Advancements in Utilizing Mobile Health Data for Mental Health Research

One of the goals of precision psychiatry is to characterize mental disorders in an individualized manner,
taking into account the underlying dynamic processes. Recent advances in mobile technologies have enabled the collection
of Ecological Momentary Assessments (EMAs) that capture multiple responses in real-time at high frequency.
However, EMA data are often multi-dimensional, correlated, and hierarchical. Mixed-effect models are commonly
used but may require restrictive assumptions about the fixed and random effects and the correlation structure. We demonstrate the use of temporal generative models which can handle these challenges present in EMA data to learn latent mental states.  

In this talk, we introduce a combined framework that detects emotionally stressful periods in older patients with chronic pain and depression and establishes data-driven rules that explain the onset of their stress periods. Despite the well-established link between stress exposure and the worsening of emotional distress and mood disorders in these patients, data-driven and long-term intervention algorithms that function without human supervision remain lacking. The first part of the framework focuses on detecting emotional stress periods, referred to as hotspots. We propose a change point detection algorithm that tracks changes in localized, low-level statistical features of passively sensed data and self-reported stress levels. The second part of the framework focuses on identifying which statistical features in which passive sensing variables are most critical in triggering the hotspots. We leverage the signed iterative random forest (siRF) to derive machine-derived rules that can serve as guidelines for determining whether patients are in a stress period at a future time. We present simulation studies under various scenarios and showcase applications of the algorithms to ALACRITY Phases I and II data. The proposed framework is expected to help form digital biomarkers from passively sensed data, enabling personalized and data-driven interventions. 

Sport-related concussions (SRCs) are a significant public health problem resulting in over 200,000 annual trips to the Emergency Departments in the United States. From a biomechanical standpoint, the concussion mechanism includes head impact resulting in high magnitude head linear and rotational accelerations. Mounting evidence from human studies has demonstrated that repetitive head impact exposure (HIE) contributes to decreased SRC tolerance in contact sport athletes. However, studies focusing on quantifying the relationship between the HIE and incident concussion have suffered from simplistic statistical methods utilized.
In our research, we use head impact telemetry (HIT) system accelerometry 1,000Hz high-frequency time series data from the NCAA-DoD Concussion Assessment, Research and Education Consortium (CARE) study to determine the association of HIE with the SRC incidence and post-SRC recovery based on the multiple characteristics of the recorded head impacts. We utilize a scalar-on-function regression approach to determine the most important head impact features as well as their time-varying influence on the SRC. 

Alzheimer's disease (AD) is a complex disorder that affects multiple biological systems including cognition, behavior and physical health. Unfortunately, the pathogenic mechanisms behind AD are not yet clear and the treatment options are still limited. The relationship between genetic risk factors, behavioral phenotypes and brain changes are not well understood. We use high-dimensional mediation analysis as an integrative framework to study the relationships among genetic factors, physical movement as assessed using wearable sensors, and AD-like brain atrophy quantified by radiomic features. We integrate genetic, accelerometry and neuroimaging data collected from 13,425 UK Biobank samples to unveil the complex relationship among genetic risk factors, behavior and brain signatures in the contexts of aging and AD. Specifically, we used a composite neuro-radiomic biomarker, SPARE-AD (Spatial Pattern of Abnormality for Recognition of Early AD) that characterizes AD-like brain atrophy, as an outcome variable to represent AD risk. Through GWAS, we identified single nucleotide polymorphisms (SNPs) that are significantly associated with SPARE-AD as exposure variables. We employed conventional summary statistics and functional principal component analysis to extract patterns of PA as mediators. After constructing these variables, we utilized a high-dimensional mediation analysis method to estimate potential mediating pathways between SNPs, multivariate PA signatures and SPARE-AD. Our analysis identified a total of 22 mediation pathways, indicating how genetic variants can influence SPARE-AD by altering physical activity. Our findings contribute to a better understanding of the pathogenic mechanisms of AD. Moreover, our research demonstrates the potential of the high-dimensional mediation analysis method in revealing the disease mechanisms.