A nurse-driven method for developing artificial intelligence in “smart” homes for aging-in-place

Fritz, Robert B.; Dermody, Gordana

doi:10.1016/j.outlook.2018.11.004

Cited by 72 publications

(83 citation statements)

References 35 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This work focuses on assessing the challenges and opportunities generated by informationgathering strategies nurse driven for data analytics. In conclusion, they affirmed that the training of algorithms led by nurses can contribute with tools that allow to monitor and alert about the abnormal state of a group of patients, such as reduction in average activity, slower walk, and increase in the use of bathrooms, without generating daily annoyances or obstructions, since for reasons of privacy, many older adults prefer not to be recorded, with a camera or microphone [64].…”

Section: Future Of Gait Analysis In Agingmentioning

confidence: 94%

“…In addition to this, with the rise of concepts and technologies such as Internet of things, data science, artificial intelligence, and smart cities and homes, among others, recent developments have focused on contributing to the older population. Such is the case of Roschelle et al [64], who trained intelligent algorithms through five different sensors (infrared motion, light, humidity, contact, and temperature) and supervision of nurses through telehealth strategies and periodic visits to the smart home for medical assistance (health-assistive smart homes) [64]. This work focuses on assessing the challenges and opportunities generated by informationgathering strategies nurse driven for data analytics.…”

Section: Future Of Gait Analysis In Agingmentioning

confidence: 99%

See 1 more Smart Citation

Smart Tracking and Wearables: Techniques in Gait Analysis and Movement in Pathological Aging

Muñoz¹,

Valderrama²,

Orozco³

et al. 2020

Smart Healthcare

View full text Add to dashboard Cite

In this chapter, we describe the aging process and, more specifically, the pathological aging, associated with neurodegenerative diseases and its relation with gait. Then, we explain the importance of using quantitative gait analysis techniques using wearables and other technologies to diagnose different conditions that can be complex to discriminate using only the physician naked-eye diagnosis. We analyze different approaches used for gait analysis using wearables and affordable devices like inertial units (IMU), accelerometers, and depth cameras like Microsoft Kinect or Intel's RealSense, which have been available at least in an academic context but will be available for daily use in the near future.

show abstract

Section: Future Of Gait Analysis In Agingmentioning

confidence: 94%

Section: Future Of Gait Analysis In Agingmentioning

confidence: 99%

Smart Tracking and Wearables: Techniques in Gait Analysis and Movement in Pathological Aging

Muñoz¹,

Valderrama²,

Orozco³

et al. 2020

Smart Healthcare

View full text Add to dashboard Cite

show abstract

“…We also excluded data showing extended stay visitors (ie, stays across multiple days and nights). More information on the nursing team’s analytic methods, including data exclusion processes, is available in the literature [ 45 , 46 ]. For training the ML model, we excluded data from light, temperature, and humidity sensors.…”

Section: Methodsmentioning

confidence: 99%

“…To train PASH, we used these existing pain-related clinical and sensor-based data. More information about the role of nurses in the longitudinal study is available in the literature [ 42 , 45 , 46 ].…”

Section: Introductionmentioning

confidence: 99%

Automated Smart Home Assessment to Support Pain Management: Multiple Methods Analysis

Fritz¹,

Wilson²,

Dermody³

et al. 2020

J Med Internet Res

Self Cite

View full text Add to dashboard Cite

Background 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. Objective 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. Methods 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. Results 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. Conclusions 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.

show abstract

“…Additionally, some scholars criticized the dissatisfactory services provided by AIP service organizations [27], the lack of active participation of voluntary organizations [28], and the inefficient delivery of certain types of AIP services [18,29]. To tackle those problems, abundant suggestions have been discussed, like adopting high-tech equipment (e.g., real-time monitoring sensors) for older people, avoiding mismatch between the needs of older people and the design of communities [5,30,31], strengthening the frequency of communication between service organizations and older people [25], fastening the collaboration, and coordination among service providers [32], sharpening skills and enriching knowledge of employee for improved service quality [32,33], and enhancing the accessibility and affordability of AIP services [30].…”

Section: Stakeholder Research On Aipmentioning

confidence: 99%

Characterizing Stakeholders of Aging-in-Place through Social Network Analysis: A Study of Nanjing, China

Zhou

et al. 2019

Sustainability

View full text Add to dashboard Cite

China currently has an elderly population of 249 million with over 97% of them ending up aging in place. Although various regional pilot programs have been conducted, a sustainable aging-in-place system has not been established to effectively and efficiently provide aging services in many cities of China. The characteristics of stakeholder networks in the aging-in-place systems have not attracted great attention from researchers. This research applies social network analysis to characterize the interactions of stakeholders in aging-in-place systems to facilitate cooperation and coordination amongst them. Using Nanjing as a case study, 23 stakeholders in Nanjing’s aging-in-place system are identified, such as the Aging Affairs Committee, Aging-in-Place Service Association, and aging-in-place service centers; and then the relationship networks of these stakeholders in terms of communication, supervision, and trust are developed and analyzed. The results show that the aging-in-place system suffers from certain defects, including the loose connection of government departments, redundant information channels, low trustworthiness of certain aging-in-place service centers, poor credibility of third-party training and assessment institutions, and excess power of the industry association. To tackle these issues, a wide spectrum of actionable measures applicable to Nanjing’s conditions, as well as high-level policy implications for other cities of China, are proposed for augmenting the communication, supervision, and trust among stakeholder groups.

show abstract

A nurse-driven method for developing artificial intelligence in “smart” homes for aging-in-place

Cited by 72 publications

References 35 publications

Smart Tracking and Wearables: Techniques in Gait Analysis and Movement in Pathological Aging

Smart Tracking and Wearables: Techniques in Gait Analysis and Movement in Pathological Aging

Automated Smart Home Assessment to Support Pain Management: Multiple Methods Analysis

Characterizing Stakeholders of Aging-in-Place through Social Network Analysis: A Study of Nanjing, China

Contact Info

Product

Resources

About