A5031022775- Non-Invasive Vital Sign Monitoring
- Molecular Biology Techniques and Applications
- Machine Learning in Healthcare
- Cancer-related molecular mechanisms research
- Hemodynamic Monitoring and Therapy
- ECG Monitoring and Analysis
- Gene expression and cancer classification
- Pancreatic function and diabetes
- Tensor decomposition and applications
- Sparse and Compressive Sensing Techniques
- Sleep and Work-Related Fatigue
- Heart Rate Variability and Autonomic Control
- Time Series Analysis and Forecasting
- Cellular transport and secretion
- Protein Kinase Regulation and GTPase Signaling
- Phonocardiography and Auscultation Techniques
- Blind Source Separation Techniques
- Fibromyalgia and Chronic Fatigue Syndrome Research
- Digital Imaging for Blood Diseases
- Musculoskeletal pain and rehabilitation
- Cardiovascular Health and Disease Prevention
University of Michigan–Ann Arbor
2015-2024
The cellular movements that construct a macropinosome have corresponding sequence of chemical transitions in the cup-shaped region plasma membrane becomes macropinosome. To determine relative positions type I phosphatidylinositol 3-kinase (PI3K) and phospholipase C (PLC) this pathway, we analyzed macropinocytosis macrophages stimulated by growth factor macrophage-colony-stimulating (M-CSF) diacylglycerol (DAG) analog phorbol 12-myristate 13-acetate (PMA). In cells with M-CSF, microscopic...
Abstract Postoperative patients are at risk of life-threatening complications such as hemodynamic decompensation or arrhythmia. Automated detection with risks via a real-time clinical decision support system may provide opportunities for early and timely interventions that can significantly improve patient outcomes. We utilize multimodal features derived from digital signal processing techniques tensor formation, well the electronic health record (EHR), to create machine learning models...
The quick Sequential Organ Failure Assessment (qSOFA) system identifies an individual's risk to progress poor sepsis-related outcomes using minimal variables. We used Support Vector Machine, Learning Using Concave and Convex Kernels, Random Forest predict increase in qSOFA score electronic health record (EHR) data, electrocardiograms (ECG), arterial line signals. structured physiological signals data a tensor format Canonical Polyadic/Parallel Factors (CP) decomposition for feature...
Osteosarcoma is a prominent bone cancer that typically affects adolescents or people in late adulthood. Early recognition of this disease relies on imaging technologies such as x-ray radiography to detect tumor size and location. This paper aims differentiate osteosarcoma from benign tumors by analyzing both RNA-seq data through combination image processing machine learning. In experimental results, the proposed method achieved an Area Under Receiver Operator Characteristic Curve (AUC)...
The aim of this research is to apply the learning using privileged information paradigm sepsis prognosis. We used signal processing electrocardiogram and electronic health record data construct support vector machines with without predict an increase in a given patient's quick-Sequential Organ Failure Assessment score, retrospective dataset. applied both small, critically ill cohort broader patients intensive care unit. Within smaller cohort, proved helpful signal-informed model, across...
Over the past decades, there has been an increase of attention to adapting machine learning methods fully exploit higher order structure tensorial data. One problem great interest is tensor classification, and in particular extension linear discriminant analysis multilinear setting. We propose a novel method for that radically different from ones considered so far, it first tensors quadratic analysis. Our proposed approach uses invariant theory extend nearest Mahalanobis distance classifier...
Meta-analysis of gene expression provides the opportunity to compare across different platforms. In this paper, we use a meta-analysis RNA-seq data collected by SJTU team and publicly available microarray build Random Forest classification model. The model had average accuracy 74.1% for cross-validation in training set achieved 80.0% on testing set.
Fibromyalgia is a musculoskeletal disorder characterized by chronic, widespread muscle pain. This condition associated with disturbed sleep, which has direct impact on patient quality of life. Patient-reported outcomes are frequently used to assess sleep quality, but show modest correlations objective measures such as polysomnography. Working towards our goal an automated ambulatory system assessing we use features from blood volume pulse (BVP) and electrodermal activity (EDA) collected...