STTR Phase II: Advancing Health Equity using Interactive Condition Assessment and Monitoring

Literaseed, Inc., State College PA

Investigators

Abstract

The broader impact/commercial potential of this Small Business Technology Transfer (STTR) Phase II project is to potentially improve patient outcomes and reduce healthcare costs by enhancing communication between patients and their medical providers. In the U.S., 78.9% of misdiagnoses are caused by miscommunication, resulting in 80,000 to 200,000 avoidable hospital deaths each year, and 56.3% of those communication gaps are related to the history-taking during the patient-provider encounter. Enhancing communication in healthcare is crucial for improving both the efficiency and quality of healthcare services. LiteraSeed’s project proposes Electronic Health Record (EHR) integration and Natural Language Processing (NLP) data extraction to enable automated chart review, facilitating possible access to critical patient data and allowing health systems to reclaim previously lost revenue due to the misclassification of patient risk. This project aims to improve the long-term efficiency of our healthcare system by addressing incomplete and conflicting EHR information, providing alerts of vital medical history, and mitigating the effects of poor health literacy, all in an effort to help empower the patient. The proposed project performs Electronic Health Records (EHR) integration of the platform and integrates it with Natural Language Processing (NLP) to extract valuable information from complex and unstructured medical records. These learnings led to the prioritization of three major technical objectives: (1) EHR integration to simplify workflow and enhance access to patient data, (2) enhancing the ML/AI risk assessment model by incorporating NLP techniques for extracting valuable information from complex, fragmented, incomplete, and contradictory medical records, and (3) conducting validation testing by clinicians to ensure the reliability and efficacy of ML/AI outputs. The integration of NLP for data extraction, combined with the patient’s self-reporting, ensures a comprehensive and accurate representation of the patient's present condition and medical history. This innovation could enable real-time risk adjustment, expedite patient care, address missed care opportunities, and boost revenue in global capitation and value-based care delivery models. 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.