Body Sensor Networks for Personalized Medicine

Permanent URI for this collectionhttps://hdl.handle.net/10125/107477

Browse

Now showing 1 - 5 of 5

Real-World Implementation Challenges Associated with a Digital Pill System to Measure Adherence to HIV Pre-Exposure Prophylaxis from Two Studies of Men Who Have Sex With Men
(2024-01-03) Goodman, Georgia; Carnes, Chris; Albrechta, Hannah; Alpert, Pamela; Hokayem, Joanne; Lee, Jasper; Boyer, Edward; Rosen, Rochelle; Mayer, Kenneth; O’Cleirigh, Conall; Chai, Peter R.
Once-daily oral pre-exposure prophylaxis (PrEP) is highly effective for HIV prevention, but its efficacy is dependent on adherence, which can be challenging for men who have sex with men (MSM) with substance use. Digital pill systems (DPS) represent a novel tool for directly measuring adherence through ingestible radiofrequency sensors that confirm ingestions in real-time. We examined operational challenges across two studies involving DPS to measure PrEP adherence. While most participants successfully operated the system, a number of technological and sociobehavioral challenges requiring intervention were identified across both studies. Technological issues were both system- and participant-related, and were primarily addressed with technical updates and participant re-education, while sociobehavioral issues, including health and housing changes and issues with technology access, warranted innovative solutions. Future research leveraging DPS technology should develop robust supportive infrastructure and mitigation procedures to promptly identify and resolve operational issues to optimize the potential benefits of DPS use.
Predicting Lower Extremity Joint Kinematics Using Multi-Modal Data in the Lab and Outdoor Environment
(2024-01-03) Hossain, Md Sanzid Bin; Guo, Zhishan; Sui, Ning; Choi, Hwan
Predicting future walking joint kinematics is crucial for assistive device control, especially in variable walking environments. Traditional optical motion capture systems provide kinematics data but require laborious post-processing, whereas IMU based systems provide direct calculations but add delays due to data collection and algorithmic processes. Predicting future kinematics helps to compensate for these delays, enabling the system real-time. Furthermore, these predicted kinematics could serve as target trajectories for assistive devices such as exoskeletal robots and lower limb prostheses. However, given the complexity of human mobility and environmental factors, this prediction remains to be challenging. To address this challenge, we propose the Dual-ED-Attention-FAM-Net, a deep learning model utilizing two encoders, two decoders, a temporal attention module, and a feature attention module. Our model outperforms the state-of-the-art LSTM model. Specifically, for Dataset A, using IMUs and a combination of IMUs and videos, RMSE values decrease from 4.45° to 4.22° and from 4.52° to 4.15°, respectively. For Dataset B, IMUs and IMUs combined with pressure insoles result in RMSE reductions from 7.09° to 6.66° and from 7.20° to 6.77°, respectively. Additionally, incorporating other modalities alongside IMUs helps improve the performance of the model.
Informing Acceptability and Feasibility of Digital Phenotyping for Personalized HIV Prevention among Marginalized Populations Presenting to the Emergency Department
(2024-01-03) Glynn, Tiffany; Khanna, Simran; Hasdianda, Mohammad Adrian; Tom, Jeremiah; Venkatasubramanian, Krishna; Dumas, Arlen; O’Cleirigh, Conall; Goldfine, Charlotte; Chai, Peter R.
For marginalized populations with ongoing HIV epidemics, alternative methods are needed for understanding the complexities of HIV risk and delivering prevention interventions. Due to lack of engagement in ambulatory care, such groups have high utilization of drop-in care. Therefore, emergency departments represent a location with those at highest risk for HIV and in highest need of novel prevention methods. Digital phenotyping via data collected from smartphones and other wearable sensors could provide the innovative vehicle for examining complex HIV risk and assist in delivering personalized prevention interventions. However, there is paucity in exploring if such methods are an option. This study aimed to fill this gap via a cross-sectional psychosocial assessment with a sample of N=85 emergency department patients with HIV risk. Findings demonstrate that although potentially feasible, acceptability of digital phenotyping is questionable. Technology-assisted HIV prevention needs to be designed with the target community and address key ethical considerations.
Heart-to-Wear: Assessing the Accuracy of Heart Rate Sensor Measurements of Wearable Devices in Uncontrolled Environments
(2024-01-03) Wolf, Simon; Seidel, Patrick; Ockenga, Tim Alvaro; Schoder, Detlef
The growing popularity of wearable devices has enabled individuals to monitor their health and offers potential benefits for remote patient monitoring. However, the reliability of diagnoses provided by these non-approved medical devices remains uncertain. This study addresses the problem of assessing the measurement accuracy of heart rate recordings from wearable devices in both controlled and uncontrolled environments. Previous research has focused on evaluating accuracy in controlled settings, neglecting the impact of external factors on device performance. We conducted a comparative study with ten healthy individuals, recording heart rates during indoor cycling and outdoor activities. Participants wore two out of three tested smartwatches (Apple Watch Ultra, Garmin Enduro 2, Polar Pacer Pro) alongside a Polar H10 chest strap as a reference device. Our findings provide evidence that the Apple Watch Ultra and the Garmin Enduro 2 are particularly resistant to external factors that can occur during regular cycling activities.
Introduction to the Minitrack on Body Sensor Networks for Personalized Medicine
(2024-01-03) Lee, Jasper; Davis-Martin, Rachel; Goldfine, Charlotte

Browse

Recent Submissions