Predicting Clinical Phenotypes in Crohn's Disease Using Machine Learning and Single-Cell 'omics

使用机器学习和单细胞组学预测克罗恩病的临床表型

基本信息

批准号：
10586795
负责人：
Sana Syed
金额：
$ 71.24万
依托单位：
UNIVERSITY OF VIRGINIA
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-05-01 至 2027-04-30
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10586795
关键词：
Address Age Years Algorithms Anemia Autoimmune Automobile Driving Behavior Benchmarking Biopsy Cells Childhood Chromosome Mapping Chronic Classification Clinical Clinical Management Complex Complication Computer Models Crohn&apos s disease Data Data Set Development Diagnosis Diagnostic Disease Disease Management Disease Outcome Disease Progression Disease Resistance Early treatment Enrollment Evaluation Fistula Functional disorder Future Gastrointestinal Diseases Gastrointestinal tract structure Gene Expression Gene Expression Profile Genes Genetic Goals Health Histology Histopathology Image Analysis Incidence Inflammatory Intervention Knowledge Literature Machine Learning Malabsorption Syndromes Maps Metadata Methodology Methods Microscopic Modeling Molecular Morphology Mucous Membrane Newly Diagnosed Operative Surgical Procedures Outcome Pathologic Patients Pattern Pediatric Crohn&apos s disease Penetration Performance Phenotype Physical shape Predictive Value Prevention Prospective cohort Publishing Relapse Reporting Research Resolution Review Literature Risk Sensitivity and Specificity Severities Slide TNF gene Testing Therapeutic Intervention Time Tissue Extracts Tissues Training Translations Visualization Work accurate diagnostics adverse outcome age group bench to bedside biobank biomedical imaging clinical care clinical phenotype clinical practice clinical predictors clinically relevant cohort cost disease phenotype feature detection genetic signature improved individual patient individualized medicine innovation machine learning method machine learning model machine learning prediction model building novel outcome prediction personalized diagnostics personalized intervention personalized medicine precision medicine predictive modeling predictive tools prevent preventive intervention prognostic prospective psychosocial recruit response risk prediction model single-cell RNA sequencing spatial integration standard of care transcriptomics treatment response

项目摘要

PROJECT SUMMARY/ABSTRACT Pediatric Crohn's disease presents as a chronic, relapsing inflammatory condition of the gastrointestinal tract, leading to malabsorption, anemia, and psychosocial decline. The incidence rate of Crohn's disease has been growing in the 10- to 18-year age group. Crohn’s disease exists on a spectrum of clinical severity, ranging from mild disease responsive to standard anti-TNFɑ therapy to severe, treatment-resistant disease with stricturing (B2) or penetrating (B3) complications often requiring surgical intervention. Distinguishing which patients will progress to more severe disease from patients who will require minimal intervention at the time of diagnosis is an urgent unmet need. Accurate and automated prediction of disease outcomes will significantly improve patient health by informing personalized interventions for individual patients. Previous attempts at generating predictive models of Crohn’s disease relying solely on clinical features of the disease and patient biodata have demonstrated promising, yet inadequate accuracies for clinical practice applications. This proposal addresses these limitations by leveraging large cohorts of archival and prospective patient clinical metadata, ‘omics, and machine learning derived tissue features to build and test machine learning models for predicting specific Crohn's disease outcomes. In Aim 1, we will build, test, and validate predictive models of Crohn’s disease using computational image analysis of gold-standard biopsy histopathology slides. We will use saliency maps and gene correlations analysis to validate our models by visualizing the tissue features of importance to our predictive models and identify specific transcriptomic changes associated with these features. In Aim 2, we will generate a clinically-relevant predictive model of Crohn’s disease by integrating the deep features extracted from histology image analysis with other patient metadata collected as part of standard clincal care. Additionally, we will collate a thorough list of published predictive models of Crohn's disease to benchmark the performance of our proposed and future predictive models. Lastly, in Aim 3 we will use cutting edge single-cell RNA sequencing and spatial transcriptomics approaches to elucidate a transcriptomic signature of Crohn's disease and characterize specific genetic profiles associated with the hallmark morphological changes in diseased tissue. These data will provide a framework for studying the subtypes and clinical outcomes of Crohn’s disease and other gastrointestinal diseases, thus driving the clinical adaptation of personalized therapy and precision medicine. This proposed research will increase the resolution of both diagnostic and prognostic information to better manage Crohn’s disease in patients and significantly shft clinical management to an individualized treatment paradigm.

项目概要/摘要儿童克罗恩病表现为一种慢性、复发性胃肠道炎症，导致吸收不良、贫血和心理衰退，克罗恩病的发病率一直很高。克罗恩病在 10 至 18 岁年龄组中存在不同的临床严重程度。对标准抗 TNFɑ 治疗有反应的轻度疾病对具有狭窄性的严重、难治性疾病 (B2) 或穿透性 (B3) 并发症通常需要手术干预。诊断时需要最少干预的患者进展为更严重的疾病对疾病结果的准确和自动化预测将显着改善患者的状况。通过为个体患者提供个性化干预措施来实现健康健康。仅依赖于疾病的临床特征和患者生物数据的克罗恩病模型该提案解决了临床实践应用中前景广阔但精度不足的问题。通过利用大量档案和前瞻性患者临床元数据、“组学”和机器学习派生的组织特征，用于构建和测试用于预测特定克罗恩病的机器学习模型在目标 1 中，我们将使用构建、测试和验证克罗恩病的预测模型。金标准活检组织病理学载玻片的计算图像分析我们将使用显着图和基因相关性分析通过可视化对我们的预测至关重要的组织特征来验证我们的模型在目标 2 中，我们将生成模型并识别与这些特征相关的特定转录组变化。通过整合从组织学中提取的深层特征，建立克罗恩病的临床相关预测模型此外，我们还将对作为标准临床护理一部分收集的其他患者元数据进行图像分析。已发布的克罗恩病预测模型的完整列表，用于衡量我们提出的性能的基准最后，在目标 3 中，我们将使用尖端的单细胞 RNA 测序和空间。转录组学方法阐明克罗恩病的转录组学特征并表征特异性这些数据将提供与患病组织的标志性形态变化相关的遗传图谱。研究克罗恩病和其他胃肠道疾病的亚型和临床结果的框架疾病，从而推动个性化治疗和精准医疗的临床适应。研究将提高诊断和预后信息的分辨率，以更好地管理克罗恩病患者的疾病，并显着地将临床管理转向个体化治疗模式。