Cancer Deep Phenotype Extraction from Electronic Medical Records

从电子病历中提取癌症深层表型

基本信息

批准号：
10268998
负责人：
HARRY S HOCHHEISER
金额：
$ 85.92万
依托单位：
BOSTON CHILDREN'S HOSPITAL
依托单位国家：
美国
项目类别：
财政年份：
2020
资助国家：
美国
起止时间：
2020-09-24 至 2025-08-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10268998
关键词：
Academic Medical Centers Address Adjuvant Advanced Malignant Neoplasm Adverse event Area Bioinformatics Brain Aneurysms Cancer Patient Cancer Research Project Caring Case Study Characteristics Clinic Clinical Clinical Informatics Collaborations Colorectal Cancer Communities Community Clinical Oncology Program Community of Practice Complement Computer software Computerized Medical Record Computing Methodologies Consumption Dana-Farber Cancer Institute Data Data Science Decision Making Diagnosis Diagnostic Disease Epigenetic Process Evaluation Funding Gene Amplification Genetic Genomics Growth Hematologic Neoplasms Hepatotoxicity Immune System Diseases Informatics Information Retrieval Investigation Laboratory Finding Literature Malignant Neoplasms Malignant neoplasm of ovary Manuals Measures Medical Medical Records Methods Methotrexate Modeling Morphology Multiple Sclerosis Natural Language Processing Neoadjuvant Therapy Neoplasm Metastasis Oncology Pathology Patient-Focused Outcomes Patients Phenotype Postoperative Period Process Public Health Rare Diseases Recording of previous events Records Research Research Personnel Rheumatoid Arthritis Severities Solid Source Stress System Techniques Technology Testing Text Time TimeLine Translational Research Treatment Protocols Visual Visualization Work analytical tool anticancer research autism spectrum disorder base cancer care cancer initiation cancer subtypes cancer type chemotherapeutic agent chemotherapy clinical care clinical investigation cohort community building comorbidity data streams design exhaustion follow-up individual patient informatics tool information organization innovation insight interactive tool interest large cell Diffuse non-Hodgkin&apos s lymphoma malignant breast neoplasm melanoma next generation sequencing novel open source precision medicine programs response tool translational cancer research translational scientist treatment response tumor tumor behavior unstructured data usability

项目摘要

Summary Precise phenotype information is needed to advance translational cancer research, particularly to unravel the effects of genetic, epigenetic, and systems changes on tumor behavior and responsiveness. Examples of phenotypic variables in cancer include: tumor morphology (e.g. histopathologic diagnosis), co-morbid conditions (e.g. associated immune disease), laboratory findings (e.g. gene amplification status), specific tumor behaviors (e.g. metastasis) and response to treatment (e.g. effect of a chemotherapeutic agent on tumor). Current models for correlating EMR data with –omics data largely ignore the clinical text, which remains one of the most important sources of phenotype information for cancer patients. Unlocking the value of clinical text has the potential to enable new insights about cancer initiation, progression, metastasis, and response to treatment. We propose further collaboration to enhance the DeepPhe platform with new methods for cancer deep phenotyping. Several aims propose investigation of biomedical information extraction where there has been little or no previous work (e.g. clinical genomic). Visualization of extracted data, usability of the software, and dissemination are also emphasized. A diverse set of oncology studies led by accomplished translational investigators in Breast Cancer, Melanoma, Ovarian Cancer, Colorectal Cancer and Diffuse Large B-cell Lymphoma will demonstrate the utility of the software. These labs will contribute phenotype variables for extraction, test utility and usability of the software, and provide the setting for an extrinsic evaluation. The proposed research bridges novel methods to automate cancer deep phenotype extraction from clinical text with emerging standards in phenotype knowledge representation and NLP. This work is highly aligned with recent calls in the scientific literature to advance scalable and robust methods of extracting and representing phenotypes for precision medicine and translational research.

概括需要精确的表型信息来推进转化癌的研究，尤其是为了解开遗传，表观遗传和系统对肿瘤行为和反应性的变化的影响。示例的例子癌症的表型变量包括：肿瘤形态（例如组织病理学诊断），合并症疾病（例如相关免疫疾病），实验室发现（例如基因扩增状态），特定的肿瘤行为（例如转移）和对治疗的反应（例如化学治疗剂对肿瘤的影响）。当前用于将EMR数据与–omics数据相关联的模型在很大程度上忽略了临床文本，这仍然是一种癌症患者表型信息的最重要来源。解锁临床文本的价值有可能使有关癌症倡议，进展，转移的新见解以及对治疗。我们提出进一步的合作，以增强Deepphe平台的新方法深度表型。有几个目的针对生物医学信息提取的建议调查几乎没有或根本没有工作（例如临床基因组）。可视化提取的数据，软件的可用性，还强调了传播。由成就的翻译领导的一组多样化的肿瘤学研究乳腺癌，黑色素瘤，卵巢癌，大肠癌和弥漫性大B细胞的研究者淋巴瘤将证明该软件的实用性。这些实验室将为表型变量提取，测试效用和软件的可用性，并为外部评估提供设置。拟议的研究桥梁桥接新型方法，使癌症从临床文本中提取深度表型，并表型知识表示和NLP中的新兴标准。这项工作与最近的科学文献中的呼吁，以提高可扩展和强大的提取和代表方法精密医学和翻译研究的表型。