Using Wearable Passive Sensing to Predict Engagement in Binge Eating in Response to Negative Affect: A Multimethod Investigation of Predictive Utility, Feasibility, and Acceptability

使用可穿戴被动传感来预测对负面情绪的暴食反应：预测效用、可行性和可接受性的多方法研究

• 批准号: 10606680
• 负责人: Emily Kelley Presseller
• 金额: $ 4.68万
• 依托单位: DREXEL UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-11-01 至 2024-10-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10606680
• 关键词: Adult; Affect; Affective; Algorithms; Arousal; Awareness; Behavioral Symptoms; Binge Eating; Binge eating disorder; Biological Markers; Bulimia; Cellular Phone; Cognitive Therapy; Communities; Conscious; Consumption; Data; Data Collection; Development; Devices; Diabetes Mellitus; Eating; Eating Behavior; Eating Disorders; Ecological momentary assessment; Focus Groups; Food; Future; Goals; Health Services Accessibility; Heart Rate; Individual; Intervention; Investigation; Knowledge; Literature; Maintenance; Measurement; Measures; Mental disorders; Methods; Modeling; Nervous system structure; Neurobehavioral Manifestations; Obesity; Participant; Patient Self-Report; Patients; Physiological; Population; Psychophysiology; Public Health; Regulation; Reporting; Research; Risk; Role; Specific qualifier value; Surveys; Symptoms; Testing; Time; Treatment outcome; acceptability and feasibility; adaptive intervention; base; clinically significant; design; emotional symptom; experience; feeding; fitbit; heart rate variability; improved; loss of control over eating; machine learning algorithm; negative affect; preference; psychiatric comorbidity; recruit; reinforced behavior; response; sensor; wearable sensor technology

PROJECT SUMMARY/ABSTRACT Binge eating, characterized by eating a large amount of food in a short period of time accompanied by a sense of loss of control over eating, is a public health crisis. Negative affect is a well-established antecedent for binge eating. The affect regulation model of binge eating posits that elevated negative affect increases momentary risk for binge eating, as engaging in binge eating alleviates negative affect and reinforces the behavior. The field’s existing capacity to identify moments of elevated negative affect, and thus risk for binge eating, has largely relied on ecological momentary assessment (EMA). EMA involves the completion of surveys in real time on one’s smartphone to report behavioral, cognitive, and emotional symptoms throughout the day. Although EMA provides ecologically valid information about daily experiences, EMA surveys are often delivered only 5-6 times per day, involve self-report of affect intensity, and are unable to assess physiological arousal that accompanies affect. Wearable, psychophysiological sensors that measure markers of affect arousal including heart rate, heart rate variability, and electrodermal activity, may augment EMA surveys to improve our capacity to accurately detect risk for binge eating in real time. These sensors can objectively, continuous, and passively measure biomarkers of nervous system arousal that coincide with affect, thus allowing them to measure affective trajectories on a continuous timescale, detect changes in negative affect before the individual is consciously aware of them, and reduce user burden to improve data completeness. Despite their potential to improve the field’s capacity to detect risk for binge eating, the feasibility and acceptability of these sensors among individuals with binge eating has not yet been established. Additionally, it is unknown whether features extracted from these sensors can adequately distinguish between positive and negative affect states, given that physiological arousal may occur during both negative and positive affect states. The aims of the present study are: 1) test the hypothesis that sensor features will distinguish positive and negative affect states in individuals with binge eating with > 60% accuracy; 2) test the hypothesis that a machine learning algorithm using sensor data and EMA-reported negative affect data to predict the occurrence of binge eating episodes will predict binge eating with greater accuracy than an algorithm using EMA-reported negative affect alone; 3) use a mixed methods approach to evaluate acceptability and feasibility of wearable sensors among individuals with binge eating. To do so, the present study will recruit 30 individuals with clinically-significant binge eating who will wear Empatica E4 wristbands to passively measure heart rate and electrodermal activity and report affect and binge eating on EMA surveys for four weeks. Participants with binge eating (N = 30) and community eating disorder clinicians (N = 10) will also complete self-report measures and focus groups to assess the feasibility, acceptability, and user preferences regarding the use of sensors to power improved momentary interventions for binge eating.

项目总结/摘要 暴饮暴食，特征是在短时间内吃下大量食物并伴有 一种对饮食失去控制的感觉，是一种公共卫生危机。负面情绪是一个公认的前因 因为暴饮暴食暴饮暴食的情绪调节模型认为， 暴饮暴食的瞬间风险，因为暴饮暴食会消除负面影响，并加强 行为该领域现有的能力，以确定升高的负面影响的时刻，从而为狂欢的风险 在很大程度上依赖于生态瞬时评估（EMA）。EMA涉及完成 在智能手机上进行真实的实时调查，以报告整个过程中的行为、认知和情绪症状 白天虽然EMA提供了关于日常经验的生态有效信息，但EMA调查通常 每天仅提供5-6次，涉及自我报告的影响强度，并且无法评估生理 伴随着情感的唤起。可穿戴的心理生理传感器，测量情感标记 包括心率、心率变异性和皮肤电活动在内的唤醒可能会增加EMA调查， 提高我们准确检测真实的暴食风险的能力。这些传感器可以客观地， 连续和被动地测量与情感一致的神经系统唤醒的生物标志物， 允许他们在连续的时间尺度上测量情感轨迹， 在个人有意识地意识到它们之前，减轻用户负担，提高数据完整性。 尽管它们有潜力提高该领域检测暴饮暴食风险的能力，但其可行性和 这些传感器在暴饮暴食的个体中的可接受性尚未建立。而且 尚不清楚从这些传感器提取的特征是否能够充分区分阳性和阴性。 消极情感状态，考虑到生理唤醒可能发生在消极和积极的影响， states.本研究的目的是：1）测试假设，传感器功能将区分积极的 和负面情绪状态的个人与暴食的准确性> 60%; 2）测试的假设， 机器学习算法使用传感器数据和EMA报告的负面影响数据来预测发生 的暴饮暴食事件将预测暴饮暴食的准确性比使用EMA报告的算法更高。 3）使用混合方法评估可穿戴设备的可接受性和可行性 在暴饮暴食的个体中的传感器。为此，本研究将招募30名 具有临床意义的暴饮暴食者，将佩戴Empatica E4腕带被动测量心率， 皮肤电活动和报告影响和暴食的EMA调查四周。参与者 暴饮暴食（N = 30）和社区饮食失调临床医生（N = 10）也将完成自我报告 措施和焦点小组，以评估有关使用的可行性，可接受性和用户偏好， 传感器为改善暴饮暴食的瞬间干预提供动力。