Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV
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.
Related
- Bioengineered algal lipids enriched in structured medium- and long-chain triacylglycerols, linoleate, and sn-2 palmitate for human milk fat substitutes
- Crowding distorts features, not objects: structured target confusions in a 4AFC conjunction task
- Neural Structural Reasoner: A Brain-inspired Architecture for Reasoning over Structured Knowledge
- From structured knowledge to flexible behaviour: the importance of local prefrontal computations
- Emotion knowledge is structured in a grid-like coordinate system in the human ventromedial prefrontal cortex
BibTeX
@misc{najafi2026knowledgeenriched,
title = {{Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV}},
author = {Mohamad Najafi and Hongyun Fu and Mathias Brochhausen and Jian Wu and Yaohang Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15713},
eprint = {2609.15713},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15713},
}
RIS
TY - UNPB
TI - Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IV
AU - Mohamad Najafi
AU - Hongyun Fu
AU - Mathias Brochhausen
AU - Jian Wu
AU - Yaohang Li
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15713
UR - https://arxiv.org/abs/2609.15713
AB - 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.
ER -