skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: PERACTIV: Personalized Activity Monitoring - Ask My Hands
Medication adherence is a major problem in the healthcare industry: it has a major impact on an individual’s health and is a major expense on the healthcare system. We note that much of human activity involves using our hands, often in conjunction with objects. Camera-based wearables for tracking human activities have sparked a lot of attention in the past few years. These technologies have the potential to track human behavior anytime, any place. This paper proposes a paradigm for medication adherence employing innovative wrist-worn camera technology. We discuss how the device was built, various experiments to demonstrate feasibility and how the device could be deployed to detect the micro-activities involved in pill taking so as to ensure medication adherence.  more » « less
Award ID(s):
1828010
PAR ID:
10344382
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
International Conference on Human-Computer Interaction (HCII) 2022. Lecture Notes in Computer Science
Volume:
13326
Page Range / eLocation ID:
255–272
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Springer Nature Switzerland)
    The prevalence of medication non-adherence poses a critical challenge with far-reaching health implications and substantial economic consequences. The PERACTIV project addresses this issue with a wrist-worn device that meticulously tracks hand and finger movements, offering real-time insights into medication intake routines. In the context of smart cities and healthcare innovation, this project provides a groundbreaking solution to the persistent problem of medication adherence. This paper introduces the integration of PERACTIV wearable technology with an automated annotation pipeline utilizing Force Sensing Resistor (FSR) technology. Placed strategically on the index finger, FSR records force during pivotal pill-related moments, eliminating the need for time-consuming manual data annotation. Together, the PERACTIV wearable and FSR-powered pipeline form a promising solution for medication adherence, particularly beneficial for individuals living independently and those with memory impairments. The research methodology involved focus groups to explore the intricacies of medication adherence challenges. Section 2 discusses the findings derived from these groups, providing a foundational understanding. Section 3 introduces the FSR-powered automated annotation pipeline, comprehensively analyzing micro-activities during pill-taking. These micro-activities encompass diverse elements, contributing to a holistic understanding crucial for effective analysis. This paper underscores the transformative potential of technology and innovation in healthcare research, setting the stage for seamless integration of medication adherence into daily life. The future promises a more connected and informed healthcare landscape driven by the synergy of PERACTIV wearable and FSR automation. 
    more » « less
  2. ; ; (, IUI '21: 26th International Conference on Intelligent User Interfaces)
    null (Ed.)
    Nearly half of people prescribed medication to treat chronic or short-term conditions do not take their medicine as prescribed. This leads to worse treatment outcomes, higher hospital admission rates, increased healthcare costs, and increased morbidity and mortality rates. While some instances of medication non-adherence are a result of problems with the treatment plan or barriers caused by the health care provider, many are instances caused by patient-related factors such as forgetting, running out of medication, and not understanding the required dosages. This presents a clear need for patient-centered systems that can reliably increase medication adherence. To that end, in this work we describe an activity recognition system capable of recognizing when individuals take medication in an unconstrained, real-world environment. Our methodology uses a modified version of the Bagging ensemble method to suit unbalanced data and a classifier trained on the prediction probabilities of the Bagging classifier to identify when individuals took medication during a full-day study. Using this methodology we are able to recognize when individuals took medication with an F-measure of 0.77. Our system is a first step towards developing personal health interfaces that are capable of providing personalized medication adherence interventions. 
    more » « less
  3. ; ; ; ; ; (, Proceedings of the ACM on Human-Computer Interaction)
    null (Ed.)
    People living with HIV experience a high level of stigma in our society. Public HIV-related stigma often leads to anxiety and depression and hinders access to social support and proper medical care. Technologies for HIV, however, have been mainly designed for treatment management and medication adherence rather than for helping people cope with public HIV-related stigma specifically. Drawing on empirical data obtained from semi-structured interviews and design activities with eight social workers and 29 people living with HIV, we unpack the ways in which needs for privacy and trust, intimacy, and social support create tensions around key coping strategies. Reflecting on these tensions, we present design implications and opportunities to empower people living with HIV to cope with public HIV-related stigma at the individual level. 
    more » « less
  4. ; (, International Conference on Distributed Computing in Sensor Systems and workshops)
    Hand hygiene is crucial in preventing the spread of infections and diseases. Lack of hand hygiene is one of the major reasons for healthcare associated infections (HAIs) in hospitals. Adherence to hand hygiene compliance by the workers in the food business is very important for preventing food-borne illness. In addition to healthcare settings and food businesses, hand washing is also vital for personal well-being. Despite the importance of hand hygiene, people often do not wash hands when necessary. Automatic detection of hand washing activity can facilitate justin-time alerts when a person forgets to wash hands. Monitoring hand washing practices is also essential in ensuring accountability and providing personalized feedback, particularly in hospitals and food businesses. Inertial sensors available in smart wrist devices can capture hand movements, and so it is feasible to detect hand washing using these devices. However, it is challenging to detect hand washing using wrist wearable sensors since hand movements are associated with a wide range of activities. In this paper, we present HAWAD, a robust solution for hand washing detection using wrist wearable inertial sensors. We leverage the distribution of penultimate layer output of a neural network to detect hand washing from a wide range of activities. Our method reduces false positives by 77% and improves F1-score by 30% compared to the baseline method. 
    more » « less
  5. ; ; ; ; (, Infection and Immunity)
    Raffatellu, Manuela (Ed.)
    ABSTRACT EnteroaggregativeEscherichia coli(EAEC) is a common cause of diarrhea worldwide and is associated with growth faltering in developing countries. EAEC are defined by a characteristic adherence pattern mediated by the aggregative adherence fimbriae (AAFs). Despite the critical role of AAF in the definition of the EAEC pathotype, it is not known what host molecules mediate adherence and EAEC pathogenesis during infection of the human gastrointestinal tract. Multiple receptor candidates have been proposed based onin vitroexperimentation. We propose that AAFs interact with multiple receptors during colonization of the human gastrointestinal mucosa, and we hypothesize that structural features of the AafA protein (the major subunit of AAF variant II produced by EAEC strain 042) promote these diverse interactions. In this study, we utilize a panel of AafA variants encoding single amino acid substitutions to understand the role of individual residues in biofilm formation as well as adherence to mucin, fibronectin, and human intestinal cells. We identify both charged and uncharged residues that participate in these interactions, and these residues cluster in two regions of the protein that may define a binding pocket at the junction of polymerized subunits. Although both bovine submaxillary mucin and human fibronectin are sialylated molecules, adherence to mucin is diminished by the removal of sialic acid residues while adherence to fibronectin is not, suggesting that the mechanisms of adherence to these molecules are distinct. Overall, our data provide insight into the structural features that determine AAF/II binding to mucin, sialic acid, and human intestinal cells. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email