I-Corps: Connected Rapid Innovation Software System to meet Medtech Development Needs

这个I-Corps项目更广泛的影响/商业潜力是开发人工智能（AI）驱动的技术，旨在加强跨学科合作，指导和人才搜索，以加速医学和生物技术研究和产品开发。目前对专家的搜索通常依赖于口碑或互联网搜索，这通常很耗时，而且可能不准确。所提出的技术可以通过以下方式克服障碍：1）促进配对，以确定合作者和导师，并在自愿的技术劳动力背景下建立团队; 2）促进对导致专家或导师推荐的因素的理解; 3）确定器械创新开发的成功/失败。拟议系统的目标是在机构内部和机构之间建立有影响力的持续联系，并使研究人员能够进行合作研究和产品部署，以改善健康状况。该I-Corps项目基于使用自然语言处理，机器学习和深度学习开发软件系统，以加强跨学科合作，指导和人才识别，以加速医学和生物技术研究和产品开发。它利用公共领域和私营公司中的叙述性文档，并在多个孤立的数据源之间执行数据融合。 所提出的创新可以使用户能够基于用户的输入（诸如关键字和摘要）通过AI推理引擎有效地识别排名的合作者、导师和类似的医疗产品。拟议的AI技术利用分布式自由文本数据库来提高搜索性能和冗余度。此外，这种强大的产品监管途径的实施可以满足早期医疗技术开发人员的需求，无论他们的当地开发生态系统和连接。该奖项反映了NSF的法定使命，并已被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

The broader impact/commercial potential of this I-Corps project is the development of artificial intelligence (AI)-driven technology aimed at enhancing interdisciplinary collaboration, mentorship, and talent searching in order to accelerate medical and biotechnological research and product development. A current search for experts commonly depends on word-of-mouth or internet search, which is often time consuming and may not be accurate. The proposed technology may overcome obstacles by 1) facilitating matchmaking to identify collaborators and mentors, and build teams in the context of a voluntary, technical workforce; 2) advancing the understanding of the factors leading to expert or mentor recommendation; and 3) identifying successes/failures in the development of device innovations. The goal of the proposed system is to create impactful, sustained connections within and across institutions, and enable researchers to conduct collaborative research and product deployment that will improve health. This I-Corps project is based on the development of a software system using natural language processing, machine learning, and deep learning to enhance interdisciplinary collaboration, mentorship, and talent identification in order to accelerate medical and biotechnological research and product development. It leverages narrative documents in the public domain and private corporations and performs data fusion across multiple siloed data sources. The proposed innovation may enable users to effectively identify ranked collaborators, mentors, and similar medical products through the AI inference engine based on user's input such as the keywords and abstract. The proposed AI technology leverages distributed free-text databases for search performance and redundancy. Additionally, the this implementation of robust product regulatory pathways may meet the needs of early-stage med-tech developers regardless of their local development ecosystem and connections.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.