Diabetes is a persistent disease in which levels of glucose
in the blood has higher than normal levels. The high blood
glucose, Hyperglycemia, is the result of a lack of the hormone
“insulin” or the performance of “insulin” is decreased, causing
too much sugar in the blood normally. Diabetes can be divided
into two major types. Type 1 diabetes, called insulin-
dependent or juvenile diabetes, occurs when the body is
unable to flight inflection to attack and destroy cells in
pancreas that make insulin. Type 2 diabetes is the most
common type of diabetes and approximately 95% of patients
with diabetes in Thailand, known as adult-onset diabetes.
Type 2 is usually occurred in older adults and some children
with obesity [1]-[2]. With type 2 diabetes, the pancreas still
produces insulin but it may be produced in insufficient
quantities that causes the level of glucose in the blood to
become too high.
Nowadays, the International Diabetes Federation (IDF)
reported more than 460 million people worldwide have
diabetes and it is expected to increase to 578 million by 2030.
The diabetes cause of the leading of death in the world and
contribute to health expenditure accounting for 10% of total
health expenditure worldwide [3]. The World Health
Organization (WHO) has declared COVID-19 as a serious
epidemic worldwide. It is important to take preventive care in
proper behavior especially patients with diabetes. With the
COVID-19 pandemic, the effects of diabetes are even more
pronounced because diabetic patients have usually to
postpone regular appointments and with uncontrolled of
glucose levels and prevention of diabetes, it might be crucial
for people with diabetes at higher risk from COVID-19.
Moreover, patients with diabetes have increasingly infected
the chance of getting seriously ill from COVID-19. Therefore,
diabetes is a chronic disease that causing an impact on both
the lives of patients and their families and a lot of medical
expenses from the family to the national level.
According to the President of the Diabetes Association of
Thailand, there were around 5 million of Thai population aged
over 15 year suffering from diabetes and the estimated
diabetes prevalence was 9.6% (2.4 million Thai people),
which included 4.8% previously diagnosed and 4.8% newly
diagnosed. Also, obesity and lifestyle habits are due to the
increasingly prevalence rate of the diabetes disease problem
especially working age population. Therefore, it is important
to educate patients on diabetes to control and treat diabetes at
right time.
Village Public Health Volunteers (VHVs) play a crucial
role in promoting health and changing health behaviors of
people in the community. Patients should be supervised by
Village public health volunteers, which will be a part of risk
reduction from complications. A follow-up home visit by
village public health volunteers is useful to patients and their
families to support people in the community. Hence, VHVs
should be trained and educated their knowledge to support
local health staff in immunization, and help to taking in simple
tasks like temperature measurement, blood pressure
measurement, first aids and etc.[4]. Consequently, village
health volunteer is a bridge between patients and health staff
to drive a public health of community. Today modern
communication and internet technologies have emerged and
developed continuously and advance technology has
dramatically revolutionized in daily life. The smart phone acts
as the smart device used to access the knowledge and to
communicate among people. Nonetheless, there are few
health mobile application for diabetes mellitus patients and
Village Public Health Volunteers.
The aim of this study were 1) to develop the health mobile
application to serve diabetic patients and volunteer staffs and
2) to observe the impact of using mobile application based on
self-learning and self-management in diabetes information
between patients with diabetes and village public health
volunteers.
Development of a Healthcare Monitoring Diabetes Mobile Application
for Community
1KANYARAT BUSSABAN, 2KANYARAT BUSSABAN, 3NAREENART RUKSUNTORN,
1JARUWAN CHUTRTONG, 1CHANYAPAT SANGSUWAN
1Faculty of Science and Technology Suan Sunandha Rajabhat University Bangkok, THAILAND
2Computer Science Program Suan Sunandha Rajabhat University Bangkok, THAILAND
3Robotics Engineering program Faculty of Industrial Technology Suan Sunandha Rajabhat University
Bangkok, THAILAND
Abstract: The purpose of this project is to develop the mobile application, by applied Machine learning, for
analyzing, collecting, monitoring, and retrieving information between patients with diabetes especially diabetes
type 2 and village public health volunteers and to study the impact of using mobile application based on self-
learning and self-management in diabetes information. This is a research and development mobile application
and the sample consisted of 30 diabetes patients and 5 village health volunteers participated in this research.
The project has demonstrated the effectiveness of using mobile application to support patients and village health
volunteers. The results showed that user satisfaction has a high level.
Keywords: Diabetes type 2, village health volunteers, mobile application, personal health, machine learning
Received: April 25, 2022. Revised: October 17, 2022. Accepted: November 24, 2022. Published: December 31, 2022.
1. Introduction
WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE
DOI: 10.37394/23208.2022.19.24
Kanyarat Bussaban, Kanyarat Bussaban,
Nareenart Ruksuntorn, Jaruwan Chutrtong,
Chanyapat Sangsuwan
E-ISSN: 2224-2902
222
Volume 19, 2022
The smart devices has widely increased to manage
diabetes in recent years and there are much of research to
conduct in this field. In the previous review, it revealed that
currently most research also focuses on the use of mobile
application [5]. The diabetic management app for patients
with type 2 diabetes helped to enhance glycemic control and
diabetes self-efficacy in a Chinese community hospital by a
randomized controlled trial [6]. The lifestyle of patients with
diabetes can be improve diabetes mellitus self-management
by focusing on food and physical activity [7]. Providing the
mobile app for type 1 diabetes mellitus (DM) assists the
patients in their daily treatment routine [8]. The mHealth has
been proposed by WHO to support healthcare systems
delivery worldwide and assessed the utilization of mhealth in
the management of patients with DM in Africa [9]. Droobi, a
diabetes management app for self-management of diabetes in
Qatar, served an efficient and convenient approach for
communication between health workers and patients [10].
Self-management is a crucial factor in glycaemic control and
mobile application improve self-management and health of
patients. Also, there are many mobile application for self-
management of diabetes [11]-[16].
Machine learning and data mining techniques were
applied to conduct research in almost aspects of diabetes [17].
An intelligent mHealth application was proposed to assess
his/her possibility of being diabetic, prediabetic or nondiabetic
without the assistance of any doctor or medical tests [18].
Deep learning-based for predicting diabetes mellitus, a mobile
application developed to build the diabetes prediction model
and the deep learning approach presented considerable
accuracy of 93% [19]. mHealth app was adapted machine
learning to increase physical activity in diabetes and
depression [20]. An expert system based on fuzzy logic was
used to diagnose with diabetic neuropathies with a sensitivity
of 89%, a specificity of 98%, and an accuracy of 93% [21].
Machine learning exploits the explosion of medical
information and it improves health quality for people with
diabetes. Most research has utilized several ML algorithms to
improve in detection and diagnosis, self-management and
personalization respectively [22].
The project was the Research and development (R&D)
approach, which generates new knowledge, products,
services, or systems by using quantitative method and
qualitative method. In this section, we will describe the
detailed methodology adapted to conduct this project.
The sample consisted of 30 diabetes patients and 4 village
public health volunteers. The mobile app was installed to
participants’ mobile phone and patients were trained to use
the mobile app. The training includes how to install app, how
to monitor blood glucose, how to communicate with health
volunteers, and how to use other functions of application. To
prevent the spread of COVID-19, 1) questionnaire will be
collected via online survey and 2) telephone interview was
applied to obtain additional new information for collected
enough data.
To implement in prediction module, the data acquired from
UCI repository (PIDD) was used to analyze classification
algorithms [23].
To implement this project, feasibility and requirement
analysis was the first step to gather the requirements based on
the user's point of view. This project was designed and
implemented using flutter framework, a free and open-source
mobile UI framework created by Google. Firebase database
has been used to store data and information. UX design and
UI design are crucial tools to support the first stage of the
design mobile application process. The main steps of creating
the user centered design are: creating user-journey map,
building UX wireframe, building prototype, graphic design
and usability testing [24]-[25]. The mobile app has 6 parts as
following: health monitoring, appointment, education,
medication, healthy eating, and prediction. Health monitoring
module is responsible for monitoring blood glucose levels and
overall health like blood pressure, and weight. Patient can
reserve and manage online appointment scheduling through
the appointment module. Patients can search and learn
information based on the disease in education module and
medication module notifies patients to specify amount of
medication taken with the time and shows the patient's drug
list. Healthy eating module recommends users to self-control
of diabetes and prediction module shows data based on a
collected user data.
Fig. 1. Example of mobile application
Machine learning is a subfield of computer science that
evolved from the study of pattern recognition and
computational learning theory in artificial intelligence
.Machine learning explores the construction and study of
algorithms that can learn from and make predictions on data.
[26].
K-Nearest Neighbor (KNN): KNN is a non-parametric
supervised machine learning algorithm used to solve both
classification and regression problem and classifies the new
data point based on a similarity measure [27]. The KNN
procedure is described by figure 2.
2. Literarture Reviews
3. Methodology
3.1 Data Collection
3.3 Machine Learning Techniques
3.2 System Design
WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE
DOI: 10.37394/23208.2022.19.24
Kanyarat Bussaban, Kanyarat Bussaban,
Nareenart Ruksuntorn, Jaruwan Chutrtong,
Chanyapat Sangsuwan
E-ISSN: 2224-2902
223
Volume 19, 2022
Fig. 2. KNN Procedure
Support Vector Machine: Support Vector Machine is a
supervised machine learning algorithm used to both
classification and regression problem [28]. The algorithm
separates a data point into class attribute using hyperplane and
the goal of the line is to maximizing the margin between the
points on either side of the so called decision line. The training
phase of SVM estimates the parameters W and b for a
hyperplane from a given training data.
W.xi + b ≥ 1 if yi = 1 (1)
W. xi + b ≤ −1 if yi = −1 (2)
where Xi = (xi1,xi2....... xim) and Yi ∈[+,-] denotes its class
label.
The training data are linear kernel. K (Xi, Xj) = < Xi, Xj>:
) (3)
subject to
yi(wxi+b)≥ 1, i=1,2…m (4)
equivalent to
(5)
where
Performance Evaluation: To judge the performance of the
classification model, we applied a confusion matrix,
calculated using the predictions of a model on a data set. There
are four probable outcomes (TP, FP, FN, and TN):
True Positive (TP): the number of positive examples
correctly classified.
False Positives (FPs): the number of negative
examples incorrectly classified as positive.
False Negatives (FN): the number of positive
examples incorrectly classified as negative.
True Negatives (TN): the number of negative
examples correctly classified as negative.
Accuracy: The formula for calculating accuracy, based on
(TP+TN)/ (TP+FP+FN+TN).
Precision: The measure of true positives over the number of
total positives, based on TP/ (TP+FP).
Recall: The measure of true positive over the count of actual
positive outcomes, expressed as: TP/ (TP+FN).
F1 Score: The harmonic mean between precision and recall,
expressed as: 2(p*r)/(p+r) where ‘p’ is precision and ‘r’ is
recall.
To achieve the goal, data preprocessing tasks have
been used to the diabetes dataset. This step is one of the most
crucial process in the machine learning approach.
Accuracy
Precision
Recall
F1-Score
KNN
72.05
88.20
73.58
79.56
SVM
73.55
79.23
79.65
79.35
Fig. 3. The performance of the model
To assess the performance of the mobile application,
questionnaire included the properties as follows: Usefulness
(14 topics), Ease of use (10 topics), Ease of Learning (10
topics) and Satisfaction (10 topics). The results of the
performance of mobile application for diabetic patients were
summed up and presented as table I.
TABLE I. THE RESULTS OF THE PERFORMANCE OF MOBILE APP
SD
1. Usefulness
4.8
0.45
2. Ease of use
4.6
0.55
3. Ease of Learning
4.4
0.50
4. Satisfaction
4.8
0.45
The study shows that the overall level of assessment
satisfaction of all dimensions was higher than level of
expectation.
The use of smart technologies increasingly prevail a
promising field of research to improve the quality of life for
the patients and their families. The development of a diabetes
monitoring application has powerfully supported patients with
diabetes and community health volunteers to enhance clinical
cure and self-management behavior. Consequently, it was
found that the satisfaction with the application of patients had
a high level of overall with the application which is caused the
ability of the application to conveniently use and connect with
caregivers or medical personnel in a timely manner. Due to
the COVID-19 outbreak, the application was used to
4. Results
5. Conclustion
WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE
DOI: 10.37394/23208.2022.19.24
Kanyarat Bussaban, Kanyarat Bussaban,
Nareenart Ruksuntorn, Jaruwan Chutrtong,
Chanyapat Sangsuwan
E-ISSN: 2224-2902
224
Volume 19, 2022
communicate with patients for online consultation, and
arrange for Regular Check-Ups. However, further studies are
needed to applied wearable technologies, IOT and machine
learning to enhance this project.
The authors express their sincere appreciation to Suan
Sunandha Rajabhat University for financial support of the
study.
[1] Type 2 diabetes: https://www.mayoclinic.org/diseases-
conditions/type-2-diabetes/symptoms-causes/syc-20351193
[2] Tunsuchart K, Lerttrakarnnon P, Srithanaviboonchai K, Likhitsathian
S, Skulphan S. Type 2 Diabetes Mellitus Related Distress in Thailand.
Int J Environ Res Public Health. 2020 Mar 30;17(7):2329. doi:
10.3390/ijerph17072329. PMID: 32235629; PMCID: PMC7177402.
[3] Thailand, Diabetes report 200-2045:
https://diabetesatlas.org/data/en/country/196/th.html
[4] B. Sanguanprasit, P. Leerapan, and P. Taechaboonsermsak, “Village
health volunteers as peer supports for glycemic control among type 2
diabetes patients in Thailand”, J Public Hlth Dev, vol. 14, no. 2, pp.
49–60, Sep. 2016.
[5] Makroum MA, Adda M, Bouzouane A, Ibrahim H. Machine Learning
and Smart Devices for Diabetes Management: Systematic Review.
Sensors (Basel). 2022 Feb 25;22(5):1843. doi: 10.3390/s22051843.
PMID: 35270989; PMCID: PMC8915068.
[6] Zhai Y, Yu W. A Mobile App for Diabetes Management: Impact on
Self-Efficacy Among Patients with Type 2 Diabetes at a Community
Hospital. Med Sci Monit. 2020 Nov 16;26:e926719. doi:
10.12659/MSM.926719. PMID: 33196634; PMCID: PMC7678242.
[7] Represas-Carrera F.J., Martínez-Ques Á.A., Clavería A. Effectiveness
of mobile applications in diabetic patients’ healthy lifestyles: A review
of systematic reviews. Prim. Care Diabetes. 2021;15:751–760. doi:
10.1016/j.pcd.2021.07.004.
[8] de Araújo, W.R.V.C., Martins, L.E.G. & Zorzal, E.R. Mobile apps for
the treatment of diabetes patients: a systematic review. Res. Biomed.
Eng. 37, 273–288 (2021). https://doi.org/10.1007/s42600-021-00150-
7
[9] Dike FO, Mutabazi JC, Ubani BC, Isa AS, Ezeude C, Musa E, Iheonye
H, Ainavi II. Implementation and impact of mobile health (mHealth)
in the management of diabetes mellitus in Africa: a systematic review
protocol. BMJ Open. 2021 Dec 17;11(12):e047556. doi:
10.1136/bmjopen-2020-047556.
[10] Alaa A. Abd-alrazaq, Noor Suleiman, Khaled Baagar, Noor Jandali,
Dari Alhuwail, Ibrahem Abdalhakam, Saad Shahbal, Abdul-Badi
Abou-Samra, Mowafa Househ, Patients and healthcare workers
experience with a mobile application for self-management of diabetes
in Qatar: A qualitative study, Computer Methods and Programs in
Biomedicine Update, Volume 1, 2021,100002,ISSN 2666-
9900,https://doi.org/10.1016/j.cmpbup.2021.100002.
[11] Faridi Z, Liberti L, Shuval K, Northrup V, Ali A, Katz DL. Evaluating
the impact of mobile telephone technology on type 2 diabetic patients’
selfmanagement: the NICHE pilot study. J Eval Clin Pract.
2008;14(3):465–9
[12] Holmen H, Torbørnsen A, Wahl AK, Jenum AK, Smastuen MC,
Arsand E,et al. A mobile health intervention for self-management and
lifestyle change for persons with type 2 diabetes, part 2: one-year
results from the Norwegian Randomized Controlled Trial RENEWING
HEALTH. JMIR Mhealth Uhealth. 2014;2(4):e57
[13] Baptista S, Trawley S, Pouwer F, Oldenburg B, Wadley G, Speight J.
What do adults with type 2 diabetes want from the “Perfect” App?
Results from the second diabetes MILES: Australia (MILES-2) study.
Diabetes Technol Ther. 2019. https://doi.org/10.1089/dia.2019.0086.
[14] Boyle L, Grainger R, Hall RM, Krebs JD. Use of and beliefs about
mobile phone apps for diabetes self-management: surveys of people in
a hospital diabetes clinic and diabetes health professionals in New
Zealand. JMIR mHealth uHealth. 2017;5(6):e85.
[15] Jeffrey B, Bagala M, Creighton A, Leavey T, Nicholls S, Wood C,
Longman J, Barker J, Pit S. Mobile phone applications and their use in
the self-management of Type 2 Diabetes Mellitus: a qualitative study
among app users and non-app users. Diabetol Metab Syndr. 2019 Oct
16;11:84. doi: 10.1186/s13098-019-0480-4. PMID: 31636719;
PMCID: PMC6794726.
[16] Petersen M and Hempler N (2017) Development and testing of a
mobile application to support diabetes self-management for people
with newly diagnosed type 2 diabetes: a design thinking case study.
BMC Med Inform Decis Mak 17: 91.
[17] Kavakiotis I., Tsave O., Salifoglou A., Maglaveras N., Vlahavas I.,
Chouvarda I. Machine learning and data mining methods in diabetes
research. Comput. Struct. Biotechnol. J. 2017;15:104–116. doi:
10.1016/j.csbj.2016.12.005.
[18] N. S. Khan, M. H. Muaz, A. Kabir and M. N. Islam, "Diabetes
Predicting mHealth Application Using Machine Learning," 2017 IEEE
International WIE Conference on Electrical and Computer Engineering
(WIECON-ECE), 2017, pp. 237-240, doi: 10.1109/WIECON-
ECE.2017.8468885.
[19] C. G. Estonilo and E. D. Festijo, "Development of Deep Learning-
Based Mobile Application for Predicting Diabetes Mellitus," 2021 4th
International Conference of Computer and Informatics Engineering
(IC2IE), 2021, pp. 13-18, doi: 10.1109/IC2IE53219.2021.9649235.
[20] Aguilera A, Figueroa CA, Hernandez-Ramos R, et almHealth app
using machine learning to increase physical activity in diabetes and
depression: clinical trial protocol for the DIAMANTE StudyBMJ Open
2020;10:e034723. doi: 10.1136/bmjopen-2019-034723
[21] Katigari MR, Ayatollahi H, Malek M, Haghighi MK. Fuzzy expert
system for diagnosing diabetic neuropathy. World J Diab. (2017) 8:80.
doi: 10.4239/wjd.v8.i2.80
[22] Jyotismita Chaki, S. Thillai Ganesh, S.K Cidham, S. Ananda Theertan,
Machine learning and artificial intelligence based Diabetes Mellitus
detection and self-management: A systematic review, Journal of King
Saud University - Computer and Information Sciences, Volume 34,
Issue 6, Part B, 2022, Pages 3204-3225, ISSN 1319-1578,
https://doi.org/10.1016/j.jksuci.2020.06.013.
[23] https://archive-beta.ics.uci.edu/
[24] Żaneta Lenczewska, UX and UI design in mobile app development
process, https://pagepro.co/blog/ux-and-ui-design-in-mobile-app/
[25] K. Kularbphettong, U. Ampant, and N. Kongrodj, “An automated
hydroponics system based on mobile application,” International
Journal of Information and Education Technology, vol. 9, no. 8, pp.
548–552, 2019. +
[26] Ron Kohavi; Foster Provost (1998). “Glossary of terms”. Machine
Learning 30: 271–274.
[27] N. Cheung, "Machine learning techniques for medical analysis,"
School of Information Technology and Electrical Engineering, B.Sc.
Thesis, University of Queenland, 2001.
[28] Cortes, C., Vapnik, V.: Support-Vector Networks. ML 20(3), 273– 297
(1995) Google Scholar
Acknowledgment
References
Creative Commons Attribution License 4.0
(Attribution 4.0 International, CC BY 4.0)
This article is published under the terms of the Creative
Commons Attribution License 4.0
https://creativecommons.org/licenses/by/4.0/deed.en_US
WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE
DOI: 10.37394/23208.2022.19.24
Kanyarat Bussaban, Kanyarat Bussaban,
Nareenart Ruksuntorn, Jaruwan Chutrtong,
Chanyapat Sangsuwan
E-ISSN: 2224-2902
225
Volume 19, 2022
