Determining biomarkers of addiction disorders and mental health using electroencephalography

在加拿大，药物滥用和成瘾性疾病已经失控，导致2016年至2020年期间有19，355名加拿大人死亡。研究人员描述说，这场危机正在恶化，因为加拿大安大略的阿片类药物相关死亡人数从2000年到2015年增加了两倍，自COVID-19爆发以来增加了120%。因此，治疗方法正在努力跟上。我们拟议的项目将对拯救成瘾者的生命产生重大影响，因为我们正在寻求提供一个客观的成瘾措施，目的是促进治疗评估和治疗。具体来说，我们将构建一个以治疗师和患者为中心的应用程序，通过脑电波来测量成瘾。从本质上讲，我们将使用先前测量的脑电图（EEG）数据来建立对成瘾的各个方面敏感的生物标志物。例如，奖励积极性，人类事件相关脑电位（ERP）的一个组成部分，已被证明在酒精成瘾的人中减少。此外，我们将使用机器学习算法（例如，支持向量机等）来区分有成瘾和无成瘾的人之间的脑电波模式。我们的项目将通过允许个人跟踪他们自己的成瘾标记来加强治疗评估和治疗，并为治疗师提供有关患者的丰富信息。

There is a health crisis in Canada where substance abuse and addiction disorders have been growing out of control, resulting in the death of 19,355 Canadians from 2016 to 2020. Researchers describe the crisis to be getting worse in that opioid-related deaths tripled from 2000 to 2015 in Ontario, Canada and increased by 120% since the onset of COVID-19. Consequently, therapies are struggling to keep up. Our proposed project will have a major impact on saving the lives of those with addiction disorders as we are seeking to provide an objective measure of addiction with the intent of facilitating therapeutic assessment and treatment. Specifically, we will build a therapist-patient centered application that measures addiction through brain-waves. Essentially, we will used previously measured electroencephalographic (EEG) data to establish biomarkers that are sensitive to various aspects of addiction. For instance, the reward positivity, a component of the human event-related brain potential (ERP) has been shown to be reduced in people with alcohol addiction. Further, we will use machine learning algorithms (e.g., Support Vector Machines, etc) to differentiate brain wave patterns between people with and without addictions. Our project will enhance therapeutic assessment and treatment by allowing individuals to track their own markers of addiction and provide therapists with a wealth of information about their patients.