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.
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.
The benefits of multimodal data integration are task-dependent and healthcare LLMs should examine clinical data modalities according to specific tasks for efficient integration, and provide practical guidance for designing efficient clinical decision support systems.
Cheng Peng, Mengxian Lyu, Ziyi Chen et al.· JAMIA Journal of the America...· 0 citations
BERT-LER is presented, a BERT-style model for coded EHR timelines pretrained and fine-tuned from a de-identified EHR dataset of 75 million patients, that encodes laboratory test results as discrete tokens while retaining graded information through percentile-based binning, paired with Integrated Gradients for token-lev...
Jun-Ni Du, Lukas Adamek, Maxim A Kryukov et al.· 0 citations
STRIDE, a machine-learning framework for sepsis detection across seven hospitals with a scalable approach to label quality, outperformed SOFA and Epic on discrimination and showed favorable calibration by Brier score, while retaining strong discrimination among SIRS-positive non-septic encounters.
I. K. Kalyvianakis, C. De Amezaga, E. Lee et al.· medRxiv· 0 citations
A domain-structured ensemble framework for perioperative outcome prediction using routinely collected EHR data, designed for extensibility across diverse clinical endpoints, is presented, using postoperative delirium (POD) as an exemplar application.
Shikhar Shukla, Cristina Barboi· IEEE International Conferenc...· 0 citations
It is argued that LASSO, not the highest-discriminating model, is the model best suited to direct clinical deployment, and lessons for the machine learning and healthcare community regarding data infrastructure, model selection, and value of calibration and interpretability in high-stakes decision support are presented...
Asra Aslam, Volodymyr Chapman, M. O'Connell et al.· 0 citations
LLMs represent a viable and flexible approach to diagnosis code extraction from unstructured clinical notes that can augment structured diagnoses and provide contextualizing metadata.
H. Razzaghi, Nhat Nguyen, M. Pargi et al.· JAMIA Open· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026