Optimization of monitoring, prediction and phenotyping of deterioration of inhospital patients using machine learning and multimodal real time data

使用机器学习和多模态实时数据优化住院患者病情恶化的监测、预测和表型分析

• 批准号: 10735863
• 负责人: Karina W. Davidson
• 金额: $ 81.48万
• 依托单位: FEINSTEIN INSTITUTE FOR MEDICAL RESEARCH
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-08-16 至 2027-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10735863
• 关键词: Address; Admission activity; Adult; Algorithms; COVID-19 patient; Caring; Cessation of life; Clinical; Clinical Data; Cluster Analysis; Communities; Country; Data; Data Set; Deterioration; Devices; Diagnosis; Diagnostic; Electronic Health Record; Floor; Health; Health system; Heart Arrest; Hospitalization; Hospitals; Hour; Inpatients; Intensive Care Units; Intervention; Intubation; Life; Link; Machine Learning; Manuals; Measurement; Measures; Medical; Modeling; Monitor; Morbidity - disease rate; Natural Language Processing; Neural Network Simulation; Nurses; Operative Surgical Procedures; Outcome; Patient Admission; Patient Monitoring; Patient-Focused Outcomes; Patients; Phenotype; Prospective cohort; Publishing; Recommendation; Recording of previous events; Recurrence; Research; Resources; Risk; Sleep; Specific qualifier value; Staff Work Load; Symptoms; Target Populations; Time; Training; Validation; Work; Workload; base; clinical predictors; cohort; cost; deep learning model; design; diagnostic value; high risk; improved; innovative technologies; large datasets; learning strategy; machine learning algorithm; machine learning prediction; model design; monitoring device; mortality; multimodality; patient population; personalized care; prediction algorithm; predictive modeling; predictive tools; preventable death; prospective; recurrent neural network; response; support tools; targeted treatment; tool; treatment strategy; unsupervised learning; vector; ward; wearable device; wearable monitor

Efficient patient monitoring on the medical-surgical wards is crucial, because up to 5% of hospitalized adult patients deteriorate, requiring transfer to the intensive care unit (ICU) or intervention of a rapid response team (RRT). Currently, vital sign measurement is performed on all patients every 4-6 hours, even the most stable. For stable patients, this monitoring is often unnecessary, whereas for higher-risk patients, vital sign monitoring every 4-6 hours is often not adequate. To address this need, we will leverage one of the largest, most diverse clinical datasets in the country, using electronic health record (EHR) data from 2.4M hospitalized patients to generate machine learning (ML) predictive models, designed to optimize patient monitoring. We will use continuous monitoring (CM) devices to identify in advance patients likely to deteriorate and specify the clinical underlying reasons of deterioration to enable timely interventions. We have applied and published similar ML approaches on other cohorts, including: 1) deep recurrent neural networks (RNNs) to avoid unnecessary overnight vitals; 2) deep learning models that use continuous monitoring data to predict clinical alerts up to 4 hours ahead of time; and 3) natural language processing on medical notes and unsupervised clustering of patients. Our approach involves collecting prospectively CM data from a targeted population of 2,000 hospitalized patients, and developing and validating models, both retrospectively and prospectively. Our approach will allow us to: Identify stable patients admitted on the medical-surgical wards to optimize vital signs monitoring. We will train a RNN model using EHR data from 2.4M hospitalizations, to predict, after vital signs are measured, stable patients for the next 8 hours, and enable eliminating the next vitals measurement. We retrospectively will validate the model, using cross-affiliation validation, and prospectively, silently validate it in 5 different hospitals. Develop a clinical deterioration algorithm, based on continuous monitoring data and clinical hard outcomes. We will collect prospective data from a targeted population of 2,000 inpatients, who are admitted on medical-surgical floors in our largest hospital, with a modified early warning score higher than 5. The CM patches will start collecting data upon admission. We will use combined clinical hard outcomes (death, intubation, cardiac arrest, unplanned ICU transfer, RRTs) to train two deep- learning models to predict deterioration up to 4 hours and up to 24 hours before. Define the early and late phenotypic substrates of hospitalized patient deterioration. Using the clinical data of 56K deteriorated patients from Aim 1 (EHR variables and extracted presenting symptoms) 4 hour and 24 hours prior to deterioration, we will perform unsupervised cluster analysis to identify unique clusters linked to phenotypes of deterioration. We will associate derived phenotype groups to clinical outcomes and treatments, to inform more targeted treatment and intervention strategies. We aim to develop new tools to align patient needs with resources, and deliver more efficient, effective, personalized, and proactive care to hospitalized patients.

对内外科病房进行有效的病人监控至关重要，因为高达5%的住院成年人 患者病情恶化，需要转移到重症监护病房(ICU)或快速反应小组的干预 (RRT)。目前，所有患者每4-6小时进行一次生命体征测量，即使是最稳定的患者也是如此。 对于病情稳定的患者，这种监测通常是不必要的，而对于高危患者，生命体征监测通常是不必要的。 每4-6小时一次往往是不够的。为了满足这一需求，我们将利用规模最大、最多样化的 全国临床数据集，使用240万住院患者的电子健康记录(EHR)数据 生成机器学习(ML)预测模型，旨在优化患者监控。我们将使用 持续监测(CM)设备，以提前识别可能恶化的患者并指定临床 恶化的根本原因，使及时干预成为可能。我们已经申请并发布了类似的ML 关于其他队列的方法，包括：1)深度递归神经网络(RNN)，以避免不必要的 夜间生命体征；2)深度学习模型，使用连续监测数据预测临床警报，最高可达4 提前数小时；以及3)医疗记录的自然语言处理和无监督的聚类 病人。我们的方法包括从2,000名目标人口中前瞻性地收集CM数据 住院患者，以及开发和验证模型，包括回顾和前瞻性。我们的 方法将使我们能够：确定内外科病房收治的稳定患者，以优化 生命体征监测。我们将使用240万住院患者的电子病历数据来训练RNN模型，以预测 生命体征被测量，患者在接下来的8小时内保持稳定，并能够消除下一个生命体征 测量。我们将使用跨从属验证来回顾验证该模型，并前瞻性地， 在5家不同的医院默默地验证它。开发一种临床恶化算法，基于连续的 监测数据和临床硬结果。我们将从目标人群中收集预期数据 2,000名住院病人，他们住在我们最大的医院的内外科楼层，早期修改了 警告分数高于5。CM补丁将在入院时开始收集数据。我们将使用组合式 临床硬结局(死亡、插管、心脏骤停、计划外ICU转院、RRT)以训练两个深度- 学习模型可以提前4小时和24小时预测病情恶化。定义早点和晚点 住院患者病情恶化的表型底物。使用56K恶化的临床数据 来自AIM 1的患者(EHR变量和提取的主要症状)在4小时和24小时之前 恶化，我们将执行非监督聚类分析，以确定与表型相关联的独特聚类 恶化。我们将把衍生表型群与临床结果和治疗联系起来，以提供更多信息 有针对性的治疗和干预策略。我们的目标是开发新的工具，使患者的需求与 资源，并为住院患者提供更高效、更有效、更个性化和更主动的护理。