the semantic layer, memory, and the loop that fills it
Neo4j · 10 aug. 2026