Building and implementing a TBI prognostic model featuring real-time analysis of brain CT images

构建并实施具有脑部 CT 图像实时分析功能的 TBI 预后模型

• 批准号: 10579329
• 负责人: Timothy William Dunn
• 金额: $ 54.11万
• 依托单位: DUKE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-01 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10579329
• 关键词: Accident and Emergency department; Admission activity; Affect; American; Brain; Caring; Categories; Cause of Death; Clinical; Clinical Trials; Collaborations; Complex; Complication; Country; Data; Data Set; Databases; Decision Making; Diagnosis; Early Diagnosis; Emergency Care; Environment; Epidemic; Future; Goals; Health system; Healthcare; Healthcare Systems; Hemorrhage; Hospitals; Hour; Inflammation; Infrastructure; Injury; Inpatients; Institution; Intervention; Left; Medical History; Methods; Modeling; Modernization; Monitor; Neural Network Simulation; Neurologic; Outcome; Output; Pathway interactions; Patient risk; Patient-Focused Outcomes; Patients; Performance; Procedures; Process; Prognosis; Prospective cohort; Provider; Psyche structure; Resources; Risk; Running; Secure; Sensitivity and Specificity; Site; TBI Patients; TBI treatment; Technology; Testing; Time; Training; Training and Education; Trauma; Traumatic Brain Injury; Triage; United States; Universities; Update; Validation; Withdrawal; Work; X-Ray Computed Tomography; clinical care; clinical risk; cohort; combat; computer infrastructure; cost; dashboard; data infrastructure; data warehouse; deep learning model; deep neural network; demographics; design; disability; discrete time; experience; experimental study; improved; machine learning model; mild traumatic brain injury; model building; network architecture; neural network architecture; neuron loss; neurosurgery; physically handicapped; predictive modeling; predictive tools; prognostic model; prospective; readmission rates; real-time images; risk prediction; tool; treatment guidelines; young adult

Scope of Work Duke will complete all work for the machine learning model building and implementation of the model into the Duke clinical workflow. For Aim 1 of the project, this work will include data extraction and cleaning, neural network architecture design, and model optimization and validation. For Aim 2, this work will include establishment of technical infrastructure for real-time image and access and processing, construction of a front-end dashboard in close collaboration with frontline clinicians, and deployment and prospective validation of the model. The latter step will also consist of education and training of hospital users. For Aim 3 of the project, Duke will guide staff at Jefferson through the model implementation and validation process, with the active integration and training performed by staff at Jefferson. In Aim 3 Duke will also run the experiments on multi-site model generalization, using retrospective data at both Duke and Jefferson. Data will be shared between Duke and Jefferson via secure ethernet transfer between Jefferson’s secure data warehouse and Duke’s Protected Analytics and Computing Environment. The end goal of the work will be to provide a sophisticated, high-accuracy, and seamlessly integrated tool for predicting the risk of actionable TBI complications over the course of a TBI patient’s hospital encounter. This method, which will augment decision-making for treating a complex neurological condition, will significantly improve overall TBI outcomes, reduce readmission rates, and minimize the extraordinary costs incurred by inefficient provision of healthcare resources.

工作范围 杜克将完成机器学习模型构建的所有工作，并将模型转化为 杜克临床工作流程。对于项目的目标1，这项工作将包括数据提取和清洗，神经网络， 架构设计、模型优化和验证。就目标2而言，这项工作将包括建立 实时成像、访问和处理技术基础设施， 与前线临床医生紧密合作，以及模型的部署和前瞻性验证。后者 这些步骤还包括对医院使用者进行教育和培训。对于该项目的目标3，杜克将指导工作人员在 杰佛逊通过模型的实施和验证过程，积极与培训相结合 由杰斐逊的工作人员表演。在目标3中，杜克还将进行多地点模型泛化的实验， 使用杜克和杰斐逊的回顾性数据。杜克和杰斐逊之间将通过安全的 Jefferson的安全数据仓库和杜克的Protected Analytics and Computing之间的以太网传输 环境这项工作的最终目标将是提供一个复杂的，高精度的，无缝的 用于预测TBI患者住院期间可采取行动的TBI并发症风险的集成工具 遭遇这种方法，这将增加决策治疗一个复杂的神经系统疾病， 显著改善TBI的总体结局，降低再入院率，并最大限度地减少额外费用 这是由于医疗资源的缺乏效率。

项目成果

Duke Liver Dataset: A Publicly Available Liver MRI Dataset with Liver Segmentation Masks and Series Labels.

杜克肝脏数据集：具有肝脏分割掩模和系列标签的公开肝脏 MRI 数据集。

• DOI: 10.1148/ryai.220275
• 发表时间: 2023
• 期刊: Radiology. Artificial intelligence
• 作者: Macdonald,JacobA;Zhu,Zhe;Konkel,Brandon;Mazurowski,MaciejA;Wiggins,WalterF;Bashir,MustafaR
• 通讯作者: Bashir,MustafaR