A5055904253- Parkinson's Disease Mechanisms and Treatments
- Voice and Speech Disorders
- Cerebral Palsy and Movement Disorders
- Balance, Gait, and Falls Prevention
- Neurological disorders and treatments
- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Amyotrophic Lateral Sclerosis Research
- AI in cancer detection
- Chronic Kidney Disease and Diabetes
- Autism Spectrum Disorder Research
- Parvovirus B19 Infection Studies
- Emotion and Mood Recognition
- COVID-19 Impact on Reproduction
- MRI in cancer diagnosis
- Artificial Intelligence in Healthcare
- Neurobiology of Language and Bilingualism
- Advanced Graph Neural Networks
- Renal and Vascular Pathologies
- Cytomegalovirus and herpesvirus research
- Domain Adaptation and Few-Shot Learning
Harvard University
2023-2024
Takeda (Japan)
2022-2024
Takeda (United States)
2023-2024
Duke University
2023
Abstract Digital health technologies can provide continuous monitoring and objective, real-world measures of Parkinson’s disease (PD), but have primarily been evaluated in small, single-site studies. In this 12-month, multicenter observational study, we whether a smartwatch smartphone application could measure features early PD. 82 individuals with early, untreated PD 50 age-matched controls wore research-grade sensors, smartwatch, while performing standardized assessments the clinic. At...
Digital measures may provide objective, sensitive, real-world of disease progression in Parkinson's (PD). However, multicenter longitudinal assessments such are few. We recently demonstrated that baseline gait, tremor, finger tapping, and speech from a commercially available smartwatch, smartphone, research-grade wearable sensors differed significantly between 82 individuals with early, untreated PD 50 age-matched controls. Here, we evaluated the change these over 12 months observational...
Aim: To develop a shiny app for doctors to investigate breast cancer treatments through new approach by incorporating unsupervised clustering and survival information. Materials & methods: Analysis is based on the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset, which contains 1726 subjects 22 variables. Cox regression was used identify risk factors K-means clustering. Logrank tests C-statistics were compared across different cluster numbers Kaplan-Meier plots...
<p class="MsoNormal" style="text-align: justify;"><span lang="EN-US" style="mso-bidi-font-size: 10.5pt; font-family: Nunito; color: #212529; background: white;">Parkinson&rsquo;s Disease (PD) is a prevalent progressive neurodegenerative condition affecting millions globally. Research has found that individuals with PD have reduced risk of certain cancers, such as colon, lung, and rectal but an increased brain cancer. Therefore, there urgent need for the development advanced...
Abstract Kidney failure is a critical health condition with significant impact on patient well-being and healthcare systems worldwide. Analyzing the longitudinal trajectory of kidney function crucial for understanding disease progression, predicting outcomes, personalizing treatment strategies. This paper proposes novel approach utilizing latent clustering techniques by incorporating survival information to analyze explore patterns within populations. Besides, we also developed web...
Approximately 0.7% of infants are born with congenital cytomegalovirus (CMV), making it the most common infection. About 1 in 5 congenitally infected babies will suffer long-term sequelae, including sensorineural deafness, intellectual disability, and epilepsy. CMV infection is highly species-dependent, rhesus (RhCMV) monkey fetuses only animal model that replicates essential features (cCMV) humans, placental transmission, fetal disease, loss. Using experimental data from RhCMV seronegative...
Abstract Online tools, such as web-based applications, aid medical doctors in recommending treatments and conducting thorough patient profile investigations. Prior studies have created survival analysis tools for cancer survival. However, these often offer basic features simplistic models, providing shallow data insights. Our research involves an in-depth risk using clustering on real-world data. We’ve developed a user-friendly Shiny application to simplify the use of our findings. By...
GNNs are effective for semi-supervised learning tasks on graphs, but they can suffer from bias due to distribution shifts between training and testing node distributions. In this paper, we propose the Invariant Graph Neural Network (IGNN) address issue of in GNNs. Specifically, IGNN learns correlation invariant features different environments, where spurious changes environments. contains two components: graph partition component environments regularizes neural network learn representation...
Abstract Digital health technologies can provide continuous monitoring and objective, real world measures of Parkinson’s disease (PD), but have primarily been evaluated in small, single-site studies. In this 12-month, multicenter observational study, we whether a smartwatch smartphone application could measure features early PD. 82 individuals with early, untreated PD 50 age-matched controls wore research-grade sensors, smartwatch, while performing standardized assessments clinic. At home,...
<title>Abstract</title> Digital measures may provide objective, sensitive, real-world of disease progression in Parkinson’s (PD). However, multi-center longitudinal assessments such are few. We recently demonstrated that baseline gait, tremor, finger tapping, and speech from a commercially available smartwatch, smartphone, research-grade wearable sensors differed significantly between 82 individuals with early, untreated PD 50 age-matched controls. Here, we evaluated the change these over 12...
Frontotemporal Dementia (FTD) encompasses a diverse group of progressive neurodegenerative diseases that impact speech production and comprehension, higher-order cognition, behavior, motor control. Traditional acoustic markers have been extensively studied in FTD, as assessments capturing apathy impairments recognizing expressing emotion. This work leverages machine learning to track changes emotional content within the individuals with FTD healthy controls. The aim project is develop tools...
Automatic prediction of amyotrophic lateral sclerosis (ALS) disease progression provides a more efficient and objective alternative than manual approaches. We propose ALS longitudinal speech transformer (ALST), neural network-based automatic predictor from recordings patients. By taking advantage high-quality pretrained features information in the recordings, our best model achieves 91.0\% AUC, improving upon previous by 5.6\% relative on TDI dataset. Careful analysis reveals that ALST is...
Automatic prediction of amyotrophic lateral sclerosis (ALS) disease progression provides a more efficient and objective alternative than manual approaches. We propose ALS longitudinal speech transformer (ALST), neural network-based automatic predictor from recordings patients. By taking advantage high-quality pretrained features information in the recordings, our best model achieves 91.0%AUC, improving upon previous by 5.6% relative on TDI dataset. Careful analysis reveals that ALST is...
Abstract Parkinson’s disease (PD) is a chronic neurological disorder that affects millions of people worldwide. One the common motor symptoms associated with PD gait impairment, leading to reduced step count and mobility. Monitoring analyzing data can provide valuable insights into progression effectiveness various treatments. The generalized additive model (GAM) presents following variables: sex (Male vs. Female, p = 0.03), handedness (Right Left/Both, 0.015), status father (Yes No, 0.056),...