Tag
This paper presents a scalable clinical data infrastructure and compares deep learning (TG-CNN) with traditional machine learning models (LASSO and Random Forests) for predicting hospitalization risk in elderly patients with multiple long-term conditions, concluding that LASSO is better suited for clinical deployment due to superior calibration.
The paper proposes DoctorAgents, an agentic AI framework that uses specialized LLM agents to iteratively generate, validate, and refine end-to-end machine learning pipelines for small, heterogeneous clinical temporal datasets, outperforming established AutoML baselines.
Proposes Patient Sampling, a pretraining sequence construction method for EHR foundation models that improves downstream performance over the standard Global Stream baseline on MIMIC-IV datasets, highlighting the importance of sequence construction in autoregressive health models.
OpenMed privacy-filter v2 using nemotron and MLX 8-bit achieves 755 tokens per second on a Mac, redacting 1,152 PII identifiers across 22 categories from a 13,000-token clinical file without data leaving the machine.
This paper introduces FoGS, a filtered mixture-of-generators pipeline that selects synthetic samples from multiple generative models to improve survival analysis training, outperforming real-data training on many datasets while preserving privacy.
This paper explores Large Language Models' inability to recognize their knowledge limits on structured clinical data, proposing a cross-model attribution divergence method to detect epistemic blind spots. The approach improves calibration and accuracy without training by combining few-shot examples and SHAP-derived feature evidence.
PSyGenTAB is a privacy-preserving framework that uses constrained optimization to generate synthetic clinical tabular data, balancing privacy and utility while preserving clinical relationships and minority-class patterns.
This paper examines the integration of multi-modal clinical data, including treatment records, pathology reports, and clinician notes, using rule-based extraction and machine learning to improve breast cancer recurrence prediction compared to single-modal approaches.
This paper introduces a parallelization strategy and adaptive steering mechanism for the Baymex algorithm to efficiently learn discretized Bayesian network classifiers for clinical data, achieving speedups over 54x on a 16-core CPU and comparable or better predictive performance than traditional models while maintaining explainability.
GiG is a knowledge graph-modulated deep learning framework that integrates biological knowledge graphs as edges and patient-specific data as node features, outperforming SOTA by up to 49% in limited-sample clinical tasks.
This study evaluates the use of large language models (Gemini 3.0 Flash) with personal health records to answer patient health queries, finding significant improvements in helpfulness, safety, and personalization when PHR context is provided.