CHOT Scholar Projects focus on improving healthcare delivery and quality of care using research and tools that exist across various disciplines. These projects involve students working under the guidance of faculty and/or industry advisors. The projects can often form a key component of their masters’ thesis or doctoral dissertation. Penn State CHOT will lead healthcare projects pertinent to population health, Access to Care, and Analytics & Innovative Technology. These collaborative projects focus specifically on data-enabled smart health and address topics with significant values to improve healthcare delivery systems.
1. Virtual Communication for the AD/ADRD CaRe Environment (V-CARE)
Collaborative Units: Penn State Health, College of Engineering, College of Nursing, University of Louisville Health, Department of Public Health, College of Engineering
Description: Persons living with Alzheimer’s Disease and Alzheimer’s Disease-Related Dementias (AD/ADRD) account for over 3 million hospital admissions per year and are about two times more likely to be hospitalized than their cognitively healthy peers. We identified the need to adapt this strategy to 1) accommodate nurses’ and care partners’ needs for an efficient, accessible alternative to face-to-face coaching; 2) provide content in an engaging environment that strengthens relational communication skills and joint decision-making; and 3) better engage the person with AD/ADRD and identify their preferences, differentiated from those of care partners. The objective of this project is to develop a virtual reality (VR) coaching program for nursing staff and for care partners of the hospitalized person with AD/ADRD. AI (artificial intelligence)-augmented VR provides an innovative mechanism to create a fully immersive 3D hospital environment and interactive, “real-life” experiences in a more engaging manner than traditional educational activities and approaches. The new capacity of V-CARE will empower novel practices of data acquisition and analytics on triadic communication, and further advance tele-dementia care during periods of acute illness and hospitalization.
2. Using large health network data and analytics to examine healthcare service disruptions during the COVID-19 pandemic: A case study of breast cancer screening
Collaborative Units: Penn State Health, College of Engineering, Penn State Cancer Institute, Biostatistics
Description: The COVID-19 pandemic has imposed tremendous stress on healthcare systems globally. In response to the epidemic—to make acute healthcare resources available for COVID-19 patients and to reduce the transmission, many healthcare facilities have temporarily suspended and postponed elective or non-urgent medical procedures, including preventive services such as cancer screenings. Regular cancer screening has been known to be effective in improving early detection of cancer diagnosis and thus long-term health outcomes. Understanding how the screening practice has been affected during the COVID-19 era will provide crucial information for practitioners and policy makers to react preemptively to mitigate the increasing morbidity and mortality in the at-risk population for years to come. In this study, we propose to use a large real-world electronic health record (EHR) network TriNetX data (with over 200 million patients in the US) and apply big health data analytics to assess the changing patterns of cancer screening for breast cancer, a most commonly diagnosed cancer in American women, before and since the COVID-19 pandemic in the US. Our objectives are to (1) evaluate temporal changes in the volume of mammogram screening since COVID-19 pandemic, and (2) to explore the disparities in these changes and to identify the subpopulation who have been affected the most.
3. Simulation Optimization of Cardiac Surgical Planning
Collaborative Units: Penn State Health, VA Health Systems, Penn State College of Engineering
Description: Heart disease is a leading cause of death worldwide. Many patients take surgical interventions to fight the battle against heart disease. Surgical successes are of paramount importance for the patients’ health and their family well-being, thereby broadly impacting the society. However, there are large variations in surgical outcomes. Modern healthcare systems are investing heavily in physiological sensing and computing technology to increase information visibility and cope with the disease complexity. Massive data are readily available in the surgical environment. Realizing the full potential of rich data streams for optimal decision support depends to a great extent on the advancement of information processing and computational modeling methodologies.
The objective of this project is to optimize cardiac surgical planning by integrating simulation optimization with physics-augmented machine learning of medical data. This objective will be accomplished by pursuing three tasks: 1) Physics-augmented artificial intelligence (AI) for cardiac modeling; 2) Optimal sensing and sequential learning of space-time, disease-altered dynamics; 3) Integrating sensor-based learning and simulation optimization for surgical planning. This project will drive cardiac modeling and simulation into clinical applications, and promote data-driven and simulation-guided surgical planning. The resulting principles and methods are generally applicable to many other domains such as environmental sensing and atmospheric simulation. More broadly, this project will develop an interdisciplinary workforce who possesses both computational skills and medical insights through a uniquely positioned educational program of “simulation optimization in healthcare”.
To view past CHOT Scholar Projects, visit here.