Tag
The paper proposes converting multimodal patient data (text, labs, vitals) into a single natural language sequence and fine-tuning LLMs for clinical prediction, achieving comparable or better performance than specialized fusion architectures across three tasks.
The paper studies interaction-aware mixture-of-experts for post-stroke rigidity prediction using multi-level views of structured health records, showing that while performance gains are minimal, routing attribution reveals systematic importance differences across views, highlighting view construction as key to interpretability.
This paper proposes an explicit multimodal routing framework for clinical prediction using EHR data, enabling interpretable, robust, and auditable reasoning across structured variables, clinical notes, and chest X-rays via discrete unimodal, bimodal, and trimodal routes with inference-time route masking for missing modality simulation.
This paper systematically compares discrete, continuous, and hybrid value encoding strategies for transformers in electronic health record data, finding that hybrid token-based approaches with binning provide robust performance and are recommended as a practical default.
This paper presents a method that uses frozen medical large language model (LLM) representations as a shared embedding space to predict primary ICD diagnosis categories from both structured and unstructured electronic health record data, achieving improved accuracy over baseline methods on MIMIC-IV and showing transferability to MIMIC-III.
PORTER is a language-grounded structured EHR foundation model that represents clinical events through text descriptions and numeric values, enabling vocabulary-independent transfer across institutions without retraining. On pediatric prediction tasks, PORTER matches fixed-vocabulary models and recovers 97.1% of AUROC when transferred to unseen event descriptions.
Introduces a foundation model–driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data for time-to-event prediction, evaluating fusion strategies on pulmonary embolism and cardiovascular disease cohorts.
QDSP is an interpretable structured learning framework for predicting death or cerebral palsy in very low birth weight infants, integrating Quota-guided Subspace Sampling and Differentiable-decision-guided Structure Perception. It outperforms baselines like XGBoost, TabNet, and TabPFN on a real cohort and external datasets, identifying clinically relevant predictors such as cPVL and birth weight.
This paper presents a hybrid framework that combines structured clinical data with LLM-generated narratives for coronary artery disease prediction, achieving high fidelity in variable extraction and comparing ML models with LLM-based zero-shot and few-shot classification.
Proposes ReTAMamba, a method using reliability-aware temporal aggregation with Mamba for irregular clinical time series prediction, achieving significant AUPRC gains on MIMIC-IV, eICU, and PhysioNet 2012.
This review paper proposes a unified framework for intervention-aware disease trajectory modeling in clinical AI, addressing static prediction failures by incorporating treatment confounder feedback and informative observation patterns.
This paper extends Foresight Learning to clinical event prediction by converting time-ordered clinical notes into prediction examples. A LoRA adapter on a 120B model improves calibration and outperforms GPT-5 on held-out questions.
Foresight Learning converts longitudinal clinical notes into prediction examples, and a LoRA adapter improves calibration and reduces uncertainty compared to base models, outperforming GPT-5 on held-out questions.