Data Analytics and Resource Development to Enhance BSSR Integration

This is a presolicitation/notice of intent to sole source for services prepared in accordance with FAR Part 8. It is the intent of the National Institutes of Health (NIH), Office of Behavioral and Social Sciences Research (OBSSR) to procure professional services on a sole source basis from Lexical Intelligence, LLC, 13013 Arctic Avenue, Rockville, MD 20853 to provide data analytics for two focus areas for OBSSR as stated in the strategic plan are to - Enhance and promote the research infrastructure, methods, and measures needed to support a more cumulative and integrated approach to behavioral and social sciences research (Priority Two) and to - Coordinate behavioral and social sciences research (BSSR) programs across the NIH and integrate BSSR within the larger NIH research enterprise (Foundational Process). The North American Industry Classification System Code (NAICS) 541511- Custom Computer Programming Services. Background: The statistics supporting the opioid crisis as a public health imperative are well known. For example, there is evidence of increasing rates over time of drug overdose deaths involving synthetic opioids other than methadone and this increase has not been significantly affected by the concurrent decrease in producing and distributing opioids. Compounding the problem is the 25% increase in pain prevalence among US adults over the past 2 decades, with strong opioid use remaining high. Purpose/Objectives: One path forward in building a cumulative knowledge base across the behavioral and social sciences is through ontologies. An ontology is a systematic method for articulating a controlled vocabulary of agreed-upon terms and their inter-relationships. If we want to move BSSR fields forward and ensure that behavioral and social science are more fully integrated into the larger biomedical enterprise, we must ensure that our terminology is more fully and accurately represented. As with all biomedical research, BSSR findings have exploded over the past 25 years, and the challenge of assessing the quality of the evidence is exacerbated by its quantity and complexity. In the behavioral sciences, we are also faced with some relatively unique challenges. Both within and across sub-fields, challenges include professional incentives for investigators to create new theories, the resultant proliferation of separate theories, constructs, and measures, and a significant jingle/jangle problem. That is, constructs with the same name may actually be different (jingle), constructs with different names may actually be the same (jangle), or most often, the relationships between constructs and terms are difficult to disentangle. For example, in some fields, the terms self-regulation, emotion regulation, and cognitive control may be used interchangeably; in other areas, distinctions between these constructs may be critical. Since 2016 we have pursued several activities for ontology development, including using natural language processing (NLP) to build taxonomies, integrating calls for ontology development into FOAs, and commissioning a National Academies of Sciences report on this topic. In this SOW, we build on this existing body of work to develop a resource of behavioral and social science-controlled vocabularies, taxonomies and ontologies. The other path forward in helping OBSSR to have a better sense of BSSR integration into the biomedical research enterprise is to assess the NIH funding portfolio at a more granular level. To this end, OBSSR would like to apply advanced computational methodologies to NIH grants data, which will allow for a more nuanced understanding about what is and is not being funded in BSSR. This need stems from a set of recommendations by a recently chartered NIH Council of Councils Working Group that was tasked with completing an assessment and providing recommendations to the NIH Director on how to better integrate and realize the benefits to overall health from behavioral research at NIH. Ultimately, OBSSR sees the need for an internal-facing tool available across NIH that will allow for more granularity in assessing the grant portfolio than what RCDC can provide. Advanced NLP techniques will be applied to NIH funding data and will help to inform our deeper understanding of how well BSSR is truly integrated into the biomedical research enterprise. Contractor Requirements, Tasks and Deliverables: The Contractor shall provide expert review, analysis, description, categorization, and evaluation of existing behavioral and social science-controlled vocabularies, taxonomies and ontologies. The Contractor shall write both a detailed and condensed summary report at the completion of the project. This report would include a collated list (or guide) to the tools/resources identified in the review. The Contractor shall apply NLP techniques to classify BSSR grant applications at a more granular level than what is currently available through RCDC. Period of Performance: September 9, 2022 - September 8, 2023 Place of Performance: The work to be performed under the resultant contract shall be performed at the Contractor's facility. Sole Source Justification: The work in the SOW requires specialized expertise and a deep understanding of behavioral ontologies as well as intricate knowledge of underlying NIH grants data behind the NIH firewall. Lexical Intelligence is uniquely positioned to fulfill the requirements in the SOW due to their unique expertise in both areas. Lexical has developed a proprietary natural language processing (NLP) platform to identify novel behavioral concepts and link them to the established MeSH hierarchy. The NIH Office of Portfolio Analysis, a sister office to OBSSR at the NIH, currently has a license to utilize this proprietary platform. The NLP platform has a number of unique characteristics that are required for this project, including compatibility with existing data processing routines and data representations at NIH, such as iSearch. Lexical Intelligence has used these unique capabilities in previous work with OBSSR to improve the indexing and representation of behavioral related terms within the National Library of Medicine's MeSH (Medical Subject Headings) and the Unified Medical Language System (UMLS) to support OBSSR's goal of behavioral ontology development and move the field toward formalized, shared, interoperable taxonomic systems which define the types of behavioral phenotypes and describe their interrelationships. Moreover, as a General Services Administration (GSA) vendor, Lexical Intelligence offers discounted rates that make this work much more cost effective given the complex skillset that is required. Taking advantage of these capabilities will enable efficient completion of the requirements. Additionally, Lexical Intelligence has unique access to and an understanding of the intricate and complex data underlying NIH grant applications. They have been instrumental in developing key NIH tools for analyzing the contents of funded and unfunded research. Lexical Intelligence's expertise and knowledge about the underlying details and technicalities of this project will be critical for ensuring its success. Their data scientists and analysts have a unique understanding of project goals as they have previously worked with OBSSR to develop and characterize behavioral ontologies and elucidate complex grant funding data. This is not a Request for Quote (RFQ), nor is a RFQ available; however, all responsive sources may submit a proposal in a timely manner which will be considered by NIH. Firms interested in responding to this notice must be able to provide the required services, property, facilities and funding specified in the SOW and in compliance with all applicable laws, regulations and policies. A determination by the Government not to compete this proposed contract based upon responses to this notice is solely within the discretion of the Government. Responses shall be in writing and shall be electronically transmitted to briscoee@mail.nih.gov by 2:00 PM EST on Wednesday, August 31, 2022. Responses shall include pricing information and shall reference Presolictation/Intent to Sole Source Notice No. 75N97022Q00042.