Key Dates

Related Announcements

• September 12, 2023 - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Predoctoral Fellowship to Promote Diversity in Health-Related Research (Parent F31-Diversity). See NOFO PA-23-271
• September 7, 2023 - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Fellowship for Students at Institutions Without NIH-Funded Institutional Predoctoral Dual-Degree Training Programs (Parent F30). See NOFO PA-23-261
• September 7, 2023 - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Postdoctoral Fellowship (Parent F32). See NOFO PA-23-262
• August 16, 2023 - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Predoctoral Fellowship (Parent F31). See NOFO PA-23-272
• January 26, 2023 - Ruth L. Kirschstein National Research Service Award (NRSA) Institutional Research Training Grant (Parent T32). See NOFO PA-23-048
• January 11, 2023 - Formative and Pilot Intervention Research to Optimize HIV Prevention and Care Continuum Outcomes (R34 Clinical Trial Optional). SEE NOFO PAR-23-060
• January 11, 2023 - Innovations to Optimize HIV Prevention and Care Continuum Outcomes (R21 Clinical Trial Optional). See NOFO PAR-23-061
• January 11, 2023 - Innovations to Optimize HIV Prevention and Care Continuum Outcomes (R01 Clinical Trial Optional). See NOFO PAR-23-062
• January 10, 2022 - Research Enhancement Award Program (REAP) for Health Professional Schools and Graduate Schools (R15 Clinical Trial Required). See NOFO PAR-21-357
• January 10, 2022 - Research Enhancement Award Program (REAP) for Health Professional Schools and Graduate Schools (R15 Clinical Trial Not Allowed). See NOFO PAR-22-060
• September 08, 2021 - Emerging Global Leader Award (K43 Independent Clinical Trial Required). See NOFO PAR-21-251
• September 08, 2021 - Emerging Global Leader Award (K43 Independent Clinical Trial Not Allowed). See NOFO PAR-21-252
• May 19, 2021 - Academic Research Enhancement Award for Undergraduate-Focused Institutions (R15 Clinical Trial Required). See NOFO PAR-21-154
• May 19, 2021 - Academic Research Enhancement Award for Undergraduate-Focused Institutions (R15 Clinical Trial Not Allowed). See NOFO PAR-21-155
• May 7, 2021 - NIMH Research Education Mentoring Program for HIV/AIDS Researchers (R25 Clinical Trial Not Allowed). See NOFO PAR-21-228
• May 12, 2020 - Mentored Clinical Scientist Research Career Development Award (Parent K08 Independent Clinical Trial Required). See NOFO PA-20-202
• May 12, 2020 - Mentored Clinical Scientist Research Career Development Award (Parent K08 Independent Clinical Trial Not Allowed). See NOFO PA-20-203
• May 12, 2020 - Mentored Patient-Oriented Research Career Development Award (Parent K23 Independent Clinical Trial Not Allowed). See NOFO PA-20-205
• May 12, 2020 - Mentored Patient-Oriented Research Career Development Award (Parent K23 Independent Clinical Trial Required). See NOFO PA-20-206
• May 7, 2020 - NIH Small Research Grant Program (Parent R03 Clinical Trial Not Allowed). See NOFO PA-20-200
• May 6, 2020 - Mentored Research Scientist Development Award (Parent K01-Independent Clinical Trial Required). See NOFO PA-20-176
• May 6, 2020 - Midcareer Investigator Award in Patient-Oriented Research (Parent K24 Independent Clinical Trial Not Allowed). See NOFO PA-20-186
• May 6, 2020 - Mentored Research Scientist Development Award (Parent K01--Independent Clinical Trial Not Allowed). See NOFO PA-20-190
• May 6, 2020 - Midcareer Investigator Award in Patient-Oriented Research (Parent K24 Independent Clinical Trial Required). See NOFO PA-20-193
• May 5, 2020 - NIH Pathway to Independence Award (Parent K99/R00 Independent Clinical Trial Required). See NOFO PA-20-187
• May 5, 2020 - NIH Pathway to Independence Award (Parent K99/R00 Independent Clinical Trial Not Allowed) See NOFO PA-20-188

Issued by

National Institute of Mental Health (NIMH)

Purpose

This NOSI seeks to advance data science research in HIV by encouraging the generation of cutting-edge synthetic datasets, artificial intelligence, and machine learning approaches to expand our capacity to address the dynamic, complex, and evolving HIV epidemic.   Team science approaches where the strength and expertise of multiple individuals across data and computational sciences, biostatistics, behavioral and social sciences, computer science, and HIV prevention and care, among others, is strongly encouraged. For the purposes of this announcement, AI/ML refers to AI and its subsets (machine learning, deep learning, neural networks, natural language processing). 

Background

The NOSI is aligned with the priorities outlined by the Office of AIDS Research, the NIH Strategic Plan for Data Science, and the NIMH Division of AIDS Research’s Program in Data Science and Emerging Methodologies in HIV.

There is increasing consensus among HIV leaders that ending the HIV epidemic in the U.S. and globally will require innovative, data-driven approaches to identify the gaps in our current understanding about HIV and to inform the development of novel approaches to respond rapidly to the HIV prevention and treatment needs especially among hard-to-reach populations. Despite the significant scientific advances in prevention, treatment, and care, as well as the widespread availability, domestically and globally, of effective prevention and treatment options, unequal access to HIV prevention, testing, and treatment services, as well as other factors such as social and structural determinants of health, have had a direct impact on HIV outcomes (The White House, 2021; UNAIDS, 2022). More widespread use of advanced data science approaches, including AI/ML and deep learning, can help to identify the critical factors, including mental health, individual, interpersonal, community, social, structural, and other health challenges, that contributes to HIV outcomes which will enable us to better target prevention efforts, optimize treatment decisions, and improve patient experience.

Maximizing data utility is a critical goal but current gaps in HIV data access, sharing, and reuse of data from a broad range of research studies, as well as challenges to obtaining data directly from routine clinical care (e.g., electronic medical records), limit the use of data science approaches toward actionable HIV testing, prevention, and treatment for all. The National HIV/AIDS Strategy (2022-2025) specifically calls for increased access to, and sharing of, HIV-relevant data to foster data-driven scientific discovery and innovation that will lead toward ending the HIV epidemic. A similar call for, and a commitment to, greater data sharing and accessibility has been made by global health funding agencies to improve public health outcomes. Despite these calls, barriers to widespread data sharing, often due to real concerns about the need to maintain privacy and the safeguarding of data, limits our ability to gain new insights from the large volume of existing data using novel big data approaches such as AI/ML. The promise of AI/ML to support HIV diagnosis, treatment, prevention, and response needs cannot be fully realized without access to high-quality, ethically sourced, and accessible data.

AI/ML learning techniques and applications are leading scientific breakthroughs in health and medicine by leveraging real-world data-driven insights for science, policy, and practice. Opportunities to use AI/ML for making predictions about the health of populations or to improve decision-making to address HIV prevention, care, and treatment needs abounds but have yet to be fully realized. Therefore, this NOSI supports three related, but distinct research needs that are critical to accelerating the HIV diagnosis, treatment, prevention, and response: 

(1) Building an infrastructure for safe and efficient data sharing - scaling HIV data science efforts by generating synthetic datasets or establishing a federated learning collaboration to rapidly respond to the dynamic, complex, and evolving HIV epidemic;

(2) Developing transparent AI/ML models - increasing the scientific, clinical, and public health utility of AI/ML models by applying, for example, eXplainable artificial intelligence (XAI) techniques to further our understanding of the mechanisms that may lead to better HIV diagnosis, prevention, and treatment efforts; and

(3) Supporting translational AI/ML research - promoting efforts to use vertically integrated AI/ML approaches that produce more meaningful and applicable results that directly benefits people with or without HIV. 

These three areas of interest, as well as other areas of programmatic research interest, are described below.

Research Objectives

This NOSI seeks transformative, translational, and transdisciplinary HIV research in AI/ML to accelerate HIV diagnosis, treatment, prevention, and response. 

Specific areas of research interest include, but are not limited to, the following:

• Generate synthetic HIV-relevant datasets that can be made available to the scientific community for AI/ML using existing (real) data that cannot be made publicly accessible due to strict regulations, privacy concerns, or the inclusion of identifying or sensitive information, assessing the quality of the synthetic data, and identifying and mitigating any potential biases;
• Use a federated learning approach to train a model using a large and more diverse dataset that can be aggregated into a consensus model identifying the underlying mental health factors, as well as social and structural factors (e.g., economic insecurity, housing instability, food insecurity, and intersectional stigma and discrimination), contributing to HIV in priority populations;
• Use XAI techniques to provide additional explanatory power for traditional ML models to support clinical decision-making in HIV care as well as exploring to what degree the predictive model mirrors expected human approaches to care;
• Apply XAI techniques to improve our understanding of the behavioral or social mechanisms that may lead to engagement in HIV diagnosis, prevention, and treatment;
• Use AI/ML technologies to process, explore, identify, classify, interpret, and visualize data, learn patterns iteratively, and predict key HIV-relevant outcomes based on what is known about HIV as well as what is unknown with attention to potential biases from source data or algorithms, application of strategies to mitigate those biases, and model explainability;
• Apply a vertically integrated approach to AI/ML development that seeks to understand the needs of the patient and clinician, prioritizes existing resources and infrastructure (i.e., taking into consideration the implementation barriers, which is critically important especially in under-resourced settings), and uses cross-disciplinary teams to improve the translation of AI/ML tools and algorithms into HIV clinical care.

Other areas of programmatic research interests include, but are not limited to:

• Supporting effective and efficient methods for HIV data curation, novel data visualization and analysis tools, and the infrastructure required to make them accessible to researchers;
• Applying statistical, mathematical, or computational approaches to integrate and harmonize diverse datasets for the discovery of underlying latent factors in complex behavioral, social, neurological, and biomedical data related to HIV acquisition, care, and comorbidities that may lead to the identification of new intervention strategies;
• Using AI/ML technologies for understanding and improving HIV prevention and treatment by integrating and harmonizing multimodal (e.g., numerical data, images, text) and multilevel (e.g., individual, community, structural) data collected using various sources such as electronic health records [EHRs], social media, wearables and sensors, smartphones, health care claims data, electronic prescription services, and so forth;
• Developing novel approaches for valid and reliable assessments, measures, or estimation of psychological, behavioral, or social-structural factors that contribute to HIV in cohorts, especially high-incidence populations, or other large data sources of people living with HIV;
• Exploring (and validating) ML approaches such as causal deep learning to estimate, for example, HIV treatment effects from observational data, accounting for selection biases in the observed data;
• Exploring the use of contemporary causal inference methods for integrating heterogenous HIV data (i.e., combining randomized clinical trials [RCTs] with observational studies) to extend findings from RCTs to key populations for the future implementation of more tailored HIV prevention, treatment, and care approaches;
• Predicting who may be at highest risk for dropping out from or more likely to return to HIV care using real-time or near real-time data (e.g., sensors, smartphone global positioning system (GPS), EHRs) to provide recommended actions and facilitate access to preventive interventions;
• Conducting simulation modeling to explore implementation strategies to improve HIV prevention and treatment that considers the complex, dynamic, and evolving individual, community, social, and structural factors that influence engagement in HIV testing, prevention, and care while considering the needs of the population in a meaningful way;
• Exploring the potential benefits and use of generative AI or large language models for HIV prevention interventions, HIV healthcare service delivery, and HIV communication, assess and promote accuracy, safety, and equity, and enhance our understanding of the needs of the consumers (e.g., clinicians, patients, community);
• Enhancing workforce development and training opportunities in AI/ML to advance health equity research and researcher diversity in HIV, see NOT-OD-20-031. 

Finally, the NIMH Division of AIDS Research strongly encourages applications that include meaningful engagement with community and/or implementing partners and other interested/affected parties throughout the entire research process.

Application and Submission Information

This notice applies to due dates on or after January 7, 2024 and subsequent receipt dates through January 8, 2027. 

Submit applications for this initiative using one of the following notices of funding opportunities  (NOFOs) or any reissues of these announcements through the expiration date of this notice.

PA-23-048 - Ruth L. Kirschstein National Research Service Award (NRSA) Institutional Research Training Grant (Parent T32).

PAR-23-060 - Formative and Pilot Intervention Research to Optimize HIV Prevention and Care Continuum Outcomes (R34 Clinical Trial Optional).

PAR-23-061- Innovations to Optimize HIV Prevention and Care Continuum Outcomes (R21 Clinical Trial Optional).

PAR-23-062 - Innovations to Optimize HIV Prevention and Care Continuum Outcomes (R01 Clinical Trial Optional).

PAR-21-357 - Research Enhancement Award Program (REAP) for Health Professional Schools and Graduate Schools (R15 Clinical Trial Required).

PAR-22-060 - Research Enhancement Award Program (REAP) for Health Professional Schools and Graduate Schools (R15 Clinical Trial Not Allowed).

PAR-21-251 - Emerging Global Leader Award (K43 Independent Clinical Trial Required).

PAR-21-252 - Emerging Global Leader Award (K43 Independent Clinical Trial Not Allowed).

PAR-21-154 - Academic Research Enhancement Award for Undergraduate-Focused Institutions (R15 Clinical Trial Required).

PAR-21-155 - Academic Research Enhancement Award for Undergraduate-Focused Institutions (R15 Clinical Trial Not Allowed).

PAR-21-228 - NIMH Research Education Mentoring Program for HIV/AIDS Researchers (R25 Clinical Trial Not Allowed).

PA-23-271  - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Predoctoral Fellowship to Promote Diversity in Health-Related Research (Parent F31-Diversity

PA-23-262   - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Postdoctoral Fellowship (Parent F32)

PA-23-261  - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Fellowship for Students at Institutions Without NIH-Funded Institutional Predoctoral Dual-Degree Training Programs (Parent F30).

PA-23-727  - Ruth L. Kirschstein National Research Service Award (NRSA) Individual Predoctoral Fellowship (Parent F31)

PA-20-202 - Mentored Clinical Scientist Research Career Development Award (Parent K08 Independent Clinical Trial Required)

PA-20-203 - Mentored Clinical Scientist Research Career Development Award (Parent K08 Independent Clinical Trial Not Allowed

PA-20-205 - Mentored Patient-Oriented Research Career Development Award (Parent K23 Independent Clinical Trial Not Allowed).

PA-20-206 - Mentored Patient-Oriented Research Career Development Award (Parent K23 Independent Clinical Trial Required)

PA-20-200 - NIH Small Research Grant Program (Parent R03 Clinical Trial Not Allowed)

PA-20-176 - Mentored Research Scientist Development Award (Parent K01-Independent Clinical Trial Required).

PA-20-186 - Midcareer Investigator Award in Patient-Oriented Research (Parent K24 Independent Clinical Trial Not Allowed)

PA-20-190 - Mentored Research Scientist Development Award (Parent K01--Independent Clinical Trial Not Allowed

PA-20-193 - Midcareer Investigator Award in Patient-Oriented Research (Parent K24 Independent Clinical Trial Required)

PA-20-187 - NIH Pathway to Independence Award (Parent K99/R00 Independent Clinical Trial Required)

PA-20-188 - NIH Pathway to Independence Award (Parent K99/R00 Independent Clinical Trial Not Allowed)

All instructions in the SF424 (R&R) Application Guide and the notice of funding opportunity used for submission must be followed, with the following additions:

• For funding consideration, applicants must include “NOT-MH-23-350” (without quotation marks) in the Agency Routing Identifier field (box 4B) of the SF424 R&R form. Applications without this information in box 4B will not be considered for this initiative.

Applications nonresponsive to terms of this NOSI will not be considered for the NOSI initiative.

Inquiries

Please direct all inquiries to the contacts in Section VII of the listed notice of funding opportunity with the following additions/substitutions:

Investigators are strongly encouraged to contact and discuss their proposed research with the scientific contact listed below prior to submitting an application to NIMH:

Lori A.J. Scott-Sheldon, Ph.D. 
National Institute of Mental Health, Division of AIDS Research
Telephone: 301-792-2309
E-mail: lori.scott-sheldon@nih.gov