Smart Cuff: Multi-Parameter Hemodynamic Monitoring via a Single Convenient Device

智能袖带：通过单个便捷设备进行多参数血流动力学监测

• 批准号: 10583061
• 负责人: RAMAKRISHNA MUKKAMALA
• 金额: $ 71.7万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-03-10 至 2027-01-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10583061
• 关键词: Achievement; Algorithms; Automated Clinical Decision Support; Blood Pressure; Blood Pressure Monitors; Blood flow; Cardiac Output; Cardiovascular system; Caring; Catheters; Clinical; Collection; Complex; Computer software; Custom; Data; Detection; Devices; Diagnosis; Diastolic blood pressure; EFRAC; Echocardiography; Enhancement Technology; Goals; Health Care Costs; Hospital Costs; Hospitals; Hypotension; Intensive Care; Intervention; Left Ventricular Ejection Fraction; Liquid substance; Machine Learning; Manuals; Measurement; Measures; Medical center; Monitor; Operative Surgical Procedures; Outcome; Patient Care; Patient-Focused Outcomes; Patients; Physiological; Population; Precision therapeutics; Pulmonary artery structure; Pulse Pressure; Real-Time Systems; Research Project Grants; Surgical Management; Systems Integration; Technology; Testing; Time; Titrations; Training; Translating; Universities; Variant; algorithm training; arm; clinical care; cohort; commercialization; heart function; hemodynamics; improved; innovation; intelligent algorithm; machine learning algorithm; monitoring device; novel; pressure; real time monitoring

PROJECT SUMMARY/ABSTRACT Multi-parameter hemodynamic monitoring is needed to manage surgical and intensive care patients. Monitoring blood pressure (BP), cardiac output (CO), and left ventricular ejection fraction (EF), in particular, permits detection of frequent hypotension and hemodynamic instability, diagnosis of the cause for selecting appropriate therapy, and titration of interventions (e.g., goal-directed therapy). However, measurement of these three hemodynamic variables currently requires multiple devices that are invasive, manual, or specialized. While the oscillometric arm cuff device is non-invasive, automated, and standard, it only estimates BP from the measured cuff pressure waveform via a population average algorithm that does not maintain accuracy over the clinical range. The overall goal of this project is to extend the ubiquitous arm cuff device for accurate and convenient multi- parameter hemodynamic monitoring via smart algorithms. The specific aims are: (1) to build an arm cuff device for recording cuff pressure waveforms; (2) to simultaneously acquire patient data with this and reference devices for algorithm training; (3) to develop and incorporate algorithms for accurately computing BP, CO, and EF from the cuff pressure waveform based on the training data; and (4) to validate the real-time Smart Cuff against reliable reference measurements in patients. The device will be developed to control the cuff pressure and incorporate custom algorithms. The cuff pressure waveform via the device and reference BP, CO, and EF via arterial and pulmonary artery catheters and echocardiography will be recorded before and after clinical interventions in many surgical and intensive care patients. These training data will be analyzed to refine or adapt previous physiologic algorithms and to investigate potentially superior machine learning algorithms for best estimation of the three hemodynamic variables. The final algorithms will be implemented for a real-time device, and the integrated system will be tested against the same reference measurements during clinical interventions but from new patients. Achievement of the specific aims will be followed by a translational project to bring the Smart Cuff to patient care and a research project to extend the device capabilities including addition of automated clinical decision support. Ultimately, these efforts may help in improving patient outcomes and reducing healthcare costs in the near-term.

项目总结/摘要 需要多参数血流动力学监测来管理手术和重症监护患者。 监测血压（BP）、心输出量（CO）和左心室射血分数（EF）， 特别是，允许检测频繁的低血压和血流动力学不稳定， 选择适当治疗的原因，以及干预措施的滴定（例如，目标导向疗法）。 然而，这三个血流动力学变量的测量目前需要多个设备 是侵入性的，手动的，或者专门的。虽然测量臂袖带装置是非侵入性的， 自动化和标准化，它只通过测量袖带压力波形来估计BP。 群体平均算法不能在临床范围内保持准确度。整体 本项目的目标是扩展无处不在的手臂袖口设备，以实现准确和方便的多功能， 通过智能算法进行血流动力学参数监测。具体目标是：（1）建立一个手臂 用于记录袖带压力波形的袖带装置;（2）与该袖带装置同时采集患者数据， 和算法训练的参考设备;（3）开发和整合算法， 基于所述训练数据从所述袖带压力波形计算BP、CO和EF;以及（4） 根据患者的可靠参考测量值验证实时智能袖带。该设备将 开发用于控制袖带压力并结合自定义算法。袖带压力 通过器械测量波形，通过动脉和肺动脉导管测量参考BP、CO和EF 超声心动图将在许多外科手术和 重症监护病人这些训练数据将被分析，以改进或适应先前的生理数据。 算法，并研究潜在的上级机器学习算法，以获得 三个血液动力学变量。最终的算法将在实时设备上实现， 在临床试验期间，将根据相同的参考测量结果对集成系统进行测试 但对于新患者。具体目标实现后， 将智能袖带引入患者护理的转化项目和将 设备功能，包括增加自动临床决策支持。最终，这些努力 可能有助于改善患者的治疗效果，并在短期内降低医疗成本。