A5026101553- Cancer Immunotherapy and Biomarkers
- Online Learning and Analytics
- Immune cells in cancer
- Muscle activation and electromyography studies
- Osteoarthritis Treatment and Mechanisms
- Balance, Gait, and Falls Prevention
- Cerebral Palsy and Movement Disorders
- Statistical Methods and Inference
- Lower Extremity Biomechanics and Pathologies
- Ferroptosis and cancer prognosis
- Online and Blended Learning
- Artificial Intelligence in Healthcare and Education
- Advanced Statistical Methods and Models
- Diabetic Foot Ulcer Assessment and Management
- Prosthetics and Rehabilitation Robotics
- Machine Learning and Data Classification
- Complex Systems and Time Series Analysis
- Colorectal Cancer Treatments and Studies
- Inflammatory Bowel Disease
- Gene expression and cancer classification
- Bladder and Urothelial Cancer Treatments
- Machine Learning in Healthcare
- Foot and Ankle Surgery
- Time Series Analysis and Forecasting
- Motor Control and Adaptation
Stanford University
2018-2024
BioClinica (United States)
2021-2022
Carnegie Mellon University
2020
Erasmus University Rotterdam
2020
Stanford Medicine
2019
École Polytechnique Fédérale de Lausanne
2015-2018
Palo Alto University
2018
Human Computer Interaction (Switzerland)
2015
Université Libre de Bruxelles
2012-2014
Abstract Many neurological and musculoskeletal diseases impair movement, which limits people’s function social participation. Quantitative assessment of motion is critical to medical decision-making but currently possible only with expensive capture systems highly trained personnel. Here, we present a method for predicting clinically relevant parameters from an ordinary video patient. Our machine learning models predict include walking speed ( r = 0.73), cadence 0.79), knee flexion angle at...
Measures of human movement dynamics can predict outcomes like injury risk or musculoskeletal disease progression. However, these measures are rarely quantified in large-scale research studies clinical practice due to the prohibitive cost, time, and expertise required. Here we present validate OpenCap, an open-source platform for computing both kinematics (i.e., motion) forces) using videos captured from two more smartphones. OpenCap leverages pose estimation algorithms identify body...
Abstract Tumor-associated macrophages are transcriptionally heterogeneous, but the spatial distribution and cell interactions that shape macrophage tissue roles remain poorly characterized. Here, we spatially resolve five distinct human populations in normal malignant breast colon reveal their cellular associations. This map reveals reside segregated micro-environmental niches with conserved compositions repeated across healthy diseased tissue. We show IL4I1+ phagocytose dying cells areas...
Summary We address the problem of dimension reduction for time series functional data (Xt:t∈Z). Such frequently arise, example, when a continuous process is segmented into some smaller natural units, such as days. Then each X t represents one intraday curve. argue that principal component analysis, though key technique in field and benchmark any competitor, does not provide an adequate setting. Functional analysis indeed static procedure which ignores essential information provided by serial...
The academic and behavioral progress of children is associated with the timely development reading writing skills. Dysgraphia, characterized as a handwriting learning disability, usually dyslexia, developmental coordination disorder (dyspraxia), or attention deficit disorder, which are all neuro-developmental disorders. Dysgraphia can seriously impair in their everyday life require therapeutic care. Early detection difficulties is, therefore, great importance pediatrics. Since beginning 20th...
To develop an automated model for staging knee osteoarthritis severity from radiographs and to compare its performance that of musculoskeletal radiologists.Radiographs the Osteoarthritis Initiative staged by a radiologist committee using Kellgren-Lawrence (KL) system were used. Before images as input convolutional neural network model, they standardized augmented automatically. The was trained with 32 116 images, tuned 4074 evaluated 4090-image test set, compared two individual radiologists...
The pedagogical modelling of everyday classroom practice is an interesting kind evidence, both for educational research and teachers' own professional development. This paper explores the usage wearable sensors machine learning techniques to automatically extract orchestration graphs (teaching activities their social plane over time), on a dataset 12 sessions enacted by two different teachers in settings. included mobile eye-tracking as well audiovisual accelerometry data from worn teacher....
Annotation of foot-contact and foot-off events is the initial step in post-processing for most quantitative gait analysis workflows. If clean force plate strikes are present, can be automatically detected. Otherwise, annotation performed manually, since reliable automatic tools not available. Automatic methods have been proposed normal gait, but usually based on heuristics coordinates velocities motion capture markers placed feet. These do generalize to pathological due greater variability...
Abstract Measures of human movement dynamics can predict outcomes like injury risk or musculoskeletal disease progression. However, these measures are rarely quantified in clinical practice due to the prohibitive cost, time, and expertise required. Here we present validate OpenCap, an open-source platform for computing using videos captured from smartphones. OpenCap’s web application enables users collect synchronous visualize data that is automatically processed cloud, thereby eliminating...
Abstract Background Freezing of gait, a common symptom Parkinson’s disease, presents as sporadic episodes in which an individual’s feet suddenly feel stuck to the ground. Inertial measurement units (IMUs) promise enable at-home monitoring and personalization therapy, but there is lack consensus on number location IMUs for detecting freezing gait. The purpose this study was assess IMU sets context both gait detection performance patient preference. Methods Sixteen people with disease were...
Physical function decline due to aging or disease can be assessed with quantitative motion analysis, but this currently requires expensive laboratory equipment. We introduce a self-guided analysis of the widely used five-repetition sit-to-stand test using smartphone. Across 35 US states, 405 participants recorded video performing in their homes. found that movement parameters extracted from smartphone videos were related diagnosis osteoarthritis, physical and mental health, body mass index,...
Abstract The influence of seasons on biological processes is poorly understood. In order to identify seasonal patterns based diverse molecular data, rather than calendar dates, we performed a deep longitudinal multiomics profiling 105 individuals over 4 years. Here, report more 1000 variations in omics analytes and clinical measures. different molecules group into two major which correlate with peaks late spring fall/early winter California. are enriched for involved human such as...
Smart learning has become a new term to describe technological and social developments (e.g., Big Open Data, Internet of Things, RFID, NFC) enable effective, efficient, engaging personalized learning. Collecting combining analytics coming from different channels can clearly provide valuable information in designing developing smart Although, the potential is very promising area, it remains non-investigated even ill-defined concept. The paper defines subset that focuses on supporting features...
Tumor-associated macrophages (TAMs) display heterogeneous phenotypes. Yet the exact tissue cues that shape macrophage functional diversity are incompletely understood. Here we discriminate, spatially resolve and reveal function of five distinct niches within malignant benign breast colon tissue. We found SPP1 TAMs reside in hypoxic necrotic tumor regions, a novel subset FOLR2 resident (TRMs) supports plasma cell niche. discover IL4I1 populate with high turnover where they phagocytose dying...
Orchestration load is the effort a teacher spends in coordinating multiple activities and learning processes. It has been proposed as construct to evaluate usability of technologies at classroom level, same way that cognitive used measure individual level. However, so far this notion remained abstract. In order ground orchestration empirical evidence study it more systematic detailed manner, we propose method quantify it, based on physiological data (concretely, mobile eye-tracking...
Freezing of gait (FOG) is a devastating motor symptom Parkinson’s disease that leads to falls, reduced mobility, and decreased quality life. Reliably eliciting FOG has been difficult in the clinical setting, which limited discovery pathophysiology and/or documentation efficacy treatments, such as different frequencies subthalamic deep brain stimulation (STN DBS). In this study we validated an instrumented task, turning barrier course (TBC), with international standard questionnaire question...