Body Sensor Networks for Personalized Medicine
Permanent URI for this collection
Browse
Recent Submissions
Item User Perspectives of Digital Pills and Adherence Support for HIV Medication: A Comparison of the etectRx ID-Capsule System™ and Wisepill Dispenser(2025-01-07) Rosen, Rochelle; Lantini, Ryan; Viamonte, Michael; Alpert, Pamela; Carrico, Adam; Chai, Peter R.; Frey, Jennifer; Merchant, Roland Clayton; Boyer, EdwardDigital Pills are a developing technology with application in a variety of medical conditions. This paper reports on interviews from a crossover clinical trial in which participants used both a novel digital pill system (ID-Capsule) and an electronic pill dispenser (Wisepill). Interviews explored user experiences, acceptability, and willingness to use both products. Data for each period of use is reported, and experiences about the two products are compared. The electronic pill dispenser was considered easy to use and convenient. The size of the pill dispenser was cited as both a facilitator and barrier to ongoing pill use. The ID-Capsule digital pill system was considered a facilitator of adherence for many users, and most found that knowing that their adherence was being monitored encouraged adherence. Using the accompanying ID-Capsule app to track days on which pills were missed was helpful. Barriers included needing to use and charge the digital pill reader. These qualitative findings provide relevant technology evaluation data for use in future iterations of this digital pill and adherence system.Item Leveraging Virtual Reality to Improve Medication Adherence among Marginalized Populations with High-risk Chronic Health Conditions: Proof-of-concept Protocol, Considerations, and Next Steps(2025-01-07) Glynn, Tiffany; Dias, Roger; Verly, Robson J.; O’Cleirigh, Conall; Chai, Peter R.Marginalized populations experience high prevalence of chronic health conditions - many of which require optimal medication adherence to avoid significant consequences for mortality and morbidity. Yet, marginalization and its complex sequelae create barriers for adherence and access to care, creating a cycle of health inequity. Individuals are not fully benefiting from evidence-based behavioral adherence interventions, like “Life-steps”, potentially due to lack of embedded experiential learning, which is key for individuals experiencing complex barriers to medication adherence. Leveraging interactive artificial intelligence technologies through immersive virtual reality is a promising avenue to bolster behavioral adherence interventions. We present our current proof-of-concept work for “Life-steps VR”, an integration of such technologies into the empiric behavioral medication adherence intervention. We then discuss our next steps for further refinement and testing of the technology with consideration for equity, democratization, and accessibility of health technologies. We conclude with a discussion of future potential iterations of Life-steps VR.Item AIARS: Towards Automated Infant Activity Recognition System using Machine Learning and Multi-sensor Fusion Data(2025-01-07) Thelagathoti, Rama Krishna; Chaudhary, Priyanka; Knarr, Brian; Schenkelberg, Michaela; Youn, Jong-Hoon; Ali, Hesham; Dinkel, DanaeInfant Activity Recognition (IAR) plays a pivotal role in modern healthcare and developmental studies,offering crucial insights into early childhood behavior and motor development. Nevertheless, identifying various categories of infant activities such as playing,crawling, and feeding, poses challenges due to the dynamic nature of a child’s age and the continuous involvement of parents or caregivers. Recognizing infant activities aids in the timely detection of motor disorders and promotes healthy movement behavior. In this study,we propose an automated Infant Activity Recognition System (AIARS) utilizing a Machine Learning (ML)approach that leverages data from wearable sensors.Initially, we compiled an Infant Activity Database(IAD) by collecting data from infants across 16 distinct activities in controlled laboratory environments. Due to the limited sample size for each activity, we aggregated these 16 activities into 3 and then 2 broader categories.Employing ML techniques, including Random Forest(RF), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGB), we developed an AIARS to classify various infant activities. Our study achieved impressive results, with an accuracy of 93.85% , an Area Under the Curve (AUC) of 99%, and an F1 score of 95.2%. We also addressed the challenges faced while applying ML methods in developing AIARS and provided recommendations to mitigate these challenges.These findings underscore the efficacy of our approach and represent a significant milestone in the domain of IAR.Item Introduction to the Minitrack on Body Sensor Networks for Personalized Medicine(2025-01-07) Lee, Jasper; Davis-Martin, Rachel; Goldfine, Charlotte