Machine Learning Models for Identifying Neural Predictors of TMS Treatment Response in MDD

用于识别 MDD 中 TMS 治疗反应神经预测因素的机器学习模型

• 批准号: 10322734
• 负责人: HELMET Talib KARIM
• 金额: $ 17.06万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-01-01 至 2025-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10322734
• 关键词: Algorithms; Anterior; Antidepressive Agents; Archives; Biological; Biomedical Engineering; Brain; Clinical; Clinical Treatment; Complex; Corpus striatum structure; Data; Data Set; Development; Doctor of Philosophy; Goals; Heterogeneity; Individual; Left; Literature; Machine Learning; Major Depressive Disorder; Measures; Mental Depression; Modeling; Motor; Neurobiology; Neurosciences; Participant; Patients; Placebos; Positioning Attribute; Prediction of Response to Therapy; Reproducibility; Research; Rest; Rewards; Testing; Time; Training; Transcranial magnetic stimulation; Universities; archive data; archived data; base; career; clinical diagnosis; clinical diagnostics; clinically translatable; cohort; cost; design; electric field; executive function; experience; individual patient; large scale data; machine learning model; neural network; neuroimaging; personalized medicine; predicting response; predictive modeling; psychologic; random forest; relating to nervous system; response; response biomarker; support vector machine; translational scientist; treatment response; voltage

Transcranial magnetic stimulation (TMS) is an effective and easy-to-tolerate treatment for major depressive disorder (MDD). TMS is costly and time-intensive so identifying markers of response would reduce financial and psychological burden. Further, treatment response is highly variable. Clinical and diagnostic heterogeneity of depression contributes to significant variability in neural markers of response. The literature on neural markers is complicated by variability in TMS intensity and targets, which may further modify response. Electrical field models estimate the degree to which a target is stimulated by considering both the intensity and structural information of each participant but at this time there are no studies that have investigated the association between brain electrical fields and treatment response. Moreover, the neurobiological correlates of dorsolateral (dlPFC) TMS treatment response are not well understood. Machine learning may be able to help us understand these complex set of features and their association to treatment response. Thus to appropriately personalize treatments, I will develop a data-driven machine learning model that uses the following: (1) pre- treatment resting state connectivity that reflects circuit dysregulation; (2) electrical field modeling to estimate the electrical field or voltage on individual patient’s brain, as a marker of sufficiency of stimulation; and (3) expected target network connectivity as a marker of target engagement. We have previously demonstrated feasibility of machine learning to predict antidepressant response in MDD. We will optimize and expand a model developed on archival University of Toronto data that predicted dlPFC TMS response. We will validate this externally on three sets of data: data we collect at University of Pittsburgh, archival data from Brown University, and sham TMS data. As an exploratory aim, we will identify whether our model that predicts dlPFC TMS treatment response is capable of predicting response to dmPFC TMS stimulation. During my PhD in Bioengineering, I developed kernel-based machine learning models to personalize neural networks markers of antidepressant response. Given the clinical and neural heterogeneity of depression, I will leverage my machine learning and neuroimaging experience by receiving training in advanced optimization approaches and depression neurobiology to identify stable, reproducible neural predictors of TMS treatment response to achieve clinically translatable personalized treatments. This will allow me to develop optimized models of treatment response and facilitate my long-term career goal to develop personalized treatment algorithms using large-scale data. My previous experiences in machine learning, bioengineering, neuroimaging, as well as the preliminary understanding of depression uniquely position me to maximize the benefits of training aims outlined in this proposal. 1

经颅磁刺激 (TMS) 是一种有效且易于耐受的重度抑郁症治疗方法 紊乱 (MDD) 成本高昂且耗时，因此识别响应标记会减少财务和时间成本。 此外，治疗反应的临床和诊断异质性也很大。 抑郁症会导致神经标记反应的显着变异。有关神经标记的文献。 TMS 强度和目标的变化使情况变得复杂，这可能会进一步改变电场的响应。 模型通过考虑强度和结构来估计目标受到刺激的程度 每个参与者的信息，但目前还没有研究调查这种关联 此外，脑电场和治疗反应之间的神经生物学相关性。 背外侧 (dlPFC) TMS 治疗反应尚不清楚，机器学习也许能够帮助我们。 这些复杂的特征及其与治疗反应的关联，从而正确理解。 个性化治疗，我将开发一个数据驱动的机器学习模型，该模型使用以下内容：（1）预 反映电路失调的治疗静息状态连接；（2）电场建模来估计 个体患者大脑上的电场或电压，作为刺激充分性的标志；以及 (3) 我们之前已经证明了预期的目标网络连接作为目标参与的标志。 机器学习预测 MDD 抗抑郁反应的可行性 我们将优化和扩展模型。 根据多伦多大学档案数据开发，预测 dlPFC TMS 响应，我们将验证这一点。 外部基于三组数据：我们在匹兹堡大学收集的数据、布朗大学的档案数据、 作为一个探索性目标，我们将确定我们的模型是否可以预测 dlPFC TMS。 在我攻读博士学位期间，治疗反应能够预测对 dmPFC TMS 刺激的反应。 生物工程，我开发了基于内核的机器学习模型来个性化神经网络标记 鉴于抑郁症的临床和神经异质性，我将利用我的机器。 通过接受高级优化方法的培训获得学习和神经影像经验 抑郁症神经生物学，以确定 TMS 治疗反应的稳定、可重复的神经预测因子，以实现 这将使我能够开发出优化的治疗模型。 响应并促进我的长期职业目标，即使用大规模开发个性化治疗算法 我之前在机器学习、生物工程、神经影像以及 对抑郁症的初步了解使我能够最大限度地发挥培训目标的好处 本提案中概述了。 1