I-Corps: Software tool to assist mental health care providers
The University Of Texas Health Science Center At Houston, Houston TX
Investigators
Abstract
The broader impact/commercial potential of this I-Corps project will be to leverage advanced computational and machine learning technology to assist psychiatric hospitals in stratifying patients' readmission risk, optimization of post-discharge interventions and promotion of wellness. Healthcare reforms in the United States have emphasized provision of value-based healthcare services as opposed to the traditional 'fee-for-service' approach. A major outcome to be used by regulatory bodies and payers is patient readmission - interpreted as a proxy measure of quality of care provided during hospitalization. Therefore, psychiatric facilities will increasingly be required to pay special attention to patients with a high likelihood of readmission after discharge. This will be a significant departure from the traditional approach and require novel analytical tools able to proactively guide interventions. Computational and machine learning technologies can assist healthcare providers in stratifying patients' readmission risks, optimize post-discharge interventions and resource allocation - translating into better patient outcomes. This I-Corps project is focused on exploring a commercialization opportunity for a computational and machine learning 'software as a service' platform that analyzes clinical informatics data from patients hospitalized in an inpatient psychiatric facility to predict post-discharge risk of readmission. In addition, the proposed platform consists of an advanced analytics engine that recommends available post-discharge intervention services and community resources to enhance the continuity of care. This platform will leverage on historical electronic health records data and a curated database of available community healthcare and social resources. It will predict readmission risk and optimize patient post-discharge interventions. The I-Corps program will allow the team to understand the customer workflow and potential for product-market fit.
View original record on NSF Award Search →