Institute and Center Funded Initiatives
Across NIH’s 27 institutes and centers, SI/ML technologies are being developed. Below are some specific examples:
Office of the Director
- NIH and the National Science Foundation have an interagency initiative called "Smart and Connected Health," which has an FOA for Smart Health and Biomedical Research in the Era of Artificial Intelligence and Advanced Data Science.
- Through the HEAL Initiative, researchers aim to design, develop, and demonstrate feasibility of Survive-OUD, an artificial intelligence driven platform to integrate complex data sources, predict patient relapse, and recommend intervention strategies for individuals impacted by opioid use disorders.
National Cancer Institute (NCI)
- The Computational Resources for Cancer Research portal allows you to explore open-access resources developed by the nation’s experts in cancer and scientific computing and meet potential collaborators. Developed with input from the cancer research community, the portal is designed to help increase understanding, access, and adoption of computational resources for cancer researchers and to foster new collaborative research projects.
- The portal allows access and the ability to use cancer-related software, datasets, and AI models, including those created by the NCI-DOE Collaboration
National Human Genome Research Institute (NHGRI)
- The ENCODE Data Analysis Center uses machine learning techniques to gain novel insights about the relationship between classes of functional elements, with the goal of annotating functional elements of the genome.
National Institute on Aging (NIA)
- NIA is reviewing applications for the Artificial Intelligence and Technology Collaboratories (AITC) for Aging Research Program. The AITC program will serve as a national resource to promote the development and implementation of AI approaches and technology through demonstration projects to improve care and health outcomes for older Americans, including persons with dementia and their caregivers.
- The Artificial Intelligence for Alzheimer’s Disease Initiative aims to create and develop advanced AI methods and apply them to extensive and rich genomic, imaging, and cognitive data. Collectively, the goals of this highly collaborative initiative leverage the promise of ML to contribute to precision diagnostics, prognostication, and targeted and novel treatments.
- NIA has funded a new study in which researchers will develop ML algorithms for the earlier identification of patients with mild cognitive impairment and Alzheimer’s disease and related dementias through natural language processing of electronic health record data and automated speech analysis of patient-doctor conversations.
Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD)
- NICHD is supporting use of a machine learning framework to predict severe maternal morbidity. Severe maternal morbidity, or life-threatening pregnancy complications at delivery, has been increasing steadily, affecting more than 50,000 women in the U.S. in 2014.
National Institute on Drug Abuse (NIDA)
- NIDA is supporting a project using a neural network-based machine vision method of video analysis to study sleep and social behaviors in mice. This non-invasive technology, if successful, will provide detailed behavioral data that can be used to measure the influence of these behaviors in large-scale genomic experiments and potentially allow for the discovery of genes that regulate addiction vulnerability.
- Using the world’s fastest supercomputer, NIDA-funded researchers are applying a new multi-omics, multi-method framework to identify gene networks associated uniquely with cigarette or opioid outcomes and networks shared across these addictions.
- NIDA’s Adolescent Brain Cognitive Development (ABCD) Study is using ML approaches to develop a youth-specific risk calculator that identifies individually based modifiable risk factors that can serve as brain-based targets for novel prevention and intervention approaches.
National Institute of Mental Health (NIMH)
- AI solutions that are understandable to humans, also known as “Explainable AI,” are important to generate new theories, move the scientific field forward, and make AI more acceptable to clinicians, patients, and their families.
NIMH supports research that applies sophisticated AI/ML explainable techniques to discover and optimize treatments for mental illnesses, emotional disturbance, and abnormal behavior, with a focus on individualized treatments and a personalized medicine approach.
National Library of Medicine (NLM)
- The Preventing Medication Dispensing Errors in Pharmacy Practice with Interpretable Machine Intelligence project works to further our knowledge for designing interpretable MI outputs and inform the development of MI models that encourage pharmacy staff to make sound clinical decisions that lead to better patient outcomes while improving work-life at lower costs of care.