The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is pioneering the development of a precision medicine platform for the management of complex diseases. As demand increases for personalized medical practice, there is a growing need to empower clinicians with sophisticated clinical decision-support tools ? especially in complex diseases, such as Multiple Sclerosis (MS). The prototype of such a tool, developed from an MS research cohort, received excellent user feedback and broad interest from the MS community. This application allows a clinician to visualize a patient?s disease progression and anticipate its trajectory. The physician can share this information with her patient from an intuitive interface to inform a more data-driven, collaborative therapeutic decision-making ? shown to increase compliance and improve outcome. Between therapeutics, disability-related costs, and other care, MS represents a yearly burden of $28 billion. This opportunity is in the hundreds of millions as it merges three rapidly-expanding markets: precision medicine, knowledge-based analytics, and clinical decision-support software. This effort opens novel collaboration opportunities, leveraging millions of publicly-funded research. The broad adoption of this tool will realize cost savings system-wide, from patients, to providers, and payers, by accelerating the path to the right treatment for each patient.
This project is a research study for a clinical decision-support software platform for the management Multiple Sclerosis (MS). This software facilitates the access to multiple types of patient data (clinical, genetics, imaging) and assesses the normality of a single patient?s data in the context of reference distributions that are custom-computed from other patients with similar baseline characteristics. This navigation tool is powered by a knowledge infrastructure and proprietary data analytics to visualize, interpret and predict multifactorial patient trajectories in a novel, more effective, and data-driven way. This NSF-PHASE I grant will enable the development of the cloud-based data infrastructure and enable a robust and generic contextualization framework for non-research health data. This framework will strengthen the portability of the application to other complex conditions. Technically, the proposed project uses a cloud-based back-end for data storage and computing, rendered on a tablet interface. From the mobile interface, the user can compare individual patients to reference group(s) bringing reference population data at the point of care. This personalized use of datasets challenges the use of averaged results from clinical trials. The contextualization of individual trajectories to reference longitudinal datasets enables the visualization of dynamically-generated, evidence-based therapeutic scenarios ? thereby achieving personalized clinical decision-making.
