Self-serve ICT-based Health Monitoring to Support Active Ageing

Mobyen Uddin Ahmed

, Jesica Rivero Espinosa

, Alenka Reissner

, Àlex Domingo

Hadi Banaee

, Amy Loutfi

and Xavier Rafael-Palou

Center for Applied Autonomous Sensor Systems, Örebro University, Fakultetsg. 1, 701 82 Örebro, Sweden

Barcelona Digital Technology Centre, C/RocBoronat, 11, MediaTIC Building 08018 Barcelona, Spain

Technosite, Fundosa Group R& D., Madrid, Spain

Zveza Društev Upokojencev Slovenije Ljubljana, Slovenia

Institut de l'Envelliment, Universitat Autònoma de Barcelona, Sant Antoni Maria Claret, 171 E 08041 Barcelona, Spain

Keywords: Healthcare Service, Health Monitoring, Blood Pressure, Blood Glucose, Pulse Rate, Activity Monitoring,

Recommendation, Alarm.

Abstract: Today, the healthcare monitoring is not limited to take place in primary care facilities simply due to

deployment of ICT. However, to support an ICT-based health monitoring, proper health parameters, sensor

devices, data communications, approaches, methods and their combination are still open challenges. This

paper presents a self-serve ICT-based health monitoring system to support active ageing by assisting seniors

to participate in regular monitoring of elderly’s health condition. Here, the main objective is to facilitate a

number of healthcare services to enable good health outcomes of healthy active living. Therefore, the

proposed approach is identified and constructed three different kinds of healthcare services: 1) real time

feedback generation service, 2) historical summary calculation service and 3) recommendation generation

service. These services are implemented considering a number of health parameters, such as, 1) blood

pressure, 2) blood glucose, 3) medication compliance, 4) weight monitoring, 5) physical activity, 6) pulse

monitoring etc. The services are evaluated in Spain and Slovenia through 2 prototypical systems, i.e.

year2prototype (Y2P) and year3prototype (Y3P) by 46 subjects (40 for Y2P and 6 for Y3P). The evaluation

results show the necessity and competence of the proposed healthcare services. In addition, the prototypical

system (i.e. Y3P) is found very much accepted and useful by most of the users.

1 INTRODUCTION

With the advent of relatively easy to acquire digital

health sensors and the communication infrastructure,

health monitoring at home is becoming increasingly

popular. Such solutions present benefits for

healthcare providers by enabling a more frequent

and continuous monitoring of patients. Of equal

importance are the benefits to the primary users, e.g.

residents who are able to be aware of their own

health parameters and their trends. An important

question to be considered in parallel to technological

development is how to interface the information

obtained from the system to the users who may have

little technical or medical expertise.

This paper presents an iterative and user centred

design approach to develop an ICT health

monitoring system for use at home. The system

integrates a number of off-the-shelf sensors into a

larger Ambient Assisted Living (AAL) framework.

Focus in this paper is put on the integration of the

various sensor components and the presentation of

information via services to the end users. Such

services include summaries of health parameters,

indication of trends and notifications of deviations.

To validate the proposed approach, user evaluations

have been performed in two countries with a

selected group of elderly users. The work performed

in this paper is part of a larger project called

SAAPHO, whose aim is to integrate health, social

and security services seamlessly in the same

architecture. This paper focuses only on the health

services, their design, and evaluation. The evaluation

results show the necessity and competence of the

proposed healthcare services. In addition, the

prototypical system (i.e. Y3P) is found very much

accepted and useful by most of the users.

374

Ahmed M., Rivero Espinosa J., Reissner A., Domingo À., Banaee H., Loutﬁ A. and Rafael-Palou X..

Self-serve ICT-based Health Monitoring to Support Active Ageing.

DOI: 10.5220/0005213403740382

In Proceedings of the International Conference on Health Informatics (HEALTHINF-2015), pages 374-382

ISBN: 978-989-758-068-0

 2015 SCITEPRESS (Science and Technology Publications, Lda.)

2 RELATED WORK

SOPRANO (Soprano, 2014) project aims to develop

smart ICT-based assisted living services with easy to

use interfaces for older people. PERSONA (Persona,

2014) aimed at advancing the paradigm of Ambient

Intelligence (Aarts, 2004) for the development of

sustainable and affordable solutions for the

independent living of elderly. Many other research

projects address the need of older people

independent living through promotion of active

ageing (Czaja, 2005) and healthy habits. AMICA

(Crespo et al, 2010) tries to emulate the medical

consultation at home: auscultation and interview.

CCE (Hanák et al, 2012) is a dementia solution,

which comprises of connectivity between the

different physical components, sensors, medication

dispenser, server, and Net TV. The H@H system

(Health@Home, 2014) gathers the wearable sensors

data, which continuously monitor patients’ physio-

pathological cardiovascular and respiratory

parameters. The HELP (Claas et al, 2012) project

proposes solutions to improve the quality of life of

Parkinson’s disease patients based on: a body sensor

and actuator network and home devices to monitor

the health parameters (e.g. blood pressure) and body

activity (e.g. to detect gait, absence of movement).

Another project IS-ACTIVE (Ruxandra et al, 2011)

emphasizes the role of the home as care

environment, by providing real-time support to

patients. PAMAP is another healthcare system

(Hendeby et al, 2010), which comprises information

acquisition and management. Other mentionable

AAL projects, which are currently dealing with

healthcare systems, are: REMOTE, ELF@Home,

Dalia, and eCAALIX that aim to be assistant

systems for daily life of elderly (Catalogue of

Projects, 2014). The authors in (Pantelopoulos and

Bourbakis, 2010; Alemdar and Ersoy, 2010; Banaee

et al, 2013) present reviews in the research and

development of the wearable sensor systems in

health monitoring. According to these reviews, most

of the works are focusing on sensor devices and

communication protocols, i.e. low-cost, energy-

efficient ad hoc deployment of multi-modal sensors

and Bluetooth, Zigbee, Wi-Fi, GPRS and 3G

network communications. Similarly, authors in

(Jovanov et al, 2005; Nee et al, 2008; Varshney,

2007) present their research on homecare monitoring

where they have shown how to receive sensor

measurements and represent these measurements on

a computer or mobile device. Moreover, in (Pansiot

et al, 2007; Ahmed et al, 2013a; Ahmed et al, 2013b;

Ahmed et al, 2013c; Ahmed et al, 2012) the authors

presented remote health monitoring systems for

elderly using wireless sensor devices. SAAPHO

aims for an ICT based healthcare solution where the

proposed services are essentially designed based on

the feedback obtained from the elderly and intended

for daily use.

3 THE ICT-BASED HEALTH

MONITORING SYSTEM

The proposed approach has identified the healthcare

services mainly in three different kinds of facilities

for each parameter: 1) real time feedback generation

service, 2) historical summary calculation service

and 3) recommendation generation service. The goal

of the Real Time Feedback Generation Service is to

provide a feedback message based on sensor

readings in real time.

Figure 1: Architecture of the ICT-based health monitoring

system.

Here, a rule-based classification method is applied to

classify the measurements. For example, a blood

pressure measurement 142/92 mmHg could be

classified as “High blood pressure” and/or BMI 26.1

by measuring user’s weight

could be classified

User-Interface in

Android Tablet

Sensors are paired

through Bluetooth

AFEA

Health Intelligent Server (HIS)

Raw data measurements,

Classifications, Reminder status

Alarm status, Generate feedback on

measurement, Prioritization, etc

Health Sensor

Unit

Blood Pressure

Activity

Blood Glucose

Medication

Compliance

Pulse Monitoring

Weight Monitoring

Collector is in

Android device

Commun

ication

via

Bluetooth

https & SOAP communication

https &

SOAP

communi

cation

https & SOAP communication

AAL

architecture

Self-serveICT-basedHealthMonitoringtoSupportActiveAgeing

375

“Overweighed”. A set of rules used in the

classification method is mainly collected from the

literature study (MCMS, 2014; eCAP, 2014;

Culhane et al, 2005; Alberti et al, 1998;

Understanding blood pressure, 2014; Why exercise,

2014; Deurenberg et al, 1991), which is further

validated through healthcare practitioners. The

historical summary calculation service calculates

historical summary on a daily and weekly basis. The

goal of this service is to provide to the user a

possibility to see and compare the summary in a

graph for a specific range of dates. In order to

calculate the summary, the service will use raw data

measurements and the classification. This service

mainly considers the frequency of classes and the

number of total measurements. For example, in

order to monitor medication compliance it calculates

“total number of medication is taken”, “total number

of medications”, and “total number of medications

are skipped”.

The main objective of the Recommendation

Generation Service is to generate a recommendation

including reminder and alarm based on user’s

historical summary and raw data measurements.

Eight different kinds of recommendations are

implemented: 1) Devices_Not_Used is generated if

there is not any received measurement over one

week duration, 2) Medications_skipped is generated

if the number of medications skipped and the

number of medication that should be taken in a day

is equal, 3) Out_Of_Normal_Range is generated if

70% of the measurements classes are outside the

normal range considering a week, 4) Fluctuation is

generated if the measurements over a week show

fluctuation in more than 70% of the cases, 5)

Weight_Loss is generated if the current weight is

less than 3 kg comparing to the previous weight (3

months ago), 6)

Weight_Increased/Weight_Decreased is generated

considering one month measurements and a

calculated slope value, 7)

Activity_Increased/Activity_Decreased is generated

considering one week measurements and a

calculated slope value, 8) A monthly summary is

generated based on the raw measurements where

statistical features i.e. maximum, minimum, average

and standard deviation for each week are calculated.

The detail about the healthcare services can be found

in (Ahmed et al, 2014). The architecture of the

proposed ICT-based health monitoring system is

presented in Figure 1.

As it can be seen from Figure 1, the architecture

is divided into two parts, i.e. the AAL (Ambient

Assisted Living) and the rest. The AAL

architecture

(presented in chapter 3.1) is used as a core

framework of the proposed ICT-based health

monitoring system. Here, AAL architecture is

connected with the rest of the components of the

health system via the user interface and the Health

Gateway. The Health Sensor Unit contains of six

health’s related preventive parameters recommended

from the user requirements stage. Different

commercial Bluetooth sensor devices were acquired

to provide those parameters, for example, the blood

pressure and weight monitoring devices are

collected from a third party vendor OMRON

and

BeneCheck

and others are in-house products

provided by the partner IZM

which are under

development. These sensor devices are paired with

an android tablet device where it runs the User-

Interface and the Collector. The Collector receives

health measurements using Bluetooth Classic and

Low Energy (BLTE) communication from the

sensor devices upon user request through the User-

Interface. The Collector is based on native Java

source code, which is in general the main

programming language for Android devices.

Adaptive Front-End Application (AFEA) is the

main module in the user interface (UI) application,

which is in charge of handling the user interactions

and of presenting the information in a way indicated

by the AAL architecture. The interaction of the user

with the UI involves, in some cases, requests for

information to the TD (Traffic Dispatcher) for

obtaining all the information requested by the user

or needed by the device for presenting a correct

interface for the specific user. As soon as the

Collector receives the measurements it transfers

them to the Health Gateway through https protocol

and SOAP web service communication. The

measurements are sent as a zip file including

timestamps, battery and some other related

information. The User-Interface developed to be

delivered through Android tablets given their low

cost, portability, direct interaction and ease of use.

The Health Gateway mainly conveys the messages

among the Collector, Health Intelligent Server (HIS)

and Middleware. It classifies the measurements,

calculates priority, asks the HIS for the message ID

and finally forwards the data to the Middleware

through Health Backend (presented in chapter 3.1).

The HIS stores all the raw measurements and

generates message ID for the communication. It also

calculates daily and weekly historical summary and

stores them in a MySQL database. The user has a

direct access to HIS to see the historical summary

through the User-Interface. HIS also generates

recommendation in weekly basis based on historical

HEALTHINF2015-InternationalConferenceonHealthInformatics

376

summary and raw data measurements. The generated

recommendations are sent to the user through Health

Gateway, Health Backend and Middleware.

3.1 AAL (Ambient Assisted Living)

Architecture

The main objective of the AAL (Ambient Assisted

Living) architecture throughout the SAAPHO

project is to be accessible, adaptable, context-aware,

interoperable, ubiquitous, scalable, and to be able to

answer the requests of the User-Interface and of the

health connected to it in an efficient way. With the

collected ones that were published in (Doménech et

al, 2013), architecture was designed based on the

INREDIS architecture (INREDIS, 2014) and on the

reference architecture of universal (UNIVERSAAL,

2014).

Traffic Dispatcher (TD) takes the requests of the

user formalized by the AFEA about different types

of information and obtains the response from the

AAL architecture. These requests could be:

messages of the different services connected to

SAAPHO or obtain URLs of external services.

Among all of them, those relevant for the health

services are the following:

- Obtain messages related to health. These

messages are stored in the TD after they are

received from the AAL architecture (sent by

the User Interface Recommender or by the

Health Gateway) and until AFEA asks for them

and indicate to the TD that they have been

shown to the user.

- Obtain the URL of the Health Gateway. This is

useful to the AFEA to know where it has to

send the measures taken by the Collector in the

user’s device.

- Obtain URLs with information of healthy

habits. While the previous request of URLs is

done by the AFEA, the user does this request.

User Interface Recommender (UIR) indicates the

way in which the information should be presented to

the user through the User-Interface, sends messages

with generic recommendations, recommendations

related to the services connected to the AAL

architecture, or recommendations of new direct

accesses to social tools. This component has a

database that contains the information that could be

useful for the generation of recommendations of

information to be shown to the user and the

information about the appearance of the interface

(Character size, symbols used, font type, background

colour…) that the user selected in the Settings

section of the User-Interface. In relation to the

health services, the UIR stores the recommendations

send by the Health Gateway, and they are used for

generating recommendations for promoting active

and healthy ageing considering the historical list of

recommendations of the user. For example, the UIR

can send a congratulation message when the level of

a specific parameter is good during a period of time

or send general advices for having a healthy life.

Together with the generation of recommendations,

the UIR is also in charge of creating the textual

messages that are included in the health messages to

be presented to the user in a suitable way. For this,

the UIR studies the type of message, the gender, the

language and the name of the user, and creates the

text adapted to these characteristics. This text will be

included in all the messages received from the

Health Gateway. This component and the AFEA

component are the UI Model and the User

Interaction Management modules of universAAL

(Sala et al, 2013)

Services Broker (SB) hosts a registry of

descriptions of the services inside the AAL

architecture but also of other services that could be

useful for the users. Together with the storage of the

information of these services, the SB also allows to

link the user with them when he/she requests for a

type of information (for example, online health

newspaper), such as the SB makes a search of a

specific service that satisfies the topics indicated by

the user and that is more suitable for the profile of

the user. This makes the platform accessible from a

cognitive point of view, because the user, for

example, does not need to know the name of the

newspaper; he/she just says that he/she wants to read

sport news. To do this, the Services Broker has also

a database of users and their profiles and the

searches done by them. This database is constantly

updated with the new searches of the users and with

new entries of services in the catalogue. The

functionality of the Context Management and of the

Service Management in universAAL is included in

the SB (Sala et al, 2013).

The Orchestrator is the module in charge of

abstracting all the dependencies among all the other

modules of the architecture. This module redirects

the communication from one module to another,

decoupling each module from the rest, making the

modules independent from each other.

Security Manager (SM) controls the access of the

users and gateways to the system generating

SessionIDs. To do that, it has a cyphered database

with the information of the user, it generates

Self-serveICT-basedHealthMonitoringtoSupportActiveAgeing

377

SessionIDs, and controls that the SessionIDs used in

the AAL architecture are correct, cutting the sending

of information when a wrong behaviour, or an

incorrect SessionID, is detected. This involves four

main different functionalities:

- User registration in the system. When a new

user wants to use SAAPHO, his/her data will

be stored in the SM database. The SAAPHO

user identifier used by the architecture is the

UUID (Universally Unique Identifier), which

guarantees that the user is identified in a unique

way by any component in the platform but also

out of the AAL architecture.

- User login. Each time that the user wants to use

SAAPHO he/she will have to log into the User-

Interface. This process involves the sending of

the username and password to the SM and the

generation of the sessionID if the data was

right.

- Health Gateway registration. This process is

similar to the previous one, but in this case the

gateways are the components that send the

parameters to be validated by the SM for

obtaining the sessionID, and the parameter sent

is a registration token.

- Validation of sessionIDs and userIDs.

Health Backend (HB) is connected to the Health

Gateway, and it is in charge of prioritizing the

information sent by the gateway and transmitting it

to the user through the AAL architecture. The

prioritization of the messages sent by the gateway is

a function based on the priorities of the provided

measures and the priority of the users; and the load

balancing of the requests of the users to have a safe

and efficient communication. The main operations in

the HB are:

- Registration of the gateway in the AAL

architecture. If the gateway is in the SM, the

backend looks for a backend of the type of the

gateway that wants to be registered with space

to handle the load of a new gateway, and if

there isn't any, a new backend of that type is

created internally and in a transparent way for

the gateway, that always sends the information

to the same backend.

- Deregistration of the gateway. The backend

frees up the space associated to that gateway

and the sessionID of that gateway is closed.

- Forwarding of the real feedback and

recommendations coming from the Health

Gateway. When a new message is received in

the HB, it is sent to the Orchestrator to be sent

to the UIR for creating the textual message

through which the real feedback or the

recommendation is presented to the user in the

UI, and after that to the TD to be shown to the

user.

4 EVALUATION

In order to assess the usability, accessibility,

applicability, impact and user satisfaction, as well as

detecting areas for improvement, the health

monitoring system was evaluated using two different

prototypes resulting of the second and third year of

the SAAPHO project. The second year prototype

(Year2Prototype) provided a complete vision of

SAAPHO, including the User-Interface, but of

limited functionality. The final and third year

prototype (Year3Prototype) contained the full pack

of functionalities, services and devices of the

system.

4.1 Year2prototype (Y2P)

The prototype considered two health parameters (i.e.

blood pressure and activity monitoring) with a part

of healthcare services (i.e. real-time feedback

generation and historical summary calculation). The

aim of this evaluation is to test a prototype, which is

very similar in functionality and appearance to the

final one. The tasks related to health carried out by

each end user were:

Task 1: Logging into the SAAPHO Platform

with own Login data.

Task 2: Setting the preferred volume and text

size.

Task 3: Checking the historical summary

information of blood pressure.

Task 4: Measuring the blood pressure and

reading the results.

Task 5: Checking the physical activity results.

Figure 2: Average scores for easiness.

HEALTHINF2015-InternationalConferenceonHealthInformatics

378

Figure 3: Average number of mistakes.

Figure 4: Average execution time.

Figure 5: Average unnecessary steps.

20 users in Slovenia, and 20 users in Spain

performed the tests. Each test took about one hour

and a half, and the tests were conducted one by one,

with a professional guiding the session, while a

video camera recorded all the user interaction with

the system. After the user carried out the complete

set of tasks, he had to respond to a questionnaire that

covered mostly the usability and applicability issues.

Afterwards, every video was reviewed and analysed,

so that every task for every user was documented as

far as execution time, use patterns, etc. Four

principles were considered for the main analysis: 1)

user-rated easiness 2) number of mistakes 3)

execution time and 4) unnecessary steps. The figures

below present the average values for different tasks.

As it can be seen from figures 2 to 5, the

SAAPHO platform was considered as being easy to

use as most of the scores were above 4 on a 1 to 5

scale (i.e. Figure

2). Task 1 (Login to SAAPHO)

was deemed the most difficult, this is probably

explained, because it was the first task, where users

had the first contact with the keyboard layout, but

still many users complained about difficulties with

most things related to text input. Similarly, Task 1

(Login to SAAPHO) had the highest number of

mistakes; again, users had difficulties dealing with

typing in text boxes (switching between fields was

one of the major difficulties). System stability and

performance also played a role in these cases. The

summary of the health related tasks considering all

four principles are presented in Table 1.

Table 1: Summary of the health related tasks.

Health Related

Tasks

No. of

Mistakes

User

Easiness

Time Unnecessary

Steps

Task 3: Check

Blood Pressure

history

0.078 4.35 01:49 0.025

Task 4: Measure

Blood Pressure

0.128 4.54 02:56 0.158

Task 5: Activity

monitor

0.353 4.94 01:40 0.118

Most users commented on the health aspects of the

SAAPHO platform as the one section they found the

most interesting, even if only two sensors were used

in Y2P testing (activity monitor and blood pressure

monitor). Also, usability of the two health tasks of

the system were deemed as very good, although the

layout of the blood pressure history charts made the

score a bit lower (hard to read and understand

because of too much data and therefore text was too

small on some charts).

4.2 Year3Prototype (Y3P)

The year3prototype considered most of the

healthcare parameters (i.e. blood pressure, blood

glucose, pulse monitoring and weight monitoring)

and services defined in section 3. The composition

of the trial formed by six participants from Spain

(n=3) and Slovenia (n=3). They were invited to use

the SAAPHO platform at their own home at least

during a month. The mean age of the 3 participants

in Spain was 69.3 (SD: 9.9); 66-72 years and the

mean age of the 3 participants in Slovenia was 65.7

(SD: 9.9); 60-74 years. Regarding the gender both in

Spain and Slovenia, 66.6% of the participants were

women (n=2) and 33.3% were men (n=1). 100% of

participants had experience using computers. 66.6%

Self-serveICT-basedHealthMonitoringtoSupportActiveAgeing

379

had experience in using tablet PC and all of them

had Internet at home.

Table 2: Summary of the health related questionnaire.

Healthcare

services

Questionnaire

Real-time

feedback

generation

Q1.How do you like the feedback messages

Q2. How useful is the SAAPHO measurement’s

classification

Q3. Any Comments on feedback messages

Historical

summary

Q4. How useful are the feedback charts

Q5. Any Comments on feedback Charts

Q6. How useful are the Daily-wise historical

summary charts

Q7. How useful are the Weekly-wise historical

summary charts

Q8. How useful are the raw data/historical

summary charts based on a selected date range

Q9. Any Comments on Historical Summary

Charts

Recommendat

ion

Q10. How do you like the recommendation

messages on “Devices_Not_Used”

Q11. How do you like the recommendation

messages on “Out_Of_Normal_Range”

Q12. How do you like the recommendation

messages on “Weight_Loss”

Q13. How do you like the recommendation

messages on “Weight_Increase/

Weight_Decreased”

Q14. How do you like the recommendation

messages on “Activity_Increase/

Activity_Decreased”

Q15. Any Comments on Textual

Recommendation messages

Each participant was equipped with a tablet running

the SAAPHO platform in the Y3P version. They had

to conduct several tasks in order to familiarize

themselves with the system and to know all

possibilities that SAAPHO offers. Researchers

contacted them frequently in order to check their

experience. First 3 days of monitoring, users had to

perform some specified tasks prepared by SAAPHO

in order to familiarize with the system.

Figure 6: Statistical analysis on the score of usefulness.

After the 4

day the users were supposed to have

enough knowledge of the system to be able to work

autonomously and they experimented with the

system by themselves. After completing the 4 weeks

of testing, a set of questionaries’ was provided to the

users in order to evaluate the usefulness of the

proposed healthcare services. The questionnaires

were divided into three parts. User’s answers were

collected both in textual form and as evaluations (a 1

to 5 scale). The Table 2 presents a summary of the

health related questionnaire.

As it can be seen from the figure 6, most of the

questions have the answer 5 as maximum score and

for average and median are around 4. However, the

minimum scores are very low i.e. 1 or 2. The reason

behind this is that one of the participants had

problems with sensor devices and Bluetooth

connections and thus was not able to access the

functionality of the system properly.

Figure 7: Statistical analysis on the score of usefulness

after removing the outlier.

If the evaluation of this participant is considered as

outlier and removed from the analysis then the result

could be improved as presented in Figure 7. Here,

the figure shows that the minimum score is 3 or 4

and the median of the some questions is 4.5 or 5.

User’s comments on the healthcare services are

summarized and presented in Table 3.

As it can be seen from the evaluation result, the

healthcare services through the prototypical system

were acceptable by most of users both in Spain and

in Slovenia. Here, all participants would recommend

the proposed ICT-based health monitoring system to

another older person since they considered it very

easy and useful in relation to the offered services.

Nevertheless, one of them mentioned again the users

that could benefit the most from it: older people

living alone or with his/her partner or caregiver;

having health problems and/or mobility difficulties;

without cognitive problems; living in an old building

without lifts.

HEALTHINF2015-InternationalConferenceonHealthInformatics

380

Table 3: Summary of the comments on healthcare

services.

Healthcare

services

Positive comments on the

services

Others

comments

Real-time

feedback

generation

The feedback messages are

excellent.

The feedback messages are useful

for quick information and a

general feeling.

Very practical and clear

I did not receive

notifications

about activity.

Historical

summary

The changes in blood pressure

and weight values are very

welcome for the health

evaluation.

The changes in blood pressure

and weight values are interesting.

Charts were very transparent.

Very practical and clear.

By choosing the date range it is

easier for me to determine the

time that interests me and the

health status at that time.

In relation to

Weight, I would

like to have

information

about the ideal

weight.

In relation to

BP, data are

difficult to

interpret.

Recommend

ation

Textual Recommendation

messages were excellent.

Recommendations were

understandable and correct.

To recommend contacting with

the doctor in case of not having

good health results is a good idea.

Information

received is not

clear.

I am not able to

judge as I very

rarely or almost

never received

the health

recommendation

messages.

4 CONCLUSIONS

This paper presents architecture of an ICT-based

health monitoring system, which allows for

information services connected to a number of

wireless health sensors. The article also describes

the integration of this system into a much wider and

extended AAL architecture (i.e. SAAPHO) that aims

to provide active aging to the elderly in their homes.

The paper has complemented the technological

aspects with user evaluation conducted in two

countries. The aim of this work has been to

investigate how users interact with monitoring

system at home, how well they are able to take the

measurements, and how well they are able to

negotiate through the various menus and options.

The aim of the paper has also been to evaluate

whether there was a perceived usefulness of the

system. Overall, the impression of the system has

been positive provided that there is relative ease in

operating the physical sensors. The level of detail of

the information has been deemed sufficient and the

textual recommendations were highly appreciated.

Both objective and subjective measures were used

for the evaluation. Future work will focus on

longitudinal evaluations deployed in larger user

groups. Also, cross-cultural differences between the

user groups will be studied when larger samples

sizes are used.

ACKNOWLEDGEMENTS

This work has been supported by the project named

SAAPHO (Secure Active Aging: Participation and Health

for the Old). The SAAPHO Project (aal-2010-3-035) is

funded by the Call AAL (Ambient Assisted Living) within

the Call 3, ICT-based solutions for advancement of older

persons’ independence and participation in the self-serve

society and by the following national agencies:

MINETUR (Spain); VDI/VDE Innovation + Technik

GmbH (Germany); Ministry of Higher Education, Science

and Technology (Slovenia); Vinnova (Sweden).

REFERENCES

Aarts, E., 2004, Ambient Intelligence: A Multimedia

Perspective. IEEE Multimedia, 11, 12-19.

Ahmed M. U.; Banaee H.; Loutfi A.; Rafael-Palou, X.,

2014. Intelligent Healthcare Services to Support

Health Monitoring of Elderly, Accepted in the

International Conference on IoT Technologies for

HealthCare, HealthyIoT, at Rome, Italy.

Ahmed, M.U.; Banaee, H.; Loutﬁ, A., 2013a. Health

monitoring for elderly: An application using case-

based reasoning and cluster analysis. ISRN Artif.

Intell., 2013, 380239.

Ahmed, M. U.; Loutfi, A., 2013b. Physical Activity

Identification using Supervised Machine Learning and

based on Pulse Rate, Advanced Computer Science &

Application, 4.

Ahmed, M. U.; Loutfi, A.; 2013c. Physical activity

classification for elderly based on pulse rate, in

Proceedings of the 10

International Conference on

Wearable Micro and Nano Technologies for

Personalized Health.

Ahmed, M. U.; Islam A. M.; A Loutfi.; 2012. A case-

based patient identification system using pulse

oximeter and a personalized health profile, in

Proceedings of the Health Sciences at 20

International Conference on Case-Based Reasoning,

Eds., Springer, Lyon, France, September 2012.

Alberti, K.G.M.M., Zimmet, P.Z., 1998. Definition,

diagnosis and classification of diabetes mellitus and its

complications. Part 1: diagnosis and classification of

diabetes mellitus. Report of a WHO Consultation.

Journal of Diabetic Medicine, 15, 539–553.

Alemdar, H., Ersoy, C., 2010. Wireless sensor networks

for healthcare: A survey. The International Journal of

Computer and Telecommunications Networking, 54,

2688-2710.

Banaee, H., Ahmed, M.U., Loutfi, A., 2013. Data Mining

Self-serveICT-basedHealthMonitoringtoSupportActiveAgeing

381

for Wearable Sensors in Health Monitoring Systems:

A Review of Recent Trends and Challenges. Sensors,

13, 17472-17500.

Catalogue of Projects 2013, Ambient Assisted Living Joint

Programme (AAL JP), Available online:

http://www.aal-europe.eu/wp-

content/uploads/2013/09/AALCatalogue2013_Final.p

df, (accessed on October 2014).

Claas, A., Albert, S., Jordi, R. S., Simon, H., Alejandro, R.

M., 2012. HELP: Optimizing Treatment of Parkinson's

Disease Patients. In proceeding of 3rd International

Conference on the Elderly and New Technologies.

Crespo, M., Sánchez, D., Crespo, F., Astorga, S., León, A.

2010. Collaborative Dialogue Agent for COPD Self-

management in AMICA: A First Insight. Advances in

Intelligent and Soft Computing, 70, 75-80.

Culhane, K. M., O'Connor, M., Lyons, D., Lyons, G. M.,

2005. Accelerometers in rehabilitation medicine for

older adults, Academic Journal of Age Ageing, 34,

556-60.

Czaja, S. J., 2005. The Impact of Aging on Access to

Technology. SIGACCESS Access. Comput, 83, 7-11.

Deurenberg P, Weststrate J.A., Seidell J.C., 1991. Body

mass index as a measure of body fatness: age- and sex-

specific prediction formulas, Br J Nutr; 65(2):105-14.

Doménech, S., Rivero, J., Coll-Planas, L., Sainz, F.J.,

Reissner, A., Miralles, F., 2013. Involving older

people in the design of an innovative technological

system promoting active aging: the SAAPHO project.

Journal of Accessibility and Design for All, 3, 13-27.

eCAP monitor for bottled medications, Information

Mediary Corporation (IMC), Available online:

http://informationmediary.com/ecap (accessed on

October 2014).

Hanák, P., Kiss, N., Kovácsházy, T., Pataki, B., Salamon,

M., Seres, Cs., Tóth, Cs., Varga, J., 2012. System

Architecture for Home Health and Patient Activity

Monitoring. 5

European Conference of the

International Federation for Medical and Biological

Engineering, pp 945-948.

Health@Home, Available online: http://www.aal-

europe.eu/projects/healthhome/ (accessed on October

2014).

Hendeby, G., Bleser, G., Lamprinos, I., Stricker, D., 2010.

Healthy Aging using Physical Activity Monitoring.

AALIANCE conference, Spain, 11-12, pp. 1-5.

INREDIS. Available online: http://www.inredis.es

(accessed on October 2014).

Jovanov, E., Milenkovic, A., Otto C., de Groen P.C.,

2005. A wireless body area network of intelligent

motion sensors for computer assisted physical

rehabilitation. J Neuroeng. Rehabil, 2, 1-10.

Medication Compliance Monitoring System (MCMS),

Cybernet Medical, Available online:

http://www.cybernetmedical.com/index.php/mcms

(accessed on October 2014).

Nee, O., Hein, A., Gorath, T., Hulsmann, N., Laleci, G.B.,

Yuksel, M., Olduz, M., Tasyurt, I., Orhan, U., Dogac,

A., Fruntelata, A., Ghiorghe, S., Ludwig, R., 2008.

SAPHIRE: intelligent healthcare monitoring based on

semantic interoperability platform: pilot applications,

Communications, IET 2008, 2, 192-201.

Pansiot, J., Stoyanov, D., McIlwraith, D., Lo, B. P., Yang,

G. Z., 2007. Ambient and wearable sensor fusion for

activity recognition in healthcare monitoring systems.

Proceedings of the 4

International Workshop on

Wearable and Implantable Body Sensor Networks

(IFBME’07), pp. 208–212.

Pantelopoulos, A., Bourbakis, N.G., 2010. A Survey on

Wearable Sensor-Based Systems for Health

Monitoring and Prognosis, Systems, IEEE

Transactions on Man, and Cybernetics, Part C:

Applications and Reviews, 40, 1-12.

Persona Project, Available online: http://www.aal-

persona.org/ (accessed on October 2014).

Ruxandra, B., Luminita, D., Alina, I., Horatiu, D., Ileana,

C., Mihai, B., 2011, IS-ACTIVE Project in Lab Trial

Phase. In Romanian Journal of Physical and

Rehabilitation Medicine, 21, 64-65.

Sala, P., Tazari, S., Farshchian, B., Furfari, F., 2013. The

universAAL Reference Architecture. universAAL

Deliverable D1.3 – E 2013.

Soprano Project, Available online: http://www.soprano-

ip.org/ (accessed on October 2014).

Understanding blood pressure readings. American Heart

Association. Available online:

http://www.heart.org/HEARTORG/Conditions/HighBl

oodPressure/AboutHighBloodPressure/Understanding-

Blood-Pressure-Readings_UCM_301764_Article.jsp,

(accessed on October 2014).

UNIVERSAAL. Available online:

http://universaal.org/index.php/es/about/about-project-

description (accessed on October 2014).

Varshney, U., 2007. Pervasive healthcare and wireless

health monitoring. Journal Mobile Networks and

Applications, 12, 113-127.

Why exercise with a Heart Rate Monitor, Available

online:

https://zsig.com/content/why_exercise_with_a_heart_r

ate_monitor_/, (accessed on October 2014).

http://wserver.flc.losrios.edu/~willson/fitns304/handouts/bodyCompositio

n.html

http://www.healthcare.omron.co.jp/bt/english/

http://www.glbiotech.com.tw/productdesc.php?pdtid=11

http://www.izm.fraunhofer.de/en.html

HEALTHINF2015-InternationalConferenceonHealthInformatics

382