Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 13297-13298· 0 citations· 9 references
TL;DR
This tutorial presents OneEHR, an open-source toolkit that defines a unified experiment contract for modern EHR modeling and enables head-to-head comparison among conventional, neural, LLM-based, and agentic methods through a single configuration-driven interface.
Abstract
Electronic health records support a wide spectrum of clinical prediction and decision-support studies, but reproducible EHR research now requires more than training a single predictive model. As the field expands from machine learning and deep learning to LLM-based and agentic AI, differences in cohort construction, temporal preprocessing, label definitions, patient-level splits, and evaluation protocols can overshadow the methods being compared, making fair comparison and model selection difficult in practice. This tutorial presents OneEHR, an open-source toolkit that defines a unified experiment contract for modern EHR modeling and enables head-to-head comparison among conventional, neural, LLM-based, and agentic methods through a single configuration-driven interface. The three-hour hands-on session interleaves a methodological survey with guided practice: participants will learn why EHR experiments are vulnerable to leakage, distribution shift, and irreproducible preprocessing, and then use OneEHR to configure, execute, compare, and interpret experiments across this method spectrum. Attendees will leave with reusable configurations and a practical framework for integrating reproducible workflows into their own clinical AI research. Code and documentation are available at https://medx-pku.github.io/OneEHR/.
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-level attributions grounded in the input EHR sequence.
Jun Ni Du, Lukas Adamek, Maxim A Kryukov et al.· 0 citations
Background: Medical artificial intelligence (AI), machine learning (ML), and deep learning (DL) studies frequently begin with datasets collected for routine care rather than for computational modeling. Such datasets may contain inconsistent variables, heterogeneous measurement time points, unexplained NaN values, poorly defined outcomes, missing metadata, and insufficient documentation, which can compromise model development before any algorithm is selected. Methods: This Technical Note proposes a physician-facing Clinical AI-Readiness Guide for preparing medical datasets before AI-based analysis. The guide was developed as a practical framework organized around pre-modeling decisions, including the clinical task, cohort, minimum common dataset, outcome definition, predictor variables, measurement timing, missing-data logic, standardization, non-tabular data linkage, data dictionary, and validation readiness. Results: The proposed guide translates AI-readiness principles into concrete data-collection rules for clinical, laboratory, imaging, physiological-signal, textual, follow-up, and multimodal data. It emphasizes clinically consistent data acquisition, reliable target labeling, explicit missing-data logic, patient-level linkage, structured metadata, and validation feasibility. A structured checklist and scoring approach are also proposed as practical pre-modeling assessment tools to classify datasets as not ready, exploratory only, ML-ready with limitations, or AI-ready for model development. Conclusions: Medical AI-readiness should be established before model development begins. By helping physicians collect, structure, and document data more consistently, the proposed guide may improve collaboration between clinical and technical teams and reduce preventable dataset-related failures in medical AI research.
Cătălin Anghel, A. Anghel, M. Craciun et al.· Journal of Clinical Medicine· 0 citations
Results indicate that a single serialization-based paradigm, without bespoke fusion architectures, is sufficient for multimodal clinical prediction - substantially reducing system complexity while matching or exceeding specialized designs.
A. Ravichandran, Bilgin Osmandoja, Klemens Budde et al.· 0 citations
Autoregressive foundation models for electronic health records (EHRs) typically inherit pretraining methods from language modeling, where patient trajectories are concatenated into a single token stream and windows are sampled from that stream. In EHR data, this choice is consequential: windows may mix multiple patients, and patients with longer records contribute more optimization updates, potentially introducing bias. We propose Patient Sampling, a pretraining sequence-construction method that allows us to control how training signal is distributed across patients. We compare this method to the standard approach, which we refer to as Global Stream. We show that stochastic Patient Sampling with controllable weighting improves performance on real-world EHR data. Across downstream clinical tasks on MIMIC-IV v2.2 and v3.1, Patient Sampling improves Macro AUROC and AUPRC over the Global Stream baseline. These results identify training and validation sequence construction as important and underexplored design choices for autoregressive EHR foundation models.
Joshua Placidi, Yuxuan Liu, Jinpei Han et al.· 0 citations
CoMedBench is introduced, a reproducible benchmark that evaluates a family of generators under a common clinical-validity framework and one shared training and evaluation engine, spanning static tabular and temporal downstream tasks on established critical-care datasets.
The increasing integration of artificial intelligence in health care has created new opportunities for improving diagnosis, prognosis, and clinical decision-making. However, the adoption of machine learning (ML) by health care professionals remains limited due to the technical complexity associated with coding and data analysis. This review article aims to bridge this gap by providing a practical, hands-on guide for non-coders to build basic ML models using structured health data. We describe a simplified four-step workflow consisting of data cleaning, model building and evaluation, external validation, and deployment for clinical use. To operationalize this process, we introduce four user-friendly, no-code applications developed using R and Shiny—CleanSight, MLSight, ValidateSight, and PredictSight. These tools enable users to preprocess data, train and evaluate ML models, and generate real-time predictions through intuitive graphical interfaces without requiring programming skills. This workflow is designed for structured/tabular clinical data and does not include computer vision tasks such as image classification or segmentation. A case study using a fictitious dataset on nonalcoholic fatty liver disease is presented to demonstrate the complete workflow, including handling missing data, training a prediction model, and applying it in a simulated clinical scenario. The applications are designed to run on standard personal computers, making them accessible in routine health care and academic settings. By simplifying complex ML processes and emphasizing practical usability, this guide empowers clinicians, including radiologists, to transform routine clinical data into actionable predictive tools. The approach has the potential to enhance data-driven clinical practice and promote wider adoption of ML in health care, particularly among users with limited technical expertise.
Himel Mondal, Pradosh Kumar Sarangi, Shaikat Mondal· Indian Journal of Radiology...· 0 citations
