This study presents a fully automated methodology for early prediction studies in clinical settings, leveraging information extracted from unstructured discharge reports. The proposed pipeline uses discharge reports to support the three main steps of early prediction: cohort selection, dataset generation, and outcome labeling. By processing discharge reports with natural language processing techniques, we can efficiently identify relevant patient cohorts, enrich structured datasets with additional clinical variables, and generate high-quality labels without manual intervention. This approach addresses the frequent issue of missing or incomplete data in codified electronic health records (EHR), capturing clinically relevant information that is often underrepresented. We evaluate the methodology in the context of predicting atrial fibrillation (AF) progression, showing that predictive models trained on datasets enriched with discharge report information achieve higher accuracy and correlation with true outcomes compared to models trained solely on structured EHR data, while also surpassing traditional clinical scores. These results demonstrate that automating the integration of unstructured clinical text can streamline early prediction studies, improve data quality, and enhance the reliability of predictive models for clinical decision-making.
Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records
Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis
Graduate School of AI, KAIST, Republic of Korea(韩国科学技术院人工智能研究生院);Haeundae Paik Hospital, Inje University, Republic of Korea(韩国延世大学海云台医院);Asan Medical Center, University of Ulsan College of Medicine, Republic of Korea(韩国釜山大学医学院阿桑医院)
A Hybrid CNN-Transformer Model for Heart Disease Prediction Using Life History Data
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);University of Houston(休斯顿大学);Shanghai Jiao Tong University(上海交通大学);New York University(纽约大学);Tulane University(杜兰大学);University of Massachusetts Boston(马萨诸塞大学波士顿分校)
An AI tool for automated analysis of large-scale unstructured clinical cine CMR databases
King’s College London(伦敦国王学院);Guy’s and St Thomas’ NHS Foundation Trust(盖伊和圣托马斯NHS基金会信托);Duke University(杜克大学);Barts Health NHS Trust(巴特健康NHS基金会信托);Alan Turing Institute(阿兰·图灵研究所);University Medical Center Utrecht(乌得勒支大学医学中心)
Automatic Extraction of Disease Risk Factors from Medical Publications
School of Computer Science, The Academic College of Tel Aviv-Yaffo(特拉维夫-雅法学术学院计算机科学学院);Division of Cardiology, Tel-Aviv Sourasky Medical Center(特拉维夫苏拉斯基医疗中心心脏病科);Faculty of Medicine, The Hebrew University of Jerusalem(希伯来大学医学院);Bioinformatics, School of Computer Science, The Academic College of Tel Aviv-Yaffo(特拉维夫-雅法学术学院计算机科学学院生物信息学方向)
Machine Learning for Multimodal Electronic Health Records-based Research: Challenges and Perspectives
Peng Cheng Laboratory(鹏城实验室);Carnegie Mellon University(卡内基梅隆大学);University of Toronto Mississauga(多伦多大学密西沙加分校);Peking University(北京大学)
背景资料:电子健康档案(Electronic Health Records,EHR)包含了丰富的患者健康历史信息,通常包括结构化和非结构化数据。已经有许多研究专注于从结构化数据中提取有价值的信息,例如疾病代码,实验室测试结果和治疗方法。然而,单靠结构化数据未必能全面反映病人的数据,而这些数据间中亦可能有错误的纪录。目的:随着机器学习(ML)和深度学习(DL)技术的最新进展,越来越多的研究试图通过合并非结构化自由文本数据来获得更准确的结果。本文回顾了使用多模态数据(即结构化和非结构化数据的组合)的研究,这些数据来自EHR,作为传统ML或DL模型的输入,以解决目标任务。材料与方法:我们在电气和电子工程师协会(IEEE)数字图书馆、PubMed和计算机械协会(ACM)数字图书馆中检索了与基于ML的多模态EHR研究相关的文章。结果和讨论:在最后的94项研究中,我们重点关注来自不同模态的数据如何使用传统的ML和DL技术进行组合和交互,以及这些算法如何应用于EHR相关任务。此外,我们调查这些融合方法的优点和局限性,并指出未来的方向ML为基础的多模态EHR研究。
Predicting Cardiopulmonary Exercise Testing Outcomes in Congenital Heart Disease Through Multi-modal Data Integration and Geometric Learning
School of Computing Science at University of Glasgow(格拉斯哥大学计算科学学院);Golden Jubilee National Hospital(金禧国家医院);Helen DeVos Children’s Hospital, Corewell Health(科尔韦尔健康海伦·德沃斯儿童医院)
Explainable AI meets Healthcare: A Study on Heart Disease Dataset
Pandit Deendayal Petroleum University(潘迪特·迪恩达亚尔石油大学);Confirm SFI Centre for Smart Manufacturing(Confirm SFI智能制造中心);Data Science Institute(数据科学研究所);National University of Ireland Galway(爱尔兰国立大学戈尔韦分校)
Adaptable Cardiovascular Disease Risk Prediction from Heterogeneous Data using Large Language Models
Eidgenössische Technische Hochschule (ETH), Zürich, Switzerland(瑞士苏黎世联邦理工学院);Max Planck Institute for Intelligent Systems, Tübingen, Germany(德国图宾根智能系统研究所);ELLIS Institute, Tübingen, Germany(德国图宾根ELLIS研究所);Stanford School of Medicine, CA, USA(美国斯坦福医学院)
A Meta-embedding-based Ensemble Approach for ICD Coding Prediction
KPMG UK(毕马威英国);Great Ormond Street Hospital for Children NHS Foundation Trust(大奥蒙德街儿童医院NHS基金会信托);UCL Great Ormond Street Institute of Child Health(伦敦大学学院大奥蒙德街儿童健康研究所)
RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records
Department of Computer Science, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校计算机科学系);Department of Pediatrics, University of Illinois College of Medicine Peoria(伊利诺伊大学皮奥里亚医学院儿科系)
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 Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech
Winterlight Labs(Winterlight实验室);University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(Vector人工智能研究所);Li Ka Shing Knowledge Institute, St Michael’s Hospital(圣迈克尔医院李嘉诚知识研究所);Surgical Safety Technologies Inc.(外科安全技术公司)
PheME: A deep ensemble framework for improving phenotype prediction from multi-modal data
Xi’an Jiaotong-Liverpool University(西交利物浦大学);Wuhan University(武汉大学);Rice University(莱斯大学);Texas A&M University(德克萨斯农工大学);University of Texas Health Science Center(德克萨斯大学健康科学中心);UTHealth Houston School of Biomedical Informatics(德克萨斯大学休斯顿健康科学中心生物医学信息学院)
本文提出 PheME 深度集成框架,融合结构化 EHR 与临床笔记的单模态和多模态模型,以提升七种疾病的表型预测性能。
Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of California(加州大学);Huazhong Agricultural University(华中农业大学);Huazhong University of Science and Technology(华中科技大学)