Haochang Shou
Associate Professor
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (4)
Major depressive disorder (MDD) is a leading cause of disability worldwide, yet its diagnosis relies on clinical symptoms alone. Using machine learning applied to deeply phenotyped, medication-free participants with MDD, we identified two neuroanatomical dimensions. Dimension 2 (D2), compared to Dimension 1 (D1), was characterized by reductions in grey and white matter and was associated with limited treatment response to both antidepressant and placebo medications. Validation in UK Biobank general population cohort (n = 37,235) confirmed that D2 is characterized by reduced grey and white matter, alongside widespread cognitive impairments, adverse events in both adulthood and childhood, increased self-harm and suicide attempts, a pro-atherogenic lipid profile, and genetic associations with neurodegenerative traits. These findings suggest that D1 and D2 reflect distinct neurobiological mechanisms underlying MDD, with important implications for and treatment outcomes. External validation was demonstrated in a general population-based cohort that delineated mechanisms underlying heterogeneity in MDD, identifying potential biomarkers that could aid in personalising treatment approaches for this debilitating disorder.
Year:
2025
Wearable devices and digital phenotyping are increasingly used in observational and interventional studies to measure real-time biosignals such as physical activity. However, integrating and comparing data across studies and cohorts remains challenging due to variability in device types, acquisition protocols, and preprocessing methods. A key challenge is removing unwanted study- or device-specific effects while preserving meaningful biological signals. These difficulties are exacerbated by the longitudinal and within-day correlations inherent in high-resolution time-varying data collected from wearable sensors. To address this, we propose INTACT (INtegration of Time-varying data from weArable sensors for physiCal acTivity), a novel method for harmonizing time-varying physical activity intensity data from accelerometers. INTACT models shared information through common eigenvalues and eigenfunctions while allowing for source-specific scale and rotation adjustments. We apply the proposed method to two real-world applications: (i) integration of accelerometer data from two waves of the National Health and Nutrition Examination Survey (NHANES), measured using different devices and reported in different units; and (ii) integration of NHANES accelerometry data with accelerometer and gyroscope measures from commercial devices. Across both applications, INTACT outperforms existing approaches in mitigating source effects while preserving biological variation, enabling more reliable cross-study comparisons of physical activity patterns.
Year:
2025
BACKGROUND Due to the rising prevalence of Alzheimer disease and related dementias, easily deployable tools to quantify risk are needed. Smartphones and smartwatches enable unobtrusive and continuous monitoring, but there is limited information regarding the feasibility, adherence, and acceptability of digital data collection among racially diverse older adults. OBJECTIVE This paper examined the feasibility, adherence, and acceptability of a 4-week combined smartwatch monitoring and ecological momentary assessment (EMA) study in a racially diverse sample of older adults. METHODS A total of 44 older adults (aged ≥55 y) with either mild cognitive impairment or healthy cognition completed an informed consent comprehension quiz, baseline cognitive testing, training regarding digital data collection, and questionnaires. Participants were instructed to wear a Garmin Vivosmart 4 smartwatch for 23 h/d for 4 weeks, sync 2 smartphone apps (Garmin and Labfront) daily, and complete a daily EMA survey with automated prompts for surveys and charging. Training time, smartwatch adherence (eg, wear time), daily EMA survey response rate, and performance on the consent quiz were quantified. Associations between feasibility and adherence metrics and participant factors were evaluated. Self-reported usability of the apps and smartwatch was collected at study end. RESULTS Consent comprehension quiz scores were high (mean 97.33%, SD 6.86% correct), and training sessions lasted on average 17.93 (SD 6.89) minutes. During the 4-week study, participants wore the smartwatch for an average of 21 h/d (SD 1.53) and showed an average response rate of 94% (SD 9.58%) to daily EMA surveys. In unadjusted bivariate analyses, age, race, and cognition were associated with feasibility and adherence measures, but only age and race remained significant in multivariate models. After accounting for all participant factors, older age was a significant predictor of longer training time, and Black race was a significant predictor of lower daily wear time. On the usability survey, all participants (45/45, 100%) indicated willingness to participate in future smartwatch studies, >80% (37/45) had a positive experience, and >90% (41/45) were satisfied with smartphone app syncing. CONCLUSIONS Smartwatch monitoring, requiring daily wear, smartphone syncing, and daily EMA survey completion, is highly feasible in older adults because adherence to daily wear and EMA surveys was high, as was general satisfaction on usability surveys. Although older participants may require more training on smartwatch and smartphone procedures and automated prompting during the study period, longitudinal monitoring with the Garmin Vivosmart 4 smartwatch and Labfront app is acceptable and feasible for collecting nearly continuous data in Black and White older adults, including those with mild cognitive impairment and those without.
Year:
2024
Alzheimer's Disease (AD) is the leading cause of dementia, affecting brain structure, function, cognition, and behaviour. While previous studies have linked brain regions to univariate outcomes (e.g., disease status), the relationship between brain-wide changes and multiple disease and behavioural outcomes of AD is still not well understood. Here, we propose Residual Partial Least Squares (re-PLS) Learning, an explainable and generalisable framework that models high-dimensional brain features and multivariate outcomes, accounting for confounders. Using re-PLS, we map the many-to-many pathways between cortical thickness and multivariate AD outcomes; identify neural biomarkers that simultaneously predict multiple outcomes; control for confounding variables; conduct longitudinal AD prediction; and perform cross-cohort AD prediction. To evaluate its efficacy, we first carry out within-cohort cross-subject validation using ADNI data, and further examine its reproducibility via between-cohort cross-validation using ADNI and OASIS data. Together, our results unveil brain regions jointly but differentially predictive of distinctive cognitive-behavioural scores in AD.
Year:
2024
Collaborators (20)
Benicio N. Frey
McMaster University
Tania Giovannetti
Professor
Temple University
Ki Sueng Choi
Associate Professor
Icahn School of Medicine at Mount Sinai
Andrew McIntosh
Professor of Biological Psychiatry
University of Edinburgh
Catherine Harmer
Associate Head of Department
University of Oxford
Boadie Dunlop
Professor and Chair
Augusta University Medical College of Georgia
Chao-Gan Yan
Professor
Tsinghua University
Martin Paulus
Laureate Institute for Brain Research
Jonathan Savitz
Associate Professor
University of Tulsa
John Deakin
The University of Manchester
Rebecca Elliott
The University of Manchester
Philippe Ryvlin
-
Irina Strigo
University of California, San Francisco
Cynthia Fu
University of East London
Heather Whalley
Professor of Neuroscience and Mental Health
University of Edinburgh
Madhukar H. Trivedi
Director
University of Texas Southwestern Medical Center
Roland Zahn
King’s College London
Marcus Munafo
University of Bath
Melanie Ganz
Associate Professor
University of Copenhagen
Beata Godlewska
University of Oxford
Make your next move.
Prepare your application
Review drafts before you send them.