NOT-MH-23-195 - Notice of Intent to Publish Funding Opportunity Announcement for Individually Measured Phenotypes to Advance Computational Translation in Mental Health (IMPACT-MH) Mechanism (U01 Clinical Trial Optional)
National Institute of Mental Health (NIMH)
The National Institute of Mental Health (NIMH) intends to promote a new initiative by publishing a Notice of Funding Opportunity (NOFO) to solicit applications for a Data Coordinating Center (DCC) to support the work of the research projects funded under the Individually Measured Phenotypes to Advance Computational Translation in Mental Health (IMPACT-MH) initiative described in the companion announcement NOT-MH-23-195. The IMPACT-MH initiative has an overall goal of using behavioral measures and computational methods to identify novel clinical signatures that could be used to guide clinical decision-making. The IMPACT-MH DCC funded under this NOFO will: (a) facilitate regular communication and coordination among the funded IMPACT-MH projects; (b) where applicable, support the use of common data elements, standard measures, and uniform data collection procedures; (c) build informatics infrastructure and pipelines necessary to gather and store de-identified, patient-level data; (d) perform computational analyses on datasets collected across all project sites; (e) monitor collected data to identify and address potential biases in data collection, analysis techniques, or subject recruitment and retention practices. The DCC will also maintain a list of the measures and tools used across the funded IMPACT-MH projects, as well as best practices of data collection and analysis, in order to inform future additional studies or future stages of the IMPACT-MH initiative.
This Notice of Intent to Publish (NOITP) is being provided to allow potential applicants sufficient time to develop meaningful collaborations and responsive projects.
The NOFO is expected to be published in Spring 2023, with an expected application due date in Summer 2023.
This NOFO will utilize the U24 activity code. Details of the planned NOFO are provided below.
Current approaches for diagnosing mental disorders lead to a great deal of heterogeneity within diagnostic groups and do not provide a sufficiently precise characterization of individual patients to maximally inform clinical decision-making. Using machine learning and other data-driven approaches to integrate data from behavioral assessment(s) with clinically available data has the potential to generate more precise and objective clinical phenotypes. These phenotypes, derived from individual participant-level measurements, could foster more informative classification schemes, improve clinical practice, and lead to the identification of specific pathology-related mechanisms.
Consistent with the Research Domain Criteria framework the companion NOFO, RFA-MH-23-105, seeks to support multiple studies that will enable data-driven algorithms to generate clinical phenotypes that can optimize evaluation at the level of the individual and which are informative for clinical purposes (e.g., predicting prognosis, enhancing clinical monitoring, and selecting effective treatments). To maximize potential clinical utility and accessibility, the IMPACT-MH RFA encourages applications that focus on the use of behavioral tasks and measures, such as computerized tasks administered via web- or device-based platforms and/or passive collection of behavioral data via mobile devices. Behavioral tasks are to be optimized to yield data amenable to computational analyses, including artificial intelligence, machine learning, or Bayesian techniques. Other measures will include data available via clinical records (such as diagnostic codes, demographic data, treatment history, clinician notes, and symptom rating instruments). Biological data, such as EEG, MRI, blood-based measures, or genomics, may be used judiciously to further refine or disambiguate novel clinical phenotypes. To ensure the longevity and usability of the data included in these research projects, the DCC will partner with the IMPACT-MH grantees to foster data collection and maintenance practices that allow for broad re-use and re-analysis of data as computational methods evolve.
The IMPACT-MH DCC is expected to collaborate with the recipients awarded under the RFA presented in the companion (NOT-MH-23-195) on activities supporting the identification of behavioral measures that provide added value to clinical records data to refine clinical decision-making. The DCC will work closely with IMPACT-MH projects to optimize harmonization, combine and store data from all IMPACT-MH projects, and monitor data to identify and address potential biases. The data analyses specific to the awards funded under the companion IMPACT-MH NOFO will be the responsibility of the IMPACT-MH grantees; however, the DCC will provide support and guidance to IMPACT-MH grantees as needed, and the DCC will conduct analyses of aggregated data sets, as appropriate.
The IMPACT-MH DCC funded under this NOFO will:
1. Facilitate coordination and communication across IMPACT-MH projects. The principal goal of the IMPACT-MH DCC is to support the efforts to identify novel clinical signatures that could be used to guide clinical decisions proposed by the IMPACT-MH projects funded under the companion NOFO (NOT-MH-23-195). The DCC will serve as a clearinghouse of novel behavioral measures, clinical assessment procedures, informatics approaches, quality improvement strategies, and research ideas proposed by IMPACT-MH projects. The DCC will (i) identify common and unique data collection, processing, and analysis methods employed across projects; (ii) facilitate partnerships among IMPACT-MH projects to use standard measures, common data elements, and integrated datasets for quality assessment and research purposes; (iii) promote fidelity monitoring and performance improvement activities across IMPACT-MH projects; and (iv) disseminate data-driven best practices for behavioral measurement, clinical assessment, and computational evaluation throughout the IMPACT-MH network. Applications should describe how the DCC will collect and store pertinent information from each IMPACT-MH project. This information includes, but is not limited to, the aims and activities of individual projects, study protocols (including details of data collection methods and measurement parameters), data processing pipelines, and analysis tools.
The IMPACT-MH DCC will support this coordination by establishing a Steering Committee to oversee collaboration efforts among the IMPACT-MH projects. The Steering Committee should include Program Director(s)/Principal Investigator(s) (PD(s)/PI(s)) from each IMPACT-MH project and any additional liaisons identified by the PI(s)/PD(s), and additional members with expertise in the overall goals of the IMPACT-MH initiative. Experts in learning health care, measurement-based treatment, health information technology, health informatics, computational modeling, and other areas may be included, as appropriate. Applicants should not, however, contact potential Steering Committee members prior to the review of the application, nor should potential Steering Committee members be named in the application to avoid conflict of interest in the review process. The DCC will be responsible for organizing, providing logistical support, and running IMPACT-MH Steering Committee meetings. These responsibilities include organizing an initial kick-off meeting to introduce project teams; identifying areas of joint scientific interest; and establishing processes and timelines for harmonization efforts (described below), data curation, and data submission. Additionally, the DCC will convene an annual all-hands meeting to highlight progress, challenges, and potential adjustments for improved coordination. The DCC will be responsible for ongoing communication with the IMPACT-MH Steering Committee through regular calls to be held at least quarterly.
2. Optimize harmonization efforts across IMPACT-MH projects. To maximize the long-term benefit of data acquisition and analysis, this initiative encourages harmonization efforts that will permit data aggregation across IMPACT-MH projects that have shared scientific goals and measures. The DCC will play a primary role in supporting cross-project harmonization via the use of common data elements, standard measures, and uniform data collection procedures, to the extent possible. The scope and focus of IMPACT-MH projects may differ along multiple dimensions, including the area of psychopathology (e.g., mood/anxiety disorders, disorders of behavior regulation, psychosis), the participant cohorts to be studied, and the specific assessments proposed. Despite these potential differences, areas amenable to standard measurement are expected among IMPACT-MH projects. IMPACT-MH DCC applicants should propose a process for (i) curating behavioral measures and common data elements planned for use by IMPACT-MH projects; and (ii) identifying opportunities for harmonizing behavioral measures, data elements, and assessment methods to increase concordance among IMPACT-MH projects. Applications are expected to outline a consensus process directed at maximizing the clinical and scientific value of common and divergent assessments used in IMPACT-MH projects.
The DCC will play an integral role in supporting the harmonization efforts across the IMPACT-MH projects and should be prepared to collect and disseminate a guideline for best practices on administration and collection parameters for the data types used throughout the IMPACT-MH projects. Additionally, the DCC should maintain a set of best practices and guidelines for the use of computational models and algorithms that will be implemented when identifying and validating clinical phenotypes.
3. Develop and maintain a robust informatics infrastructure. The DCC will be responsible for building and maintaining an informatics infrastructure along with pipelines to gather and store de-identified subject-level data. The purpose of these tools is to support computational analyses on datasets from all IMPACT-MH projects. The data center will ensure the data are Findable, Accessible, Interoperable, and Reusable (FAIR, https://www.force11.org/group/fairgroup/fairprinciples) to enable primary and secondary analyses. As part of the data infrastructure, the DCC will create validation tools to verify that data submitted by the IMPACT-MH projects are consistent with the allowable values in the measures used.
The DCC will have responsibility for uploading subject-level data aggregated from the IMPACT-MH projects to the NIMH Data Archive (NDA). All data will be deposited into the NDA and made available to qualified investigators with approved NDA data access agreements according to the NDA data sharing regimen. The IMPACT-MH projects will use the NIMH Globally Unique Identifier (GUID) infrastructure to create de-identified subject codes. Staff at the NIMH Data Archive will be responsible for exporting the GUID infrastructure to all project teams. The DCC will maintain privacy procedures and security processes for safely receiving and storing de-identified data from each of the project teams.
4. Perform computational analyses on aggregated datasets. The DCC will also be responsible for analyses of the aggregated data from IMPACT-MH projects. While it will be difficult for DCC applicants to propose specific analysis plans before knowing the available data and protocols for the IMPACT-MH projects, DCC applications should describe general approaches to test and optimize different computational models or algorithms. If the DCC team has prior experience deriving or validating clinical phenotypes, the relevant methodologies should be described in the application. Applications should also include plans to take models used successfully on data from one IMPACT-MH project and apply them to data from another project. The DCC will engage in ongoing collaborations with NIMH program staff to determine potential analyses based on the funded projects. The DCC will offer technical assistance to project teams when needed, specifically concerning the optimization of local computational methods to identify or validate clinical phenotypes.
5. Monitor and address potential biases in collected data and analytic approaches. The IMPACT-MH initiative recognizes the promise of data-driven approaches and computational modeling to support precision mental health, particularly as machine learning and artificial intelligence methods offer novel ways to identify patterns in large-scale, multimodal datasets. The initiative equally recognizes that computational approaches can introduce or exacerbate biases, which have the potential to occur at multiple stages of a research study. As a critical extension of its role in data and informatics management, the DCC is expected to carry out regular data evaluations, in partnership with awarded IMPACT-MH projects, to identify and address potential biases. The NIH Office of Data Science Strategy (ODSS) offers guidelines for researchers employing data-driven technologies. Specifically, they advise that researchers employing these technologies must take steps to minimize the harms that could result from their research, including but not limited to addressing (1) biases in datasets, algorithms, and applications; (2) issues related to identifiability and privacy; (3) impacts on disadvantaged or marginalized groups; (4) health disparities; and (5) unintended, adverse social, individual, and community consequences of research. Sources of bias in the data include, but are not limited to measurement tools and processes, subject recruitment and retention practices, handling of missing data, and computational algorithms. IMPACT-MH recipients will be responsible for primary evaluations of project data, and the DCC will be responsible for oversight of the data aggregated across projects. In this capacity, the DCC should monitor for assumptions and practices that introduce unintended bias and should develop strategies for countering these biases. Applications should propose a process to assess aggregated data and provide resources to individual project teams to ensure that biases are detected and mitigated.
Key Personnel Expertise
The PD/PI (or Multi-PDs/PIs) of the DCC must be experienced in the coordination and management of multi-site clinical research studies, including success in meeting milestones and timelines. Additional expertise on the DCC team should include proficiency with multimodal data, and state of the art computational and data analytic skills.
Enhancing Diverse Perspectives
This NOFO requires a Plan for Enhancing Diverse Perspectives (PEDP) as part of the application (see further below). Applicants are strongly encouraged to read the NOFO instructions carefully and view the available PEDP guidance material. Applicants are strongly encouraged to attend the Technical Assistance teleconference to ask for information on preparing a PEDP.
NIH recognizes that diverse teams working together and capitalizing on innovative ideas and distinct perspectives outperform homogeneous teams. There are many benefits that flow from a diverse scientific workforce, including fostering scientific innovation, enhancing global competitiveness, contributing to robust learning environments, improving the quality of the research, advancing the likelihood that underserved populations participate in, and benefit from research, and enhancing public trust. See Notice of NIH's Interest in Diversity (NOT-OD-20-031).
To support the best science, NIH encourages inclusivity in research. Examples of structures that promote diverse perspectives include, but are not limited to:
Applications must include a Plan for Enhancing Diverse Perspectives (PEDP) will be assessed as part of the scientific and technical peer review evaluation, as well as considered among programmatic matters with respect to funding decisions.
Applicants are strongly encouraged to consult with NIMH program staff when developing plans for an application.
Application budgets are limited to no more than $1,000,000 in direct costs per year.
Applications are not being solicited at this time.
Please direct all inquiries to:
Jenni Pacheco, Ph.D.
National Institute of Mental Health (NIMH)