ORCID Profile
0000-0002-0320-6763
Current Organisation
Washington State University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: SAGE Publications
Date: 2020
Abstract: The training of artificial intelligence requires integrating real-world context and mathematical computations. To achieve efficacious smart health artificial intelligence, contextual clinical knowledge serving as ground truth is required. Qualitative methods are well-suited to lend consistent and valid ground truth. In this methods article, we illustrate the use of qualitative descriptive methods for providing ground truth when training an intelligent agent to detect Restless Leg Syndrome. We show how one interdisciplinary, inter-methodological research team used both sensor-based data and the participant’s description of their experience with an episode of Restless Leg Syndrome for training the intelligent agent. We make the case for clinicians with qualitative research expertise to be included at the design table to ensure optimal efficacy of smart health artificial intelligence and a positive end-user experience.
Publisher: Wiley
Date: 03-09-2021
DOI: 10.1111/JAN.14996
Abstract: Ageing‐in‐place for older people could be more feasible with the support of smart home technology. Ageing in‐place may maximize the independence of older adults and enhance their well‐being and quality of life, while decreasing the financial burden of residential care costs, and addressing workforce shortages. However, the uptake of smart home technology is very low among older adults. Accordingly, the aim of this study was to explore factors influencing community‐dwelling older adults’ readiness to adopt smart home technology. A qualitative exploratory study design was utilized. Descriptive data were collected between 2019 and 2020 to provide context of s le characteristics for community‐dwelling older adults aged ≥65 years. Qualitative data were collected via semi‐structured interviews and focus groups, to generate an understanding of older adult's perspectives. Thematic analysis of interviews and focus group transcripts was completed. The Elderadopt model was the conceptual framework used in the analysis of the findings. Several factors influenced community‐dwelling older adults’ ( N = 19) readiness to adopt smart home technology. Five qualitative themes were identified: knowledge, health and safety, independence, security and cost. Community‐dwelling older adults were open to adopting smart home technology to support independence despite some concerns about security and loss of privacy. Opportunities to share information about smart home technology need to be increased to promote awareness and discussion. Wider adoption of smart home technology globally into the model of aged care can have positive impacts on caregiver burden, clinical workforce, health care utilization and health care economics. Nurses, as the main providers of healthcare in this sector need to be knowledgeable about the options available and be able to provide information and respond to questions know about ageing‐in‐place technologies to best support older adults and their families.
Publisher: JMIR Publications Inc.
Date: 28-08-2020
Abstract: oorly managed pain can lead to substance use disorders, depression, suicide, worsening health, and increased use of health services. Most pain assessments occur in clinical settings away from patients’ natural environments. Advances in smart home technology may allow observation of pain in the home setting. Smart homes recognizing human behaviors may be useful for quantifying functional pain interference, thereby creating new ways of assessing pain and supporting people living with pain. his study aimed to determine if a smart home can detect pain-related behaviors to perform automated assessment and support intervention for persons with chronic pain. multiple methods, secondary data analysis was conducted using historic ambient sensor data and weekly nursing assessment data from 11 independent older adults reporting pain across 1-2 years of smart home monitoring. A qualitative approach was used to interpret sensor-based data of 27 unique pain events to support clinician-guided training of a machine learning model. A periodogram was used to calculate circadian rhythm strength, and a random forest containing 100 trees was employed to train a machine learning model to recognize pain-related behaviors. The model extracted 550 behavioral markers for each sensor-based data segment. These were treated as both a binary classification problem (event, control) and a regression problem. e found 13 clinically relevant behaviors, revealing 6 pain-related behavioral qualitative themes. Quantitative results were classified using a clinician-guided random forest technique that yielded a classification accuracy of 0.70, sensitivity of 0.72, specificity of 0.69, area under the receiver operating characteristic curve of 0.756, and area under the precision-recall curve of 0.777 in comparison to using standard anomaly detection techniques without clinician guidance (0.16 accuracy achieved i P /i & .001). The regression formulation achieved moderate correlation, with i r /i =0.42. indings of this secondary data analysis reveal that a pain-assessing smart home may recognize pain-related behaviors. Utilizing clinicians’ real-world knowledge when developing pain-assessing machine learning models improves the model’s performance. A larger study focusing on pain-related behaviors is warranted to improve and test model performance.
Publisher: Wiley
Date: 23-08-2023
DOI: 10.1111/JAN.15826
Abstract: The aim of this study was to explore factors that influence family caregiver readiness to adopt health smart home technology for their care‐dependent older adult family member. Health smart homes are designed to remotely monitor the health and wellness of community‐dwelling older adults supporting independent living for as long as possible. Accordingly, if the health smart home is deployed into the home of a care‐depended older adult, it can potentially support family caregivers by facilitating workforce participation and give piece of mind to the family caregiver who may not live close to the older adult. However, wider adoption of health smart home technologies into the homes of community‐older adults is low, and little is known about the factors that influence the readiness of family caregivers to adopt smart home technologies for their care‐dependent older adults. A qualitative Descriptive study design was utilized. Qualitative data were collected between 2019 and 2020 via semi‐structured interviews. Thematic analysis of interviews was completed, and data were organized into themes. Study findings show that caregiver readiness ( N = 10) to adopt smart home technology to monitor older adult family members were influenced by five primary themes including a ‘big brother effect’, ‘framing for acceptance’, ‘data privacy’, ‘burden’ and ‘cost.’ Family caregivers were open to adopting smart home technology to support the independent living of their older adult family members. However, the readiness of family caregivers was inextricably linked to the older adults' readiness for smart home adoption. The family caregiver's primary concern was on how they could frame the idea of the smart home to overcome what they viewed as hesitancy to adopt in the older adult. The findings suggest that family caregivers endeavour to balance the hesitancy in their older adult family members with the potential benefits of smart home technology. Family caregivers could benefit if their care‐dependent older adults adopt smart home technology. Recognizing the role of caregivers and their perspectives on using smart home technologies with their care‐dependents is critical to the meaningful design, use and adoption.
Publisher: JMIR Publications Inc.
Date: 06-11-2020
DOI: 10.2196/23943
Abstract: Poorly managed pain can lead to substance use disorders, depression, suicide, worsening health, and increased use of health services. Most pain assessments occur in clinical settings away from patients’ natural environments. Advances in smart home technology may allow observation of pain in the home setting. Smart homes recognizing human behaviors may be useful for quantifying functional pain interference, thereby creating new ways of assessing pain and supporting people living with pain. This study aimed to determine if a smart home can detect pain-related behaviors to perform automated assessment and support intervention for persons with chronic pain. A multiple methods, secondary data analysis was conducted using historic ambient sensor data and weekly nursing assessment data from 11 independent older adults reporting pain across 1-2 years of smart home monitoring. A qualitative approach was used to interpret sensor-based data of 27 unique pain events to support clinician-guided training of a machine learning model. A periodogram was used to calculate circadian rhythm strength, and a random forest containing 100 trees was employed to train a machine learning model to recognize pain-related behaviors. The model extracted 550 behavioral markers for each sensor-based data segment. These were treated as both a binary classification problem (event, control) and a regression problem. We found 13 clinically relevant behaviors, revealing 6 pain-related behavioral qualitative themes. Quantitative results were classified using a clinician-guided random forest technique that yielded a classification accuracy of 0.70, sensitivity of 0.72, specificity of 0.69, area under the receiver operating characteristic curve of 0.756, and area under the precision-recall curve of 0.777 in comparison to using standard anomaly detection techniques without clinician guidance (0.16 accuracy achieved P .001). The regression formulation achieved moderate correlation, with r=0.42. Findings of this secondary data analysis reveal that a pain-assessing smart home may recognize pain-related behaviors. Utilizing clinicians’ real-world knowledge when developing pain-assessing machine learning models improves the model’s performance. A larger study focusing on pain-related behaviors is warranted to improve and test model performance.
Location: United States of America
No related grants have been discovered for Roschelle Fritz.