=Paper=
{{Paper
|id=Vol-3276/SSS-22_FinalPaper_85
|storemode=property
|title=Modeling, Monitoring and Measuring of Social
Isolation for Community-based Care in Nursing House
|pdfUrl=https://ceur-ws.org/Vol-3276/SSS-22_FinalPaper_85.pdf
|volume=Vol-3276
|authors=Shintaro Nagama, Masayuki Numao
|dblpUrl=https://dblp.org/rec/conf/aaaiss/NagamaN22
}}
==Modeling, Monitoring and Measuring of Social
Isolation for Community-based Care in Nursing House==
https://ceur-ws.org/Vol-3276/SSS-22_FinalPaper_85.pdf
Modeling, Monitoring and Measuring of Social Isolation for Community-based
Care in Nursing House
Shintaro Nagama and Masayuki Numao
Department of Communication Engineering and Informatics
The University of Electro-Communications
1-5-1, Chofugaoka, Chofu-shi
Tokyo 182-8585, JAPAN
numao@cs.uec.ac.jp
Abstract dementia in nursing home, how daily activities and sleep af-
fect to long-time changes of state.
We proposed a model to monitor and measure social isolation
and developed a monitoring system for nursing home. We de-
fined s ocial a ctivities i n d aily l iving ( SADL) w hich a re es- Modeling of Social Isolation
sential for living in the community, such as conversation with To understand social isolation, the relationship among other
others, playing game, eating together, etc. We also defined entities such as community, care, symptoms, mental issue
measuring scheme by extending FIM, since FIM measures
(feeling) and human function should be identified. It is be-
the normal ADL, our measuring scheme measures SADL. Fi-
nally, we evaluated the system by conducting clinical experi- cause that social isolation is caused by community events
ment in actual environment. such as bereavement with partners, mental events such as
loneliness, and human functions events such as physical and
cognitive decline. Human Functions is further divided into
Introduction cognitive function and physical activity. Social isolation de-
According to CIGNA’s 2018 survey, 40% of the participants velops as a symptom of depression or acceleration of cog-
said that they have sometimes or always a feeling of iso- nitive decline. There is a care such as rehabilitation to deal
lation and loneliness. Social isolation is caused by a com- with them. A model of these is shown in Figure 1.
bination of various kinds of incidents such as: high blood
pressure, heart disease, obesity, decreased immunity, affect
depression, cognitive decline, Alzheimer’s disease, and var-
ious parts until death. In order to understand the state of so-
cial isolation, it is important to build a model to represent a
relationship between social isolation and other factors such
as cognitive functions, social activity, etc.
Thus, we first designed the social isolation model by W3
standard ontology language OWL. To measure ADL per-
formance, functional independence measurement (FIM) is
known an established method to evaluate the state of physi-
cal and cognitive function as individual independence. In or-
der to measure the social activity performance, we define So-
cial activities in daily living (SADL) which includes activi- Figure 1: Social Isolation Model
ties such as eating with friends, chatting with friends, meet-
ing to family member, etc. Some activities are overlapped
with normal ADL, but the difference is that the ADL is in-
terested in the subject’s activities, whereas SADL is inter- Monitoring of Social Isolation
ested in the interaction between the subject and other people In the above model, Community and Human Functions
in community. Based on the SADL, measuring framework is classes are used for monitoring social isolation. We place
designed by extending FIM, to measure the social activity. SADL properties in Community class and normal ADL
To evaluate feasibility of our proposal, we developed properties in Human Function class. SADL identifies the
a multi-modal sensor based monitoring system named activity in the community such as conversation, eating to-
“Mimamori-Fukuro (watching owl)”. Collaboration with St. gether, playing game, etc.
Marianna University School of Medicine, we conducted a
clinical experiment to monitor the activity of residents with Physical Activity
___________________________________ Physical activity refers to an individual’s daily activities
In T. Kido, K. Takadama (Eds.), Proceedings of the AAAI 2022 Spring Symposium such as eating, excretion, and moving etc. All of the FIM
“How Fair is Fair? Achieving Wellbeing AI”, Stanford University, Palo Alto, California,
USA, March 21–23, 2022. Copyright © 2022 for this paper by its authors. Use permitted
under Creative Commons License Attribution 4.0 International (CC BY 4.0).
43
exercise items are used as indicators. The maximum score is
91 points.
Cognitive Function
Cognitive function refers to memory, comprehension, ex-
pressive ability, and communication ability. All of FIM’s
cognitive items are used as indicators. The maximum is 35
points.
Social Activity in Daily Living
Social activities refer to activities with social exchanges Figure 3: Movement Monitoring Result
such as communication with friends. Conversations with
others in nursing home, participation in recreation, conver-
sations with nursing staff, family visits, etc. Specifically, we Experiment and Evaluation
will give a score based on the items related to Social Loneli- We conducted a clinical experiment in actual nursing home
ness in LUBBEN SOCIAL NETWORK SCALE-6(Lubben and a simulated experiment at a laboratory room. For the ex-
et al. 2006) and De Jong Gierveld Loneliness Scale(De Jong periment at nursing home, we installed RFID: 5 antennas at
2010). It can be measured with two types of information: celling, and RFID tags at desks, chairs, slippers, and cloth-
action-based scoring and in-formation obtained from con- ing. 1 robot at public area.
versations such as whether a person who can speak is famil- Figure 3 shows the gantt chart (left) and radar chart (right)
iar. The maximum is 45 points. of the person with different care level (upper and lower).
Gantt char shows the movement of resident in a specific day.
Each line shows the period the person stays in a specific lo-
Implementation of System cation, which is recognized as ADL because many ADL is
We integrate different kind of sensors that are installed dif- location based. Other ADL and SADL should be recognized
ferently: centralized and distributed. First one is vital sign by combination of location and vital sign and conversion that
and cognitive status monitoring by a robot ”Watching Owl” are monitored by the robot.
(Figure 2) which is placed in a resident’s private room. The Radar chart shows the social isolation score in three axis:
robot has a camera, microwave sensor, and temperature sen- pysical activity score, cognitive function score, and SADL
sor, which can identify person, measure vital sign, and rec- score. In the upper diagram, the person spent long time in
ognize facial expressions. It can also make a conversation conversation with other person, which reflects a good score
such as greeting and simple chatting, by which it can mea- of social activity in the radar chart, the person also gets a
sure cognitive function and SADL. The measurement of good score of HDS-R. On the other hand, the person in the
cognitive function is based on the HDS-R. lower diagram spent most of time alone, which results in the
Second one is location and movement monitoring using poor score at the radar chart.
RFID. RFID tags are attached to the clothings of residents,
such as pajama and shoes to identify their location and References
movement. They are also attached to the tools such as wheel Lubben, J.; Blozik, E.; Gillmann, G.; Iliffe, S.; von
chair and sticks to identify the usage of tools. RFID reader Renteln Kruse, W.; Beck, J. C.; and Stuck, A. E. 2006.
and antenna installed in the facility to read the RFID tag. Performance of an Abbreviated Version of the Lubben
Social Network Scale Among Three European Community-
Dwelling Older Adult Populations. The Gerontologist,
46(4): 503–513.
De Jong, V. T. T., Gierveld J. 2010. The De Jong Gierveld
short scales for emotional and social loneliness: tested on
data from 7 countries in the UN generations and gender
surveys. Eur J Ageing, 7(2): 121–130.
Acknowledgments
This work was supported by JSPS KAKENHI Grant Num-
ber JP20H04289 ”Functional Independence Measurement
System based on ADL Ontology for Aged Person”
Figure 2: Mimamori-Fukuro (Watching OWL)
44