A machine learning based fetal monitoring system to predict and prevent fetal hypoxia.

基于机器学习的胎儿监测系统，用于预测和预防胎儿缺氧。

• 批准号: 10760437
• 负责人: Bonnie Lesley Zell
• 金额: $ 26.13万
• 依托单位: DELFINA CARE INC.
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-09-05 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10760437
• 关键词: Address; Adverse event; Algorithms; Brain Injuries; Cardiotocography; Caring; Cerebral Palsy; Cesarean section; Clinical; Clinical Management; Computer software; Coupled; Data; Data Set; Development; Devices; Discipline of obstetrics; Effectiveness; Electronic Health Record; Electronics; FDA approved; Fatigue; Fetal Heart Rate; Fetal Monitoring; Future; Grant; Guidelines; Health; Health Professional; Hospitals; Hypoxia; Injury; Intelligence; Intervention; Knowledge; Machine Learning; Manuals; Marketing; Measurement; Measures; Modeling; Monitor; Mothers; Newborn Infant; Outcome; Output; Patient Care; Patient Monitoring System; Performance; Perinatal Hypoxia; Personal Satisfaction; Phase; Physicians; Pregnancy; Pregnant Women; Provider; Research; Risk; Risk Assessment; Safety; Sensitivity and Specificity; Signal Transduction; Site; Standardization; System; Techniques; Testing; Time; Training; United States; Uterus; Validation; Visualization; adverse pregnancy outcome; clinical decision support; clinical decision-making; clinical predictors; clinical research site; commercialization; data visualization; efficacy evaluation; evidence base; fetal; fetus hypoxia; improved; improved outcome; insight; intrapartum; machine learning algorithm; machine learning method; machine learning model; machine learning prediction; mobile application; neonatal encephalopathy; neonatal hypoxic-ischemic brain injury; novel; patient safety; phase 1 testing; predictive modeling; prevent; software systems; standard of care; stillbirth; success; tool; ward

Project Summary/Abstract: Although EFM is widely deployed in the United States for most deliveries, it has failed to reduce rates for hypoxic injuries such as neonatal encephalopathy, despite an increased rate of cesarean sections. This lack of improvement has been attributed to inconsistent applications of vague guidelines during manual analysis of EFM tracings. Existing automated tools available in the market to augment physician capabilities take the form of low-precision simplistic rule-based alerts, which cause alarm fatigue and also fail to deliver improvements. This project proposes the creation and validation of a machine learning model for prediction of intrapartum fetal hypoxia with high sensitivity and specificity to address this need. Using a multi-site dataset of 50,000 tracings coupled with electronic health records, a combination of clinical knowledge and a variety of machine learning techniques will be used to create a model with leading performance. To clear the high bar set by FDA for patient safety with a de novo device, this proposal aims to validate this model by demonstrating high sensitivity and specificity on a held-out portion of this large multi-site data set, along with a user study to demonstrate improved performance by clinicians with software assistance. After this project demonstrates the safety and efficacy of this model for patient care, a future Phase II will beta test a software solution integrating this model in labor and delivery wards. The research plan outlined in this proposal will give obstetricians a valuable evidence-based tool to help them interpret EFM tracings.

项目概要/摘要： 尽管EFM在美国的大多数交付中都得到了广泛部署，但它未能降低 缺氧性损伤，如新生儿脑病，尽管剖宫产率增加。这种缺乏 改进归因于在人工分析期间不一致地应用模糊的指导方针， EFM跟踪。市场上现有的增强医生能力的自动化工具采取以下形式 基于规则的低精度简单化警报，导致警报疲劳，也无法提供改进。 该项目提出了一个机器学习模型的创建和验证，用于预测产时胎儿 低氧具有高灵敏度和特异性，以满足这一需求。使用包含50，000个描记的多站点数据集 再加上电子健康记录，结合临床知识和各种机器学习， 技术将用于创建具有领先性能的模型。为了清除FDA为 患者安全性与从头器械，该提案旨在通过证明高灵敏度来验证该模型 和特异性，这一大型多站点数据集的保留部分，沿着用户研究，以证明 通过软件辅助提高临床医生的性能。在这个项目证明了安全性和 为了验证该模型对患者护理的有效性，未来的第二阶段将测试集成该模型的软件解决方案 在分娩和分娩病房。该研究计划概述了这一建议将给产科医生一个宝贵的 以证据为基础的工具，以帮助他们解释EFM跟踪。