analiza aiqbench
This research presents an efficient alternative to computationally expensive language models for predicting hospital readmissions by leveraging structured EHR data augmented with medical ontologies. The study demonstrates that sparse, interpretable feature representations can match the performance of note-based methods while significantly reducing resource requirements. These findings offer a practical pathway for deploying predictive analytics in clinical settings where interpretability and cost-efficiency are critical.
Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV
arXiv:2609.15713v1 Announce Type: new Abstract: Recent approaches to 30-day hospital readmission prediction rely on pre-trained language models applied to discharge summaries. Although these methods achieve strong performance, they depend on the availability of clinical notes, incur substantial computational costs, and yield representations that lack interpretability. We propose a knowledge-enriched feature representation that augments structured Electronic Health Record (EHR) data with four medical knowledge sources: disease ontology mapping, procedure classification, drug ingredient vocabulary, and organ system laboratory aggregation, without using clinical notes. Each feature dimension corresponds to a named clinical concept, yielding a sparse and interpretable patient representation. The approach is evaluated with six classifiers on a MIMIC-IV v2.2 cohort. Under 20-fold cross-validation, the best configuration achieves an AUROC of 0.743. This performance is comparable to that of previously reported methods on this dataset, including both those using only structured data and those incorporating clinical notes, while requiring considerably less computational cost. Interpretability analysis shows that demographics, organ system labs, drug ingredient features, and first-level ontology disease categories drive prediction, while deeper hierarchy levels contribute negligibly. These findings indicate that knowledge-enriched structured features offer a competitive and efficient alternative to embeddings from clinical notes for 30-day readmission prediction.
Abstract:Recent approaches to 30-day hospital readmission prediction rely on pre-trained language models applied to discharge summaries. Although these methods achieve strong performance, they depend on the availability of clinical notes, incur substantial computational costs, and yield representations that lack interpretability. We propose a knowledge-enriched feature representation that augments structured Electronic Health Record (EHR) data with four medical knowledge sources: disease ontology mapping, procedure classification, drug ingredient vocabulary, and organ system laboratory aggregation, without using clinical notes. Each feature dimension corresponds to a named clinical concept, yielding a sparse and interpretable patient representation. The approach is evaluated with six classifiers on a MIMIC-IV v2.2 cohort. Under 20-fold cross-validation, the best configuration achieves an AUROC of 0.743. This performance is comparable to that of previously reported methods on this dataset, including both those using only structured data and those incorporating clinical notes, while requiring considerably less computational cost. Interpretability analysis shows that demographics, organ system labs, drug ingredient features, and first-level ontology disease categories drive prediction, while deeper hierarchy levels contribute negligibly. These findings indicate that knowledge-enriched structured features offer a competitive and efficient alternative to embeddings from clinical notes for 30-day readmission prediction.
15 pages, 3 figures. Accepted at SDSC 2026 Mid-Atlantic
Machine Learning (cs.LG); Quantitative Methods (q-bio.QM)
arXiv:2609.15713 [cs.LG]
(or arXiv:2609.15713v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.15713 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 · 298 cuvinte
Subiecte conexe
Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
arXiv · 3 sept. 2026
HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction
arXiv · 21 sept. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
Models Can't Remember Their Training. Neither Can You.
LessWrong · 19 iul. 2026