Forecasting Maternal Satisfaction with the Quality of Pregnancy and

Childbirth Services using the ANFIS Method

Angel Jelita, Ermi Girsang, Sri Lestari R. Nasution

Faculty of Medical, Universitas Prima Indonesia, Indonesia

Keywords: Quality of Service, Pregnancy, Childbirth, Maternal Satisfaction.

Abstract: The decrease in the number of patient visits to a hospital allegedly due to dissatisfaction because of the

unexpected quality of service. The purpose of this study was to analyze the effect of the quality of pregnancy

and childbirth services on maternal satisfaction. Evaluating and modeling variables on 18,782 respondents

with 200 samples were conducted. Supporting analysis of the questionnaire data using univariate, bivariate

with chi-square test, and multivariate with multiple logistic regression at the 95% confidence level ( = 0.05)

was chosen. The results of modeling using the Adaptive Neuro-Fuzzy Inference System (ANFIS) method

showed satisfactory results with an accuracy of 92.3%. While statistically there was the influence of physical

evidence, reliability, quick response, and empathy to patient satisfaction p <0.05. The variable that had the

greatest influence on maternal satisfaction was responsiveness with a good chance of 7.9 times higher toward

the less good.

1 INTRODUCTION

The success of maternal health efforts can be seen

from the indicators of Maternal Mortality Rate

(MMR). This indicator is not only able to assess

maternal health programs, moreover it is able to

assess the degree of public health (because of its

sensitivity to improving health services, both in terms

of accessibility and quality) (Ministry of Health

Republic of Indonesia, 2015). WHO defines maternal

mortality as a death that accurs during pregnancy or

within a period of 42 days after the pregnancy ends,

which is caused by all caused to or aggravated bu

pregnancy or its handling, but not due to

accident/injuries (Askar, M. 2019). The 2012 IDHS

is 359 maternal deaths per 100,000 live births. AKI

again showed a decrease to 305 maternal deaths per

100,000 live births based on the 2015 Intercensal

Population Survey (SUPAS) (BPS, 2015). This

achievement is still far from the Sustainable

Development Goals (SDGs) target in 2030, reducing

maternal mortality to below 70 per 100,000 live births

(Ministry of Health, 2017).

Most cases of maternal and perinatal mortality

occur in women who do not receive antenatal care

with more than 99% that women living in developing

counties (Dauletyarova, M. A, 2018). Data from the

North Sumatra Province Health Service shows that

maternal deaths in 2016 were 175 cases. The maternal

death was caused by eclampsia factors, such as

seizures, edema or swelling of the body, the presence

of kidney leakage and the most severe, namely

hypertension totaling 38 people. Bleeding factors,

such as maternal anemia 47 cases, infection 10 cases,

parturition jams 3 cases, abortion 3 cases and others

70 cases. The highest number of maternal deaths in

Deli Serdang Regency is 27 people, North Nias is 22

people, Asahan is 21 people. However, Labura and

Nias have not received the data (Provincial Health

Office, 2017).

AKI in North Sumatra reached 194 people in

2017. The number has decreased from 2016 which

was 240 people. Although maternal mortality and

infant mortality rates have declined, the health sector

has SDGs indicators (Medan City Health Office,

2018). Based on the health profile of North Sumatra

Province in 2016, the ratio of specialist doctors,

including obstetric specialists to 100,000 residents

was 19.80, while the ratio of midwives to 100,000

residents was 139.53. This shows that there is still a

lack of specialist doctors and the distribution is also

uneven in 33 districts / cities (Provincial Health

Office, 2017).

Maternity period is important and crucial in the

life of women. An array of services is provide to

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

Forecasting Maternal Satisfaction with the Quality of Pregnancy and Childbirth Services using the ANFIS Method.

DOI: 10.5220/0010291401330140

In Proceedings of the International Conference on Health Informatics, Medical, Biological Engineering, and Pharmaceutical (HIMBEP 2020), pages 133-140

ISBN: 978-989-758-500-5

133

pregnant women during this period. These service

include prenatal care and counselling, skilled

delivery, assistance recourse to caesarean sections.

Developing world have high risk of maternal

mortality. 1 in 38 women as compared to 1 in 3700

women, leading to increased number of women

seeking maternal helath (Konlan, K.D, 2018).

Lari and colleagues define that patient satisfaction

as the extent of an individual’s experience compared

with her expectations or what patients’ and the

population need to receive from health care service.

WHO encourages the presence of skilled doctors at

each birth to reduce maternal mortality and

recommends that women satisfaction be assessed to

improve the effectiveness and quality of health care

(sayed et al, 2018). Bramadat et all (in Ajayi, A. I,

2019) defined satisfaction a “positive feeling” or

“effective response” to an event. Srivastava et al (in

Ajayi, A. I, 2019) that women satisfaction with

maternal health care services, three dimensions of

care are structural, processes and outcomes. The

structural includes good physical environment,

cleanliness of wards, theatres and toilets and adequate

human and material resouces. The process aspect

relate to interpersonal and emotional support received

from doctors or midwives, privacy and promptness.

While the outcome aspect relate to connotes the

health status of the mother and the baby.

Services for pregnant and childbirth women are

carried out by health workers, professionally will be

done as well as possible so that pregnant women feel

satisfied with the services provided (Varney, 2015).

Many factors can influence a person to feel satisfied

with services in health facilities such as clinics, health

centers, and hospitals such as the experience of

midwives and doctors during the examination

process, complete facilities, ease of location of health

facilities that are easily accessible, competitive rates,

speed Dauin conducting examinations friendliness of

midwives and doctors in ANC and childbirth services

(Baety, 2015).

Based on Amu, H & Nyarko, S.H (2019) research,

a few issues were considered to asses maternal

satisfaction with services provide. These included

satisfaction with head-to-toe examination, health

education, services relating to drugs and delivery

serives. Accros the maternal healthcare continue, the

assessment of maternal satisfaction has basically

focused on physical environment, available of

services, hygiene and accommodation conditions,

interpersonal relationshipwith healthcare

professional, the organization of work, and the

competence and skilled of healthcare professional.

In terms of service, health workers will make the

best effort in services such as increasing inspection

facilities that do not yet exist, improving facilities

such as waiting rooms, and parking spaces for

visitors' vehicles, increasing the level of skills of

health workers such as attending health training or

seminars on ANC issues and childbirth (Spiritual,

2016; Turnip et al, 2020; Wijaya et al, 2019). Health

facilities such as clinics, health centers, maternity

hospitals, hospitals are required to be able to provide

quality services that can meet the needs and desires of

clients (Prawirohardjo, 2013). Health facilities can

have better services than others, for example in terms

of providing motivation to clients, hospitality

services by providing smiles, greetings, and

greetings, providing low prices, especially for the

lower middle class. The quality of health services in

good health facilities is maternity homes that are truly

quality and able to compete (Barata, 2014).

Quality must start from the needs of the patient

(client) and end on the perception of the patient

(client). This means that a good quality image is not

based on the viewpoint or perception of the service

provider, but based on the viewpoint or perception of

the patient (client). Zeithaml, Berry, and Parasuraman

in Tjiptono stated that service quality consists of

tangible, reliability, responsiveness, assurance, and

empathy (Tjiptono & Chandra, 2015). Perception of

quality maternity services differed significantly by

the type of facility used by women. Based on Konlan

K. D etal (2018) researchin Nepal, women considered

the private hospital to provide quality meternity

services due to the avaibility of amenities and

equipment as well as good midwife-client

relationship. In addition, attitudes and behaviors of

maternal health care providers influence health care

seeking and quality of care.

Mindaye & Taye's research in Addis Ababa,

Ethiopia, concluded that from 406 research

respondents that respondents were satisfied with

laboratory services (physical / direct evidence) with

an average of less than 30 minutes. Respondent

satisfaction is more influenced by the complete

facilities so as to facilitate service to patients

(Mindaye & Taye, 2012). Hermanto's research

examines Midwifery Inpatient at Dr. H. Soemarno

Sosroatmodjo Bulungan East Kalimantan in 2010

found that the factors related to patient satisfaction

were maternal perceptions of reliability,

responsiveness, assurance, empathy, and direct

evidence (Hermanto, 2010). Likewise Kahar's

research at the Barru District Hospital in 2017

showed that there was an influence of reliability,

responsiveness, assurance, empathy, and direct

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

134

evidence. Reliability variable is the most influential

factor on inpatient satisfaction (Kahar, Palu, &

Raodhah, 2017).

Getting good and proper quality health services

were the desire of every individual who wants to do

care and treatment. This concerns about individual

satisfaction in receiving services through health

facilities that aim to maintain and improve health and

cure disease.

2 METHOD

Stella Maris Hospital in Medan is included in the

category of special hospitals that provide services for

maternal and child health problems, ranging from

maternal, reproductive and children. Integrated

services at the Stella Maris Mother and Child

Hospital are carried out by a dedicated team of

Obstetrics and Gynecology Specialists, Pediatricians,

Neonatologists and nurses. Stella Maris Hospital

provides high-quality health services for all matters

related to fertility, pregnancy, menstrual problems,

menopause, pelvic infections, cancer in women, and

health care for infants, children and adults.

Based on interviews conducted by researchers in

an initial survey of 15 visiting mothers, 9 people were

satisfied with the services provided during pregnancy

and childbirth. While 6 other people feel less satisfied

with the quality of pregnancy and childbirth services.

The dissatisfaction felt by the mother was related to

the presence of some doctors and nurses who are not

friendly, waiting in line for a long time due to the

large number of patients that must be treated,

communication with nurses was less intertwined,

there were some nurses who less responsive when

asked for help by patients, and lack of empathy.

This type of research was a quantitative analytic

study with a cross sectional study design. The study

population was 18,782 people, and samples were

obtained about 200 respondents. The research

sampling technique was accidental sampling.

Univariate data analysis, bivariate using chi-square

test, and multivariate using multiple logistic

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

0.05).

Adaptive neuro fuzzy inference system (ANFIS)

method is a method that uses artificial neural

networks to implement fuzzy inference systems. The

advantage of fuzzy inference systems is that they can

translate knowledge from experts in the form of rules,

but it usually takes a long time to determine the

membership function. Therefore it takes learning

techniques from artificial neural networks to

automate the process so that it can reduce search time,

this causes the ANFIS method to be very well applied

in various fields (Turnip, 2018). Similar to artificial

neural networks, there are also layers in ANFIS but

the number is an average of five layers as shown in

Figure 1. In general, the mathematical form of ANFIS

IF x is A1 AND y is B1 THEN f1 = p1x + q1y + r1

IF x is A2 AND y is B2 THEN f2 = p2x + q2y + r2

dengan,

2211

fwfw

f 





Figure 1: ANFIS processing scheme with input and output

layers.

In the Figure 1, the first layer functions to convert

crisp numbers into fuzzy numbers by using fuzzy sets.

In the second layer, each input goes to the same layer

to find out firing strength. In the third layer

normalization calculations were carried out before

applying to the fourth layer. Normalization was the

process of re-weighting to obtain a total / max of one.

On the fourth layer, the process was continued by

multiplying with functions that involve inputs (x and

y) to produce output that was already in the form of

CRISP. The final step was to accumulate the results

of the fourth layer (for the two rules). While for the

learning method, backpropagation with the principle

of minimizing errors that occur in the form of mean

absolute percent error was used (Kusumandari et al,

2018; Turnip et al, 2018).

In this study, the independent variables in the

form of appropriateness, change efficacy,

management support, and personal fit are used as

inputs and the independent variables in the form of

accreditation sustainability as an output were used in

the modeling using ANFIS method. About 40% of the

measured data from queries are used as a data training

and the last part were used for data testing.

3 RESULTS AND DISCUSSIONS

Characteristics of respondents involved in the study

can be seen as in Table 1.

Forecasting Maternal Satisfaction with the Quality of Pregnancy and Childbirth Services using the ANFIS Method

135

Table 1: Characteristics of Research Respondents.

Characteristics

Respondents

Age (years):

a. <20

b. 20-35

c. ≥35

131

65,5

34,5

Numbers

200

100,0

Education :

a. Midble high

school

b. Diploma

c. Undergraduate

19,5

49,0

31,5

Numbers

200

100,0

Occupation:

a. House wife

b. Official staff

c. Private

employees

d. Entrepreneurs /

Traders

45,5

12,5

7,5

34,5

Numbers

200

100,0

Childbirth of:

a. First

b. Second

c. Third

d. Fourth

e. Fifth

17,0

39,5

33,5

9,0

1,0

Jumlah

200

100,0

Based on the results of the bivariate analysis, all

independent variables were found to be significantly

related to maternal satis faction. The complete

Chi-Square statistical test results can be seen in Table

Table 2: The Relationship of Each Independent and

Dependent Variable.

Variables

Mother's

satisfaction

Numbers

value

Satisfy

LessStasisfy

Tangible:

Good

Less

125

136

142

156

142

143

0,000

Reliability:

Good

Less

123

138

0,000

Responsivene

ss:

Good

Less

0,000

Assurance:

Good

Less

124

129

0,000

Empathy:

Good

Less

0,000

The results of multivariate analysis with multiple

logistic regression tests showed that from the five

candidate model variables, four variables were found

that affect maternal satisfaction, namely tangible,

reliability, responsiveness, and empathy. The most

influential variable was the responsiveness variable

with the value Exp (B) / OR = 7.985 (Table 3), which

means that mothers who expressed good hospital

responsiveness, had the opportunity to feel satisfied

with pregnancy and childbirth services by 7.9 times

higher than those of not good.

Table 3: Multiple Logistic Regression Test Results.

Variable

Sig.

Exp(B)

95%CI for

Exp(B)

Tangible

Reliability

Responsiveness

Empathy

2,028

1,115

2,078

1,552

-10,52

0,000

0,029

0,000

0,002

7,598

3,049

7,985

4,719

2,919-19,782

1,121-8,293

2,902-21,976

1,799-12,373

3.1 Tangible Effect

Tangibles was the ability of a company to show its

existence to external parties. The appearance of the

office and employees, the ability of physical facilities

and infrastructure, and the surrounding environment

were tangible proof of the services provided by the

service buyer. Appearance of services was not only

limited to the physical appearance of a magnificent

building but also the appearance of officers and the

availability of supporting facilities and infrastructure.

Tangible dimensions are the appearance and ability of

reliable physical facilities and infrastructure.

Tangible includes the comfort of inpatient rooms,

environmental cleanliness, appearance of medical

personnel, and completeness. The quality of a health

service is closely related to the will in meeting the

needs of the users of health services, the more perfect

the fulfillment of these needs the better the quality of

service.

Based on the results of multivariate analysis with

the results of the study indicate that there is an

influence of physical evidence (tangible) on maternal

satisfaction, p = 0,000 <0.05. Variable physical

evidence that has a value of Exp (B) / OR = 7.598

means that mothers who state good hospital physical

evidence, have the opportunity to feel satisfied with

pregnancy and childbirth services by 7.5 times higher

than mothers who state that hospital tangibility is not

good.

Based on the results of this study prove that

tangibles significantly influence the satisfaction of

mothers who receive pregnancy and childbirth

services. Mothers who stated that the quality of

services based on good physical evidence dimensions

tended to feel satisfied, and conversely mothers who

said that physical evidence was less good tended to

feel dissatisfied.

It was assumed that the satisfaction felt by the

mother as a respondent relates to a clean and

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

136

comfortable pregnancy and maternity examination

room, equipment, clean and well-maintained

bathroom. Likewise, the appearance of health

workers (doctors, midwives, nurses) must be clean

and neat. The things that are visible to the eye and can

be assessed directly cause patients to be able to

provide an assessment in accordance with what is

perceived. If the physical evidence that was felt and

seen exceeds what is expected then the patient will

feel satisfied.

3.2 Reliability Effect

The perception of the reliability of midwifery services

can be viewed from the ability of officers to provide

services properly, such as the ability of doctors to

diagnose illnesses, heal or hospital obligations, all

hospitalized patients must be given medical care,

nursing care or midwifery care regardless of the class

of care. In general, midwifery inpatients stated that

the reliability of inpatients was good. Respondents

who stated that the reliability they received was good

was due to a series of examinations the doctor was

able to immediately know the patient's illness and

they were given drugs and injections according to

schedule.

Based on the results of the study indicate that

there was an effect of reliability on maternal

satisfaction, p = 0.029 <0.05. The reliability variable

has a value of Exp (B) / OR = 3.049, which means

that patients who state good hospital reliability, have

the opportunity to feel satisfied with pregnancy and

childbirth services by 3 times higher which was not

good. The results of this study prove that reliability in

pregnancy and childbirth services has a significant

effect on patient satisfaction.

Reliability was assumed to be related to officers

providing information about the results of pregnancy

examinations and childbirth actions and routinely

receive doctor and midwife/nurse service visits.

Health workers must answer all patient complaints

about pregnancy and childbirth and explain the results

of the examination that has been done. Reliability is

also related to the actions taken by health workers in

conducting a thorough examination. The reliability of

health workers is an important concern in the quality

of pregnancy and childbirth services so that patients

become more confident.

3.3 Responsiveness Effects

Responsiveness was one of the determining factors in

the progress of a hospital. Satisfaction was a

condition when the needs, desires, and expectations

of patients can be met through the consumed products

/ services. The quality of health services is generally

associated with satisfaction of health services. Based

on the results of the study showed that there was an

effect of responsiveness on patient satisfaction, p =

0,000 <0.05. The responsiveness variable has a value

of Exp (B) / OR = 7.985 which means that patients

who state that the hospital's responsiveness was good,

have a 7.9% higher chance of being satisfied with

pregnancy and childbirth services.

The results of this study indicate that

responsiveness in pregnancy and childbirth services

has a significant effect on satisfaction.

Responsiveness was assumed in increasing patient

satisfaction related to the readiness of health workers

to come immediately if called and asked for help.

Health workers also routinely carry out checks and

respond to complaints felt by patients. The

responsiveness of health workers was also related to

examinations carried out according to schedule so

that patients are not aware of the conditions they are

experiencing. In this study shows that responsiveness

was the variable that has the biggest effect on patient

satisfaction.

3.4 Empathy Effects

Based on the results of the study showed that there

was an empathy effect on patient satisfaction, p =

0.002 <0.05. The empathy variable (empathy) which

has a value of Exp (B) / OR = 4,719 means that

patients who state that the hospital empathy was

good, have the opportunity to feel satisfied with

pregnancy and childbirth services by 4.7 times higher

than the less good ones.

Indicators of patient satisfaction in hospitals can

be applied by improving service management so that

patient satisfaction can be realized such as empathy

or attention from health workers. In addition, the

quality of empathy dimensions of service can be a

factor in choosing a quality hospital. The empathy

service variables measured included nurses serving

regardless of social status, providing guidance about

illness and its prevention, communicating with

patients well, introducing themselves to patients and

giving attention. Responsiveness is one factor the

results of this study prove that the quality of service

in the empathy dimension significantly influences

patient satisfaction in pregnancy and childbirth

services.

Empathy can be done by getting patients to

communicate effectively about the conditions of

pregnancy and childbirth. Hospitality and courtesy in

dealing with patients are also evaluated where health

workers must be friendly and polite. Health workers

Forecasting Maternal Satisfaction with the Quality of Pregnancy and Childbirth Services using the ANFIS Method

137

must also provide opportunities for patients to express

health problems they face, and express feelings

during pregnancy, childbirth and also after childbirth.

All of that was delivered in language that is easily

understood by patients so that they feel satisfied and

also states that the quality of service was on the

empathy dimension.

Stages of the implementation of the Adaptive

Neuro-Fuzzy Inference System method in forecasting

maternal satisfaction based on the quality of

pregnancy and childbirth services is making a

flowchart design, conducting data clustering using

fuzzy C-Mean, determining the neurontiap of each

layer, looking for parameter values using recursive

LSE, then determining error calculation using a sum

square error and deciding on a model of forecasting

maternal satisfaction.

After the system was designed and used as a

system of forecasting maternal satisfaction with the

quality of pregnancy and childbirth services, the

system's accuracy level must be tested. In this study,

the involved 200 respondents' data from

questionnaires, where 2/3 of the overall data is used

as training data (150 data). The first step when

running a program for forecasting maternal

satisfaction is to enter data (150 training data) into the

training form as shown in Figure 2 (a) input the

required values that include tangible data, reliability,

responsiveness and target output in the form of

maternal satisfaction and then continue filling

training data Figure 2 (b). Training data here was

class, maximum epoh, error, learning rate and

momentum. Training data for class was 5, maximum

epoh was 40, error tolerance was 10-6 (Fig. 3 (a),

learning rate was 0.9 and momentum 0.6. By using

hybrid learning methods, ANFIS can map input

values towards output values based on knowledge

which is trained in the form of fuzzy rules.

Figure 3 (b) shows how the relationship of 150

data checking taken randomly from 200 data, with

FIS output was ANFIS learning outcomes from 150

training data. It can be seen that from the 100th data

up to 145 data distributions began to spread and

differs from the first 150 which tend to be converging.

This was because ANFIS has never recognize the

provided so it makes the accuracy in ANFIS method

decrease. After updating the rules about 1024 which

the variables are interconnected, the prediction model

design was obtained as shown in Figure 4. Figure 4

above is also called ANFIS Architecture which

consists of 5 input variables, each of which has 4

classes and the rightmost layer is the output in the

form of maternal satisfaction. Membership function

for input variables as a combination of membership

functions was triangular representation (trimf). Fig.5

is a comparison between satisfaction output measured

from the questionnaire towards ANFIS learning with

accuracy level of 97.48%. Those accuracy level

indicates that the designed predictive model could

predict the mather’s satisfication level with an error

value of 0.0251.

(a)

(b)

Figure 2: (a) Membership function and (b) Training data.

(a)

(b)

Figure 3: (a) Taining error about 10-6 and (b) Checking

data: FIS output.

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

138

Figure 4: (a) Deigned Model ANFIS for Mother’ s

Satisfication prediction.

Figure 5: (a) Classification accuracy about 97.48%.

4 CONCLUSIONS

Physical evidence, reliability, responsiveness, and

empathy affect patient satisfaction, while the

guarantee variable has no effect. The most influential

variable in this study is the responsiveness variable

which has a value of Exp (B) / OR = 7.985, which

means that patients who state good hospital

responsiveness, have the opportunity to feel satisfied

with pregnancy and childbirth services by 7.9 times

higher than the less well.

After conducting an experiment by entering the

class variable is 5, the maximum epoh is 400, error is

10-6, the range of learning rate values is 0.6 to 0.9,

and the range of values of momentum = 0.6 to 0.9.

The results that showed the smallest SSE were

learning rate 0.9 and momentum 0.6 with SSE

0.0251. The accuracy of the results of forecasting

maternal satisfaction with the ANFIS method is

97.48% with a relatively small error. These results

indicate that the design of a predictive model can be

used to predict the level of satisfaction of mothers

giving birth at a hospital based on quality criteria for

pregnancy and childbirth services.

REFERENCES

Ajayi, A. I., 2019. “I am alive; my baby is alive”:

Understanding reasons for satisfaction and

Dissatisfaction with maternal health care services in the

context of user fee removal policy in Nigeria. PLos

ONE 14(12):e0227010.

https://doi.org/10.1371/journal.pone.0227010

Amu, H and Nyarko S.H., 2019. Satisfaction with Maternal

Healthcare Services in the Ketu South Municipality,

Ghana: A Qualitaty Case Study. Biomed Research

International Vol 2019

https://doi.org/10.1155/2019/2516469.

Askar, M., 2019. Level of Satisfaction and Loyalty of

Mother towards Delivery Service at Labuang Baji

Hospital, Makassar Pub;isher: Humanistic Network for

Science and Technology 2019 Vol 3(2).

Azwar, A., 2016. Menjaga Mutu Pelayanan Kesehatan

(Cetakan 3). Jakarta: Pustaka Sinar Harapan.

Baety, A. N., 2015. Kehamilan dan Persalinan Panduan

Praktik Pemeriksaan. Yogyakarta: Graha Ilmu.

Barata, A. A., 2014. Dasar-Dasar Pelayanan Prima

(Cetakan 3). Jakarta: Elex Media Komputindo.

BPS, 2015. Survei Penduduk Antar Sensus (SUPAS) 2015.

Jakarta: Badan Pusat Statistik.

Burhanuddin, N., 2016. Hubungan Mutu Pelayanan

Kesehatan Dengan Kepuasan Pasien Rsud Syekh Yusuf

Gowa. Jurnal MKMI, 12(1), 41-46.

Dauletyarova, M. A et al (2018). Are Kazakhstani Women

Satisfied with Antenatal Care? Implementing the WHO

Tool to Asses the Quality of Antenatal Services.

International journal of Enviromental research and

Public Health 2018, 15, 325.

https://doi.org/10.3390/ijerph15020325

http://heanoti.com/index.php/hn/article/view/hn302

Dewi, G., 2015. Studi Pemanfaatan Pelayanan Antenatal

Terhadap Kelainan Kesehatan pada Ibu hamil di

Puskesmas Ulaweng, Kabupaten Bone. Fakultas

Kesehatan Masyarakat Universitas Hasanuddin

Makassar.

Dinkes Kota Medan., 2018. Profil Kesehatan Kota Medan

Tahun 2017. Medan: Dinas Kesehatan Kota Medan.

Dinkes Provsu. (2017). Profil Kesehatan Provinsi Sumatera

Utara Tahun 2016. Medan: Dinas Kesehatan Provinsi

Sumatera Utara.

Hermanto, D., 2010. Pengaruh Persepsi Mutu Pelayanan

Kebidanan Terhadap Kepuasan Pasien Rawat Inap

Kebidanan Di RSUD Dr. H. Soemarno Sosroatmodjo

Bulungan Kalimantan Timur. Program Pasca Sarjana

Universitas Diponegoro Semarang.

Hoseini B. L et al., 2019. Assesment of Maternal

Satisfaction with the Quality of Obstetric Care Provided

in the Maternity Unit of Mobini Hospital, Sabzevar,

Iran. Int J Pediatric 2019; 7(5):9367-9377.

http://doi.org/10.22038/ijp.2019.368662.3283.

Immas, H. A. P., Saryadi, & Dewi, R. S., 2013. Pengaruh

Kualitas Pelayanan terhadap Kepuasan Pasien di

Rumah Sakit Islam Kota Magelang. Jurnal Ilmu

Administrasi Bisnis, 2(3), 110-116.

Forecasting Maternal Satisfaction with the Quality of Pregnancy and Childbirth Services using the ANFIS Method

139

Jacobalis, S., 2012. Penilaian Mutu Pelayanan Kesehatan

dan Akreditasi Rumah Sakit. Jakarta: Kumpulan

Naskah Ilmiah Kongres PRSSI.

Kahar, A. W., Palu, B., & Raodhah, S., 2017. Pengaruh

Persepsi Mutu Pelayanan Kebidanan terhadap

Kepuasan Pasien Rawat Inap di RSUD Barru Sulawesi

Selatan Tahun 2017. Al-Sihah : Public Health Science

Journal, 9(2), 112–127.

Kemenkes RI., 2015. Kajian Kematian Ibu dan Anak di

Indonesia. Jakarta: Badan Penelitian dan

Pengembangan Kesehatan Kementerian Kesehatan

Republik Indonesia.

Kemenkes RI., 2017. Profil Kesehatan Indonesia Tahun

2016. Jakarta: Kementerian Kesehatan Republik

Indonesia.

Konian, KD et al., 2018. Perception of Pregnant Women on

Maternity Care Services at the Volta Regional Hospital,

Ghana. Int J of Community Medicine and Public

Health. 2018 jul:5(7)2699-2704

https://www.researchgate.net/publication/325947902

Kotler, P., & Keller, K., 2017. Manajemen Pemasaran

(Edisi 12). Jakarta: Indeks.

Kurniasari, A., & Kuntjoro, T., 2016. Analisis Kebutuhan

Pelanggan Puskesmas Pijoan Baru Provinsi Jambi.

Yogyakarta: Fakultas Kedokteran Universitas Gajah

Mada.

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.

Lemmens S.M.P et al., 2020. Perinatal Factors Related to

Pregnancy and Childbirth Satisfaction: a Prospective

Cohort study. Journal of Psychosomatic Obstetric &

Ginecology

https://doi.org/10.1080/0167482X.2019.1708894

Lupiyoadi, R., 2016. Manajemen Pemasaran Jasa

(Cetakan 5). Jakarta: Salemba Empat.

Mindaye, T., & Taye, B., 2012. Patients satisfaction with

laboratory services at antiretroviral therapy clinics in

public hospitals, Addis Ababa, Ethiopia. BMC

Research Notes, 4(5), 241-251.

Noreti, 2016. Analisis Pengaruh Kualitas Layanan

Terhadap Kepuasan Pasien Pada Puskesmas Mendawai

Kecamatan Arut Selatan Kabupaten Kotawaringin

Barat. Program Pascasarjana Universitas Terbuka.

Prawirohardjo, S., 2013. Buku Panduan Praktis Pelayanan

Kesehatan Maternal dan Neonatal. Jakarta: Yayasan

Bina Pustaka Sarwono Prawirahardjo.

Ristirini, 2007. Upaya Pemberdayaan Masyarakat Miskin

di Pedesaan dalam Rangka making Pregnancy Safer

(Analisis Situasi Upaya Pelayanan Kesehatan

Maternal). Jurnal Kedokteran Indonesia, 2(2), 21-29.

Rohani, 2016. Asuhan Kebidanan Pada Masa Persalinan

(Cetakan 2). Jakarta: Salemba Medika.

Sayed W et al., 2019. Maternal Satisfaction with Delivery

Services at Tertiary University Hospital in Upper

Egypt, is it actually Satifying. Int J reprod Contrecept

Obstet Ginecology. 2018 Jul; 7(7):2547-2552.

http://dx.doi.org/10.18203/2320-1770.ijrcog20182859

Simbala, W., Rattu, A. J. M., & Sondakh, R. C., 2013.

Hubungan Antara Kualitas Jasa Pelayanan Perawat

Dengan Tingkat Kepuasan Pasien Di Ruang Rawat Inap

Rumah Sakit Islam Sitti Maryam Kota Manado

(Fakultas Kesehatan Masyarakat Universitas Sam

Ratulangi).

Soepardan, S. (2015). Konsep Kebidanan. Jakarta: EGC.

Susmaneli, H., & Triana, A., 2014. Dimensi Mutu

Pelayanan Kebidanan terhadap Kepuasan Pasien

Program Jampersal. Kesmas: National Public Health

Journal, 8(8), 418-422.

https://doi.org/10.21109/kesmas.v8i8.414

Telaumbanua, Y., 2014. Pengaruh Kualitas Pelayanan

Terhadap Kepuasan Konsumen Dan Rekomendasi Dari

Mulut Ke Mulut Pada Pasien Klinik Dan Rumah

Bersalin Tabita Gunungsitoli. Program Pascasarjana

Universitas Suamtera Utara.

Tjiptono, F., & Chandra, G., 2015. Strategi Pemasaran

(Edisi 4).

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.

Varney, H., 2015. Buku Ajar Asuhan Kebidanan. Jakarta:

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.

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

140