p–ISSN: 2723 - 6609 e-ISSN: 2745-5254

Vol. 5, No. 6 June 2024 http://jist.publikasiindonesia.id/

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2690

Comparison of K Nearest Neighbor Algorithm with Apriori

Algorithm to Analyze Lifestyle Patterns in Hypertensive

Patients

Steven

1*

, Ricky Wijaya

2

, Helbert Yawin

3

, Saut Dohot Siregar

4

Universitas Prima Indonesia, Indonesia

Email:

[email protected]

1*

, [email protected]

2

,

[email protected]

3

, [email protected]

4

*Correspondence

ABSTRACT

Keywords: k nearest

neighbor algorithm,

apriori algorithm, lifestyle

patterns, hypertensive

patients

Hypertension is one of the most influential cardiovascular

diseases that can lead to organ disorders such as heart

dysfunction or stroke and hypertension is often discovered

by chance. This disease can interfere with the work of other

organs if left untreated, especially the heart and kidneys.

Not paying attention to diet, exercise, stress, smoking, and

drinking alcohol can all be causes of increased risk of

hypertension. To predict people with hypertension and find

out the comparison of behavior and lifestyle patterns with

hypertension patients using a priori algorithm in the case

study of Sei Semayang Health Center. So the results of

rapidminer use the apriori algorithm to analyze the

Comparison of K the nearest Neighbor Algorithm with the

apriori Algorithm to Analyze Lifestyle Patterns in

Hypertensive Patients the results obtained is U1 which

means there are people with hypertension aged 25-38 years

who have more hypertension and the results are H2 which

means that people have but do not control to the doctor

with a pattern style such as consuming alcohol, Smoking,

and lack of exercise, sugar consumption, consumption of

saturated fat and foods that contain a lot of salt and rarely

consume vegetables or fruits and foods containing MSG

then more and more people who have hypertension with an

unhealthy lifestyle.

Introduction

Hypertension is one of the most influential risks of cardiovascular diseases that

can lead to organ disorders such as heart dysfunction or stroke and hypertension is often

discovered by chance. Hypertension is a condition when blood pressure rises drastically

to above-normal limits and forces the intensity of work on the heart to pump blood in

order to provide the body's oxygen needs (Agus et al., 2021). This disease can interfere

with the work of other organs if left untreated, especially the heart and kidneys. Not

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2691

paying attention to diet, exercise, stress, smoking, and drinking alcohol can all be causes

of increased risk of hypertension (Lasmadasari et al., 2021).

Based on data collected by researchers at the Sei Semayang Health Center from

January to March of 2023, out of 1100 patients, there were 760 people with

hypertension. The results of interviews with patients with high blood pressure at Sei

Semayang Health Center found that they often ate fast food with added salt, sodium,

and fatty foods; they also only did physical activities such as work and never exercised

regularly, and 4 of them had a habit of smoking by smoking more than 10 cigarettes a

day. According to the information from the regional health center of the Sei Semayang

Health Center, the number of sick people at the Sei Semayang Health Center in 2021

was 1100 cases and most of the cases were hypertension.

Based on data on the age of early adulthood (early adult), namely the age of 21-40

years old, with male and female genders in total, and information about the highest

incidence of hypertension from several villages in Sei Semayang Health Center, the

exact cause of blood pressure is not yet clearly known (Awalullaili, Ispriyanti, &

Widiharih, 2023). Experts reveal the cause of high blood pressure, namely

environmental factors such as behavior or lifestyle in the form of obesity, lack of

activity, and foods high in salt (Khairani, Kamil, & Tahlil, 2020).

The Apriori Algorithm is used in data mining for the itemset of transactional

databases. To establish the mining rule association of a database exchange, it takes time

to carry out the frequent items process, which is done to find the smallest support value

and the smallest confidence value (Melviani, Aryzki, Rahman, Putri, & Riadi, 2022).

Apriori uses an iterative approach that uses k-itemset to explore (k+1)-itemset, (k+1)-

itemset candidates are obtained from combining two itemsets in the k region. (k+1)-item

candidates that have frequencies in subsets that rarely appear or below the threshold will

be separated and excluded to determine association rules and one method can be used to

classify regional poverty depth levels in the East Java Province using the K-Nearest

Neighbor (KNN) Algorithm (Rahmadayanti, Anggraini, & Susanti, 2023). KNN is a

method of classification based on objects "close" to each other that will have similar

characteristics; That is, if an object is known for its characteristics, then the object

although different can also be predicted based on its closest (Matondang, Mayanda, &

Nurul, 2019). K-Nearest Neighbor has the advantage that it can process large training

data efficiently has robust noise training and can provide accurate data results. The

operating principle of the K-Nearest Neighbor Algorithm is to analyze the shortest

distance between the data you want to evaluate and the closest (k) to the training data

based on the supervised teaching method. The data is then grouped into classes based on

type (k) majority.

In the previous study, the identification of patterns in the symptoms of

hypertension utilizing the Apriori Algorithm based on a case study at the Rafina

Medical Center Clinic which in this study used Orange Software, obtained 3% and a

minimum confidence value of 70%, which resulted in 2 association rules (Nurzanah,

Alam, & Hermanto, 2022). The application of the Apriori Algorithm to patients with

Steven, Ricky Wijaya, Helbert Yawin, Saut Dohot Siregar

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2692

hypertension was carried out by distributing questionnaires at the health center which

found 6 patterns/rules with lift ratios ≥ 1 from testing 300 data on patients with

hypertension using a support value of 30% and confidence 85%. There is also a

previous research on the Implementation of Apriori Algorithm to Find Frequent items in

Shopping Cart using a sample of 100 transactions from point of sales database with

Apriori Algorithm resulting in research results in the form of 98.9% of people with

hypertension will feel symptoms of headache with a lift ratio value of 2.41; Based on

these results, the rules of the association can be said to be valid (Azwanti & Elisa,

2019).

Based on the analysis above, the purpose of the researcher is to conduct a study

entitled "Comparison of K-Nearest Neighbor Algorithm with Apriori Algorithm to

Analyze Lifestyle Patterns in Hypertensive Patients". Such studies can help gain

patterns in behavior and lifestyle in hypertensive patients.

This study aims to analyze cases found in Sei Semayang Health Center in

analyzing behavior and lifestyle patterns against sufferers of hypertension using the

Apriori Algorithm in the case study of Sei Semayang Health Center and comparing the

method with the K-Nearest Neighbor Algorithm to find the most effective method in

cases of hypertension that can prevent more hypertension in Sei Semayang people with

a better lifestyle pattern.

Research Methods

Types of Research

This study uses quantitative methods x with clear data sources. The object of this

study is data on hypertension patients at the Sei Semayang Health Center. The object of

study will be assessed objectively based on datasets using the K-Nearest Neighbor

Algorithm and Apriori Algorithm to analyze lifestyle patterns in hypertensive patients.

Object of Research

The object of research in this study is the Sei Semayang Health Center located on

Jl. Medan Krio, Sunggal, Deli Serdang, North Sumatra 20351, with the online website

link of https://dinkes.deliserdangkab.go.id/halaman/puskesmas-sei-semayang.html

Method x Data Collection

Observation

Observe research subjects to determine effectiveness, development, impact, etc. In

this regard, observationx can be done in various ways.

Questionnaire

Data was collected by asking respondents a series of questions or written

statements. Questions can be open or close ended.

Interview

Interviews are conducted in order to obtain correct information from reliable

sources.

Document

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2693

A written or printed letter that can be used as evidence to assist in the completion

of the research report.

Literature Study

Data is collected by reviewing literature, documents, books, and reports related to

the problem to be solved.

Figure 1 Stages of Research

Stages of Research

The research phase in Figure 1 describes the process to be carried out from the

research and the research as a whole. From Figure 1 it can be seen that the stages to be

carried out are as follows:

1. Preparation: This stage is the stage of processing research data at the Sei Semayang

Health Center. Define and create a research plan.

2. Literature review: conducted by reviewing and examining literature related to the

comparison of the K-Nearest Neighbor Algorithm with the Apriori Algorithm to

analyze lifestyle patterns in patients with hypertension.

3. Comparison of the K-Nearest Neighbor Algorithm with the Apriori Algorithm to

analyze lifestyle patterns in people with hypertension.

4. Data collection: conducted through accounting, observation, and documentary

interviews.

5. Mining data processing: The collected information is processed through the results of

questions about the analysis of hypertension patients using the Apriori Algorithm in

the case study of Sei Semayang Health Center.

6. Results and discussion: Describe the results of the data mining process carried out

using the comparison method between Apriori and K-Nearest Neighbor

7. Conclusions research and make proposals for the further development of the

company.

Method Algorithm K-Nearest Neighbor

The K-Nearest Neighbor method is an algorithm of learning outcomes and

monitored queries of new cases classified under part of a large catalog of the

K-Nearest

Neighbor

Algorithm.

Proximity

is determined by distance metrics. Euclidean

distance

Steven, Ricky Wijaya, Helbert Yawin, Saut Dohot Siregar

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2694

or Euclidean metrics is the distance of the straight

"normal" line

between two points in

Euclidean

space

(Purwono, Dewi, Wibisono, & Dewa, 2022)

.

𝑛

𝐷

𝑥,𝑦

=

√∑

(

𝑥

𝑖

x

−

𝑦

𝑖

x

)2

𝑡=1

Explanation:

D

= Proximity distance of ox

x = Training data

1

y = Testing data

o

n = Number of individual attributes between 1 t

o

n

Results and Discussion

Dataset

This study uses datasets from data on hypertensive patients in the case study of

Sei Semayang Health Center from January to March 2023 which was proposed to

predict the analysis of behavior patterns.

Table 1

Data on hypertension patients in the case study of Sei Semayang Health Center Data from

January to March of 2023

No

Name

Age

Hypert

ension

Smoki

ng

Alcoh

ol

Cons

umpt

ion

Exerci

se

Rice

Con

sum

ptio

n

Sugar

Con

sum

ptio

n

…

MSG

Consu

mptio

n

1

A.

Jalalu

din

Alfari

zi

25-34

years

old

Presen

t but

n

ot

contr

olled

Nev

er

smok

ed

Yes

Enou

gh

3 X /

Week

1 X

/

Wee

k

…

Yes

2

A’an

Mah

endr

a

> 64

years

old

Prese

nt

but

not

contr

olled

Neve

r

smok

ed

Yes

Less

1 X /

Week

2 X

/

Wee

k

…

Yes

3

Aan

Pah

yub

i

55-64

years

old

Present

and

control

led

Nev

er

smok

ed

Yes

Less

Eve

ry

day

1 X

/

Wee

k

…

Yes

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2695

4

Abdul

Roup

> 64

years

old

Presen

t but

not

contr

olled

Ne

ver

smok

ed

Yes

Less

1 X /

Week

2 X

/

Wee

k

…

Yes

5

Abdull

ah

Sopia

n

34-55

years

old

Present

and

control

led

Ne

ver

smok

ed

Yes

Less

1 X /

Week

Nev

er

…

Yes

6

Ade

Kho

lilah

55-64

years

old

Present

and

controlled

Ne

ver

smok

ed

No

ne

Enou

gh

Eve

ry

day

1 X

/

Wee

k

…

Yes

7

Christ

ian

Wing

25-34

years

old

Present

and

controlled

Ne

ver

smok

ed

No

ne

Less

Eve

ry

day

2 X

/

Wee

k

…

Yes

8

Adel

lia

Ekka

Princ

ess

25-34

years

old

Present

and

control

led

Ne

ver

smok

ed

Not

Less

Eve

ry

day

2 X

/

Wee

k

…

Yes

9

Adi

nda

Arij

ki

Isla

miat

i

25-34

years

old

Prese

nt but

not

contr

olled

Ne

ver

smok

ed

Yes

Enou

gh

Ne

ver

1 X

/

Wee

k

…

None

10

Adira

Cahya

Putri

25-34

years

old

Presen

t but

not

contr

olled

Ne

ver

smok

ed

Yes

Enou

gh

2 X /

Week

2 X

/

Wee

k

…

None

11

Adi

tya

Cha

ndr

a

25-34

years

old

Present

but not

controll

ed

Nev

er

smok

ed

Yes

Enou

gh

2 X /

Week

2 X

/

Wee

k

…

None

…

76

1

Alfieri

34-55

years

old

Present

and

control

Nev

er

smok

ed

Yes

Enou

gh

1 X /

Week

Nev

er

…

Yes

Steven, Ricky Wijaya, Helbert Yawin, Saut Dohot Siregar

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2696

led

Research Design

This stage starts with an observation, after which it is continued by collecting

data, which is then plugged into Excel for processing with the calculation process and

following the stages of the linear regression method. The results of the data processing

can be used in the rapid-miner application to see accurate results.

Information:

1. The problem analysis analyzed data on people with hypertension in the case study of

Sei Semayang Health Center from January to March of 2023.

2. Studying scientific literature requires utilizing various sources that can be used to

obtain information for research.

3. Establish a method to resolve the problem. This study used the Apriori Algorithm.

4. Collect data on people with hypertension in a case study of Sei Semayang Health

Center from January to March of 2023.

5. Processing data is done using data mining in the Apriori Algorithm method.

6. Testing the data, done using the rapid miner x5.3 tool.

7. Conclusion was included in analyzing data on patients with hypertension in the case

study of Sei Semayang Health Center.

Algorithm Method

After equalizing the values, the next step is grouping using the Apriori Algorithm.

From this process will be obtained a prediction of hypertension sufferers in the case

study of Sei Semayang Health Center using the Apriori Algorithm method. The process

of the Apriori Algorithm is as follows:

Collecting Datasets

Below is a table using a dataset from data on hypertension patients in the case

study of Sei Semayang Health Center which is proposed to predict data on patients with

hypertension in the case study of Sei Semayang Health Center conducted using linear

algorithm method.

Table 2

Table of classification data for people with hypertension in the case study of Sei Semayang

Health Center

Attribute

Informatio

n

Gender

Male

Female

Age

25-37 years old (U1)

38-55 years old (U2)

55-64 years

old (U3)

Hypertension

Present but not controlled

(H1)

Present and

controlled(H2)

Smoking

None (M1)

Yes (M2)

Alcohol

Consumption

Less (KA1)

Enough (KA2)

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2697

Sports

Less (O1)

Sufficient (O2)

Rice Consumption

Never (KB1)

1 X / Week (KB2)

2X/Week

(KB3)

Sugar Consumption

Never (KG1)

1X/Week (KG2)

2 X/Week

(KG3)

Consumption of

Side Dishes

Never (KLP1)

1 X / Week (KLP2)

2 X/Week

(KL3)

Consumption of

saturated fat

Never (KLJ1)

1 X/Week (KLJ2)

2 X / Week

(KLJ3)

Consumption of

Unsaturated Fats

Never (KLTJ1)

1 X/Week (KLTJ2)

2 X / Week

(KLTJ3)

Salt Consumption

Never (KG1)

1X/Week (KG2)

2 X/Week

(KG3)

Vegetable

Consumption

Never (KS1)

1 X/Week (KS2)

2 X/Week

(KS3)

Fruit Consumption-

Fruits

Never (KB1)

1 X / Week (KB2)

2 X / Week

(KB3)

Consumption of

Fried Snacks

Never (KJG1)

1X/Week (KJG2)

2 X/Week

(KJG3)

MSG Consumption

None (KM1)

Yes (KM2)

Table 3

Data initializing table

NO

Name

Gend

er

Age

Hyperte

nsion

Smoki

ng

Alcoho

l

Consu

mption

Exerci

se

…

MSG

Consu

mptio

n

1

A.

Jalaludin

Alfarizi

Male

25-

37

years

old

Present

but not

controlle

d

Never

smoke

d

KA2

O2

…

KM2

2

A’an

Mahend

ra

Male

> 64

years

old

Present

but not

controll

ed

Neve

r

smoke

d

KA2

O1

…

KM2

3

Aan

Pahyu

bi

Male

55-

64

years

old

Present

and

controll

ed

Never

smoke

d

KA2

O1

…

KM2

4

Abdul

Roup

Male

> 64

years

old

Present

but not

controll

ed

Neve

r

smoke

d

KA2

O1

…

KM2

5

Abdull

ah

Sopian

Male

38-

55

years

old

Present

and

controll

ed

Nev

er

smoked

KA2

O1

…

KM2

6

Ade

Kholil

ah

Female

55-

64

years

old

Present

and

controll

ed

Neve

r

smoke

d

KA1

O2

…

KM2

Adella

Female

25-

37

Present

Never

smoke

…

Steven, Ricky Wijaya, Helbert Yawin, Saut Dohot Siregar

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2698

7

Christiya

nti

years

old

and

controll

ed

d

KA1

O1

KM2

…

760

Andrea

s

Trimur

ni

Male

25-

37

years

old

Present

and

controll

ed

Never

smoke

d

KA1

O1

…

KM2

761

Andres

Setiaw

an

Male

25-

37

years

old

Present

and

controll

ed

Never

smoke

d

KA1

O1

…

KM2

Apriori Algorithm testing using rapid miner

At this stage, the data normalization process aims to provide data characteristics

for a more specific range, so that data can be processed efficiently using Apriori

Algorithm methods with rapidminer applications.

Results of Hypertensive Patient Data in the Case Study of Sei Semayang Health

Center Using the Rapid Miner Application

The results of export value data using the rapid miner application from

hypertensive patient data in the case study of Sei Semayang Health Center from January

to March of 2023 obtained the results of analysis of Lifestyle Patterns in Hypertensive

Patients

Table 4

Data table of patients with hypertension using the rapid Miner application

Premise

s

Conclus

ion

Suppo

rt

Confide

nce

Laplac

e

Gain

p-

s

Lift

Conditio

n

Male

KM2

0.421

27

0718

0.83106

267

0.9431

71

402

-

0.592541

436

0.046692

332

1.1246

53

034

1.5452459

45

H2

KB3,

KM2

0.466

85

0829

0.85353

535

4

0.9482

14

286

-

0.627071

823

0.107246

421

1.2982

34

445

2.3387311

87

KB3,

H2

KM2

0.466

85

0829

0.91598

916

0.9716

37

694

-

0.552486

188

0.090231

144

1.2395

81

592

3.1073338

09

H2

KM2

0.504

14

3646

0.92171

717

2

0.9723

21

429

-

0.589779

006

0.099966

423

1.2473

33

145

3.3346996

97

Female

M1

0.422

65

1934

0.85714

285

7

0.9528

21

462

-

0.563535

912

0.073944

629

1.2120

53

571

2.0497237

57

O2

M1

0.477

90

0552

0.86716

792

0.9528

04

987

-

0.624309

392

0.088168

859

1.2262

29

637

2.204419

89

KJG3

KG3

0.441

98

895

1

-

0.441988

95

0.246634

718

2.2625

1.5452459

45

KLJ3

KG3

0.441

98

1

-

0.246634

2.2625

2.3387311

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2699

895

0.441988

95

718

87

…

KLJ3,

KLTJ3

KG3

0.441

98

895

1

-

0.441988

95

0.246634

718

2.2625

2.204419

89

KLJ3

KG3,

KS3

0.441

98

895

1

-

0.441988

95

0.246634

718

2.2625

1.5452459

45

Age Analysis Graph of the Case Study of Sei Semayang Health Center

From data on hypertension patients in the case study of Sei Semayang Health

Center, data from January to March of 2023, using the rapid miner application, results

in the form of U1 were obtained, which means that most people with hypertension are

aged 25-38 years old.

Steven, Ricky Wijaya, Helbert Yawin, Saut Dohot Siregar

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2700

Figure 3.

Graph of age analysis of hypertension sufferers, case study of Sei Semayang Health

Center

Hypertension Analysis Graph of the Case Study of Sei Semayang Health Center

From data on hypertension patients in the case study of Sei Semayang Health

Center, data from January to January March 2023, the result obtained was H2, which

means that people have hypertension but do not visit a doctor.

Figure 4

Hypertension analysis graph of the case study of Sei Semayang Health Center

K-Nearest Neighbor (K-NN) Algorithm Testing Using Rapid Miner

In this stage, we will normalize data which aims to equalize the characteristics of

the data to be more specific, so that it can be processed efficiently with the K-Nearest

Neighbor Algorithm method in the rapidminer application.

Figure 5. Display of the K-Nearest Neighbor (K-NN) Algorithm testing process

K-3 Cross Validation Test Results Using K-Nearest Neighbor (K-NN) Algorithm

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2701

Below are the results of K-3 Cross Validation testing in the case study of Sei

Semayang Health Center, which obtained 92.74% class precision for those who have

hypertension but are not controlled and 88.84% class precision for those who have

hypertension and control.

Figure 6. K-3 Cross Validation test process view

Conclusion

Following the analysis using linear regression, the next step was to group the

results for comparison. The research utilized the Apriori Algorithm in RapidMiner to

study the behavior patterns and lifestyle of hypertension patients at Sei Semayang

Health Center. The findings, labeled as U1, revealed that most hypertension patients are

aged 25-38 years old. Additionally, the same data analysis identified a pattern, denoted

as H2, showing that many hypertensive individuals do not regularly visit doctors and

engage in unhealthy behaviors such as consuming alcohol, smoking, lack of exercise,

high sugar intake, consumption of saturated fats, MSG, and high-salt foods, and rarely

consuming vegetables or fruits. This indicates that an unhealthy lifestyle significantly

contributes to hypertension. Furthermore, using the K-Nearest Neighbor (K-NN)

Algorithm with K-3 Cross Validation, the study achieved a class precision of 92.74%

for uncontrolled hypertension cases and 88.84% for controlled cases, demonstrating the

algorithm's effectiveness in accurately classifying hypertension patients.

Steven, Ricky Wijaya, Helbert Yawin, Saut Dohot Siregar

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2702

Bibliography

Agus, Wantor, Admi, Syarif, Khairun, Nisa Berawi, Kurnia, Muludi, Sri, Ratna

Sulistiyanti, & Sutyarso, Sutyarso. (2021). Implementasi Metode Pembobotan

Berbasis Aturan Dan Metode Profile Matching Pada Sistem Pakar Medis Untuk

Prediksi Risiko Hipertensi. Jurnal Teknoinfo, 15(2). Retrieved from

http://ejurnal.teknokrat.ac.id/index.php/teknoinfo/article/view/1523

Aprian Hidayat, R. (2019). Identifikasi Pola Data Hipertensi Dengan Implementasi

Metode Association Rules Menggunakan Algoritma Apriori (Doctoral

dissertation, Universitas Siliwangi).

Aprillia, Y. (2020). Gaya Hidup dan Pola Makan Terhadap Kejadian Hipertensi. Jurnal

Ilmiah Kesehatan Sandi Husada, 9(2), 1044-1050.

Awalullaili, Fithroh Oktavi, Ispriyanti, Dwi, & Widiharih, Tatik. (2023). Klasifikasi

Penyakit Hipertensi Menggunakan Metode Svm Grid Search Dan Svm Genetic

Algorithm (Ga). Jurnal Gaussian, 11(4), 488–498.

Azwanti, Nurul, & Elisa, Erlin. (2019). Analisis Pola Penyakit Hipertensi Menggunakan

Algoritma C4. 5. InfoTekJar (Jurnal Nas. Inform. Dan Teknol. Jaringan), 3(2),

220–227. Retrieved from

https://jurnal.uisu.ac.id/index.php/infotekjar/article/view/944/pdf

Khairani, Cut, Kamil, Hajjul, & Tahlil, Teuku. (2020). Analisis faktor resiko dalam

mengendalikan hipertensi di kabupaten Aceh Besar. Jurnal Kesehatan Cehadum,

2(4), 1–13. Retrieved from https://jkc.puskadokesa.com/jkc/article/view/66

Lasmadasari, Novi, Nilawati, Iin, Sukatemin, Sukatemin, Ester, Ester, Elvionita, Elva,

Pralingga, Yogi, & Tiara, Tiara. (2021). Penerapan Algoritma Hipertensi, Menu

Dash Dan Latihan Otot Progresif Dalam Asuhan Keperawatan Untuk

Menurunkan Tekanan Darah. Jurnal Riset Media Keperawatan, 4(2), 54–62.

Matondang, Nurhafifah, Mayanda, M. S., & Nurul, C. (2019). Deteksi Hipertensi

Dengan Metode Artificial Neural Network. Seminar Nasional Informatika, Sistem

Informasi Dan Keamanan Siber (SEINASI-KESI), 2(1), 1–6. Retrieved from

https://conference.upnvj.ac.id/index.php/seinasikesi/article/view/184

Melviani, Melviani, Aryzki, Saftia, Rahman, Agenia, Putri, Gina Aima, & Riadi, Setia

D. R. (2022). Pengaruh Gaya Hidup Terhadap Penyakit Hipertensi Berdasarkan

Teori TPB (Theory Of Planned Behavior). Journal Pharmaceutical Care and

Sciences, 2(2), 30–38. Retrieved from https://doi.org/10.33859/jpcs.v2i2.164

Nurzanah, Salsabilla Choerunnisa, Alam, Syariful, & Hermanto, Teguh Iman. (2022).

Analisis Association Rule Untuk Identifikasi Pola Gejala Penyakit Hipertensi

Menggunakan Algoritma Apriori (Studi Kasus: Klinik Rafina Medical Center).

JIKO (Jurnal Informatika Dan Komputer), 5(2), 132–141. Retrieved from

https://ejournal.unkhair.ac.id/index.php/jiko/article/view/4792/3121

Comparison of K Nearest Neighbor Algorithm with Apriori Algorithm to Analyze Lifestyle

Patterns in Hypertensive Patients

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 6, June 2024 2703

Purwono, Purwono, Dewi, Pramesti, Wibisono, Sony Kartika, & Dewa, Bala Putra.

(2022). Model Prediksi Otomatis Jenis Penyakit Hipertensi dengan Pemanfaatan

Algoritma Machine Learning Artificial Neural Network. Insect (Informatics and

Security): Jurnal Teknik Informatika, 7(2), 82–90. Retrieved from

https://doi.org/10.33506/insect.v7i2.1828

Putra, S. (2022). Pengaruh Gaya Hidup Dengan Kejadian Hipertensi di Indonesia (A:

Systematic Review). Jurnal Pendidikan Tambusai, 6(2), 15794-15798.

Putri, H. N. (2022). Penerapan Algoritma Apriori Dalam Menentukan Pola Perilaku

Dan Gaya Hidup Terhadap Penderita Hipertensi. Penerapan Algoritma Apriori

Dalam Menentukan Pola Perilaku Dan Gaya Hidup Terhadap Penderita

Hipertensi, 5(3), 450-458.

Rahmadayanti, Fitria, Anggraini, Inda, & Susanti, Tri. (2023). Pengklasterisasian Data

Penyakit Hipertensi dengan Menggunakan Metode K-Means. Journal of

Information System Research (JOSH), 4(2), 737–741.

Wijaya, Y. F., & Triayudi, A. (2023). Perbandingan Algoritma Klasifikasi Data Mining

Pada Prediksi Penyakit Diabetes. Journal of Computer System and Informatics

(JoSYC), 5(1), 165-174.