Towards autonomous management of cardiogenic shock

迈向心源性休克的自主管理

基本信息

批准号：
10580751
负责人：
Nicholas E. Houstis
金额：
$ 16.8万
依托单位：
MASSACHUSETTS GENERAL HOSPITAL
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-04-01 至 2024-06-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10580751
关键词：
Algorithms Artificial Intelligence Automation Aviation Awareness Behavior Benchmarking Cardiac Cardiogenic Shock Cardiovascular Models Cardiovascular Physiology Caring Cessation of life Clinical Clinical Data Cognitive Complex Computerized Medical Record Congestive Heart Failure Critical Illness Data Data Set Databases Decision Making Devices Dose Electronic Health Record Environment Event Family Feedback Functional disorder Future General Hospitals Goals Growth Hand Head Heart failure Human Intensive Care Intensive Care Units Intervention Knowledge Learning Life Massachusetts Measurement Mechanics Methods Modeling Monitor Nature Operative Surgical Procedures Organ failure Outcome Oxygen Patient-Focused Outcomes Patients Performance Pharmaceutical Preparations Phase Physicians Physiology Policies Policy Analysis Psyche structure Psychological reinforcement Publishing Quality of Care Rewards Robotics Role Safety Sampling Self-Help Devices Suggestion System Techniques Technology Telemetry Time Titrations Training Work algorithm training animation cardiac intensive care unit comorbidity computer science computerized tools design digital health experience hemodynamics improved individualized medicine learning algorithm learning strategy patient response preservation simulation support tools tool unethical

项目摘要

Project Summary Physicians in the cardiac intensive care unit (CCU) make decisions in an increasingly data- and knowledge- rich world, yet often they get little help. Currently, each physician makes decisions based on his or her mental model of the patient’s physiology, together with mental predictions of the patient’s response to intervention. This approach can lead to a range of behaviors that compromise patient outcomes, including oversimplification of the physiology, errors due to cognitive overload, and physician to physician variability in decision making. A computational tool equipped with quantitative knowledge of physiology, the ability to systematically evaluate all the data, and informed by a database of past action-outcome events could aid the physician with valuable suggestions for action. We propose to train an algorithm to make decisions about dosing vasoactive medications and initiating mechanical support in patients with cardiogenic shock due to decompensated heart failure. This focused set of decisions entails calculations about the physiology that are normally performed in a physician’s head. We frame the decision problem as optimizing cardiovascular function to preserve oxygen delivery, and we apply tools from optimal control. Rather than hand-design a CCU controller we will use reinforcement learning (RL) techniques to “fit” one. The field of RL has experienced explosive growth over the past few years, with notable advances in strategic decision problems and robotics. A key challenge in the clinical environment is that the exploration phase of learning (“trial and error”) would be unethical in real patients. A second challenge is that the availability of patient data, while growing, is likely to be a bottleneck. We will leverage state-of-the-art model-based RL to train an algorithm using a combination of simulation and off-policy learning from historical data. We will use a model of cardiovascular physiology that underlies cardiac simulators in use today for the training of cardiologists. Historical patient data will come from the Massachusetts General Hospital Clinical Data Animation Center which has recorded real-time telemetry waveform data in addition to standard electronic medical record data from all CCU patients spanning several years. This is one of the largest and most complete datasets of its kind. The complexity of managing cardiogenic shock will continue to escalate as tools become more sophisticated and patients live longer, with more extensive comorbidities. Advanced decision support tools could help tame this complexity, improving the quality of care as well as democratizing it.

项目概要心脏重症监护病房 (CCU) 的医生根据越来越多的数据和数据做出决策知识丰富的世界，但他们往往得不到什么帮助。目前，每个医生都根据自己的情况做出决定。她对患者生理机能的心理模型，以及对患者反应的心理预测这种方法可能会导致一系列损害患者治疗结果的行为，包括生理学的过度简化、认知超载导致的错误以及医生之间的差异一种具有定量生理学知识和能力的计算工具。系统地评估所有数据，并通过过去行动结果事件的数据库提供信息，可以帮助医生提出宝贵的行动建议。我们建议训练一种算法来做出有关血管活性药物的剂量和启动的决策失代偿性心力衰竭导致的心源性休克患者的机械支持。决策需要对生理学进行计算，而这些计算通常是在医生的头脑中进行的。决策问题是优化心血管功能以保持氧气输送，我们应用以下工具我们将使用强化学习 (RL) 技术，而不是手动设计 CCU 控制器。强化学习领域在过去几年中经历了爆炸性增长，在以下方面取得了显着进展。战略决策问题和机器人技术在临床环境中的一个关键挑战是探索阶段。对于真实的患者来说，学习（“试错”）是不道德的第二个挑战是可用性。患者数据虽然不断增长，但很可能成为瓶颈。我们将利用最先进的基于模型的强化学习进行训练。结合模拟和从历史数据中学习的算法我们将使用一个模型。心血管生理学是当今用于培训心脏病专家的心脏模拟器的基础。历史患者数据将来自麻省总医院临床数据动画中心，该中心除了来自所有地方的标准电子病历数据之外，还记录了实时遥测波形数据这是同类数据中最大、最完整的数据集之一。随着工具变得更加复杂和复杂，管理心源性休克的复杂性将继续升级患有更广泛合并症的患者寿命更长，先进的决策支持工具可以帮助解决这一问题。复杂性，提高护理质量并使其民主化。