iTransform: Wearable Biosensors to Detect the Evolution of Opioid Tolerance in Opioid Naïve Individuals

iTransform：可穿戴生物传感器检测阿片类药物耐受性的演变

基本信息

批准号：
9889092
负责人：
STEPHANIE P CARREIRO
金额：
$ 18.86万
依托单位：
UNIV OF MASSACHUSETTS MED SCH WORCESTER
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-04-01 至 2022-03-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9889092
关键词：
Accident and Emergency department Acute Age Algorithms Analgesics Area Behavior Therapy Behavioral Big Data Biological Markers Biometry Biosensing Techniques Biosensor Characteristics Consent Data Data Analyses Data Analytics Data Collection Data Science Data Set Development Devices Doctor of Philosophy Dose Drug abuse Ensure Evaluation Event Evolution Fracture Funding Galvanic Skin Response Gender Genetic Goals Heroin Abuse Immersion Individual Ingestion Intervention Investigation Italy K-Series Research Career Programs Knowledge Machine Learning Measurement Measures Medical Mentored Patient-Oriented Research Career Development Award Mentors Mentorship Methods Monitor Morbidity - disease rate Motion Opiate Addiction Opioid Opioid Analgesics Overdose Pain Participant Patients Pattern Pattern Recognition Pharmaceutical Preparations Physiological Physiology Pilot Projects Population Predictive Analytics Productivity Protocols documentation Public Health Records Relapse Reporting Research Research Personnel Research Project Grants Research Training Risk Risk Factors Safety Science Scientist Signal Transduction Skin Temperature Source Substance Use Disorder Substance abuse problem Teacher Professional Development Techniques Technology Testing Therapeutic Therapeutic Effect Therapeutic Uses Time Training United States National Institutes of Health Work Wrist addiction analytical method base behavioral health career comparative data integrity data management digital experience high risk innovation insight learning algorithm mHealth machine learning algorithm machine learning method mortality novel opiate tolerance opioid abuse opioid mortality opioid overdose opioid therapy opioid use prediction algorithm prescription opioid prevent programs recruit response sensor signal processing skills social success supervised learning tool

项目摘要

PROJECT SUMMARY The integrated research and training plans outlined in this K23 submission will prepare me for a career as a clinician-scientist conducting translational substance abuse research. My career goal is to perform hypothesis- driven original research investigations directed toward reducing morbidity and mortality from opioid overdose. In this proposal, I intend to deploy wearable biosensors (small devices that continuously record physiology) to study the effects of therapeutic administration of opioid analgesics. I have already studied wearable biosensors in individuals receiving opioids; my preliminary data demonstrates that opioid-tolerant individuals have different biometric signals than non-tolerant individuals. This observation suggests that biosensors can be used to identify the onset of tolerance, an important event that correlates with higher doses of opioid analgesics, and higher risk of death from opioid overdose. Biosensor data management and analysis requires signal processing, data analytic, and machine learning techniques; these approaches are beyond the areas of traditional medical training. My short-term goal is to utilize this K23 award to fill my knowledge gaps in wearable biosensing and advanced data analysis so that I can generate ever more innovative responses to the problem of opioid prescribing, tolerance, misuse, addiction, and overdose. To optimize this important line of investigation, I have developed a training plan that includes: 1) completing a PhD through the Millennium PhD program; 2) expanding my skills in wearable biosensing and behavioral health-based research; 3) developing an understanding of signal processing and machine learning; 4) developing data analytic and data science skills; and 5) expanding my research presentation and dissemination skills. I will achieve these goals through directed coursework, focused seminars, and practical experience. My mentorship team of expert investigators who will ensure my productivity and success includes E. Boyer (primary mentor), D. Smelson, J. Fang, and P. Indic (secondary mentors), and D. Ganesan (advisor) My research plan has three specific aims: 1) to deploy a wearable biosensor technology to detect digital biomarkers associated with the initiation of opioid analgesic therapy in an opioid naïve population; 2) to use signal-processing analytics to identify transitions in digital biomarkers with progressive opioid use and to identify individual characteristics associated with this transition; and, 3) to apply and explore supervised learning algorithms that can predict transitions in digital biomarkers that herald the onset of opioid tolerance. To identify dynamic patterns in response to opioids, I will study the digital biomarkers of opioid-naïve patients with acute fractures who are prescribed opioid analgesics. Results will be used to develop “big data” approaches to apply predictive algorithms to identify the onset of opioid tolerance. This work has the potential to prevent development of problematic opioid use and will provide the basis for subsequent R01 submissions to implement sensor-based interventions triggered by the onset of tolerance in individuals receiving opioid analgesics.

项目概要这份 K23 提交文件中概述的综合研究和培训计划将为我的职业生涯做好准备进行转化药物滥用研究的临床医生科学家。我的职业目标是进行假设- 推动了旨在降低阿片类药物过量导致的发病率和死亡率的原始研究调查。这个提案，我打算部署可穿戴生物传感器（连续记录生理学的小型设备）来研究阿片类镇痛药的治疗效果我已经研究过可穿戴生物传感器。接受阿片类药物的个体；我的初步数据表明，阿片类药物耐受的个体有不同的这一观察表明生物传感器可用于识别。耐受性的发生，这是与较高剂量的阿片类镇痛药和较高风险相关的重要事件生物传感器数据管理和分析需要信号处理、数据。分析和机器学习技术；这些方法超出了传统医学的领域我的短期目标是利用这个 K23 奖项来填补我在可穿戴生物传感和技术方面的知识空白。先进的数据分析，以便我能够针对阿片类药物问题提出更具创新性的应对措施为了优化这一重要的研究方向，我对处方、耐受性、滥用、成瘾和过量进行了研究。制定了一项培训计划，其中包括：1）通过千年博士项目完成博士学位；2）扩大我在可穿戴生物传感和行为健康研究方面的技能；3）加深对信号的理解；处理和机器学习；4）发展数据分析和数据科学技能；5）扩展我的能力；我将通过有针对性的课程作业来实现这些目标。我的专家指导团队将确保我的生产力。成功者包括 E. Boyer（主要导师）、D. Smelson、J. Fang 和 P. Indic（二级导师），以及 D. Ganesan（顾问）我的研究计划有三个具体目标：1）部署可穿戴生物传感器技术检测与在未使用阿片类药物的人群中开始阿片类药物镇痛治疗相关的数字生物标志物； 2) 使用信号处理分析来识别数字生物标志物随着阿片类药物使用的进展而发生的转变，识别与此转变相关的个人特征；3）应用和探索监督；可以预测预示阿片类药物耐受性开始的数字生物标记物转变的学习算法。识别对阿片类药物反应的动态模式，我将研究未使用阿片类药物的患者的数字生物标志物服用阿片类镇痛药的急性骨折患者的结果将用于开发“大数据”方法。应用预测算法来识别阿片类药物耐受的发生，这项工作有可能预防阿片类药物耐受。开发有问题的阿片类药物使用，并将为后续 R01 提交的实施提供基础由接受阿片类镇痛药的个体出现耐受性而触发的基于传感器的干预措施。