Predicting post-transplant kidney function from pre-transplant biopsy and clinical biomarkers using a convolutional neural network

使用卷积神经网络根据移植前活检和临床生物标志物预测移植后肾功能

• 批准号: 10315165
• 负责人: Mackenzie Anne Eagleson
• 金额: $ 8.65万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2023-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10315165
• 关键词: Adopted; Adoption; Advisory Committees; Algorithms; Allografting; Biometry; Biopsy; Cessation of life; Chronic; Clinical; Counseling; Country; Data; Data Analyses; Data Set; Decision Making; Deterioration; Doctor of Philosophy; Donor person; Environment; Epidemiology; Evaluation; Feedback; Funding; Glomerular Filtration Rate; Health; Histologic; Histology; Hospitals; Hour; Human; Image; Institution; Instruction; Interview; Kidney; Kidney Transplantation; Knowledge; Learning; Lesion; Life; Link; Logistics; Machine Learning; Maryland; Medicine; Mentors; Modeling; Modernization; Operative Surgical Procedures; Organ; Outcome; Pathologic; Pathologist; Pathology; Patients; Performance; Persons; Physicians; Positioning Attribute; Provider; Public Health Schools; Qualitative Methods; Recovery; Renal function; Reporting; Reproducibility; Research; Research Personnel; Risk; Savings; Scientist; Severities; Slide; Specialist; Standardization; Statistical Computing; Supervision; Surgeon; Techniques; Time; Training; Transplant Recipients; Transplant Surgeon; Transplantation; Transplantation Surgery; United States National Institutes of Health; Validation; Visual; Waiting Lists; adaptive learning; advanced analytics; base; career; clinical biomarkers; clinical investigation; clinical practice; convolutional neural network; data registry; design; experience; graft function; implantation; improved; indexing; kidney biopsy; levan; mortality; new technology; next generation; post-transplant; prevent; prognostic significance; prognostic value; rapid technique; skills; success; task analysis; tool; transplant centers; transplant registry

PROJECT SUMMARY/ABSTRACT The need for transplantable kidneys far exceeds their availability with over 90,000 candidates currently waitlisted but less than 22,000 transplants performed annually. Over 8,000 patients are removed from the waitlist each year due to death or deterioration in health while awaiting an offer. Despite this critical need for organs, nearly 20% of recovered kidneys are ultimately discarded. The most commonly reported reason for discard is unfavorable histology on donor biopsy. These pre-transplant biopsies are performed in order to assess the quality of the organ and are often used as a tool to predict post-implantation allograft performance. Unfortunately, the prognostic significance of biopsy findings is controversial and there is growing concern regarding the reliability and reproducibility of data derived from biopsy interpretation due to inter-pathologist variability. Recent evidence demonstrates that recipient graft outcomes correlate only with donor biopsy interpretation performed by an experienced renal pathologist. However, most transplant centers have no more than a handful of dedicated expert renal pathologists; given that organ recovery often occurs at remote hospitals late at night or on weekends, biopsies are usually interpreted by on-call pathologists without dedicated training in renal histology. These providers tend to overestimate the severity of chronic lesions, resulting in the inappropriate discard of otherwise acceptable organs. Convolutional neural networks (CNNs), a machine learning technique, can equal or exceed human performance in visual analysis tasks in an automated, objective fashion. We propose to leverage this new technology to accomplish the following aims: (1) To develop a CNN that reliably and accurately predicts post- transplant graft function from digitized procurement biopsy slides and donor and recipient metrics in the Scientific Registry of Transplant Recipients (SRTR) dataset; (2) To compare the predictive accuracy of our CNN to currently available donor risk scores; and (3) To qualitatively evaluate CNN adoptability, acceptability, and utility by clinicians. These aims are highly feasible given our group's expertise in machine learning, kidney transplantation, and analysis of SRTR data. We hypothesize that we can build a CNN that provides transplant physicians with accurate pre-operative real- time estimates of post-transplant graft success to help guide patient counseling. If the proposed aims are achieved, feedback from our CNN could prevent the inappropriate discard of thousands of kidneys and decrease waitlist mortality by increasing the number of transplants performed across the country. By conducting this research, Dr. Eagleson will cultivate a skillset that includes national registry data analysis, qualitative methods, and machine learning: important modern techniques that are rapidly becoming used throughout medicine and will serve her well throughout her career as an independent surgeon-scientist.

项目摘要/摘要 目前有超过90,000名候选人，对可移植肾脏的需求远远超过其可用性 候补名单，但每年不到22,000个移植物进行。超过8,000名患者被从 每年由于健康的死亡或恶化而在等待要约时候补名单。尽管有迫切需要 器官，近20％的回收肾脏最终被丢弃。最常见的原因 丢弃是对供体活检的组织学不利的。这些前移植活检是为了 评估器官的质量，通常被用作预测植入后同种异体移植性能的工具。 不幸的是，活检发现的预后意义是有争议的，并且越来越关注 关于从活检解释中得出的数据的可靠性和可重复性 可变性。最近的证据表明，受体移植结果仅与供体活检相关 由经验丰富的肾脏病理学家进行的解释。但是，大多数移植中心不再 比少数敬业的专家肾脏病理学家；鉴于器官恢复经常发生在遥控 晚上或周末的医院，活检通常是由无人驾驶病理学家解释的 肾脏组织学的专门培训。这些提供者倾向于高估慢性病变的严重程度， 导致不当丢弃原本可接受的器官。 卷积神经网络（CNN）是一种机器学习技术，可以等于或超过人类 以自动，客观的方式执行视觉分析任务。我们建议利用这个新的 实现以下目的的技术：（1）开发可靠，准确预测后的CNN 来自数字化采购活检载玻片以及供体和受体指标的移植移植功能 移植接受者的科学注册表（SRTR）数据集； （2）比较我们的预测准确性 CNN目前可用的捐助者风险分数； （3）定性评估CNN的可采用性，可接受性， 和临床医生的公用事业。鉴于我们小组在机器学习方面的专业知识，肾脏是非常可行的 SRTR数据的移植和分析。 我们假设我们可以构建一个CNN，该CNN为移植医师提供了准确的术前的实地 移植后移植物成功的时间估计，以帮助指导患者咨询。如果拟议的目的是 实现的，我们的CNN的反馈可以防止丢弃成千上万的肾脏和 通过增加全国进行的移植数量来降低候补名单的死亡率。经过 在这项研究中，Eagleson博士将培养一个技能集，其中包括国家注册表数据分析， 定性方法和机器学习：迅速使用的重要现代技术 在整个医学中，她将在整个职业生涯中以独立的外科医生科学家的身份为她服务。