Myra A. Aud

Linguistic summarization of video for fall detection using voxel person and fuzzy logic

In this paper, we present a method for recognizing human activity from linguistic summarizations of temporal fuzzy inference curves representing the states of a three-dimensional object called voxel person. A hierarchy of fuzzy logic is used, where the output from each level is summarized and fed into the next level. We present a two level model for fall detection. The first level infers the states of the person at each image. The second level operates on linguistic summarizations of voxel persons states and inference regarding activity is performed. The rules used for fall detection were designed under the supervision of nurses to ensure that they reflect the manner in which elders perform these activities. The proposed framework is extremely flexible. Rules can be modified, added, or removed, allowing for per-resident customization based on knowledge about their cognitive and physical ability.

Modeling Human Activity From Voxel Person Using Fuzzy Logic

As part of an interdisciplinary collaboration on elder-care monitoring, a sensor suite for the home has been augmented with video cameras. Multiple cameras are used to view the same environment and the world is quantized into nonoverlapping volume elements (voxels). Through the use of silhouettes, a privacy protected image representation of the human acquired from multiple cameras, a 3-D representation of the human is built in real time, called voxel person. Features are extracted from voxel person and fuzzy logic is used to reason about the membership degree of a predetermined number of states at each frame. Fuzzy logic enables human activity, which is inherently fuzzy and case-based, to be reliably modeled. Membership values provide the foundation for rejecting unknown activities, something that nearly all current approaches are insufficient in doing. We discuss temporal fuzzy confidence curves for the common elderly abnormal activity of falling. The automated system is also compared to a ground truth acquired by a human. The proposed soft computing activity analysis framework is extremely flexible. Rules can be modified, added, or removed, allowing per-resident customization based on knowledge about their cognitive and functionality ability. To the best of our knowledge, this is a new application of fuzzy logic in a novel approach to modeling and monitoring human activity, in particular, the well-being of an elderly resident, from video.

Dangerous wandering: Elopements of older adults with dementia from long-term care facilities

Wandering is a commonly observed behavior among older adults with Alzheimers disease (AD) and other types of dementia. When wandering around becomes wandering away, older adults with dementia are at high risk of injury. This exploratory, qualitative study described the circumstances, environmental risks, and injuries sustained in 62 elopements from long-term care facilities by elderly residents with dementia. Content analysis of the reports of the elopements identified patterns that included: 1) a lack of effective precautions to prevent elopement when residents had indicated an intent to elope, had repeatedly attempted to elope, or had a history of elopement; 2) a lack of awareness by the staff of resident location; and 3) ineffective use of alarm devices intended to alert staff to elopement attempts.

Automated Technology to Speed Recognition of Signs of Illness in Older Adults

Our team has developed a technological innovation that detects changes in health status that indicate impending acute illness or exacerbation of chronic illness before usual assessment methods or self-reports of illness. We successfully used this information in a 1-year prospective study to alert health care providers so they could readily assess the situation and initiate early treatment to improve functional independence. Intervention participants showed significant improvements (as compared with the control group) for the Short Physical Performance Battery gait speed score at Quarter 3 (p = 0.03), hand grip-left at Quarter 2 (p = 0.02), hand grip-right at Quarter 4 (p = 0.05), and the GAITRite functional ambulation profile score at Quarter 2 (p = 0.05). Technological methods such as these could be widely adopted in older adult housing, long-term care settings, and in private homes where older adults wish to remain independent for as long as possible.

TigerPlace, A State-Academic-Private Project to Revolutionize Traditional Long-Term Care

ABSTRACT The Aging in Place Project at the University of Missouri (MU) required legislation in 1999 and 2001 to be fully realized. An innovative home health agency was initiated by the Sinclair School of Nursing specifically to help older adults age in place in the environment of their choice. In 2004, an innovative independent living environment was built and is operated by a private long term care company, as a special facility where residents can truly age in place and never fear being moved to a traditional nursing home unless they choose to do so. With care provided by the home care agency with registered nurse care coordination services, residents receive preventative and early illness recognition assistance that have markedly improved their lives. Evaluation of aging in place reveal registered nurse care coordination improves outcomes of cognition, depression, activities of daily living, incontinence, pain, and shortness of breath as well as delaying or preventing nursing home placement. Links with MU students, faculty, and nearly every school or college on campus enrich the lives of the students and residents of the housing environment. Research projects are encouraged and residents who choose to participate are enjoying helping with developing cutting technology to help other seniors age in place.

Admissions to skilled nursing facilities from assisted living facilities.

Minimum Data Set data from 15,977 residents were analyzed to investigate the reasons older adults were admitted to skilled nursing facilities from assisted living facilities. Residents admitted from assisted living facilities, private homes, hospitals, and hospitals with previous assisted living facility residence were compared. Findings suggest that residents admitted from assisted living facilities are more likely to be older, to have diagnoses of dementia and depression, and to be placed in Alzheimers special care units.

Evaluation of aging in place model with home care services and registered nurse care coordination in senior housing

A state-sponsored evaluation of aging in place (AIP) as an alternative to assisted living and nursing home has been underway in Missouri. Cost, physical, and mental health assessment data reveal the cost-effectiveness and positive health measures of AIP. Findings of the first four years of the AIP evaluation of two long-term care settings in Missouri with registered nurse care coordination are compared with national data for traditional long-term care. The combined care and housing cost for any resident who received care services beyond base services of AIP and who qualified for nursing home care has never approached or exceeded the cost of nursing home care at either location. Both mental health and physical health measures indicate the health restoration and independence effectiveness of the AIP model for long-term care.

Improving Nurse Care Coordination With Technology

Technology offers potential solutions to the pending crisis of healthcare for older adults, while healthcare workers are in short supply. Technology can enable remote monitoring of individuals and early detection of potential problems, so that early interventions can help older adults remain as healthy and independent as possible. Research is under way with passive monitoring technology in senior housing that is finding patterns in the data that can enhance nurse care coordination through early illness detection. With early detection, interventions can be more effective and reduce hospitalization and other healthcare expenses. Case studies are presented, and implications are discussed.

Passive sensor technology interface to assess elder activity in independent living.

Background:The effectiveness of clinical information systems to improve nursing and patient outcomes depends on human factors, including system usability, organizational workflow, and user satisfaction. Objective:The aim of this study was to examine to what extent residents, family members, and clinicians find a sensor data interface used to monitor elder activity levels usable and useful in an independent living setting. Methods:Three independent expert reviewers conducted an initial heuristic evaluation. Subsequently, 20 end users (5 residents, 5 family members, 5 registered nurses, and 5 physicians) participated in the evaluation. During the evaluation, each participant was asked to complete three scenarios taken from three residents. Morae recorder software was used to capture data during the user interactions. Results:The heuristic evaluation resulted in 26 recommendations for interface improvement; these were classified under the headings content, aesthetic appeal, navigation, and architecture, which were derived from heuristic results. Total time for elderly residents to complete scenarios was much greater than for other users. Family members spent more time than clinicians but less time than residents did to complete scenarios. Elder residents and family members had difficulty interpreting clinical data and graphs, experienced information overload, and did not understand terminology. All users found the sensor data interface useful for identifying changing resident activities. Discussion:Older adult users have special needs that should be addressed when designing clinical interfaces for them, especially information as important as health information. Evaluating human factors during user interactions with clinical information systems should be a requirement before implementation.

Developing a Comprehensive Electronic Health Record to Enhance Nursing Care Coordination, Use of Technology, and Research

As in acute care, use of health information technology in long-term care holds promise for increased efficiency, better accuracy, reduced costs, and improved outcomes. A comprehensive electronic health record (EHR), which encompasses all health care measures that clinicians want to use-both standard health care assessments and those acquired through emerging technology-is the key to improved, efficient clinical decision making. New technologies using sensors to passively monitor older adults at home are being developed and are commercially available. However, integrating the clinical information systems with passive monitoring data so that clinical decision making is enhanced and patient records are complete is challenging. Researchers at the University of Missouri (MU) are developing a comprehensive EHR to: (a) enhance nursing care coordination at TigerPlace, independent senior housing that helps residents age in place; (b) integrate clinical data and data from new technology; and (c) advance technology and clinical research.