Call for Proposals

Public-Private Partnerships to Improve Population Health Using Artificial Intelligence and Machine Learning (AI/ML)

Year 4

Overview

The AIM-AHEAD Public-Private Partnerships to Improve Population Health Using AI/ML Program is designed to support mutually beneficial partnerships between a local, state, and/or tribal health department and a: 1) higher education institution and/or 2) data-science-oriented organization with an accessible data library. These collaborations are effective modalities to conduct AI/ML studies that address health and align with the overall goal of AIM-AHEAD. Over 370 health departments exist in the United States, many of which are accredited and have research units that manage grants and conduct studies. Public health departments play a vital role in shaping the conditions for population health and addressing unmet health needs in their communities. These departments are critical and trusted organizations that can benefit from enhancing their AI/ML capabilities to advance various aspects of public health, including early detection and monitoring, predictive analytics, disease surveillance, outbreak detection, healthcare resource allocation, and personalized interventions.

Partnerships among public health department professionals, academic researchers, and data-science/AI/ML experts can further leverage data-driven insights that contribute to more effective and efficient public health strategies to improve community health outcomes. These approaches align with the AIM-AHEAD goals, North Stars, and overarching Healthy People 2030 goals “…to improve the health and well-being of all.” Further, mutually beneficial partnerships comprised of health departments, academic institutions, and private data science-oriented organizations can play a crucial role in addressing obstacles and promoting the successful implementation of AI/ML capabilities.

This Call for Proposals (CFP) invites AI/ML applications relevant to public health such as:

• Predictive modeling (early disease prediction, identifying individuals at high risk for specific health conditions)
• Patient care (developing AI-powered tools for personalized treatment plans and interventions)
• Disease surveillance (using AI/ML to improve disease surveillance systems to detect outbreaks more quickly)
• Targeted health communications (developing AI-powered chatbots to improve health communication and health literacy)
• Forecasting trends in morbidity and mortality using heterogeneous data sources
• Identify differences in health outcomes and develop strategies to improve population health
• Streamlining tasks such as automatic analysis and reporting

Partnerships among and between public health departments, universities, and data science organizations can significantly advance AI/ML research by leveraging expertise, access to real-world healthcare data, technical proficiency for data analysis using advanced algorithms, and clinical expertise to interpret results and translate them into meaningful applications leading to more impactful and relevant AI/ML solutions in healthcare settings.

AIM-AHEAD Background

The AIM-AHEAD Coordinating Center supports multidisciplinary research projects that use artificial intelligence/machine learning (AI/ML) to develop novel algorithms and approaches to address chronic diseases in impacted populations, in alignment with the AIM-AHEAD North Stars. Of particular interest are research projects that use new or real-world synthetic data or existing datasets that include but are not limited to electronic health records (EHR), images, and lifestyle factors to develop and enhance AI/ML algorithms and applications that have the potential to reduce health compromising factors while improving healthcare and outcomes for all.

AIM-AHEAD will establish mutually beneficial, coordinated, and trusted partnerships to empower researchers and communities across the United States in the development of Artificial Intelligence and Machine Learning (AI/ML) models and improve the capabilities of this emerging technology, beginning with electronic health record (EHR) and extending to other lifestyle data to improve health for all Americans. The rapid increase in the volume of data generated through EHR and other biomedical research presents exciting opportunities for developing data science approaches (e.g., AI/ML methods) for biomedical research and improving healthcare. Many challenges can limit widespread use of AI/ML technologies, such as the cost, capability for widespread application, and access to appropriate infrastructure, resources, and training. Additionally, there is a lack of comprehensive and high-quality AI-ready data and a shortage of a pipeline of talented researchers in industry and academia to harness the potential of AI/ML to advance biomedical research and the practice of medicine. This program aims to build AI talent and technology to improve the health of all Americans. The program will bring AI tools to impact patients and support hospitals that otherwise would not have had the resources or bandwidth to investigate advances in AI and ML.

AIM-AHEAD Coordinating Center

The AIM-AHEAD program seeks to establish mutually beneficial, coordinated, and trusted partnerships to empower researchers and communities across the United States in the development of artificial intelligence and machine learning (AI/ML) models and improve the capabilities of this emerging technology, beginning with the use of electronic health record (EHR) and extending to other lifestyle data to improve health for all Americans. The AIM-AHEAD Coordinating Center (A-CC) is building a consortium of institutions and organizations from all stakeholder groups (academic institutions, community organizations, private businesses, non- profits, and healthcare organizations) across the nation.

The A-CC will focus initially on coordination, assessment, planning, and capacity building to enhance the use of artificial intelligence (AI) and machine learning (ML) in research among the consortium institutions and organizations, and to build and sustain trusted relationships between the consortium and groups impacted by health problems. The A-CC is comprised of four main cores:

Leadership/Administrative Core: Lead the overall A-CC, recruit and coordinate consortium members, project management, partnerships, stakeholder engagement, and outreach to develop AI/ML talented researchers in health research, and to establish trusted relationships with key stakeholders to enhance the volume and quality of data used in AI/ML research. The Leadership/Administrative Core will operate as a Pass-Through Entity (PTE) for this Federal program.

Data Science Training Core: Assess, develop, and implement data science training curriculum and workforce development resources in AI/ML.

Data and Research Core: Determine and address research priorities and needs in linking and preparing linking and preparing multiple sources and types of research data to form an inclusive basis for AI/ML use cases that will illuminate strategies and approaches to address health problems. This may include facilitating the extraction and transformation of data from electronic health records (EHR) for research use and consideration of lifestyle data as crucial contributors to health.

Infrastructure Core: Assessment of data, computing, and software infrastructure models, tools, resources, data science policies, and AI/ML computing models that will facilitate AI/ML and health research; and establishment of pilot data and analysis environments to accelerate overall A-CC aims.

AIM-AHEAD North Stars

Projects must be aligned with one or more of the AIM-AHEAD North Stars:

1. North Star 1: Develop a representative AI/ML workforce with broad participation.
2. North Star 2: Increase knowledge, awareness and national-scale community engagement and empowerment in AI/ML.
3. North Star 3: Use AI/ML to improve behavioral health, cardiometabolic health and cancer outcomes for all.
4. North Star 4: Build community capacity and infrastructure in AI/ML to address community-centric health needs and challenges.

Consistent with NIH practice and applicable law, the AIM-AHEAD program will not use the race, ethnicity, or sex of prospective program participants or faculty as an eligibility or selection criteria. The race, ethnicity, or sex of candidates will not be considered by NIH in the application review process or when making funding decisions.

Program Directors/Principal Investigators (PD(s)/PI(s))

All PD(s)/PI(s) must have an eRA Commons account. PD(s)/PI(s) should work with their organizational officials to either create a new account or affiliate their existing account with the applicant organization in eRA Commons. PD(s)/PI(s) who are also organizational Signing Officials must have two distinct eRA Commons accounts, one for each role. Obtaining an eRA Commons account can take up to 2 weeks, so applicants should request an account as soon as possible.

Eligible Individuals (Program Director/Principal Investigator)

For institutions/organizations proposing multiple PDs/PIs, please consult the Multiple Program Director/Principal Investigator Policy and submission details in the Senior/Key Person Profile (Expanded) Component of the How to Apply – Application Guide.

Eligibility for Current and Prior AIM-AHEAD Awardees

Applicants who have previously received AIM-AHEAD funding are eligible to apply; however, the research question(s) must be distinct from the previously funded application.

Individuals may not hold multiple AIM-AHEAD awards except under exceptional circumstances.  Consequently, the following limitations apply:

• An applicant who applies to more than one AIM-AHEAD program, and is recommended for more than one award, should be aware that AIM-AHEAD will determine the program for which the applicant will receive an award.
• An applicant currently participating as a trainee or PI in an AIM-AHEAD program, and who still would be an active awardee in the current program at the start of the second program, is not eligible to receive a second award without appropriate justification and approval from the second program.
• An applicant serving as PI or a Co-I/contributor on a current AIM-AHEAD research award is not eligible to hold multiple AIM-AHEAD research awards.

Exceptions to these limitations will require a request in writing, with justification, from the applicant.  The request will be reviewed by AIM-AHEAD leadership and granted only at AIM-AHEAD’s discretion.

Eligible Organizations

Public-Private dyad or triad applicant teams are eligible to apply for this CFP; however, teams must include a local, state, and/or tribal public health department.  The second (dyad) or third (triad) partner must include a private higher education institution or data science-oriented organization.

Any of these three types of institutions are eligible to be the primary applicant organization, however, the primary applicant must be a domestic institution located in the United States and its territories.

Applications that do not include a health department will be considered non-responsive to the Call for Proposals and returned without review.

The objective of this funding opportunity is for public health departments to co-design and co-lead AI/ML research projects with their partners by leveraging health department data resources, further supporting informed decisions and interventions to improve population health, particularly in areas such as disease surveillance, outbreak detection, and health education.

Applicant institutions must meet the respective eligibility criteria below:

Public Health Departments may include the following:

• Organizations with current or pending accreditation by the Public Health Accreditation Board (PHAB), with the infrastructure to manage research grants
• Tribal health services, departments, or equivalents
• Special district governments
• County governments
• State governments
• City or township governments

Higher Education Institutions

In accordance with the goals of the AIM-AHEAD Coordinating Center, the following types of higher education institutions are highly encouraged to apply for support:

• Public/State Controlled Institutions of Higher Education
• Private Institutions of Higher Education

Data Science-Oriented Organizations may include the following:

• Small businesses
  • Eligible to receive and manage federal funding and the associated required funding
  • Ability and willingness to share data with the applicant partner organizations
• For-profit organizations (other than small businesses)
  • Eligible to receive and manage federal funding and the associated required funding
  • Ability and willingness to share data with the applicant partner organizations
• Nonprofits other than institutions of higher education
  • Nonprofits with 501(c)(3) IRS Status
  • Nonprofits without 501(c)(3) IRS Status
  • Community-Based Organizations
  • Tribal health and/or human service organizations or tribally derived institutions (e.g. Urban Indian Health Organizations, Tribal Epidemiology Centers)

Community organizations, nonprofits and non-academic institutions with a documented interest in working with high-risk populations are strongly encouraged to apply. Before applying, these organizations must be registered with System for Award Management (SAM; see https://sam.gov/content/home) and must maintain active SAM registration throughout the award period (please see below for Required Registrations for Primary Applicant Institutions/Organizations). Federally recognized tribes and their derivatives are exempt from this requirement. 

Foreign Institutions

Non-domestic (non-U.S.) Entities (Foreign Institutions) are not eligible to apply.

Non-domestic (non-U.S.) components of U.S. Organizations are not eligible to apply.

Foreign components, as defined in the NIH Grants Policy Statement, are not allowed.

Required Registrations for Primary Applicant Institutions/Organizations

Applicant organizations must complete and maintain the following registrations as described in the SF 424 (R&R) Application Guide to be eligible to apply for or receive an award.  All registrations must be completed prior to the application being submitted.  Registration can take 6 weeks or more, so applicants should begin the registration process as soon as possible.  The NIH Policy on Late Submission of Grant Applications states that failure to complete registrations in advance of a due date is not a valid reason for a late submission.

System of Award Management (SAM): Applicants must complete and maintain an active registration, which requires renewal at least annually.  The renewal process may require as much time as the initial registration.  SAM registration includes the assignment of a Commercial and Government Entity (CAGE) Code for domestic organizations that have not already been assigned a CAGE Code.  Federally recognized tribes and their derivatives are exempt from this requirement.

Unique Entity Identifier (UEI): A UEI is issued as part of the SAM.gov registration process.  The same UEI must be used for all registrations, as well as the grant application.

eRA Commons: Once the UEI is issued, organizations can register with eRA Commons in tandem with completing their Grants.gov registration. All registrations must be in place at the time of submission.  eRA Commons requires organizations to identify at least one Signing Official (SO) and at least one Program Director/Principal Investigator (PD/PI) account in order to submit an application.

Grants.gov registration: Applicants must have an active SAM registration in order to complete the Grants.gov registration.

Organizational Structure and Nature of Collaboration Among the Required Partners

Organizational structure: The team structure should avoid giving any single individual undue authority that prevents contributions from the wider team for setting program priorities, resource distribution, and rewards. Strong leadership is required for complex team efforts to succeed, while at the same time effective team leadership requires decision-making based on an amalgam of interests, expertise, and roles, guided by recognized project objectives. Applicants should develop a management structure based on project objectives that effectively promotes the proposed research.

Nature of the Collaboration: A framework for sharing and/or integrating data across team members must be customized to fit the specific data needs of the project. Plans for data archiving and long-term preservation for team use should be described in the proposal (See Partnership Plan Section on p. 12). Depending on the needs and challenges of managing team data, applicant teams may also include and justify data/resource sharing and management systems and/or hiring of professional data science staff.

Engagement: Partners are encouraged to utilize a community engaged approach in all aspects of the project.

Research Topics of Interest

Studies that can help advance public health research in high priority areas aligned with the AIM-AHEAD North Stars are strongly encouraged. Topics of interest include, but are not limited to:

• Use of predictive modeling in enhancing the accuracy, efficiency, and actionable insights in public health decision-making
• Studies that employ AI-driven disease forecasting
• Novel studies that develop new analytical tools and methods 
• Studies that use AI methods, including machine learning and natural language processing to enhance risk prediction approaches
• Machine learning algorithms for EHRs in public health departments
• Use of AI in public health diagnostics to increase the speed and precision of diagnostic procedures

Budget Estimates, Number of Awards, and Duration of the Program

Funding for the Implementation Phase will be contingent on the progress and completion of the Planning Phase. AIM-AHEAD anticipates supporting up to 12 projects in the Planning Phase. Of these, up to 7 projects that meet the following criteria will be selected for further funding in the Implementation Phase:

• Demonstrated successful progress in the planning phase
• Are novel, impactful and/or practical
• Demonstrate meaningful collaboration and co-design with public health departments and data science organizations
• Have the potential for meaningful and practical impact to the public health departments and their communities

The budget limit for each application is $612,500 in total costs. Projects will include a 6-month Planning Phase (maximum budget of $87,500) and a 12-month Implementation Phase (maximum budget of $525,000). A refined study protocol and data analysis plan must be submitted at the end of the Planning Phase.

A final report describing the implementation outcomes (e.g., measurable improvements in efficiency, accuracy, productivity, cost reduction, or how well a new practice, policy, or intervention was adopted, integrated, and sustained by integrating the developed AI/ML model into real-world operations) is required at the conclusion of the Implementation Phase. Funded applications must be completed within 18 months from the start date (September 2, 2025). Requests for no cost extensions are only permitted with approval from NIH.

Potential Risks/Challenges and Mitigation Measures

The risks and challenges for the Public-Private Partnerships to Improve Population Health Using AI/ML program include submission of timely invoices and monthly reports as well as completion of monthly project management and evaluation documents. Potential mitigation strategies involve the development of standardized reporting tools, the use of easily accessible systems for information exchange, applicant organizations sufficiently staffed to facilitate compliance, and appreciation of the heterogeneity of organizational infrastructures.

Expected Outcomes, Impact, and Anticipated Benefits of the Program

Expected Outcomes: The Public-Private Partnerships to Improve Population Health Using AI/ML program is expected to expand the AIM-AHEAD consortium, lead to consortium pilot grant applications, and enhance the professional networks of AIM-AHEAD stakeholders in AI/ML research. Dyad or triad applicant teams are eligible for this CFP. Teams must include a 1) local, state, and/or tribal public health department in partnership (MPI/Co-Lead) with a 2) higher education institution and/or 3) data science-oriented organization with a library of sharable data.

Impact: Any of the three types of institutions/organizations are eligible to be the primary applicant, however, the objective of this funding opportunity is for public health departments to co-design and co-lead AI/ML research projects with their partners by leveraging health department data resources, further supporting informed decisions and interventions to improve population health, particularly in areas like disease surveillance, outbreak detection, and health education.

Findings from the funded projects are expected to generate strong proof-of-concept data that can serve as the empirical foundation for subsequent NIH grant applications. Expected outcomes include the submission of a peer-reviewed manuscript, plans for the sustainability of the partnerships, and plans for a subsequent grant application from the awardee teams.

Benefits: Anticipated benefits of the Public-Private Partnerships to Improve Population Health Using AI/ML program will include:

• Enhancement of the data infrastructure of accredited health departments
• Strengthening the public health infrastructure
• Creation of new AIM-AHEAD stakeholders
• Enhancement of the public health workforce
• Expanded literacy in public health and population health

Submission Guidelines

The AIM-AHEAD Consortium utilizes the online portal InfoReady to upload and submit each completed component of proposal applications. Please use Chrome, Firefox, or Edge. — If you are using Safari, make sure to clear your cache before logging in.

Application Process

Which Consortium hub should I connect with?

Be sure to record the relevant Hub on your application that represents your geographic location.

Application Components

1. Applicant Information (Principal Investigator(s)/Program Director(s))
   • Provide names, institution/organizations, departments, position titles, research areas, and email addresses
2. Biosketches in NIH (https://grants.nih.gov/grants/forms/biosketch.htm) or other format, a curriculum vitae, or a professional resume (maximum 5 pages). Biosketches are required for all key personnel.
3. Letters of support are required from government public health departments conveying support for the project, resources, and assurance for protected time for their staff to participate in the project. Letters of support do not count towards the page limitation.
4. Proposal Summary (limit 2000 characters/approx. 300 words)
5. The proposed research focus or scope must fall within the AIM-AHEAD North Stars (see above).
   • The Research Description should consist of the following sections:
     1. Title and Specific Aims (1 page)
        • Provide a clear, concise summary of the aims of the proposed work and its relationship to your long-term goals. State the hypothesis to be tested.
     2. Significance (1 page)
        • State the premise for the research grant.
        • State the importance of the problem, the critical issue to be addressed and the significance and relevance for public health departments.
        • Explain how the proposed project will advance scientific knowledge or technical capability.
        • Describe how the proposed project will contribute to the production of a subsequent extramural grant application.
     3. Approach and Timeline (4 pages)
        • Planning Phase (6 months)
          • To The planning phase can be used to establish DUAs, prepare datasets for analysis, collect preliminary data, prepare small scale feasibility studies, establish necessary infrastructure, and/or strengthen partnerships before undertaking the Implementation Phase.
          • Outline the processes for establishing a data use agreement and obtaining IRB approval within the first 90 days of the award.
        • Implementation Phase (12 months)
          • Demonstrate the feasibility of accomplishing the proposed research within 18 months.
          • A refined Statement of Work (SOW) and an updated Implementation Plan will be required at the conclusion of the Planning Phase.
          • Describe a community-engaged and/or collaborative research study design and strategies for participation of partners and partner organizations.
          • Description of the specific data source, primary data collection or a database.
          • Clearly specify anticipated outcomes and deliverables of the proposed effort.
          • Briefly describe the anticipated longer-term directions of research program, and plans to secure sustainable funding for the work.
     4. Investigative Team (1 page maximum)
        • Provide a description of the investigative team and their experience related to the proposed study
        • Must clearly identify the plan for collaboration among partners and the contribution of each member of the research team
     5. Partnership Plan (1 page maximum)
        • Provide a description of the partnership plan/partnering agreement for the project which includes the following elements: overall goals/vision, roles/responsibilities (with a description of who will do what?), authorship/credit, communication/contingencies and conflicts of interest.
     6. References Cited (1 page maximum)
        • List only references cited in the project description or supplementary documents of the proposal.
     7. The Budget and Budget Justification (7 pages maximum)
        • Use the NIH Research & Related Budget Form.
        • The budget justification (2 pages) should provide a detailed description and justification for all budgeted items with separate fields for itemizing costs (consultants, equipment, supplies, travel, etc.). The total budget cannot exceed $612,500 and must include direct and indirect costs. Applicants should budget for travel to the AIM-AHEAD Consortium Annual Meeting (2-day meeting, July/Aug, TBD).
     8. Responsible Conduct of Research, Human Subjects, and Animal Training
        • NIH funding requires that investigators and all key personnel MUST comply with the Responsible Conduct of Research Additionally, projects that involve human subjects or data from living humans are require to submit the study protocol for review from an Institutional Review Board (IRB) and provide documentation of the determination from the IRB.

There is flexibility in assigning page limits among the proposal components (see above), but the complete application should not exceed 16 pages.Use 11-point Arial font, single-spaced lines and margins of at least 0.5 inches.

1. Administrative review

   Applications are reviewed administratively when they are submitted. Administrative staff will verify that all required documents are included. Applications not meeting these requirements will be returned for corrections. Corrected proposals must be resubmitted within 48 hours of receiving administrative review correction requests. No extensions will be given.

2. Scientific review

   Applications submitted to the AIM-AHEAD Coordinating Center will be reviewed for scientific and technical merit through a peer-review process. Peer reviewers will use the following criteria to evaluate the applications.

   • To what extent does the proposal align with the central goals of AIM-AHEAD Consortium? To what extent is the project likely to advance these goals?
   • Are the application’s specific aims sufficiently independent?
   • What is the likelihood of accomplishing the specific aims within the period of the award?
   • To what extent is the proposed approach appropriate to achieve the goals of the project? What is the likelihood of a successful outcome?
   • Does the proposal include a description of the historical collaboration among the partners?
   • To what extent is the proposed project mutually beneficial for each partner?
   • To what extent does the proposal appropriately consider ethical, legal, and privacy concerns?
   • Is the project likely to generate sufficient preliminary data that can lead to a larger NIH grant application?
   • To what extent does the proposal briefly describe a likely follow-up grant application aligned with the central goals of AIM-AHEAD Consortium?
   • How likely are the proposed partnerships to be sustainable beyond the duration of the award?

   All eligible applications will be reviewed following a modified NIH peer review process. The standard NIH scoring range (1-9) will be used to assess the strengths and weaknesses of the application regarding the following criteria:

   • Overall Impact
   • Significance
   • Innovation
   • Approach

   Additional Review Criteria: The applicant team and the institutional environment will be evaluated by the reviewers and considered when ranking applications but will not be assigned a priority score.

3. Programmatic review

   The AIM-AHEAD MPIs will conduct a programmatic review of applications.  The primary criterion for programmatic review is the application evaluation by the scientific reviewers.  Additional consideration will be given to alignment with AIM-AHEAD North Stars, stakeholder composition and geographical distribution of the overall cohort consistent with AIM-AHEAD program goals.  Results of the programmatic review will be submitted to NIH for approval of awardees.

Reviewers will identify a subset of proposals to be recommended for funding. The NIH AIM-AHEAD program staff will review the final pool of applications recommended for funding and provide the final approval. PIs of proposals approved for funding will be notified by email. Brief feedback from the reviewers will be provided to all applicants via email.

Grantee Expectations

Grantees will work closely with pertinent AIM-AHEAD Cores during the implementation of their projects. In addition, grantees will also be expected to comply with AIM-AHEAD program guidelines which include:

1. Participation in monthly awardee meetings (via Zoom)
2. Timely submission of monthly reports, invoices, and surveys
3. Participation in annual hub and AIM-AHEAD Consortium meetings
4. Presentation of project results in AIM-AHEAD meetings
5. Agreement for AIM-AHEAD to disseminate study findings through online websites, social media, and other communication channels.
6. Provision of a summary of research status about milestones listed in the proposal, challenges faced and plans to overcome those challenges, usage of funds, and next steps.
7. Within 60 days following the project end date, submit a final report of research findings, usage of funds, and a list of publications, grant applications, articles, and reference presentations emerging from the research.

Data Resources

Applicants are strongly encouraged to utilize data from the health department partner to pilot AI/ML applications to strengthen their operations, co-design interventions and preventions, or improve health outcomes in partnership with the communities they serve.

Alternatively, applicants may apply to use existing AIM-AHEAD resources including the OCHIN Database on AIM-AHEAD Service Workbench or MedStar Health through the AIM-AHEAD Data Bridge (AADB). Applicants may also propose using existing, large-scale databases – such as those typically housed in state or tribal health departments – appropriate to their applications. In such instances, applicants are expected to document that analysis of said databases can address not only the proposed research questions, but also the requirements of the AIM-AHEAD goals, especially North Star III: Use AI/ML to improve behavioral health, cardiometabolic health and cancer outcomes for all. 

Data Set Options for Research Funded by AIM-AHEAD

These data sources are options for projects teams to propose for AIM-AHEAD-funded research projects. Applicants may also propose other data sources for their projects. As noted in the right column, AIM-AHEAD data partners provide extra services to facilitate access and mentorship to AIM-AHEAD-approved project teams. 

OCHIN Database 

A nonprofit leader in health care innovation, OCHIN operates the most comprehensive database on healthcare and outcomes of primary care patients in the United States, including 1.3 million rural residents. The OCHIN Epic EHR data warehouse aggregates electronic health record (EHR) and area-level data from over 280 health systems with over 2,400 clinic sites throughout the United States (>40 states). Approved AIM-AHEAD projects can access >10 years of longitudinal OCHIN Epic ambulatory EHR data.

The primary sources of OCHIN data are outpatient community-based health centers (CHCs), which deliver comprehensive, high-quality primary care and other services such as dental, pharmacy, mental health, substance abuse treatment, and social work care regardless of patients’ ability to pay.

Explore the OCHIN Database through Cohort Discovery, a web-based software tool for obtaining counts of patients matching user-specified inclusion/exclusion criteria. To gain access to Cohort Discovery, AIM-AHEAD program applicants must have completed and be up to date with standard training in Human Subjects Research and Responsible Conduct of Research. Access will be granted within 3 – 7 business days. Request Access to Cohort Discovery

About the OCHIN Database

• Data years available for AIM-AHEAD: 2012-2023
• Patients with one or more ambulatory, telehealth, or dental visit at a member clinic site on or after 1/1/2012
• Records from institutionalized patients and neonates (<28 days old) are excluded

Data Access

AIM-AHEAD-awarded projects approved by OCHIN’s Data Access Committee are provisioned a custom HIPAA Limited Dataset, per each project’s specific aims, accessible via the AIM-AHEAD Service Workbench.

Access to data requires:

• A data specification worksheet approved by OCHIN
• An IRB determination
• An executed Data Use Agreement

Data Bridge from MedStar Health

The MedStar Health Research Institute (MHRI) hosts the Data Bridge from MedStar Health (AADB), a comprehensive multimodal data resource providing AI/ML-ready datasets to approved AIM-AHEAD awardees. The AADB affords access to various health data types, including Electronic Health Records (EHR), medical imaging, and clinical notes, all curated under appropriate regulatory clearance (IRB, DUA).

MedStar Health’s extensive mid-Atlantic clinical network includes 10 hospitals (33% rural) and over 300 points-of-care, all connected via MedStar’s EHR system (Cerner Millennium platform). Awardees can request project-specific datasets, and AADB provides access to pre-curated or custom-curated AI/ML-ready datasets to meet the needs of specific research questions. 

1. Custom-Curated Datasets 

AADB offers on-demand tailored datasets to support a wide range of research methodologies, ensuring that researchers receive data structured to align with their specific study objectives. These datasets can include varied levels of PHI, determined by HIPAA’s minimum necessary standard, and are available upon regulatory approval. Custom curated datasets include temporal data allowing longitudinal studies as well as access to unstructured data (clinical notes) in line with the data needs of the research projects.

2. Pre-Curated Multimodal Datasets in AADB Library

AADB hosts a growing library of structured pre-curated datasets integrating EHR, and imaging, that are readily accessible following regulatory clearance:

• Maternal Health Dataset
• Chronic Disease Dataset
• Behavioral Health Dataset
• Breast and Lung Cancer: Clinical & Imaging Dataset
• Brain Imaging Dataset
• Thyroid Imaging Dataset
• Cardiac Imaging Dataset

Concierge Services

In addition to providing datasets, AADB also offers concierge services, which include on-demand consultations with AADB methodologists and informaticians. These experts assist awardees in:

• Dataset curation & customization based on specific research needs.
• Technical support including provision of detailed data dictionaries for all custom datasets, finalization of data specifications, data access support, and analytical guidance.
• Support in selecting appropriate research methodologies for AI/ML applications.

For more details on dataset availability and regulatory requirements, visit the AADB website: https://www.aim-ahead.net/data-and-research-core/aadb-access/

ScHaRe

As described on the NIMHD website, https://www.nimhd.nih.gov/resources/schare/, ScHaRe is a cloud-based platform for health research designed to:  

• Leverage population science, and behavioral Big Data and cloud computing tools to foster a paradigm shift in healthcare delivery, and health outcomes research.
• Advance use of transparency and ethical inquiry by developing innovative strategies and securing perspectives.
• Upskill novice untrained users in data science through cloud computing skills training, cross-discipline mentoring, and multi-career level collaborating on research.
• Provide a data science cloud computing resource for community colleges and low resource institutions and organizations.
• Offer a project data repository centered on core common data elements for enhanced data interoperability and compliance with NIH Data Management and Sharing Policy.

Scientific review begins on June 30, 2025 and funding decisions will be made between then and the September 2, 2025 proposed program start date.

More details to come.

Questions regarding the Partnerships to Improve Population Health Using AI/ML Program may be directed to the Program HelpDesk

Program MPIs

Bettina M. Beech, DrPH, MPH and Spero M. Manson, PhD

*Calendar dates may be adjusted according to timeline dictated by award.