Design a Predictive Analytics Model of Hospital Accreditation

Continuity from Employee Readiness based on Artificial Intelligence

Alimunir Gultom, Ermi Girsang, Sri Lestari R. Nasution

Faculty of Medical, Universitas Prima Indonesia, Indonesia

Keywords: Employee Readiness, Accreditation Continuity, Hospital.

Abstract: Hospitals are required to have an accreditation in an effort to improve the quality of health services. Some

employees feel accreditation is a workload and they are not ready to carry out the sustainability of hospital

accreditation. The purpose of this study is to design a predictive analytics model of hospital accreditation

continuity from employee readiness using support vector machine (SVM) method. The data were obtained

from a population of 230 employee with sample of 70 respondents. Statistically, measurement data from the

questionnaire was processed using univariate, bivariate with chi-square tests, and multivariate with multiple

logistic regression at a 95% confidence level ( = 0.05). For hospital application needs, measurement data

are modeled by the SVM method. The results showed that there was a relationship between readiness to

change, management support, and self-benefits to the sustainability of hospital accreditation p <0.05. The

variable that has the greatest relationship with the sustainability of hospital accreditation is management

support with the value Exp (B) / OR = 18.978. The results of predictive model between input and output

variables show significant success with an accuracy rate of 88.6%.

1 INTRODUCTION

Law Number 44 Year 2009 (regarding Hospitals)

Article 29 letter b states that hospitals are required to

provide safe, quality, anti-discrimination and

effective health services by prioritizing patient

interests in accordance with service standards. Then

in Article 40 paragraph (1) it is stated that in an effort

to improve the quality of hospital services,

accreditation must be carried out periodically at least

once every three years (Secretariat of the Republic of

Indonesia, 2009). Based on the aforementioned laws

hospital accreditation is important to be carried out on

the grounds that quality can be integrated and

cultivated into the service system.

Policies related to accreditation have been set in

the regulation of the minister of health number 34 of

2017 concerning accreditation and number 99 of 2015

concerning changes to the regulation of the minister

of health number 71 of 2013 concerning health

services on national health insurance. Accreditation is

an important requirement to be fulfilled by hospitals

because in addition to aiming to guarantee the quality

of health services to the community, it can also be

evidence that the hospital has a commitment to

provide plenary and standard services (Idris, 2019).

Internationally, accreditation is a widely adopted tool

for quality control and quality improvement in health

care . In accreditation, an external institution assesses

an organisation based on predefined quality standards

and after a formalsite visit by surveyors, the

accreditation body decides whether to grant

accreditation status to the organization (Due et al,

2019).

Accreditation programmes in developing

countries, especially in the Middle East, are rapidly

picking up pace, and numerous healthcare

organizations are becoming involved in enhancing

the quality of their healthcare by adopting such

programmes, thereby enhancing their reliability and

showing their commitment to improving quality of

care (Algunmeeyn et al, 2019). Through the

accreditation process, one of the benefits is to

increase public trust where hospitals focus on patient

safety and quality of service (Ministry of Health,

Republic of Indonesia, 2011). Developing countries

frequently use hospital accreditation to guarantee

quality and patient safety (Subashnie Devkaran and

Patrick O’Farrell, 2015). Imperfections found in

health services have caused so many people to use

health services in neighboring countries such as

Singapore and Malaysia (Leonarda, 2011).

Gultom, A., Girsang, E. and R. Nasution, S.

Design a Predictive Analytics Model of Hospital Accreditation Continuity from Employee Readiness based on Artiﬁcial Intelligence.

DOI: 10.5220/0010289300960103

In Proceedings of the International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical (HIMBEP 2020), pages 96-103

ISBN: 978-989-758-500-5

Acreditation of primary care settings was shown

to strengthen quality control and improvement. Result

of study on the effectiveness of quality-improvement

in primary care showed management progress in the

practice that applied organizational standards (Alia

Ghareeb, Hana Saod and mohamad el zoghbi, 2018).

Hospital accreditation is widely adopted as a

visible measure of an organization’s quality and

safety management standards compliance. Hospital

accreditation programmes are avenues through which

a complex policy intervention functions to promote

adherence to quality and safety management

standards and drive continuous quality improvement

on a more practical level, these programmes represent

a quality management system (QMS), total quality

management (TQM) or continuous quality

improvement (CQI) standards that should lead to an

improvement of the hospital’s overall performance

(Wardhani et al, 2019).

In general, medical personnel assume that the

quality of service will be guaranteed to be good by

increasing the quality of the expertise of doctors with

continuous education and practice, and sophisticated

equipment (Azwar, 2015). However, the community

as service users, hospital managers, hospital owners,

and those who have direct or indirect interests in

hospital services can have a different opinion

(Leonarda, 2011).

Hariyono's research at Rajawali Citra General

Hospital in Bantul Regency stated that there were still

difficulties in the preparation of human resources

considering that the staff appointed to prepare the

accreditation device did not understand occupational

health safety science (Hariyono, 2013). According to

Algunmeeyn et al (2020) at Jordanian hospital that

The present study has explored the main obstacles to

implementing accreditation, based on responses from

a sample of hospital staff members (including nurses

and doctors): low wages and poor incentives, high

workload, the cost of accreditation implementation,

staff shortages, and high staff turnover. These barriers

should be addressed because they could impact on

accreditation in hospitals; negatively influencing the

quality of healthcare services and thereby incurring

serious problems.

Research conducted by Hariyono (2013) at

Rajawali Citra General Hospital in Bantul Regency

related to the analysis of readiness to face hospital

accreditation that readiness to change employees or

hospital employees is one of the factors that

encourage the sustainability of accreditation. There

are still difficulties in the preparation of hospital

human resources because the staff appointed to

prepare the accreditation tools do not understand

well. Research Mandawati et al. (2018) at KRT

Setjonegoro Wonosobo Hospital got the result that

nurses had a positive perception of accreditation and

were ready to change, besides that nurses also hoped

that the spirit of accreditation would not only be

limited to assessment.

Based on research Sembodo et al (2019) that an

Accreditation Status positively meaningful with

Service Quality, Service Quality is positively related

to Patient Satisfaction and there is a significant

positive relationship indirectly between Accreditation

Status and Patient Satisfaction. But the accreditation

results did not always directly improve the quality of

hospital services. This is because accreditation of

health services in Indonesia has not yet assessed the

clinical indicators of health services (Soepojo et al,

2012; Turnip et al, 2020; Wijaya et al, 2019 ).

Based on data from the Stella Maris Hospital in

Medan, there were 230 permanent staff consisting of

30 medical staff, 72 nurses, 54 midwives, 15

laboratory workers, 21 pharmacists, 10 nutrition

workers , radiology staffs as much as 2 people,

maintenance staff 11 people, medical records staff as

many as 3 people, administrative and administrative

staff as many as 12 people. To provide the best

service in carrying out operational activities for

people who come for treatment or delivery, the work

shifts are divided into 3 (three) shifts for operations

24 hours a day, while for administrative (office)

activities only consist of 1 (one) shift.

The preliminary survey was conducted by

interviewing 15 employees about services after

hospital accreditation: as many as 8 people said they

continue to work in accordance with the demands of

hospital accreditation that is working with maximum

service. As many as 7 people said that after

accreditation was completed, they could be more

relaxed in carrying out the work, because they felt

burdened as when accreditation would be done by

doing work that exceeded work on normal days.

Sometimes employees must work overtime in the

accreditation process. Accreditation encourages

employees (medical and non-medical personnel) to

reopen standard operating procedures that have so far

only been used as documentation. All nursing

activities have Standard Operating Procedures

(SOPs) that must be obeyed.

To facilitate management in monitoring and

making decisions, the relationship between employee

readiness and the sustainability of hospital

accreditation is developed using the Support vector

machine (SVM) method. The application of SVM

methods in the hospital management is still rarely

used especially in terms of accreditation.

Design a Predictive Analytics Model of Hospital Accreditation Continuity from Employee Readiness based on Artiﬁcial Intelligence

2 METHOD

This type of research used in this research was a

quantitative analytic study with a cross sectional

research design. This research was conducted at the

Stella Maris Hospital in Medan in November 2019.

The population of the study was 230 employee, and

the sample was obtained by 70 respondents with

stratified random sampling technique. Statistically,

data from the results of questionnaire measurements

were evaluated by univariate, bivariate using chi-

square tests, and multivariate using multiple logistic

regression tests with a confidence level of 95% ( =

0.05).

Machine learning is an application branch of

Artificial Intelligence that focuses on developing a

system that is able to learn on its own without having

to be repeatedly programmed by humans. Machine

learning applications require data as learning material

(training) before issuing outputs. Support vector

machine (SVM) is a technique for making

predictions, both in the case of classification and

regression. SVM is in the same class as Artificial

Neural Network in terms of functions and problem

conditions that can be solved (Kusumandari et al,

2018; Turnip et al, 2018). In this study, the SVM

technique is used to find the optimal separator

function (classifier) that can separate two data sets

from two different classes. The use of machine

learning techniques, because of their convincing

performance in predicting the class of new data. In

general, the classification process has two processes

as (i) The training process uses training data sets that

have known labels to build models or functions, (ii)

The testing process uses data testing sets to predict

and test the accuracy of the model or function that will

built in the training process.

The concept of SVM can be explained simply as

an attempt to find the best hyperplane that functions

as a separator of two classes in the input space (Turnip

et al, 2018). The classification problem can be

translated by trying to find a line (hyperplane)

separating between two groups as in Figure 1. The

best hyperplane separator between the two classes can

be found by measuring the hyperplane's margin and

finding its maximum point. The closest pattern is

known as a support vector. The solid line in Figure 1

shows the best hyperplane, which is located right in

the middle of the two classes, while the red and

yellow dots in the black circle are support vectors.

Figure 1: The best hyperplane that separates the two classes

-1 and +1 with SVM.

In this paper, the SVM method was used develop

a predictive analytics model that will automatically

recognize and predict the name of a hospital

accreditation continuity from an employee readiness.

This is essentially the problem of acreditation

information that the classifier to predict the level of a

hospital status from current conditions without

complicated measurement of many possible

variables. The diagram of the SVM predictive model

is shown in Figure 2.

Figure 2: The SVM Predictive Model Diagram.

3 RESULTS AND DISCUSSIONS

Characteristics of respondents including age, sex, last

education, and length of work can be seen in Table 1.

Most respondents aged <32 years (54.3%), aged> 32

years (45.7%), female sex (74.3%), male (25.7%).

Most of them have D-3 education (55.7%), a small

proportion have D-4 and S2 education respectively

(1.4%). Most respondents worked> 5 years (64.3%),

a small proportion worked <5 years (35.7%).

HIMBEP 2020 - International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical

Table 1: Characteristics of Research Respondents.

Characteristics

Numbe

f %

Age:

a. <32

. ≥32

54,3

45,7

Numbe

70 100,0

Sex :

a. Male

. Female

25,7

74,3

Numbe

70 100,0

Education :

a. SMA/SMK

b. D3

c. D4

d. S1

e. S2

15,7

55,7

1,4

25,7

1,4

Numbe

70 100,0

Length of work:

a. <5 years

. ≥5 years

35,7

64,3

Total 70 100,0

Based on the results of bivariate analysis obtained

a significant relationship with the sustainability of

accreditation, namely the accuracy to change (p =

0.017), self-confidence (p = 0.001), management

support (p = 0,000), and self-benefit (p = 0,000).

Table 2: The Relationship of Each Independent and

Dependent Variable.

Variables A

Continuity of

Accreditation

Total

value

Goo

Lsss

f % F % F

Accuracy for

Chan

0,017

Precise 52 88,1 7 11,9

Less Precise 6 54,5 5 45,5 11

Confident:

0,001

h 48 92,3 4 7,7

Low 10 55,6 8 44,4

Management

ort:

Support 53 91,4 5 8,6

Less Support 5 41,7 7 58,3

Benefits:

Hel

ful 50 92,6 4 7,4

Less

Helpfull

8 50 8 50

Furthermore, multivariate analysis with multiple

logistic regression tests showed that of the 4 variables

tested were found as many as 3 variables related to

the sustainability of hospital accreditation namely

accuracy for change, management support and self-

benefit.

The variable that has the highest weighting

relationship with output is the management support

variable with the value Exp (B) / OR = 18.978. While

the accuracy to change variable has the value Exp (B)

/ OR = 9,229 and the benefit variable for yourself has

the value Exp (B) / OR = 7,539. Overall results of

multiple regression tests can be seen in Table 3.

Table 3: Multiple Logistic Regression Test Results.

Variables B Sig. Exp(B)

95%CI for

Exp(B)

Accuracy to change

Management support

Benefits

Constant

2,222

2,943

2,020

-11,015

0,027

0,002

0,019

0,000

9,23

18,9

7,54

1,294-65,802

2,828-127,341

1,392-40,829

3.1 Accuracy for Change

Based on the results of the study showed that there

was a relationship of accuracy to change with the

continuity of accreditation, p = 0.027 <0.05. The

accuracy to change variable has a value of Exp (B) /

OR = 9,229 meaning that employees with

accreditation were the right time to change, have the

opportunity to have a good hospital accreditation 9.2

times higher than employees who claim accreditation

was not the right time for change. Positive

perceptions should be put to good use by hospital

leaders to improve services on an ongoing basis. This

spirit can be used as capital to improve services by

assessing the quality of clinical service indicators so

that patients will really feel the difference in the

services provided by the hospital.

Appropriateness to make changes was a

dimension of someone's readiness that explains the

individual's belief that the proposed change will be

right for the organization and the organization will

benefit from implementing change. Individuals will

believe there were logical reasons for change and the

need for proposed changes, and focus on the benefits

of change for the company, the efficiency obtained

from changes, and the congruence of company goals

with change goals (Holt, Armenakis, Field, & Harris,

2007). Obligations to accredit services provided

encourage almost all hospitals to carry out the

program, especially since the government also gives

obligations to the central and regional governments to

support hospitals in their area when accrediting.

The results of this study prove that the readiness

of employees on the dimensions of accuracy to

Design a Predictive Analytics Model of Hospital Accreditation Continuity from Employee Readiness based on Artiﬁcial Intelligence

change was significantly related to the sustainability

of accreditation. Employees who have readiness to

change tend to continue to carry out work in

accordance with hospital accreditation demands and

conversely employees who were less ready to change

feel that the implementation of accreditation will

continue to add to their workload. Employees who

were ready to change and claim that accreditation is a

good time to change are confident that by doing

accreditation there will be a change that is better for

the hospital and for itself. The existence of

accreditation will also change the organization of the

hospital for the better than before. Employees also

believe that with the accreditation of hospitals, they

will benefit from being the community's reference for

treatment.

According to the assumption, Accreditation was a

logical or reasonable reason for most employees to

improve their performance in accordance with their

respective professions. Accreditation was considered

as a need for better change and employees can work

more safely, comfortably, effectively and efficiently.

However, a small number of employees feel that

accreditation is a workload because they have to carry

out work in accordance with accreditation standards,

which they say adds to the workload.

3.2 Management Support

Based on the results of the study showed that there

was a relationship between management support and

the sustainability of hospital accreditation is p = 0.002

<0.05. Management support variable that has a value

of Exp (B) / OR = 18.978 means that employees who

declare hospital management support in the

continuity of hospital accreditation have a good

chance of continuing accreditation by 18.978 times

higher than employees who claim hospital

management was less supportive.

In general, hospitals are not ready to face

accreditation because they do not yet have a policy

related to the implementation of officers for the

protection of medical record documents from damage

and loss, the absence of working groups,

infrastructure that does not support and the limitations

of the hospital management system. In addition,

nurses also hope that the support of hospital

management and the spirit of accreditation will not

only end with the completion of the assessment.

At present many hospital leaders consider that

accreditation was merely achieving the graduation

status of the hospital and increasing the "prestige" of

the hospital when it gets an accreditation certificate

so that it often ignores the process of achieving

graduation, which means maintaining the quality

culture and patient safety on an ongoing basis is often

neglected.

For hospital management, the accreditation

program is a valid instrument to determine the extent

to which services at the hospital meet national

standards. Accredited status can also increase public

trust in services in hospitals and as a means of

preventing malpractice cases. The results of this study

prove that management support is related to the

sustainability of hospital accreditation. In addition,

management provides full support to employees who

strive to change in accordance with accreditation

demands. Management also provides support for

employees to have creative ideas at work and in

accordance with the demands of accreditation that can

improve service quality

3.3 Benefits for Yourself

Based on the results of the study showed that there

was a relationship of benefits for theirself with the

sustainability of hospital accreditation was p = 0.019

<0.05. The benefit variable itself with the value Exp

(B) / OR = 7.539 means that employees who claim to

be beneficial to themselves have a good chance of

continuing hospital accreditation by 7.5 times higher

than employees who claim to be beneficial to

themselves. Some employees stated that the reason

for approving accreditation was that there were many

positive impacts in accreditation, including: more

organized management of hospitals. And changes in

the way decisions are made by the leadership. All

employees come to know what indicators to consider

in service, how to report problems, and decisions

based on the aspirations of subordinates.

Personal benefit is a dimension that explains

aspects of beliefs about the perceived personal

benefits that will be obtained if the change is

implemented. The matter of concern, especially in

maintaining the application of accreditation standards

is not easy. There needs to be a common perception

about the benefits of hospital accreditation, both the

benefits for themselves and the benefits for the

hospital, so that all employees play an active role,

with encouragement and monitoring of the leaders.

Individual perception can directly influence

participation to increase commitment to work

decisions and productivity.

The results of this study prove that employee

readiness on the self-benefit dimension was

significantly related to the continuity and

sustainability of hospital accreditation. Employees

who claim that accreditation was beneficial for

HIMBEP 2020 - International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical

100

themselves tend to carry out continuous work in

accordance with the demands of accreditation. The

most important thing was that they learn more about

new things related to their work and daily tasks.

According to the researchers' assumptions,

employees who claim that accreditation was

beneficial for themselves can work according to the

job description because so far they sometimes do

work that is not their job. This will make them better

trained to carry out work that is their responsibility

and make them more skilled.

In the application of SVM method, the best

hyperplane was obtained using 2D plane as shown in

Figure 2. Clearly visible in the hyperline image

functions to separate between classes. In the correct

prediction the class / group agree () for accuracy to

change can reach the range of 35-40 and confident it

can reach the range of 35-40. From Figure 1 (x-axis

is accuracy of change and y is confident), it was

known that the output value obtained by the amount

of training data is 50% of the initial data. From the

results of the output in Figure 2 it is known that the

level of accuracy of the prediction results with

training data is 0.886 or 88.6%. Accuracy is used to

see a measure of how well the model tolerates results

with attributes in the data used.

Sensitivity is used

to measure the proportion of positive observations

that are precisely predicted. Then the specificity value

is 0.8134 or 82%. 'Specificity' is used to measure the

proportion of negative observations that are precisely

predicted. Then for an accuracy balance value of

0.8151 or 82%. 'Balanced Accurancy' is used to

measure the accuracy of the proportion of positive

class observations that are precisely predicted.

Figure 2: the 2D hyperplane for classes separation.

In Figure 3 (confolution matrix) there are two

colors, blue (correct prediction) and orange (incorrect

prediction). If one of the colors is getting thicker, then

it shows that the prediction is toward the intense

color. For example: in the picture above the solid

color is blue and the faintest is orange, then the

incorrect prediction is smaller. Furthermore, the

percentage of accreditation data that has been

classified can be seen in Figure 3. There are also TPR

and FDR which are the conclusions of each percent

prediction of correct and incorrect

Figure 3: Confusion matrix of clasification results

In Figure 4, parallel output image only serves to

see the relations between variables that have been

used as input in this data, then here can also be seen,

which relations are correct and incorrect.

Figure 4: Predictions model

Design a Predictive Analytics Model of Hospital Accreditation Continuity from Employee Readiness based on Artiﬁcial Intelligence

101

4 CONCLUSIONS

The results showed that there was a relationship of

accuracy to change, management support, self-

benefit with the sustainability of hospital

accreditation. While self-confidence is not related.

The management support variable has a greater

relationship with the continuity of hospital

accreditation both with Exp (B) / OR value = 18,978.

It is known that the classification of the SVM

model in training data is of type C-classificaton, with

a radial kernel. Cost is the kernel parameter value is

1, gamma parameter value is 0.125, and the number

of support vectors is 70. The accuracy level of the

prediction results with training data is 0.886 or 88%,

for the sensitivity value obtained is 0.8167 or 81%,

then the Specificity value is 0.8134 or 81%, and the

balance accuracy value is 0.8151 or 81%.

REFERENCES

Azwar, A. 2015. Menjaga Mutu Pelayanan Kesehatan.

Jakarta: Pustaka Sinar Harapan.

Algumeeyn et al 2020. Exploring staff perspectives of the

barriers to the implementation of accreditation in

Jordanian hospitals, Case Study. International Journal

of Healtcare Management.

https://doi.org/10.1080/20479700.2020.1763233

Ayuningtyas, D & Rahmadhani, S. R 2019. Puskesmas

Readiness in Accreditation Implementation as Effort to

Improve The heath Service Quality in Sumbawa

District, Journal of Indonesian Health Policy and

Administration. Vol 4. No 2: 27-35.

Devkaran and O’ Farrel 2015. The Impact of hospital

accreditation on qualitaty measures: an interruptd time

series analysis, BMC Health Service Research. (2015)

15:137

https:// doi.org 10.1186/s12913-015-0784-5

Due et al 2019. Understanding accreditation standards in

general practice- a Qualitative study, MBC Family

Practice. (2019) 20:23

http://doi.org/10.1186/s12875-019-0910-2

Ghareeb et al., 2018. Examining the Impact of

Accreditation on Primary Heatlcare organization in

Qatar, BMC Medical Education. (2018) 18:216

https://doi.org/10.1186/s12909-018-1321-0

Hariyono, W. 2013. Analisis kesiapan menghadapi

akreditasi pada pelayanan administrasi dan

manejemen di rumah sakit umum rajawali citra

kabupaten Bantul. Kesmas, 1(2), 113-116.

Hendroyogi, S. R., & Harsono, M. 2016. Keterkaitan

Antara Persepsi Pentingnya Akreditasi Rumah Sakit

Dengan Partisipasi, Komitmen, Kepuasan Kerja, Dan

Kinerja Karyawan. Jurnal Manajemen Dayasaing,

18(2), 122-137.

https://doi.org/10.23917/dayasaing.v18i2.4509

Holt, D. T., Armenakis, A. A., Field, H., & Harris, S. G.

2007. Readiness forOrganizational Change: The

Systematic Development of a Scale, Journal of Applied

Behavioral Science, 43(2), 232-245.

Idris, F. 2019. Rumah Sakit Terakreditasi, Wujudkan

Jaminan Kesehatan yang Berkualitas Tanpa

Diskriminasi. Jakarta: Badan Penyelenggara Jaminan

Sosial.

Kemenkes RI. 2011. Standar Akreditasi Rumah Sakit.

Jakarta: Kementerian Kesehatan Republik Indonesia.

Kusumandari, D., Risqyawan, M., Yazir, M., Turnip, M.,

Darma, A. and Turnip, A., 2018. Application of

convolutional neural network classifier for wireless

arrhythmia detection, Journal of Physics: Conference

Series, Volume 1080 (2018) 012048 doi:

10.1088/1742-6596/1080/1/012048.

Leonarda, R. 2011. Gambaran Persiapan Penilaian

Akreditasi Rumah Sakit Bersalin Asih Jakarta Tahun

2011. Universitas Indonesia.

Mandawati, M., Fuadi, M. J., & Jaelan. 2018. Dampak

akreditasi rumah sakit: studi kualitatif terhadap

perawat di RSUD KRT Setjonegoro Wonosobo.

NURSCOPE: Jurnal Penelitian Dan Pemikiran Ilmiah

Keperawatan, 4(4), 23-29.

Robbins, S. P., & Judge, T. A. 2014. Perilaku Organisasi

(Cetakan 12). Jakarta: Salemba Empat.

Santoso, A. 2016. Akreditasi Rumah Sakit: Kepentingan

Rumah Sakit atau Masyarakat?

Sekretariat Negara RI. 2009. Undang-Undang No. 36

Tahun 2009 tentang Kesehatan. Jakarta: Sekretariat

Negara Republik Indonesia.

Sembodo et al., 2019. Service Quality Model with Cultural

Perspective in Effect on Patient Satisfaction in

Hospitals with Different Accreditation Status. Medico-

legal update. Vol. 19. No. 1204-209.

https://doi.org/10.5958/0974-1283.2019.00041.0.

Soepojo, P., Koentjoro, T., & Utarini, A., 2012.

Bechmarking system akreditasi rumah sakit di

Indonesia dan Australia. Jurnal Manajemen Pelayanan

Kesehatan, 2(2), 1-8.

Turnip, A., Andrian, Turnip, M., Dharma, A., Paninsari, D.,

Nababan, T., Ginting, C.N., 2020. An application of

modified filter algorithm fetal electrocardiogram

signals with various subjects, International Journal of

Artificial Intelligence, vol. 18, no., 2020.

Turnip, A., Ilham Rizqywan, M., Kusumandari, D., et al.,

2018. Classification of ECG signal with Support Vector

Machine Method for Arrhythmia Detection, Journal of

Physics: Conference Series, Vol. 970 (2018) 012012

doi: 10.1088/1742-6596/970/1/012012.

Turnip, A., Kusumandari, D., Pamungkas, D., 2018. Drug

Abuse Identification based EEG-P300 Amplitude and

Latency with Fuzzy Logic Calssifier, IEEE International

Conference on Applied Engineering, (ICAE), 3-4 Oct.

2018, DOI: 10.1109/INCAE.2018.8579378.

Wantouw, S., Antariksa, Yanuwiadi, B., & Tamod, Z. 2014.

Perception and Participationon Co-Management of

Green Open Space in Coastal Reclamation Area

Manado. International Journal of Applied Sociology,

1(1), 108-113.

HIMBEP 2020 - International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical

102

Wardhani et al., 2019. Hospital Accreditation status in

Indonesia: Associated with hospital characteristics,

market competition intensity, and hospital

performance?, BMC Health Service Research (2019)

19: 372. http://doi.org/10.1186/s12913-019-4187-x.

Wijaya, C., Andrian, M., Harahap, M., Turnip, A., 2019.

Abnormalities State Detection from P-Wave, QRS

Complex, and T-Wave in Noisy ECG, Journal of

Physics: Conference Series, Volume 1230, (2019)

012015. doi:10.1088/1742-6596/1230/1/012015.

Design a Predictive Analytics Model of Hospital Accreditation Continuity from Employee Readiness based on Artiﬁcial Intelligence

103