Siyuan Gao

Siyuan Gao

Auto-generated profile, based on publicly available information

Siyuan Gao

Pinterest, Inc, San Francisco, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 July 2018 in Nature Communications
Verified
Journal Article
Open access
PDF file
AGAbigail S. Greene
Abigail S. Greene
SGSiyuan Gao
Siyuan Gao
DSDustin Scheinost
Dustin Scheinost
RCR. Todd Constable
R. Todd Constable
Recent work has begun to relate individual differences in brain functional organization to human behaviors and cognition, but the best brain state to reveal such relationships remains an open question. In two large, independent data sets, we here show that cognitive tasks amplify trait-relevant individual differences in patterns of functional connectivity, such that predictive models built from task fMRI data outperform models built from resting-state fMRI data. Further, certain tasks consistently yield better predictions of fluid intelligence than others, and the task that generates the best-performing models varies by sex. By considering task-induced brain state and sex, the best-performing model explains over 20% of the variance in fluid intelligence scores, as compared to <6% of variance explained by rest-based models. This suggests that identifying and inducing the right brain state in a given group can better reveal brain-behavior relationships, motivating a paradigm shift from rest- to task-based functional connectivity analyses.

1 August 2020 in Cell Reports
Verified
Journal Article
Open access
AGAbigail S. Greene
Abigail S. Greene
SGSiyuan Gao
Siyuan Gao
SNStephanie Noble
Stephanie Noble
DSDustin Scheinost
Dustin Scheinost
RCR. Todd Constable
R. Todd Constable
Functional connectivity (FC) calculated from task fMRI data better reveals brain-phenotype relationships than rest-based FC, but how tasks have this effect is unknown. In over 700 individuals performing seven tasks, we use psychophysiological interaction (PPI) and predictive modeling analyses to demonstrate that task-induced changes in FC successfully predict phenotype, and these changes are not simply driven by task activation. Activation, however, is useful for prediction only if the in-scanner task is related to the predicted phenotype. To further characterize these predictive FC changes, we develop and apply an inter-subject PPI analysis. We find that moderate, but not high, task-induced consistency of the blood-oxygen-level-dependent (BOLD) signal across individuals is useful for prediction. Together, these findings demonstrate that in-scanner tasks have distributed, phenotypically relevant effects on brain functional organization, and they offer a framework to leverage both task activation and FC to reveal the neural bases of complex human traits, symptoms, and behaviors.

7 December 2020 in Nature Human Behaviour
Verified
Journal Article
Closed access
PDF file
CHCorey Horien
Corey Horien
SNStephanie Noble
Stephanie Noble
AGAbigail S. Greene
Abigail S. Greene
KLKangjoo Lee
Kangjoo Lee
DBDaniel S. Barron
Daniel S. Barron
DSDustin Scheinost
Dustin Scheinost

13 June 2022 in Molecular Psychiatry
Verified
Journal Article
Open access
PDF file
LTLink Tejavibulya
Link Tejavibulya
MRMax Rolison
Max Rolison
SGSiyuan Gao
Siyuan Gao
QLQinghao Liang
Qinghao Liang
HPHannah Peterson
Hannah Peterson
DSDustin Scheinost
Dustin Scheinost
Predictive modeling using neuroimaging data has the potential to improve our understanding of the neurobiology underlying psychiatric disorders and putatively information interventions. Accordingly, there is a plethora of literature reviewing published studies, the mathematics underlying machine learning, and the best practices for using these approaches. As our knowledge of mental health and machine learning continue to evolve, we instead aim to look forward and “predict” topics that we believe will be important in current and future studies. Some of the most discussed topics in machine learning, such as bias and fairness, the handling of dirty data, and interpretable models, may be less familiar to the broader community using neuroimaging-based predictive modeling in psychiatry. In a similar vein, transdiagnostic research and targeting brain-based features for psychiatric intervention are modern topics in psychiatry that predictive models are well-suited to tackle. In this work, we target an audience who is a researcher familiar with the fundamental procedures of machine learning and who wishes to increase their knowledge of ongoing topics in the field. We aim to accelerate the utility and applications of neuroimaging-based predictive models for psychiatric research by highlighting and considering these topics. Furthermore, though not a focus, these ideas generalize to neuroimaging-based predictive modeling in other clinical neurosciences and predictive modeling with different data types (e.g., digital health data).

1 October 2021 in Developmental Cognitive Neuroscience
Verified
Journal Article
Open access
ADAlexander Dufford
Alexander Dufford
SNStephanie Noble
Stephanie Noble
SGSiyuan Gao
Siyuan Gao
DSDustin Scheinost
Dustin Scheinost
The uniqueness and stability of the adolescent and adult functional connectome has been demonstrated to be high (80-95 % identification) using connectome-based identification (ID) or "fingerprinting". However, it is unclear to what extent individuals exhibit similar distinctiveness and stability in infancy, a developmental period of rapid and unparalleled brain development. In this study, we examined connectome-based ID rates within and across the first year of life using a longitudinal infant dataset at 1.5 month and 9 months of age. We also calculated the test-retest reliability of individual connections across the first year of life using the intraclass correlation coefficient (ICC). Overall, we found substantially lower infant ID rates than have been reported in adult and adolescent populations. Within-session ID rates were moderate and significant (ID = 48.94-70.83 %). Between-session ID rates were very low and not significant, with task-to-task connectomes resulting in the highest between-session ID rate (ID = 26.6 %). Similarly, average edge-level test-retest reliability was higher within-session than between-session (mean within-session ICC = 0.17, mean between-session ICC = 0.10). These findings suggest a lack of uniqueness and stability in functional connectomes across the first year of life consistent with the unparalleled changes in brain functional organization during this critical period.

27 November 2020 in bioRxiv
Verified
Preprint
Open access
PDF file
SGSiyuan Gao
Siyuan Gao
GMGal Mishne
Gal Mishne
DSDustin Scheinost
Dustin Scheinost
Large-scale brain dynamics are believed to lie in a latent, low-dimensional space. Typically, the embeddings of brain scans are derived independently from different cognitive tasks or resting-state data, ignoring a potentially large—and shared—portion of this space. Here, we establish that a shared, robust, and interpretable low-dimensional space of brain dynamics can be recovered from a rich repertoire of task based fMRI data. This occurs when relying on non-linear approaches as opposed to traditional linear methods. The embedding maintains proper temporal progression of the tasks, revealing brain states and the dynamics of network integration. We demonstrate that resting-state data embeds fully onto the same task embedding, indicating similar brain states are present in both task and resting-state data. Our findings suggest analysis of fMRI data from multiple cognitive tasks in a low-dimensional space is possible and desirable, and our proposed framework can thus provide an interpretable framework to investigate brain dynamics in the low-dimensional space.