I-Corps: Translation Potential of a Digital Pet Health Management Software Platform

This I-Corps project is based on the development of a proprietary pet health management platform designed to integrate, standardize, and analyze fragmented veterinary health records. Currently, pet medical data is typically treated as a clinical by-product, available only in the form of paper printouts or static Portable Document Format (PDF) files. This lack of interoperability impacts a $150 billion pet industry, making it difficult to consistently track animal health and creates severe data fragmentation across multiple clinics. This technology provides a digital platform that standardizes records from disparate sources into a secure, unified location, allowing pet owners to seamlessly collect, organize, and share medical histories. In addition, the health data may be used to predict a pet’s healthspan (the number of years spent in good health) and mortality risk. This technology may provide pet owners and veterinary professionals with a data-driven approach to companion animal healthcare. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of an integrated health intelligence platform that transforms unstructured veterinary records into actionable, predictive insights. Currently, storage of health records (e.g., lab tests, vitals, clinical notes) relies on physical records or the manual entry of data fields. This technology automates data extraction through a pipeline that enables generative Artificial Intelligence (AI)-powered document parsing to convert most file formats, such as scanned Portable Document Formats (PDFs) and images, into standardized, longitudinal biometric data. In addition, deep learning is used for risk assessment. This unique capability is used to generate real-time estimates of mortality risk and the healthy lifespan of pets, while simultaneously establishing a secure, privacy-preserving framework for validating and sharing clinical data with veterinarians and researchers. The technical results include prototype testing that implemented core data fusion, secure storage, and predictive modeling modules using simulated cohorts derived from empirical datasets. Beyond serving as a digital health management tool, this platform may function as an AI-ready infrastructure that can provide health outcome prediction on small data by integrating foundation models and external knowledge databases. This technology may lay the groundwork for advanced analytics, machine learning pipelines, and predictive models that can accelerate discovery in veterinary science and animal health technology. 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.