Global Deep Learning Initiative to Understand Outcomes in Major Depression

全球深度学习计划了解重度抑郁症的结果

• 批准号: 10735255
• 负责人: Roberto Goya-Maldonado
• 金额: $ 66.38万
• 依托单位: UNIVERSITY OF SOUTHERN CALIFORNIA
• 依托单位国家: 美国
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-06-01 至 2028-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10735255
• 关键词: 3-Dimensional; Address; Adverse effects; Antidepressive Agents; Artificial Intelligence; Australia; Biological Markers; Brain; Brain Diseases; Brain Mapping; Brain imaging; Brain region; China; Chinese; Classification; Clinical; Clinical Data; Clinical assessments; Code; Data; Data Set; Diagnosis; Diagnostic; Diffusion; Disease; Disease remission; Double-Blind Method; Electroconvulsive Therapy; Ensure; Ethics; Functional Magnetic Resonance Imaging; Germany; Goals; Graph; Hamilton Rating Scale for Depression; Hybrids; Individual; International; Intervention; Learning; Legal; MRI Scans; Magnetic Resonance Imaging; Major Depressive Disorder; Maps; Measures; Mental Depression; Methods; Modeling; Montgomery and Asberg depression rating scale; Morbidity - disease rate; Multimodal Imaging; Neurosciences; Outcome; Participant; Patients; Pattern; Performance; Persons; Pharmaceutical Preparations; Pharmacotherapy; Phenotype; Population; Prediction of Response to Therapy; Predictive Factor; Privacy; Procedures; Psychiatry; Psychotherapy; Randomized, Controlled Trials; Recovery; Research; Research Personnel; Sampling; Scanning; Screening procedure; Severities; Structure; Surface; Symptoms; Testing; Training; Treatment Protocols; Treatment outcome; United States National Institutes of Health; Work; alternative treatment; artificial intelligence method; biobank; biosignature; brain based; brain magnetic resonance imaging; clinical predictors; cohort; combat; convolutional neural network; data exchange; data harmonization; deep learning; deep learning model; depressive symptoms; disability; diverse data; experience; feature extraction; imaging modality; improved; innovation; interest; learning strategy; multimodal neuroimaging; multimodality; neuroimaging; neuromechanism; novel; outcome prediction; precision medicine; predicting response; predictive modeling; predictive signature; repetitive transcranial magnetic stimulation; response; tool; transfer learning; treatment duration; treatment effect; treatment response; treatment-resistant depression; web site

ABSTRACT Major depressive disorder (MDD) is the leading cause of disability worldwide, and around half of MDD patients have treatment-resistant depression. The use and clinical benefit of rTMS have escalated greatly in recent years. As only 40-50% of patients respond to current standard rTMS, there is great interest in predicting which patients are likely to respond, what brain features best predict response, and how these features relate to the core biosignatures of MDD. To address this, and responding to NIH’s call for Precision Medicine approaches, our Global Deep Learning Initiative to Understand Outcomes in Major Depression unites international leaders in MDD and rTMS research, neuroimaging, and AI to identify generalizable predictors of rTMS response, and assess how they relate to brain biomarkers of MDD. Two major innovations are proposed. First, we use novel deep learning methods, based on convolutional neural networks, to extract predictive features from multimodal brain images (sMRI, DTI, and rsfMRI); tactics applied in whole-brain and surface-based mapping of brain function and structure, DVAEs for feature extraction, and transfer learning (to learn from auxiliary datasets and tasks) will distill predictive features while protecting individual privacy. CNNs trained on multimodal brain maps for our predictive tasks will distill additional layers of information that have not yet been fully exploited in MDD research, to better predict clinical status and treatment response. Second, our worldwide ENIGMA-MDD network will provide diverse test data from globally representative populations, to ensure that our predictive models do not break down when tested on diverse data. ENIGMA’s harmonized extraction of brain measures across worldwide cohorts will enhance rigor and ensure that analyses are well-powered and consistently performed. We include an important partnership with REST-meta-MDD, a Chinese consortium collecting multimodal imaging data from patients with MDD, to test the generalizability of our predictive models. The likely outcome of our work is a set of pre-screening tools to predict who will respond best to rTMS, and a deeper understanding of the brain signatures of MDD that predict treatment outcomes following rTMS. All tools will be made public via NITRC and ENIGMA websites, and will be tested across our ENIGMA network, guaranteeing impact of the work for large- scale outcome prediction within and outside of MDD research.

摘要 重度抑郁症（MDD）是全球残疾的主要原因，约有一半的MDD患者 患有难治性抑郁症近年来，rTMS的使用和临床受益大大增加。 由于只有40 - 50%的患者对目前的标准rTMS有反应， 哪些大脑特征最能预测反应，以及这些特征与核心的关系 MDD的生物特征。为了解决这个问题，并响应NIH对精准医学方法的呼吁，我们的 了解大萧条结果的全球深度学习倡议联合国际领导人， MDD和rTMS研究、神经影像学和AI，以确定rTMS反应的可推广预测因素，以及 评估它们与抑郁症大脑生物标志物的关系。提出了两个重大创新。首先，我们用小说 基于卷积神经网络的深度学习方法，用于从多模态数据中提取预测特征 脑成像（sMRI、DTI和rsfMRI）;应用于全脑和基于表面的脑功能映射的策略 用于特征提取的DVAE和迁移学习（从辅助数据集和任务中学习）将 提取预测功能，同时保护个人隐私。CNN在多模态大脑地图上训练， 预测任务将提取尚未在MDD研究中充分利用的额外信息层， 以更好地预测临床状态和治疗反应。其次，我们的全球ENIGMA-MDD网络将 提供来自全球代表性人群的各种测试数据，以确保我们的预测模型不会 在不同的数据上进行测试时，ENIGMA在全球范围内统一提取大脑测量数据 分组将提高严谨性，并确保分析具有良好的效力和一致性。我们包括 与REST-meta-MDD建立了重要的合作伙伴关系，这是一个中国联盟，收集来自 MDD患者，以测试我们的预测模型的普遍性。我们工作的可能结果是 预筛选工具，以预测谁将对rTMS反应最好，以及对大脑的更深入了解 MDD的特征，预测rTMS后的治疗结果。所有工具将通过NITRC公开， ENIGMA网站，并将在我们的ENIGMA网络进行测试，保证工作的影响大- MDD研究内外的量表结果预测。