生成逼真的合成电子健康记录（EHR）在加速医疗研究、促进 AI 模型开发和增强患者隐私方面具有巨大前景。然而，现有生成方法通常将 EHR 视为离散医疗代码的扁平序列。这种做法忽视了两个关键方面：临床编码系统固有的层次组织结构，以及代码描述所提供的丰富语义上下文。因此，合成患者序列往往缺乏较高的临床保真度，并且在下游临床任务中的效用有限。本文提出层次与语义引导的 Transformer（Hierarchy- and Semantics-Guided Transformer，HiSGT），这是一种在生成过程中同时利用层次信息和语义信息的新颖框架。HiSGT 构建层次图以编码临床代码之间的父子关系和兄弟关系，并采用图神经网络获得具有层次感知能力的嵌入。随后，这些嵌入与从预训练临床语言模型（例如 ClinicalBERT）中提取的语义嵌入相融合，使基于 Transformer 的生成器能够更准确地建模真实 EHR 中固有的细微临床模式。在 MIMIC-III 和 MIMIC-IV 数据集上的大量实验表明，HiSGT 显著提升了合成数据与真实患者记录之间的统计一致性，并支持慢性病分类等稳健的下游应用。通过克服传统基于原始代码的生成模型的局限，HiSGT 代表了迈向临床高保真合成数据生成的重要一步，也提供了一种适用于可解释医疗代码表示的通用范式，并在数据增强和隐私保护型医疗分析中具有宝贵应用价值。
英文摘要：
Generating realistic synthetic electronic health records (EHRs) holds tremendous promise for accelerating healthcare research, facilitating AI model development and enhancing patient privacy. However, existing generative methods typically treat EHRs as flat sequences of discrete medical codes. This approach overlooks two critical aspects: the inherent hierarchical organization of clinical coding systems and the rich semantic context provided by code descriptions. Consequently, synthetic patient sequences often lack high clinical fidelity and have limited utility in downstream clinical tasks. In this paper, we propose the Hierarchy- and Semantics-Guided Transformer (HiSGT), a novel framework that leverages both hierarchical and semantic information for the generative process. HiSGT constructs a hierarchical graph to encode parent-child and sibling relationships among clinical codes and employs a graph neural network to derive hierarchy-aware embeddings. These are then fused with semantic embeddings extracted from a pre-trained clinical language model (e.g., ClinicalBERT), enabling the Transformer-based generator to more accurately model the nuanced clinical patterns inherent in real EHRs. Extensive experiments on the MIMIC-III and MIMIC-IV datasets demonstrate that HiSGT significantly improves the statistical alignment of synthetic data with real patient records, as well as supports robust downstream applications such as chronic disease classification. By addressing the limitations of conventional raw code-based generative models, HiSGT represents a significant step toward clinically high-fidelity synthetic data generation and a general paradigm suitable for interpretable medical code representation, offering valuable applications in data augmentation and privacy-preserving healthcare analytics.
Northwestern University（西北大学）；Northwestern University Feinberg School of Medicine（西北大学费恩伯格医学院）；Simpson Querrey Lung Institute for Translational Science（辛普森奎雷转化科学肺研究所）
CLEF: EEG Foundation Model for Learning Clinical Semantics
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布里奇沃特医院）；Massachusetts General Hospital, Harvard Medical School（哈佛医学院麻省总医院）
Electronic Health Records (EHR) have been heavily used in modern healthcare systems for recording patients' admission information to hospitals. Many data-driven approaches employ temporal features in EHR for predicting specific diseases, readmission times, or diagnoses of patients. However, most existing predictive models cannot fully utilize EHR data, due to an inherent lack of labels in supervised training for some temporal events. Moreover, it is hard for existing works to simultaneously provide generic and personalized interpretability. To address these challenges, we first propose a hyper…
IQVIA（艾昆纬）；Georgia Institute of Technology（佐治亚理工学院）；IBM Research AI（IBM人工智能研究院）
Medication recommendation is an important healthcare application. It is commonly formulated as a temporal prediction task. Hence, most existing works only utilize longitudinal electronic health records (EHRs) from a small number of patients with multiple visits ignoring a large number of patients with a single visit (selection bias). Moreover, important hierarchical knowledge such as diagnosis hierarchy is not leveraged in the representation learning process. To address these challenges, we propose G-BERT, a new model to combine the power of Graph Neural Networks (GNNs) and BERT (Bidirectional…
Geisinger（盖辛格医疗中心）；University of Kentucky（肯塔基大学）；University of New Mexico（新墨西哥大学）
Predicting future clinical events helps physicians guide appropriate intervention. Machine learning has tremendous promise to assist physicians with predictions based on the discovery of complex patterns from historical data, such as large, longitudinal electronic health records (EHR). This study is a first attempt to demonstrate such capabilities using raw echocardiographic videos of the heart. We show that a large dataset of 723,754 clinically-acquired echocardiographic videos (~45 million images) linked to longitudinal follow-up data in 27,028 patients can be used to train a deep neural net…
When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusion
Department of Computer Science（计算机科学系）；Hong Kong Baptist University（香港 Baptist 大学）；Division of Artificial Intelligence（人工智能 division）；Lingnan University（Lingnan 大学）；School of Nursing（护理学院）；The Hong Kong Polytechnic University（香港理工大学）
University of Minnesota（明尼苏达大学）；University of Pittsburgh（匹兹堡大学）
Electronic Health Records (EHR) data analysis plays a crucial role in healthcare system quality. Because of its highly complex underlying causality and limited observable nature, causal inference on EHR is quite challenging. Deep Learning (DL) achieved great success among the advanced machine learning methodologies. Nevertheless, it is still obstructed by the inappropriately assumed causal conditions. This work proposed a novel method to quantify clinically well-defined causal effects as a generalized estimation vector that is simply utilizable for causal models. We incorporated it into DL mod…
CAP: Towards PPG Universal Representation Learning with Patient-level Supervision
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Peking University（北京大学）；Independent Researcher（独立研究者）；Jinling Clinical Medical College College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics（金陵临床医学院人工智能学院南京航空航天大学）
Coefficient of Variation Masking: A Volatility-Aware Strategy for EHR Foundation Models
Massachusetts Institute of Technology (MIT)（麻省理工学院）；Technical University of Munich (TUM)（慕尼黑技术大学）；MICS CentraleSupélec – Université Paris-Saclay（巴黎萨克雷大学CentraleSupélec研究所）；Harvard Medical School（哈佛医学院）；Beth Israel Deaconess Medical Center（贝斯以色列医疗中心）；Institute of Pathology Technical University of Munich（慕尼黑技术大学病理研究所）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
On Using Large Language Models to Enhance Clinically-Driven Missing Data Recovery Algorithms in Electronic Health Records
Department of Statistical Sciences, Wake Forest University（统计科学系，威克森林大学）；Wake Forest University（威克森林大学）；Wake Forest University School of Medicine（威克森林大学医学院）；Department of Psychology, North Carolina State University（心理学系，北卡罗来纳州立大学）；Department of Biostatistics and Data Science, Wake Forest University School of Medicine（生物统计学与数据科学系，威克森林大学医学院）；Department of Anesthesiology, Division of Critical Care Medicine, Wake Forest University School of Medicine（麻醉学系，重症医学科，威克森林大学医学院）；Outcomes Research Consortium（结局研究联盟）
Electronic health records (EHR) are widely believed to hold a profusion of actionable insights, encrypted in an irregular, semi-structured format, amidst a loud noise background. To simplify learning patterns of health and disease, medical codes in EHR can be decomposed into semantic units connected by hierarchical graphs. Building on earlier synergy between Bidirectional Encoder Representations from Transformers (BERT) and Graph Attention Networks (GAT), we present H-BERT, which ingests complete graph tree expansions of hierarchical medical codes as opposed to only ingesting the leaves and pu…
A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studies
Harvard T.H. Chan School of Public Health（哈佛T.H. 洪学校公共卫生学院）；Harvard Medical School（哈佛医学院）；Bentley University（伯顿大学）；Columbia University（哥伦比亚大学）；Boston Children’s Hospital（波士顿儿童医院）；Computational Health Informatics Program（计算健康信息学计划）；Department of Pediatrics（儿科部门）；Brigham and Women’s Hospital（布里奇沃特医院）
The rapid growth of electronic health record (EHR) datasets opens up promising opportunities to understand human diseases in a systematic way. However, effective extraction of clinical knowledge from the EHR data has been hindered by its sparsity and noisy information. We present KG-ETM, an end-to-end knowledge graph-based multimodal embedded topic model. KG-ETM distills latent disease topics from EHR data by learning the embedding from the medical knowledge graphs. We applied KG-ETM to a large-scale EHR dataset consisting of over 1 million patients. We evaluated its performance based on EHR r…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Microsoft Research（微软研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）；Harvard School of Public Health（哈佛公共卫生学院）；Massachusetts Institute of Technology（麻省理工学院）；New York University（纽约大学）
Modern electronic health records (EHRs) provide data to answer clinically meaningful questions. The growing data in EHRs makes healthcare ripe for the use of machine learning. However, learning in a clinical setting presents unique challenges that complicate the use of common machine learning methodologies. For example, diseases in EHRs are poorly labeled, conditions can encompass multiple underlying endotypes, and healthy individuals are underrepresented. This article serves as a primer to illuminate these challenges and highlights opportunities for members of the machine learning community t…
Bruno Kessler Institute（布鲁诺·凯斯勒研究所）；University of Trento（特伦托大学）；Hasso Plattner Institute for Digital Health at Mount Sinai（西奈山哈索·普拉特纳数字健康研究所）；Institute for Next Generation Healthcare（下一代医疗保健研究所）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；Azienda USL Centro “Santi”（圣蒂中央地方卫生局）；HK3 Lab（HK3实验室）
Deriving disease subtypes from electronic health records (EHRs) can guide next-generation personalized medicine. However, challenges in summarizing and representing patient data prevent widespread practice of scalable EHR-based stratification analysis. Here we present an unsupervised framework based on deep learning to process heterogeneous EHRs and derive patient representations that can efficiently and effectively enable patient stratification at scale. We considered EHRs of 1,608,741 patients from a diverse hospital cohort comprising of a total of 57,464 clinical concepts. We introduce a re…
Contrastive Learning on Multimodal Analysis of Electronic Health Records
Harvard T.H. Chan School of Public Health（哈佛T.H. 柏林公共卫生学院）；Harvard Medical School（哈佛医学院）；Rutgers University（罗格斯大学）；National University of Singapore（新加坡国立大学）
Understanding patterns of diagnoses, medications, procedures, and laboratory tests from electronic health records (EHRs) and health insurer claims is important for understanding disease risk and for efficient clinical development, which often require rules-based curation in collaboration with clinicians. We extended an unsupervised phenotyping algorithm, mixEHR, to an online version allowing us to use it on order of magnitude larger datasets including a large, US-based claims dataset and a rich regional EHR dataset. In addition to recapitulating previously observed disease groups, we discovere…
The increased adoption of Electronic Health Records(EHRs) has brought changes to the way the patient care is carried out. The rich heterogeneous and temporal data space stored in EHRs can be leveraged by machine learning models to capture the underlying information and make clinically relevant predictions. This can be exploited to support public health activities such as pharmacovigilance and specifically mitigate the public health issue of Adverse Drug Events(ADEs). The aim of this article is, therefore, to investigate the various ways of handling temporal data for the purpose of detecting AD…
An Investigation of Memorization Risk in Healthcare Foundation Models
MIT Broad Institute of MIT and Harvard（MIT Broad研究所（MIT和哈佛））；Vector Institute（向量研究所）；MIT；Chalmers University of Technology（查尔姆斯理工大学）；University of Gothenburg（哥德堡大学）；University of Toronto（多伦多大学）；University Health Network (UHN)（大学健康网络）；Worcester Polytechnic Institute（沃思维尔理工学院）；Computer Science Department（计算机科学系）
Khoury College of Computer Sciences, Northeastern University（东北大学科里计算机科学学院）；Brigham and Women’s Hospital（布莱根妇女医院）
Electronic Health Records (EHRs) provide vital contextual information to radiologists and other physicians when making a diagnosis. Unfortunately, because a given patient's record may contain hundreds of notes and reports, identifying relevant information within these in the short time typically allotted to a case is very difficult. We propose and evaluate models that extract relevant text snippets from patient records to provide a rough case summary intended to aid physicians considering one or more diagnoses. This is hard because direct supervision (i.e., physician annotations of snippets re…
A Structural FHMM for Interpretable Disease Trajectories in T2DM
Swiss Data Science Center (SDSC)（瑞士数据科学中心（SDSC））；Ecole Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；ETH Zürich（苏黎世联邦理工学院）；Institute of Pharmaceutical Sciences（药学院）
xMICD: Explainable Representation of Multiple ICD Codes
Leibniz Institute for Prevention Research and Epidemiology - BIPS（莱布尼茨预防研究与流行病学研究所——BIPS）；Institute of Science Tokyo（东京科学大学）；Faculty of Medicine Siriraj Hospital, Mahidol University（玛希隆大学诗里拉吉医学院）
University of Oxford（牛津大学）；NIHR Oxford Biomedical Research Centre（英国国家健康研究所牛津生物医学研究中心）；Oxford University Hospitals NHS Foundation Trust（牛津大学医院国民保健服务基金会信托）
Deep learning models have shown tremendous potential in learning representations, which are able to capture some key properties of the data. This makes them great candidates for transfer learning: Exploiting commonalities between different learning tasks to transfer knowledge from one task to another. Electronic health records (EHR) research is one of the domains that has witnessed a growing number of deep learning techniques employed for learning clinically-meaningful representations of medical concepts (such as diseases and medications). Despite this growth, the approaches to benchmark and a…
DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits
Department of Computer Science and Information Systems, Birla Institute of Technology and Science, Pilani, Hyderabad Campus（计算机科学与信息系统系，比拉理工学院，比拉理工学院，海得拉巴校区）
Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification
Vanderbilt University（范德堡大学）；Siemens Healthineers（西门子医疗）；Saint Luke’s Mid America Heart Institute（圣卢克中美洲心脏研究所）；Vanderbilt University Medical Center（范德堡大学医学中心）
McGill University（麦吉尔大学）；McGill Adult Unit for Congenital Heart Disease Excellence（麦吉尔大学成人先天性心脏病卓越中心）
Motivation: Electronic health record (EHR) data provides a new venue to elucidate disease comorbidities and latent phenotypes for precision medicine. To fully exploit its potential, a realistic data generative process of the EHR data needs to be modelled. We present MixEHR-S to jointly infer specialist-disease topics from the EHR data. As the key contribution, we model the specialist assignments and ICD-coded diagnoses as the latent topics based on patient's underlying disease topic mixture in a novel unified supervised hierarchical Bayesian topic model. For efficient inference, we developed a…
Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching
Department of Artificial Intelligence and Informatics, Mayo Clinic（人工智能与信息学系，梅奥诊所）；Computer Science Department, University of Tulsa（图兰大学计算机科学系）；Mayo Clinic Comprehensive Cancer Center, Mayo Clinic（梅奥诊所综合癌症中心，梅奥诊所）；Division of Community Pediatric and Adolescent Medicine, Department of Pediatrics, Mayo Clinic（社区儿科与青少年医学分会，儿科部，梅奥诊所）；Department of Neurology, Mayo Clinic（神经病学部，梅奥诊所）；Department of Radiation Oncology, Mayo Clinic（放射肿瘤学部，梅奥诊所）；Department of Quantitative Health Sciences, Mayo Clinic（定量健康科学部，梅奥诊所）
