Project Grant DP2EB035858

Award Date 9/21/23
Completion Date 9/20/26
Dollars Obligated $1.3M
Funding Federal Agency
Office of the Director
Federal Grant Program
93.310
Assistance Type
Project Grant
Place of Performance
Hawaii, USA
Similar Awards
This $174,788 National Science Foundation (NSF) award under the Computer and Information Science and Engineering (CISE) program focuses on enhancing the assessment and diagnosis of Attention Deficit Hyperactivity Disorder (ADHD). The project aims to develop computational approaches to collect and analyze ADHD-related data, leveraging technologies such as inertial movement units, touch-sensitive screens, and high-precision cameras to gather insights into hyperactivity behaviors. The goal is to...
This $857,216 federal Project Grant award from the National Institute of Mental Health (NIMH) under CFDA 93.242 Mental Health Research Grants will be used by Boston Children's Hospital to conduct a longitudinal study examining the neurodevelopmental trajectories and social determinants leading to early symptoms of Attention Deficit Hyperactivity Disorder (ADHD) and disruptive behaviors in children. The study will leverage an existing large, diverse cohort of low-resourced infants seen in an...
This federal Project Grant award of $812,950 from the National Institute of Mental Health (NIMH) under the Mental Health Research Grants program (CFDA 93.242) aims to advance precision psychiatry and improve mental health outcomes through a collaborative research effort. The primary objectives are to: Create a federated transfer-learning platform to develop generalizable and bias-aware algorithms for mental health applications. Integrate state-of-the-art methods to perform inclusive...
The National Institute of Mental Health (NIMH) awarded a $615,908 Project Grant (CFDA 93.242 - Mental Health Research Grants) to Nurelm Inc. on August 15, 2024. The project, titled "Using Machine Learning and Sensing to Contextualize Hyperactivity Measurement on Wearable Devices", will develop and validate the LEMURDX software system, which uses smartwatch sensors and machine learning algorithms to objectively measure hyperactivity in children with ADHD. The project aims to refine...
This Project Grant award from the National Institute of Mental Health (NIMH), under the Mental Health Research Grants program (CFDA 93.242), will deliver several key products and services over a period of 5 years. The $480,834 award, effective September 6, 2024, will leverage electronic health record databases to develop machine learning-based models for predicting clinical outcomes in psychosis-related disorders, including treatment response, illness severity, medical comorbidities, and...
This federal Project Grant award, funded by the National Institute of Mental Health (NIMH) under the Mental Health Research Grants program (CFDA 93.242), aims to develop digital strategies to advance help-seeking in youth at clinical high risk for developing psychosis. The project, titled "Digital Strategies to Advance Help-Seeking in Youth at Clinical High Risk for Developing Psychosis," is being led by the Trustees of Columbia University in the City of New York, with a subcontract to...
This $287,000 Project Grant award from the National Institute of Mental Health (NIMH), under the Mental Health Research Grants program (CFDA 93.242), supports the development of machine learning-based predictive models and sub-classification approaches for psychosis-related disorders using electronic health records (EHRs). The key objectives are to: Leverage two independent EHR databases to build individual-level prediction models for key clinical outcomes like treatment response, illness...
The National Institute of Environmental Health Sciences (NIEHS) awarded a $1,042,200 Project Grant (CFDA 93.879 - Medical Library Assistance) to The Leland Stanford Junior University to develop and validate a novel computational framework for identifying, validating, and characterizing biological subtypes of psychiatric disorders, with a focus on autism. The key objectives of this 4-year project (8/9/2024 to 5/31/2028) are to: Develop and validate methods to extract individual-level neural...
This $508,500.00 Project Grant award from the National Institute of Mental Health (NIMH) under CFDA Program 93.242 - Mental Health Research Grants will enable New York University School of Medicine to leverage electronic health records (EHRs) and advanced analytical techniques to develop predictive models for clinical outcomes in psychosis-related disorders. The key objectives are to: Build machine learning-based models to forecast treatment response, illness severity, medical comorbidities, and...
Lifespan Digital Health LLC was awarded a $255,409 Project Grant from the National Science Foundation under the NSF Technology, Innovation, and Partnerships program (CFDA 47.084) to develop bio-behavioral technology and provide mental health services. Specifically, the company will use predictive algorithms, wearable technology, and peripheral autonomic biofeedback to provide timely data and enable mental health professionals to treat students. This innovative approach aims to address the...

This $1,309,500 Project Grant awarded by the National Institutes of Health (NIH) under the Trans-NIH Research Support (CFDA 93.310) program supports the development of a novel digital psychiatry diagnostic framework that utilizes crowdsourcing algorithms to improve the specificity of machine learning models in distinguishing between autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD) in adolescents. The key products and services to be delivered under this 3-year project include:

  1. Implementing a gamified digital platform for structured data collection through remote social interaction sessions, where participant behaviors are recorded via webcam and microphone.

  2. Developing a crowdsourcing pipeline to extract nuanced social behavioral features from the recorded videos, using multiple choice annotations provided by distributed crowd workers.

  3. Training deep learning models to leverage the crowd-powered behavioral feature vectors to predict diagnostic categories for ASD and ADHD, as well as quantify the presence of individual behavioral characteristics.

This innovative approach aims to enable more accessible and precise digital psychiatric diagnostics, particularly for underserved populations who face barriers to obtaining neuropsychiatric healthcare services.

Generated 7/16/24, 6:26 AM