Press Release
August 15th, 2024
August 15th, 2024
State College, PA (August 15, 2024) - LiteraSeed, Inc. has been awarded a National Science Foundation (NSF) Small Business Technology Transfer (STTR) Phase II grant, in partnership with Virginia Tech’s Machine Learning Laboratory, for $997,693 to enhance its patient data communication platform. LiteraSeed’s innovative, visual-based tool empowers patients to effectively share critical health information, regardless of language proficiency or health literacy, improving accessibility and care. The funding will streamline product integration with electronic health record (EHR) systems for faster, more efficient provider access at the point-of-care. By harnessing cutting-edge artificial intelligence (AI) and machine learning (ML) technologies, this advancement will also unlock powerful data extraction and analysis capabilities, paving the way for more personalized and data-driven patient care in the rapidly evolving healthcare landscape.
The company aims to 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 $238 billion in costs to the healthcare system. 56.3% of those communication gaps are related to the medical history capture during the patient-provider encounter. The high prevalence of low English and health literacy in the U.S. amplifies this problem. 120 million people – 36% of the population – have low health literacy and 67.3 million people – 21.9% of the population – speak a language other than English as their primary language.
“Cultural barriers, less access to care, and language and literacy barriers put already vulnerable communities at greater risk of missed or misdiagnosis, which can lead to critical medical issues and death,” said LiteraSeed Co-founder and COO, Aziza Ismail. “Enhancing communication is crucial for improving the efficiency and quality of healthcare services, as well as patient outcomes.”
In a yet to be published clinical study, LiteraSeed’s Phase I project demonstrated success in symptom capture and risk prediction for low English proficiency and/or low health literacy patients. In a head-to-head obstetrics and gynecology (OB/GYN) clinical study, LiteraSeed identified more symptoms than the provider that were relevant to the care plan and could have led to an earlier diagnosis and treatment. Additionally, a nationwide dataset of 7.1M inpatient medical records was obtained and eight different ML models with ensemble learning were trained and tested on 105,538 maternal and neonatal patient records. Preliminary implementation of LiteraSeed’s AI risk assessment model was able to predict the risks of mortality and major surgical intervention with 98.1% and 99.6% accuracy, respectively.
The integration of natural language processing (NLP) for data extraction combined with the patient’s self-reporting supports a comprehensive and accurate representation of the patient's present condition and medical history. This innovation will 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 project aims to improve the long-term efficiency of the U.S. 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 and reduce healthcare costs.
“The need for practical, technology-driven solutions in healthcare has never been greater. Our partnership with LiteraSeed goes beyond innovation—it’s about transforming patient-provider interactions to improve health outcomes for all populations,” said Hoda Eldardiry, Director of the Machine Learning Laboratory and Associate Professor at Virginia Tech. “By leveraging advancements in LLMs, we’re tackling one of the most overlooked challenges in medicine—enabling more effective and reliable communication of crucial health data with diverse patient groups. This collaboration bridges groundbreaking research with real-world impact, giving our students hands-on experience in AI-driven clinical innovation and empowering them to drive meaningful change in healthcare.”
LiteraSeed is a mission-driven startup advancing health equity for the most vulnerable by improving communication between patients and providers. We strongly believe that nobody should suffer harm nor be denied high-quality healthcare because of a communication barrier due to language, literacy, or education. We have built a visuals-based communication platform to bridge these gaps, while establishing trust in the process. Our technology is demonstrated to make it easier for patients with low-literacy to capture symptoms progressively as a condition monitoring and analytics platform, using ubiquitous web and mobile technologies. More information: literaseed.io
The Machine Learning Laboratory research focuses on multisource and graph machine learning. We are developing graph-based deep learning techniques for NLP, time-series prediction, and control. We develop our research in the context of various applications including cyber security, computer vision, healthcare, and AI ethics. More information: people.cs.vt.edu/hdardiry/collaborators
With locations in Blacksburg and Roanoke, Virginia, the Washington D.C. metro area, and presence around the world, Virginia Tech offers approximately 280 undergraduate and graduate degree programs to more than 38,000 undergraduate, graduate, and professional students. Virginia Tech is a designated an R1 institution, which is the highest designation for research universities, and is one of six senior military colleges in the U.S. For fiscal year 2024, Virginia Tech reported a record $453.4 million in sponsored research expenditures. Virginia Tech is a vibrant community encompassing 4,000 faculty who conduct cutting-edge research, seven research institutes, and hundreds of centers and labs, blending technology and innovation into all fields of study through its commitment to hands-on learning.
America’s Seed Fund, powered by NSF, awards $200 million annually to startups and small businesses, transforming scientific discovery into products and services with commercial and societal impact. Startups working across almost all areas of science and technology can receive up to $2 million in non-dilutive funds to support research and development (R&D), helping de-risk technology for commercial success. America’s Seed Fund is congressionally mandated through the Small Business Innovation Research (SBIR) program. The NSF is an independent federal agency with a budget of about $9 billion that supports fundamental research and education across all fields of science and engineering. For more information, visit seedfund.nsf.gov.
LiteraSeed
Aziza Ismail
COO & Co-founder
Virginia Tech
Chelsea Seeber
Director of Marketing and Communications,
College of Engineering
chelseab29@vt.edu
(540) 231-2108
