Browsing by Subject "Optimal transport"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Optimal transport- and kernel-based early detection of mild cognitive impairment patients based on magnetic resonance and positron emission tomography images
    (BMC, 2022) Liu, Ziyu; Johnson, Travis S.; Shao, Wei; Zhang, Min; Zhang, Jie; Huang, Kun; Biostatistics and Health Data Science, School of Medicine
    Background: To help clinicians provide timely treatment and delay disease progression, it is crucial to identify dementia patients during the mild cognitive impairment (MCI) stage and stratify these MCI patients into early and late MCI stages before they progress to Alzheimer's disease (AD). In the process of diagnosing MCI and AD in living patients, brain scans are collected using neuroimaging technologies such as computed tomography (CT), magnetic resonance imaging (MRI), or positron emission tomography (PET). These brain scans measure the volume and molecular activity within the brain resulting in a very promising avenue to diagnose patients early in a minimally invasive manner. Methods: We have developed an optimal transport based transfer learning model to discriminate between early and late MCI. Combing this transfer learning model with bootstrap aggregation strategy, we overcome the overfitting problem and improve model stability and prediction accuracy. Results: With the transfer learning methods that we have developed, we outperform the current state of the art MCI stage classification frameworks and show that it is crucial to leverage Alzheimer's disease and normal control subjects to accurately predict early and late stage cognitive impairment. Conclusions: Our method is the current state of the art based on benchmark comparisons. This method is a necessary technological stepping stone to widespread clinical usage of MRI-based early detection of AD.
  • Thumbnail Image
    Item
    Predicting Alzheimer's disease subtypes and understanding their molecular characteristics in living patients with transcriptomic trajectory profiling
    (Wiley, 2025) Huang, Xiaoqing; Jannu, Asha Jacob; Song, Ziyan; Jury-Garfe, Nur; Lasagna-Reeves, Cristian A.; Alzheimer’s Disease Neuroimaging Initiative; Johnson, Travis S.; Huang, Kun; Zhang, Jie; Biostatistics and Health Data Science, Richard M. Fairbanks School of Public Health
    Introduction: Deciphering the diverse molecular mechanisms in living Alzheimer's disease (AD) patients is a big challenge but is pivotal for disease prognosis and precision medicine development. Methods: Utilizing an optimal transport approach, we conducted graph-based mapping of transcriptomic profiles to transfer AD subtype labels from ROSMAP monocyte samples to ADNI and ANMerge peripheral blood mononuclear cells. Subsequently, differential expression followed by comparative pathway and diffusion pseudotime analysis were applied to each cohort to infer the progression trajectories. Survival analysis with real follow-up time was used to obtain potential biomarkers for AD prognosis. Results: AD subtype labels were accurately transferred onto the blood samples of ADNI and ANMerge living patients. Pathways and associated genes in neutrophil degranulation-like immune process, immune acute phase response, and IL-6 signaling were significantly associated with AD progression. Discussion: The work enhanced our understanding of AD progression in different subtypes, offering insights into potential biomarkers and personalized interventions for improved patient care. Highlights: We applied an innovative optimal transport-based approach to map transcriptomic data from different Alzheimer's disease (AD) cohort studies and transfer known AD subtype labels from ROSMAP monocyte samples to peripheral blood mononuclear cell (PBMC) samples within ADNI and ANMerge cohorts. Through comprehensive trajectory and comparative analysis, we investigated the molecular mechanisms underlying different disease progression trajectories in AD. We validated the accuracy of our AD subtype label transfer and identified prognostic genetic markers associated with disease progression, facilitating personalized treatment strategies. By identifying and predicting distinctive AD subtypes and their associated pathways, our study contributes to a deeper understanding of AD heterogeneity.