Depression as a disease of network disruption: learning from multiple sclerosis

抑郁症是一种网络中断疾病：从多发性硬化症中学习

基本信息

批准号：
10643057
负责人：
Erica Berlin Baller
金额：
$ 19.49万
依托单位：
UNIVERSITY OF PENNSYLVANIA
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-07-01 至 2028-06-30
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10643057
关键词：
Acceleration Adult Affect Age Atrophic Attention Biological Markers Brain Brain region Chronic Disease Clinical Clinical Trials Clinical assessments Cognition Computational Technique Computerized Medical Record Computing Methodologies Data Data Set Diagnosis Dimensions Disease Dorsal Exclusion Fascicle Female Fiber Foundations Functional disorder Heterogeneity Image Immune Impairment Knowledge Learning Lesion Location Magnetic Resonance Imaging Maps Measures Mediating Mediation Medical Mental Depression Mentored Patient-Oriented Research Career Development Award Mentorship Mimosa Modeling Multiple Sclerosis Neurocognitive Participant Patients Pattern Pennsylvania Performance Persons Phenotype Prevalence Process Psychiatry Public Health Recording of previous events Reproducibility Research Sampling Severities Sex Differences Societies Stroke Structure Symptoms System Techniques Testing Training United States University resources Visit White Matter Disease algorithmic methodologies automated segmentation biotypes clinical care cognitive function cognitive testing comorbid depression comorbidity cost depressive symptoms experience gray matter individual variation instrument machine learning algorithm machine learning method male network dysfunction neuropsychiatric symptom predictive modeling programs prospective psychiatric symptom recruit supervised learning symptomatology tool treatment stratification white matter

项目摘要

PROJECT ABSTRACT/SUMMARY Multiplesclerosis (MS) is an immune-mediatedneurological disorder that affects one million people in the United States. Up to 50% of patients with MS experience depression, yet the mechanisms of depression in MS remain under-investigated. MS is characterized by white matter lesions, suggesting that brain network disruption may underly depression symptoms. Studies of medically healthy participants with depression have described associations between white matter variability and depressive symptoms, but frequently exclude participants with medical comorbidities and thus cannot be extrapolated to people with intracranial diseases. Previous research using lesion network mapping, a technique for mapping heterogeneous gray matter lesions to neuropsychiatric symptoms, has demonstrated that strokes in gray matter associated with depression disrupt a reproducible depression network. However, such techniques have never been applied to white matter disease or MS. Studying white matter lesions associated with depression in MS may provide a way to understand both the pathophysiology of depression in MS and general network mechanisms of depression more broadly. The purpose of this current study is to investigate how brain network disruption underlies depression by learning from the example of multiple sclerosis. In Aim 1, I will delineate how depression in adults with MS is associated with white matter lesion location and burden in a retrospective sample of 1,554 MS patients with research-grade 3T MRIs acquired as part of clinical care. Depression and MS diagnoses will be obtained from the electronic medical record. While this sample provides an ideal dataset for developing a model, the electronic medical record does not contain granular depression measures. In Aim 2, I will obtain structured clinical and cognitive assessments for MS patients and prospectively evaluate white matter integrity as a predictor of dimensional depressive symptoms. However, it is possible that symptoms of depression may reflect heterogenous brain network disruption patterns. Therefore, in Aim 3, I will use advanced semi-supervised machine learning methods to parse heterogeneity in MS white matter lesion burden in the retrospective sample and test whether this model predicts phenotypic heterogeneity in our deeply-phenotyped prospective sample. The support of the K23 award will provide the applicant with the training necessary to achieve these aims. The training objectives will be accomplished with the support of an outstanding mentorship team, Drs. Satterthwaite, Shinohara, Bassett, Bar- Or, Fox, McCoy, and the world class resources of the University of Pennsylvania. Together, the proposed scientific aims and training objectives will form the foundation for an independent research program that will use techniques from computational psychiatry to understand depression in patients with medical comorbidities.

项目摘要/总结多发性硬化症 (MS) 是一种免疫介导的神经系统疾病，影响着 100 万人美国。高达 50% 的多发性硬化症患者患有抑郁症，但抑郁症的机制并不复杂多发性硬化症的研究仍未充分。 MS 的特点是白质病变，表明大脑网络干扰可能是抑郁症状的根源。对患有抑郁症的身体健康参与者的研究描述了白质变异性与抑郁症状之间的关联，但经常排除患有合并症的参与者，因此不能推断患有颅内疾病的人。先前的研究使用病变网络映射，这是一种绘制异质灰质病变的技术神经精神症状，已证明与抑郁症相关的灰质中风破坏了一个可重复的抑郁症网络。然而，此类技术从未应用于白质疾病或女士。研究与多发性硬化症抑郁症相关的白质病变可能提供一种了解两者的方法多发性硬化症抑郁症的病理生理学以及更广泛的抑郁症的一般网络机制。这当前这项研究的目的是通过学习来调查大脑网络破坏如何导致抑郁症多发性硬化症的例子。在目标 1 中，我将描述成人多发性硬化症患者的抑郁症与以下疾病之间的关系： 1,554 名研究级 3T 多发性硬化症患者的回顾性样本中的白质病变位置和负担作为临床护理的一部分获得的 MRI。抑郁症和多发性硬化症的诊断将从电子医疗中获得记录。虽然此示例为开发模型提供了理想的数据集，但电子病历确实不包含颗粒状抑制措施。在目标 2 中，我将获得结构化的临床和认知评估针对多发性硬化症患者并前瞻性评估白质完整性作为维度抑郁的预测因子症状。然而，抑郁症的症状可能反映了异质的大脑网络破坏模式。因此，在目标3中，我将使用先进的半监督机器学习方法来解析回顾性样本中 MS 白质病变负担的异质性，并测试该模型是否预测我们的深度表型前瞻性样本中的表型异质性。 K23奖的支持将为申请人提供实现这些目标所需的培训。培训目标将是在杰出的导师团队 Drs. 的支持下完成了这项工作。萨特思韦特、筱原、巴塞特、巴尔—— 或者，福克斯、麦考伊和宾夕法尼亚大学的世界级资源。共同提出的科学目标和培训目标将构成独立研究计划的基础，该计划将使用计算精神病学技术用于了解患有合并症的患者的抑郁症。