SBIR Phase I: Critical Disease Care Using Multi-Modality Mining

Syprosoft, Inc., Irvine CA

Investigators

Abstract

This Small Business Innovation Research Phase I project will establish the feasibility of using multi-modality data mining for predicting the progression of critical diseases in an individual patient. Current practices in critical disease care focus on assessing the stage of disease rather than on predicting the progression of disease. Different clinical, imaging and laboratory test modalities are used to assess disease stage. Some assessments have predictive abilities but usually without accounting for interventions. The proposed Critical Disease Data Mining System (CDDMS) will fuse the modality predictions to formulate a holistic prognosis for an individual patient undergoing a particular intervention. This research will validate the hypotheses that data mining can be used for: (1) prognosis about the progression of critical diseases, (2) assessing efficacy of a specific intervention, and (3) formulating a holistic prognosis that is superior to modality predictions. It is expected that the CDDMS holistic prognosis will correlate better with the actual outcomes than the modality predictions. If successful, the CDDMS will provide customized critical disease care; resulting in earlier and more effective interventions. It will reduce need for multiple, redundant biopsies and surgeries, aid research on population subgroups, monitor specialized interventions, and provide an ongoing self-correcting medical information-management system. This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).