Early Signs: digital phenotyping to identify digital biomarkers for predicting burnout and cognitive functioning in ED clinicians

早期迹象：通过数字表型分析来识别数字生物标志物，以预测急诊临床医生的倦怠和认知功能

• 批准号: 10449250
• 负责人: Katharina Schultebraucks
• 金额: $ 72.56万
• 依托单位: COLUMBIA UNIVERSITY HEALTH SCIENCES
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-15 至 2022-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10449250
• 关键词: Accident and Emergency department; Affect; Behavioral; Biological Markers; Blood specimen; COVID-19 pandemic; Cardiovascular Diseases; Chronic stress; Clinical; Complement; Computing Methodologies; Data; Data Analyses; Detection; Development; Diagnostic; Disasters; Emergency Care; Emergency Department Physician; Emergency Nursing; Emergency Situation; Emergency department crowding; Emotional; Emotions; Environment; Exposure to; Face; Facial Expression; Feedback; Foundations; Goals; Hair; Head Movements; Health; Health Personnel; Healthcare; Healthcare Systems; High Prevalence; Hydrocortisone; Impaired cognition; Individual; Intervention; Interview; Knowledge; Longitudinal prospective study; Machine Learning; Measures; Mediating; Medical Errors; Methods; Modality; Monitor; Movement; Mydriasis; Nurses; Occupations; Outcome; Pathology; Patient Care; Patient Self-Report; Patients; Pattern; Pattern Recognition; Performance; Personal Satisfaction; Persons; Phenotype; Physicians; Physiological; Prevention; Prevention strategy; Prognosis; Psyche structure; Public Health; Reporting; Research; Risk; Sampling; Schedule; Secure; Self Care; Self Management; Sleep; Societies; Speech; Stress; Stress Tests; Structure; Symptoms; Testing; Time; Training; Vertebral column; Visit; Voice; Well in self; Work; acute care; anthropogenesis; base; biomarker panel; burnout; cardiovascular disorder risk; cardiovascular effects; cardiovascular risk factor; care systems; clinical predictors; clinical risk; clinically relevant; cognitive function; cognitive performance; cohort; deep learning; deep learning algorithm; deep neural network; digital; executive function; experience; gaze; improved; individual patient; innovation; mortality; multimodality; novel; pandemic disease; predictive marker; prognostic; prognostic tool; prognostic value; programs; psychologic; psychological outcomes; response; safety net; screening; shift work; social; stressor; transfer learning

Project Summary The Emergency Department (ED) is a central pillar of the health care system. ED physicians and nurses are exposed to high work-related stressors in addition to disruptive day-night shifts. The well- being of the 150,000 ED clinicians in the U.S. is important for public health with significant downstream effects on the well-being of the 145 million patients that are served every year. Of the 1 million U.S. physicians, 45% are reporting burnout symptoms and the number increases to 70% in ED physicians and up to 82% in ED nurses. Clinician burnout is associated with increased risk for cardiovascular diseases, mortality, medical errors, but also stress-mediated physiological alterations and cognitive decline. Yet, the knowledge about the long-term development of burnout is limited. To effectively intervene, the timely identification of ED clinicians at risk for burnout is a critical prerequisite. This study proposes an innovative approach using digital phenotyping to discover and test Digital Biomarkers as predictors of burnout symptoms and cognitive function. This proposed prospective longitudinal study will chart cognitive functioning and burnout symptom trajectories in a cohort of 350 ED clinicians to inform when, where, and how to intervene. We will use advanced computational methods to extract objective markers for burnout and cognitive decline from video and audio data. Based on our preliminary data, we hypothesize that voice and speech content, head movement, pupil dilation, gaze, and facial landmark features of emotion provide probabilistic information that will allow us to identify digital biomarkers for burnout and cognitive function. We will test the relevance of the discovered digital biomarkers and determine their discriminatory accuracy to distinguish between risk for clinically relevant vs. non-relevant burnout symptoms. We examine the association of digital biomarkers with physiological markers of chronic stress (i.e., hair cortisol concentration). We will also assess the association of digital biomarkers with the long-term job-related stress load of individual ED clinicians such as high ED crowding, patient acuity level, ED staffing, sleep, and shift schedules. This research program aims to deliver an objective, accurate, and reliable digital measure for clinician well-being. Such digital biomarkers will enable more efficient ED clinician self-management and will promote low-threshold prevention strategies. The mental and physical well-being of ED clinicians is of high value to those who work day in and day out to save the lives of others and is the foundation of a well-functioning, high-quality emergency care system.

项目摘要 急诊科（艾德）是卫生保健系统的核心支柱。艾德医生和 护士除了要承受令人不安的日夜轮班外，还要承受与工作有关的高度压力。井- 作为美国15万名艾德临床医生中的一员， 这对每年接受服务的1.45亿患者的福祉产生了下游影响。的1 100万美国医生中，45%报告有倦怠症状，而这一数字在2013年增加到70% 艾德医生和高达82%的艾德护士。临床医生职业倦怠与以下风险增加相关： 心血管疾病、死亡率、医疗差错，以及压力介导的生理变化 和认知能力下降然而，对职业倦怠的长期发展的认识是有限的。到 有效干预，及时识别艾德临床医生的倦怠风险是一个关键 先决条件。这项研究提出了一种创新的方法，使用数字表型来发现和 测试数字生物标志物作为倦怠症状和认知功能的预测因子。 这项前瞻性纵向研究将绘制认知功能和倦怠 在一个由350名艾德临床医生组成的队列中研究症状轨迹，以告知何时、何地以及如何进行干预。 我们将使用先进的计算方法来提取倦怠和认知的客观标记， 从视频和音频数据下降。根据我们的初步数据，我们假设声音和 言语内容、头部运动、瞳孔扩张、凝视和情感的面部标志特征 提供概率信息，使我们能够识别倦怠的数字生物标志物， 认知功能 我们将测试所发现的数字生物标志物的相关性，并确定它们的区分度。 区分临床相关与非相关倦怠症状风险的准确性。我们 检查数字生物标志物与慢性应激的生理标志物的关联（即，头发 皮质醇浓度）。我们还将评估数字生物标志物与长期 个体艾德临床医生工作相关压力负荷，例如高艾德拥挤度、患者紧急程度、艾德 人员配备睡眠和轮班安排这项研究计划旨在提供一个客观，准确， 和可靠的数字测量临床医生的福祉。这种数字生物标志物将使更有效的 艾德临床医生自我管理，并将促进低门槛预防策略。的精神和 艾德临床医生的身体健康对于那些日复一日地工作以拯救 它是一个功能完善、高质量的紧急护理系统的基础。