Cohort 4

Awardee Organization(s): Health Tequity LLC
Principal Investigator(s): Katherine Kim, PhD, MPH, MBA
Official Project Title: A novel digital twin for chronic care coordination and healthy aging
AITC Partner: PennAITech
Website(s): www.HealthTequity.net

Chronic illnesses such as diabetes and hypertension challenge goals of healthy aging, with burdens on individuals, family caregivers, and the healthcare system. Uncontrolled chronic illnesses are a risk factor for cognitive decline, Alzheimer’s disease and related dementias, and frailty. We need solutions for older adults to age with independence, to lead healthier lives, and to maintain access to their healthcare services when needed. The questions we want to answer are: What are all the possible behavioral, lifestyle, and medical treatment options for people with chronic illness? When and how should those interventions be rolled-out for the best outcomes over time as people age (trajectories)? How could you weigh all the potential scenarios and make the best decisions?
We use data from remote monitoring, clinical care, and healthcare utilization, to develop Health Digital Twins (HDTs) for community-dwelling older adults with diabetes and/or hypertension and insights for both the individual and healthcare providers. Digital twins can be defined as (physical and/or virtual) machines or computer-based models that are simulating or “twinning” the life of a physical entity (an object, process, human, or a human-related feature). We generate HDTs via deep phenotyping and application of two state-of-the-art AI methods to take advantage of the pros and limit the cons of each: a generative model using variational autoencoder and a large language model coupled with retrieval- augmented generation. HDTs leverage population level data across urban and rural settings and combines it with a patient’s unique data, to deliver personalized recommendations.

Awardee Organization(s): University of Texas Health Science Center at Houston
Principal Investigator(s): Min Ji Kwak, MD, MS, DrPH
Official Project Title: Detection of adverse drug event using NLP among older adults with heart failure
AITC Partner: PennAITech
Website(s): https://med.uth.edu/internalmedicine/2022/11/17/min-ji-kwak-md-ms-drph/

Adverse drug events (ADEs) in older adults with heart failure are a serious public health concern. These drug-related complications can be life-threatening and significantly reduce quality of life. To capture ADEs correctly, doctors need to carefully review a patient’s symptoms, medical history, prescription changes, and past records. However, this can be difficult to do thoroughly during a busy clinic visit.
An automatic tool using an Artificial Intelligence tool can help by scanning a patient’s past medical records for signs of an ADE. This tool can be built into electronic health records to provide real-time assessments. While current AI models typically handle only one task at a time—like identifying medications—ADE detection requires a more advanced system that can process multiple tasks and make complex decisions.
To address this, we are developing a specialized AI framework called AIDE4HF. This system will leverage existing tools to detect ADEs in older adults taking heart failure medications. Our project has two main goals:
1.Create a high-quality dataset of ADEs related to heart failure medications in older adults.
2.Develop and test a powerful AI system that can accurately detect these ADEs.
This research is a collaboration between UTHealth McGovern Medical School and UTHealth McWilliams School of Biomedical Informatics. By combining expertise from multiple fields, we aim to create a model that closely mimics real clinical decision-making and has the potential to be widely used in medical practice.