PennAITech Awardees

Awardee Organization(s): DreamFace Technologies LLC
Principal Investigator(s): Mohammad H. Mahoor, PhD
Official Project Title: Building Deep Digital Twins for Prediction of AD/ADR/MCI in Older Adults
AITC Partner: PennAITech
Website(s): https://dreamfacetech.com/

The Alzheimer’s Association predicts that the number of Americans aged 65 and older with Alzheimer’s disease-related dementia (ADRD) will reach over 12 million people by 2050. ADRD often stars with mild cognitive impairment (MCI), which is characterized by challenges in memory, language, and thinking skills. Early MCI detection is vital for identifying those at risk of dementia, offering support, advice, and ongoing monitoring. Currently, older adults with MCI are diagnosed clinically; however, their daily challenges are often not noticeable to those whom they encounter irregularly. Artificial Intelligence (AI) holds promise for early cognitive impairment detection, with many AI studies focusing on expensive clinical assessments and medical scans like positron emission tomography (PET) and MRI. There is a pressing need for additional research to advance innovative, cost-effective, and accessible approaches for early detection and prediction of AD and MCI. Human digital twins are at the forefront of aging and longevity research, aiming to create personalized AI models that comprehensively simulate an individual’s behavioral, biological, physical, mental, and socio-emotional attributes using health and medical records. These models hold the potential to revolutionize our understanding, prediction, and management of the aging process, offering personalized healthcare solutions. This pilot project aims to investigate AI techniques that leverage multi-modal audio-visual data, along with other available data modalities, to develop human digital twins for research in aging and, more specifically, for predicting MCI and the early onset of AD/ADRD. We design and implement a Deep Digital Twins (DDT) model using Conditional Variational Autoencoders (CVAEs) suitable for heterogeneous multi-modal data including speech, transcribed speech, and facial videos. We then evaluate the efficacy of the proposed model using publicly available datasets such as the I-CONECT and ADReSS datasets, which contain multi-modal data and other metadata suitable for our project. We hypothesize that DDTs trained using multi-modal comprehensive data can predict MCI/AD with high fidelity and accuracy compared to uni-modal data. We compare our proposed DDT with state-of-the-art models in the literature. We assess the models’ performance, taking into account the impact of diverse data to ensure they remain unbiased. The expected outcome of this research are knowledge and prototyped Deep Digital Twins capable of assessing and predicting MCI/AD conditions in older adults. It is expected that the DDTs generate the longitudinal trajectories sampled from the data as well as predict the subject’s future condition.

Awardee Organization(s): Viginia Commonwealth University
Principal Investigator(s): Jane Chung, PhD, RN | Eyuphan Bulut, PhD | Ingrid Pretzer-Aboff, PhD, RN
Official Project Title: A Device Free WiFi Sensing System to Assess Daily Activities and Mobility in Low-Income Older Adults With and Without Cognitive Impairment
AITC Partner: PennAITech
Website(s):
https://nursing.vcu.edu
https://egr.vcu.edu

Low-income older adults face an increased risk of cognitive impairment and dementia. Cognitive impairment affects the ability to perform and manage daily activities and mobility behaviors. Detecting the changes in these abilities early is crucial but often difficult among low-income older adults due to limited resources. Our ultimate goal is to meet the unmet needs of low-income older adults by creating a cutting-edge system that uses Wi-Fi signals to localize and recognize different patterns of in-home activities and mobility. We will employ machine learning algorithms to process the Channel State Information of the collected Wi-Fi signals and extract different activity features. Our system will automatically categorize and quantify daily activities such as sitting, walking, meal preparation, watching TV, phone use, and leaving the home. Our project will gather Wi-Fi signal-based activity patterns and frequencies, selfreported physical function and psychosocial health data, and older adults’ feedback on technology acceptance and implementation. This innovative project aims to empower low-income older adults by harnessing the power of Wi-Fi sensing technology and machine learning to detect cognitive decline as early as possible. By providing an accessible and cost-effective solution, we can improve the lives of vulnerable older adults and enhance their brain health.

Awardee Organization(s): University of Pennsylvania
Principal Investigator(s): Gary Weissman, MD, MSHP
Official Project Title: Advancing Diagnostic Excellence for Older Adults Through Collective Intelligence and Imitation Learning
AITC Partner: PennAITech
Website(s): https://www.med.upenn.edu

Diagnostic errors are common in the primary care setting and lead to direct patient harms, increased healthcare costs, and decrease patient satisfaction. Older adults are especially at risk for such diagnostic errors because of their higher comorbidity burden, medical complexity, increased rates of frailty and cognitive impairment, and decreased representation in clinical datasets and research studies. Artificial intelligence (AI) and machine learning (ML) methods have good face validity for offering clinical decision support (CDS) in this setting to promote diagnostic excellence. However, there is little data to suggest that any particular diagnostic CDS is transparent, reproducible, equitable, and effective at improving the diagnostic process. Therefore, our objective is to create a diagnostic CDS system for use in primary care clinics to facilitate the diagnostic process, present suggestions about important features of the history and exam to consider that are tailored to patient characteristics, and promote diagnostic excellence for older adults. This proposal overcomes existing limitations to training diagnostic CDS systems in primary care where there is a broad diagnostic scope and tremendous clinical uncertainty around training labels. To accomplish this, we will rely on imitation learning and collective intelligence to build AI/ML models that provide predicted suggestions into diagnosis and tests based on expected behaviors from peer clinicians caring for similar patients. These models will be trained using existing data from the electronic health record and deployed in a pilot study across diverse primary care clinics to assess their diagnostic accuracy and acceptability to clinicians, patients, and their caregivers.

Awardee Organization(s): University of Virginia | University of Pennsylvania
Principal Investigator(s): Aidong Zhang, PhD | Carol Manning, PhD | Li Shen, PhD | Mary Regina Boland, PhD, MPhil
Official Project Title: Fairness and Robust Interpretability of Prediction Approaches for Aging and Alzheimer’s Disease
AITC Partner: PennAITech
Website(s):
https://engineering.virginia.edu
https://www.cs.virginia.edu/~az9eg/website/home.html
https://www.med.upenn.edu

Machine learning (ML) approaches have been increasingly used for facilitating clinical decision-making in Alzheimer’s Disease (AD) and AD related dementia (ADRD). However, recent research has shown that existing ML techniques are prone to unintentional biases towards protected attributes such as age, race, sex, gender, and/or ethnicity. Moreover, although deep learning (DL) models have been a great success in many applications including AD/ADRD prediction, DL models are usually expressed in a way that is not interpretable. Thus, ML approaches using health data may incur ethical and trustworthiness concerns that may result in the unfair treatment of patients. As decision-making systems for aging and AD/ADRD become popular, a major challenge is how to ethically integrate AI/ML methods into the lives of people, given that ethical principles may often be violated in existing methods. This has become an important issue for both the ML community and the AD/ADRD community. Moreover, ML approaches that are not transparent can be prone to repeating discriminatory patterns from prior data or generating new ones based on biased learned patterns. This project develops electronic health records (EHRs) based ML methods for Penn Medicine EHR AD/ADRD datasets that are fair, generalizable, and interpretable solutions that would help inform the clinician for AD/ADRD diagnosis and care management. We focus on studying fairness and interpretability, two important factors for making AI methods trustworthy, particularly during deployment or use of the methods. We study how bias affects our prediction models. Also, we will develop explainable methods to increase clinical interpretability.

Awardee Organization(s): University of Tennessee, Knoxville
Principal Investigator(s): Xiaopeng Zhao, PhD
Official Project Title: MUSICARE-VR: Music Intervention with Virtual Reality for Alzheimer’s Care
AITC Partner: PennAITech
Website(s): https://mabe.utk.edu/

MUSICARE-VR is an innovative system that combines the benefits of music intervention with the connective power of virtual reality to improve the well-being of people with Alzheimer’s disease and related dementia (PwADRD). By providing engaging music sessions in a virtual environment, MUSICARE-VR aims to enhance cognitive function, physical activity, emotional positivity, and social connectedness among PwADRD, especially those living in isolation. The system will be developed using cutting-edge virtual reality technologies. PwADRD will participate in personalized, interactive music activities led by skilled music therapists, fostering a sense of achievement and encouraging repeated engagement. A key feature of MUSICARE-VR is the integration of artificial intelligence (AI), which will adapt music interventions in real-time based on users’ emotional and physiological responses, ensuring an engaging and effective experience. AI-powered virtual agents will also join the sessions, enhancing social interactions and overall engagement. To ensure the system’s success, MUSICARE-VR will be developed through a user-centered, iterative design process. The feasibility and acceptance of the system will be evaluated among PwADRD and their caregivers, with a focus on usability, engagement metrics, and participant feedback. By combining music intervention, virtual reality, and AI, MUSICARE-VR promises to be a groundbreaking tool for improving the quality of life of PwADRD and their caregivers.

Awardee Organization(s): PyrAmes Inc.
Principal Investigator(s): Xina Quan, PhD
Official Project Title: Improved Algorithms for Wearable Blood Pressure Monitoring for Older Adults
AITC Partner: PennAITech
Website(s): https://pyrameshealth.com/

Older adults with high blood pressure (BP) are at increased risk of severe health concerns, e.g. heart disease, congestive heart failure, ischemic stroke, cerebral hemorrhage, vascular dementia and Alzheimer’s disease. Frequent measurements improve BP control, leading to improved outcomes.
A significant barrier to BP control is obtaining sufficient measurements for effective management. Continuous monitoring with invasive arterial lines is limited to critical care facilities. Periodic cuff measurements through ambulatory BP monitoring provide an indication of BP variation, but devices are cumbersome and uncomfortable, leading to incorrect or insufficient usage.
A more convenient, cost-effective BP monitoring method providing passive measurements and actionable information potentially leads to reduced risk from cardiovascular disease. PyrAmes has developed a comfortable, easy-to-use sensor band to monitor BP, enabling long-term, personalized BP management. It is soft, flexible, and lightweight, and has been validated for use with patients with fragile skin. Our innovative approach uses patented capacitive sensors to capture pulse waveform data, which is processed on a connected mobile device with neural networks to accurately determine BP values and provide detailed information about cardiovascular health.
Our first device, Boppli®, was FDA-cleared in 2023 for continuously monitoring the BP of critically-ill neonates. Our adult monitor uses identical sensors and validated software infrastructure and has shown initial feasibility. This project accelerates development for the older adult population, leading to FDA clearance and commercialization.
Our technology has the potential to become as ubiquitous for BP measurement as pulse oximeters are today, due to its accuracy, convenience, and ease of use.