Developing an Objective and Quantifiable Measure of Itch Using Artificial Intelligence and Radio Signals

使用人工智能和无线电信号开发客观且可量化的瘙痒测量方法

• 批准号: 10365429
• 负责人: Dina Katabi
• 金额: $ 27.69万
• 依托单位: MASSACHUSETTS INSTITUTE OF TECHNOLOGY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-01 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10365429
• 关键词: Address; Adherence; Affect; Artificial Intelligence; Behavior; Body part; Breathing; Child; Circadian Rhythms; Clinic; Clinical; Clinical Research; Clinical Trials; Collaborations; Communities; Data; Development; Devices; Disease; Disease Management; Environment; Expenditure; FDA approved; Future; Gait; Gold; Heart Rate; Home; Human; Impaired cognition; Life; Light; Longitudinal Studies; Machine Learning; Measures; Methods; Monitor; Morbidity - disease rate; Motion; Neural Network Simulation; Observational Study; Outcome Assessment; Patient Self-Report; Patients; Perception; Performance; Persons; Polysomnography; Population; Privacy; Property; Pruritus; Quality of life; Radio; Reaction; Research; Respiration; Self Assessment; Sensitivity and Specificity; Severities; Signal Transduction; Skin; Sleep; Sleep Stages; Sleep disturbances; Testing; Therapeutic; Time; Vulnerable Populations; Wrist; actigraphy; awake; base; chronic itch; chronic pain; drug development; falls; improved; machine learning model; novel; novel therapeutics; prospective; sensor; sensor technology; skin irritation; sleep onset; sleep quality; standard of care; success; therapy development; wearable device; wearable sensor technology; wireless electronic; wireless fidelity; wireless sensor

PROJECT SUMMARY Chronic itch affects 13% of the population and is associated with over $90 billion in annual population- expenditures in the US. It has a profound negative impact on quality of life, and is often as debilitating as chronic pain. Yet, there are currently no FDA-approved treatments for chronic itch. A major obstacle in assessing therapeutics for itch is the difficulty in measuring it, which hinders assessment of outcomes in the clinic and the development of new drugs. The current clinical standard for quantifying itch relies on patients’ self-assessment of the severity of their itch on a scale of 0 to 10, which is: 1) highly subjective and hard to generalize across patients, 2) lacks sensitivity to small changes, and 3) is difficult to use in vulnerable populations such as children and those with cognitive impairment. Thus, clinical research on itch has an urgent need for a new objective, accurate, and low overhead method for quantifying itch. Furthermore, given that disturbed sleep is a major factor leading to diminished quality of life for chronic itch patients, the new method should ideally also assess sleep quality. The overall objective of our proposal is to provide an objective, sensitive, and reliable metric for measuring both itch and its impact on sleep. The central hypothesis of this proposal is that a novel, wireless sensor can be employed to effectively capture scratching activity and associated itch morbidity, and also measure its impact on sleep. Our approach is based on a non-obtrusive wireless device that sits in the background at home, much like a Wi-Fi router. It analyses the radio signals that bounce off people's bodies using novel machine learning models to infer people’s sleep quality and scratching motion -- and it does it in a touchless manner without asking patients to wear sensors, or incur any burden. The Katabi lab invented this sensor technology and has already demonstrated its ability to measure sleep stages, respiration signal, heart rate, falls, gait and other behaviors in humans. Further, the Katabi and Kim labs have preliminary data that demonstrate the feasibility of extending this method to monitor scratching in a touchless manner in chronic itch patients. The specific aims of this proposal will assess the accuracy, sensitivity, and specificity of this novel method in measuring nocturnal scratching in chronic itch patients, its performance in comparison to the current clinical standard based on patients’ self-assessment of their condition, and its ability to track changes over time in the same patient. It will also leverage the device’s ability to monitor sleep to assess the impact of itch on patients’ sleep quality, and the relationship between sleep metrics (e.g., sleep onset, sleep efficiency, and sleep stages) and scratching severity. The rationale for this proposal is that the ability to quantify itch and its impact on sleep in an objective, sensitive method that is widely applicable, including to children and cognitively impaired patients, would improve clinical research, and facilitate the assessment of therapeutics for both disease management and drug development.

项目摘要 慢性瘙痒影响13%的人口，每年与超过900亿美元的人口有关- 在美国的支出。它对生活质量产生深远的负面影响，并且通常与慢性病一样令人衰弱 痛苦然而，目前还没有FDA批准的治疗慢性瘙痒的方法。评估的主要障碍 瘙痒的治疗方法是测量它的困难，这阻碍了临床结果的评估， 开发新药。目前量化瘙痒的临床标准依赖于患者的自我评估 他们瘙痒的严重程度在0到10的范围内，这是：1）高度主观，难以概括 患者，2）对微小变化缺乏敏感性，3）难以用于儿童等弱势人群 和认知障碍的人。因此，瘙痒的临床研究迫切需要一个新的目标， 准确，低开销的方法来量化瘙痒。此外，鉴于睡眠障碍是一个主要因素， 导致慢性瘙痒患者的生活质量下降，新方法也应该理想地评估睡眠 质量.我们提案的总体目标是提供一个客观、敏感和可靠的指标， 测量瘙痒及其对睡眠的影响。这项提议的中心假设是，一种新颖的无线 传感器可用于有效地捕获抓挠活动和相关的瘙痒发病率，并且还 测量它对睡眠的影响。我们的方法是基于一个非侵入性的无线设备，坐在 在家里的背景，就像一个Wi-Fi路由器。它分析了从人体反射回来的无线电信号， 新的机器学习模型来推断人们的睡眠质量和抓挠动作-而且它是在一个无接触的 这种方式不会要求患者佩戴传感器，也不会产生任何负担。Katabi实验室发明了这个传感器 技术，并已证明其能够测量睡眠阶段，呼吸信号，心率，福尔斯， 步态和其他人类行为。此外，Katabi和Kim实验室的初步数据表明， 将该方法扩展到以非接触方式监测慢性瘙痒患者的抓挠的可行性。的 该提案的具体目标将评估这种新方法的准确性、灵敏度和特异性， 测量慢性瘙痒患者的夜间抓挠，其性能与当前临床 该标准基于患者对其病情的自我评估，以及其跟踪患者病情随时间变化的能力。 同一个病人它还将利用该设备监测睡眠的能力来评估瘙痒对患者睡眠的影响。 睡眠质量以及睡眠度量之间的关系（例如，睡眠起始、睡眠效率和睡眠阶段） 和抓挠严重性。这项提议的基本原理是，量化瘙痒及其对睡眠的影响的能力 在一种广泛适用的客观、敏感的方法中，包括儿童和认知障碍患者， 将改善临床研究，并促进对疾病管理和 药物开发