STATISTICAL ANALYSIS ON HYPERTENSIVE

IN-PATIENT AND OUT-PATIENT

(A Case study of central hospital, Auchi)

BY

BALOGUN, ASHLEY GOODNESS

MAT NO: (ICT/2222004735)

A PROJECT SUBMITTED TO THE DEPARTMENT OF STATISTICS,

SCHOOL OF INFORMATION AND COMMUNICATION TECHNOLOGY,
AUCHI POLYTECHNIC, AUCHI, EDO STATE, NIGERIA

IN PARTIAL FULFILMENT OF THE REQUIREMENTS FOR THE

AWARD OF HIGHER NATIONAL DIPLOMA (HND) IN STATISTICS,

NOVEMBER, 2022
 CERTIFICATION

We, the undersigned, hereby certify that this project work was carried out by

BALOGUN ASHLEY GOODNESS with MATRIC NO: ICT/2222004735 of

the Department of Statistics, School of Information and Communication

Technology. Auchi Polytechnic, Auchi.

We also certify that the work is adequate in scope and quality in partial

fulfilment of the requirements for the award of Higher National Diploma (HND) in

Statistics.

___________________ ______________
MR. ADEYEMI, T.O Date
Project Supervisor

____________________ ______________
MR. BADA, O Date
Head, Department of Statistics

ii
 DEDICATION

This project work is dedicated to Almighty God and my beloved Mothers.

iii
 ACKNOWLEDGEMENT

A project of this magnitude would not have seen the light of the day but for

the encouragement and immeasurable contributions of a number of people.

Foremost, I thank God Almighty for making the completion of this project an

immersed success, if not for his mercies and grace I would not be able to do

anything.

My sincere acknowledgement goes to my project supervisor Mr. Adeyemi,

T.O who out of his busy schedule found time to go through this project work so I

could achieve the best also my sincere greetings also go to the Head of Department

of Statistics Mr. Bada, O for his contribution to the growth of the students and the

Department in general.

I also want to use this medium to acknowledge the contributions of family

members for their prayers, endurance, finance and encouragement. To all my

friends who have been my source of assistance morally and otherwise during these

period, most especially my B.A.T brothers, May the blessings of the Almighty be

with you all.

iv
 TABLE OF CONTENTS

TITTLE PAGE i
CERTIFICATION ii
DEDICATION iii
ACKNOWLEDGEMENT iv
TABLE OF CONTENTS v
ABSTRACT vii
CHAPTER ONE: INTRODUCTION 1
1.1 Background of the Study 1
1.2 Statement of the Problem 3
1.3 Aims and Objectives of the Study 3
1.4 Significance of the Study 4
1.5 Scope of the Study 4
1.6 Limitation of the Study. 5
1.7 Definition of Terms 5
CHAPTER TWO: LITERATURE REVIEW 7
2.1 Introduction 7
2.2 Current literature of the Review 7
2.3 Relevant theory of the Review 15
2.4 Summary of the Review 17
CHAPTER THREE: RESEARCH METHODOLOGY 18
3.1 Research Design 18
3.2 Target Population of the Study 18
3.3 Sample Inclusion Criteria 18
3.4 Method of Data Collection 19
3.5 Method of Data Analysis 19
3.5.1 Deseasonalized Data 20
CHAPTER FOUR: DATA PRESENTATION, ANALYSIS, AND DISCUSSION 22
4.1 Data Presentation 22

v
4.2 Data Analysis 24
4.3 Discussions 35
CHAPTER FIVE: SUMMARY CONCLUSION AND RECOMMENDATIONS 37
5.1 Summary of Findings 37
5.2 Conclusion 38
5.3 Recommendations 38
REFERENCES 40

vi
 ABSTRACT

Hypertension is a killer disease that should be taking seriously. The purpose of this
research work was to carry out a statistical analysis on hypertensive (in-patient and out-
patient) using the central hospital, Auchi as a case study. The secondary method of data
collection was used to obtain data from the hospital records of hypertensive inpatient
and outpatient. The decomposition method of time series analysis was adopted by the
researcher to forecast for the number of hypertensive inpatient and outpatient, this was
achieved with the use of Minitab statistical software; the findings shows that there is an
increase in the number of hypertensive outpatient but a reduction in the hypertensive
inpatient. The research concluded that the hospital should pay more attention to
outpatient as patient rather gets treatment and go home than be admitted as an inpatient
the research recommends that the management of central hospital should put in
place corrective measure to check the way in which hypertensive inpatients are
attended to as it might be a drawback to why patient prefer outpatient visit than
been admitted for proper checks.

vii
 CHAPTER ONE

INTRODUCTION

1.1 Background of the study

According to World Health Organization (WHO), Hypertension is also known

as high or raised blood pressure, is a condition in which the blood vessels have

persistently raised pressure. Blood is carried from the heart to all parts of the body in

the vessels. Each time the heart beats, it pumps blood into the vessels. Blood

pressure is created by the force of blood pushing against the walls of blood vessels

(arteries) as it is pumped by the heart. The higher the pressure, the harder the heart

has to pump. Hypertension is a serious medical condition and can increase the risk

of heart, brain, kidney and other diseases. It is a major cause of premature death

worldwide, with upwards of 1 in 4 men and 1 in 5 women – over a billion people -

having the condition.

The burden of hypertension is felt disproportionately in low- and middle-

income countries, where two thirds of cases are found, largely due to increased risk

factors in those populations in recent decades (WHO, 2021). High blood pressure is

a common condition that affects the body's arteries. It's also called hypertension. If

you have high blood pressure, the force of the blood pushing against the artery walls

is consistently too high. The heart has to work harder to pump blood Basile J,

1
 (2022). Blood pressure is measured in millimeters of mercury (mm Hg). In general,

hypertension is a blood pressure reading of 130/80 mm Hg or higher.

The American College of Cardiology and the American Heart Association

divide blood pressure into four general categories. Ideal blood pressure is

categorized as normal.)

 Normal blood pressure. Blood pressure is 120/80 mm Hg or lower.

 Elevated blood pressure. The top number ranges from 120 to 129 mm Hg and the

bottom number is below, not above, 80 mm Hg.

 Stage 1 hypertension. The top number ranges from 130 to 139 mm Hg or the

bottom number is between 80 and 89 mm Hg.

 Stage 2 hypertension. The top number is 140 mm Hg or higher or the bottom

number is 90 mm Hg or higher.

Blood pressure higher than 180/120 mm Hg is considered a hypertensive emergency

or crisis. Seek emergency medical help for anyone with these blood pressure

numbers.

Untreated, high blood pressure increases the risk of heart attack, stroke and other

serious health problems. It's important to have your blood pressure checked at least

every two years starting at age 18. Some people need more-frequent checks.

2
Healthy lifestyle habits such as not smoking, exercising and eating well can help

prevent and treat high blood pressure. Some people need medicine to treat high

blood pressure (Thomas G, 2022).

1.2 Statement of the problem

Patients will visit the hospital for treatment because at some point, some

number of persons will fall ill and would require medical attentions, this may be due

to accumulated stress, change of environment and so on. Some will be admitted to

the hospital while some will be attended to and thereafter leave the hospital after

receiving treatment. This project therefore seeks to redress the issue of hypertensive

patient (in-patient and out-patients) visit to the hospital for treatment and also

intends to employ the use time series analysis to model the attendance of inpatient

and outpatient in central hospital Auchi using the records obtained from the hospital.

1.3 Aims and Objectives of the study

The aim of this study is to carry out a time series analysis on in-patient and

out-patient on hypertensive patient in central hospital, Auchi; the specific objectives

are:

i. To examine the general trend of hypertensive patient in central hospital,

Auchi;

3
 ii. To determine the records of hypertensive inpatients attendance in central

hospital.

iii. To determine the records of hypertensive outpatient’s attendance in central

hospital.

iv. To fit a trend for inpatient on hypertensive patient using the decomposition

method of time series.

v. To fit a trend for outpatient on hypertensive patient using the decomposition

method of time series.

vi. Use the time series model to forecast hypertensive inpatient

vii. Use the time series model to forecast hypertensive outpatient

1.4 Significance of the study

This study is significant in the following ways;

i Help the hospital management to know how to cater for their patients and the

allocation of patient to doctors which can help reduce the waiting time of patient in

the hospital.

ii. For those who may intend to carry out project of this nature, this project may

serve as a reference point to the researcher.

iii. To understand the importance of trend analysis in pattern of patience

(inpatient and outpatient) attendance.

4
1.5 Scope of the study

The cumbersome nature of the project would not be able to look at every area

of hospitals in the area of study; hence, this study is limited to Central hospital

Auchi. The scope of the study is also limited to the use of patient (inpatient and

outpatient) record who were admitted for hypertension in the hospital. The

Decomposition of time series analysis will be adopted for the data analysis.

1.6 Limitation of the study.

Every project has its own shortcoming which ranges from finance to data

collection and so on. This project is no exemption of such short comings, leaving the

class to the hospital where data was collected was one major shortcoming because I

have to forfeit lectures sometimes for data collection so that the aim of the project

can be met.

1.7 Definition of terms

Health: the state of being free from physical or psychological disease, illness, or

malfunction; or wellness.

Healthcare: the act of taking care of ones’ health.

Hospital: this is an institution of health where sick persons are been taking and

attended to.

5
Inpatient: these are patient who comes to receive treatment and they are been

admitted in the hospital

Outpatient: these are patient who comes to the hospital for treatment and leaves

after the check-up is complete.

Surgery: A medical specialty that uses operative manual and instrumental

techniques on a patient to investigate and/or treat a pathological condition such as

disease or injury to help improve bodily function or appearance or sometimes for

some other reason.

VCT: Voluntary Counseling and Testing (VCT) for HIV

6
 CHAPTER TWO

LITERATURE REVIEW

2.1 Introduction

Patient (in-patient and out-patient) attendance is only a way to describe how

patient comes into the hospital for treatment at different arrival time for different

purposes. It deals with drug, equipment, treatment, human resources and other

relevant information on how the patient is been attended to whether he will be

admitted or allowed to go back home after receiving treatment. They are a means to

create legible and organized patient data and to access clinical information about

individual patients. In contrast, this chapter will discuss the project work under the

following headings; current literature review, review of relevant theories and

summary of the chapter.

2.2 Current literature of the Review

Hospital is an institution for health care that provides treatment for patient by

specialized staff and equipment. Usually, hospitals are funded by the public sector,

by health organizations (for profit or non-profit), health insurance companies or

charities, including funds by direct charitable donations.

Historically, hospitals were often founded and funded by religious orders or

charitable individuals and leaders. Modern-day hospitals are largely staffed by

7
professional physicians, surgeons, and nurses. Hospitals are distinguished by their

ownership, scope of services, and whether they are teaching hospitals with academic

affiliations. Hospitals may be operated as proprietary (for-profit) businesses, owned

either by corporations or individuals such as the physicians or they may be

voluntary-owned by non-profit corporations, religious organizations, or operated by

federal, state, or city governments. Voluntary and non-profit hospitals are usually

governed by a board of trustees, selected from among community business and civic

leaders, who serve without pay to oversee hospital operations. Most community

hospitals offer emergency services as well as a range of inpatient and outpatient

medical and surgical services. Community hospitals, where most people receive

care, are typically small, with fifty to five hundred beds. These hospitals normally

provide quality care for routine medical and surgical problems. Some community

hospitals are non-profit corporations, supported by local funding. These include

hospitals supported by religious, cooperative, or osteopathic organizations (Bailey

N.T.J & Welch J.D (2012)). In the 1990s, increasing numbers of not-for-profit

community hospitals have converted their ownership status, becoming proprietary

hospitals that are owned and operated on a for-profit basis by corporations. These

hospitals have joined investor-owned corporations because they need additional

financial resources to maintain their existence in an increasingly competitive

industry. Investor-owned corporations acquire not for profit hospitals to build

8
market share, expand their provider networks, and penetrate new health care

markets.

Teaching hospitals are those tertiary hospitals affiliated with medical schools,

nursing schools, or allied-health professions training programs. Teaching hospitals

are the primary sites for training new physicians where interns and residents work

under the supervision of experienced physicians. Non-teaching hospitals also may

maintain affiliations with medical schools and some also serve as sites for nursing

and allied-health professions students as well as physicians-in-training. Most

teaching hospitals, which provide clinical training for medical students and other

health care professionals, are affiliated with a medical school and may have several

hundred beds. Many of the physicians on staff at the hospital also hold teaching

positions at the university affiliated with the hospital, in addition to teaching

physicians-in-training at the bedsides of the patients. Patients in teaching hospitals

understand that they may be examined by medical students and residents in addition

to their primary "attending" physicians. One advantage of obtaining care at a

university-affiliated teaching hospital is the opportunity to receive treatment from

highly qualified physicians with access to the most advanced technology and

equipment. A disadvantage is the inconvenience and invasion of privacy that may

result from multiple examinations performed by residents and students. When

compared with smaller community hospitals, some teaching hospitals have

9
reputations for being very impersonal; however, patients with complex, unusual, or

difficult diagnoses usually benefit from the presence of acknowledged medical

experts and more comprehensive resources available at these facilities. A teaching

hospital combines assistance to patients with teaching to medical students and nurses

and often is linked to a medical school, nursing school or university.

Public hospitals are owned and operated by federal, state, or local

governments. Many have a continuing tradition of caring for the poor. They are

usually located in the inner cities and are often in precarious financial situations

because many of their patients are unable to pay for services. The federal

government matches the states' contribution to provide a certain minimal level of

available coverage, and the states may offer additional services at their own expense.

This is the best type of hospital; it is set up to deal with many kinds of diseases and

injuries, and normally has an emergency department to deal with immediate and

urgent threats to health. This is the major health care facility in its region, with large

numbers of beds for intensive care and long-term care; and specialized facilities for

surgery, plastic surgery, childbirth, and bioassay laboratories. This is a special type

of hospital meant for a particular case like trauma centres, rehabilitation hospitals,

children's hospitals, seniors' (geriatric) hospitals, and hospitals for dealing with

specific medical needs such as psychiatric problems, certain disease categories such

10
as cardiac, intensive care unit, neurology, cancer centre, and obstetrics and

gynaecology, oncology, or orthopaedics problems.

A medical facility smaller than a hospital is generally called a clinic, and often

is run by a government agency for health services or a private partnership of

physicians (in nations where private practice is allowed).

In a hospital where patients are taken care of, when a patient visits the

hospital, the patient is an inpatient if he/she is admitted while is an outpatient when

he/she is not admitted. Or a patient is rushed in case of emergency. Some patients go

to a hospital just for diagnosis, treatment, or therapy and then leave as outpatients

without staying overnight; while others are admitted and stay overnight or for

several days or weeks or months as inpatients. Hospitals usually are distinguished

from other types of medical facilities by their ability to admit and care for inpatients

whilst the others often are described as clinics. When a patient enters the hospital the

following sequence of operation is carried out.

First and foremost, the patient is registered in the card/registration room, and

then the patient goes to the nurse’s workbench for examination (vital signs), the

nurses then carries the patient folder to the doctors’ workbench for diagnosis. After

the diagnosis, the patient is then sent to the laboratory for test or the patient is sent to

the pharmacy for collection of drugs; the pharmacy section checks the patients

prescribed drugs and cost them before the folder is sent to the bill office for billing.

11
 After diagnosis the patient can also be referred to another clinic or to see a

consultant in the same hospital. For example he/she may be referred for radiology

services (CT scan, MRI, and ultrasound) or to special services like dental care. There

may also be possibilities for surgical services. The inpatient may recover fully and

be discharged or die and will be given a death report. A Hospital is a place where

patients visit to for medical check-up or diagnosis and treatment. Hospitals provide

facilities like: -

Consultation and diagnoses of diseases by doctors; Provision of treatment

facilities; Facility for admitting Patients (providing beds, nursing, medicines etc.);

Immunization of patients/children.

Various operational works are done in a hospital; all these works are done manually

using papers as follows:

i. Recording information about the patients that visit a hospital for

treatment,

ii. Generating bills.

iii. Recording information related to diagnosis given to patients.

iv. Keeping record of the Immunization provided to children/patients.

v. Keeping information about various diseases and medicines available to

cure them.

12
 The health care sector is an area of social and economic interest in several

countries; therefore, there have been lots of efforts in the use of electronic health

records. Nevertheless, there is evidence suggesting that these systems have not been

adopted as expected, and although there are some proposals to support their

adoption, the proposed support is not by means of information and communication

technology which can provide automatic tools of support.

A striking and widely observable feature of outpatient clinics in Nigerian public

hospitals is the excessively long-time which patients are obliged to wait before

seeing their doctors. It is common to find that the average waiting time is several

hours contrary to patients’ expectations and the patients charter of England that

patients should not wait longer than 30 minutes before seeing their doctor (Adesanya

T, Gholahan O, Ghannam O, 2012). This long waiting time may be mainly due to

the single block appointment system practiced by these hospitals which entails

giving all the days’ prospective patients the same appointment time before the

beginning of the clinic and then serving them on a first come first serve basis. The

single block appointment system inherently favours long waiting times since it

requires all the patients of the day to arrive at the same time, before the

commencement of the clinic and then wait until they are served (Mardiah FP, Basri

MH, 2013). The modified block and scattered (time specific) appointment systems

spread the arrival of patients throughout the duration of the clinic and thus reduces

13
waiting time. In modified block scheduling a smaller number of patients are

assigned to smaller segments of time such as hourly throughout the clinic session

(MazaheriHabibi MR, Abadi FM, Tabesh H, Vakili-Arki H, Abu-Hanna A, Eslami

S, 2018). Individual scheduling, the most commonly used scheduling technique in

developed countries and some developing countries occurs when a single patient is

scheduled for a specific point in time, with the timing of the appointments

determined according to the supply of care providers and the mean time spent with

each patient.9Of the 3 common appointment types the scattered (time specific}

system has been shown to produce the highest reduction in waiting time (KlassenKJ,

Rohleder TR, 2016).

To keep patients waiting longer than absolutely necessary is clearly

undesirable on humanitarian grounds. In addition, excessive waiting time in most

users represents loss of man hours which could be better utilized for economic

productivity and national development or leisure. Also, the congregation of many

patients in hospital waiting rooms for several hours favours the spread of

communicable diseases like tuberculosis and increases the burden of nosocomial

infections in our hospitals. This highlights the need for an appointment system that

will facilitate reduction in waiting times to a level that patients will not have to wait

longer than 30 minutes before seeing their doctors. Long waiting times in outpatient

14
clinics negatively affect patients’ satisfaction and currently, organizations interested

in quality services that satisfy their clients always work to reduce waiting times.

In the past it was considered acceptable to expect clients in outpatient clinics

to wait for several hours before they are attended to by their doctor. However,

clients’ expectations are being shaped by service providers in other industries and

some private providers who give prompt service, and this may no longer be

considered to be the case. Also, an increasing number of clients who are having the

benefit of receiving care in more developed countries where time specific

appointments are given, and clients do not have to wait for hours to be served are

unable to understand why such an appointment system is not in operation in some

Nigerian public health facilities.

2.3 Relevant theory of the review

According to (Hahn-Goldberg. S et.al., 2014) the cost of attending to a patient

is dependent on if the patient will be attended to instantly or been admitted in the

hospital. Generally, it is argued that patient that are admitted in hospitals tend to pay

more compared to those who just come receive treatment and go, this might be due

to the intensive care been given to the patient when admitted into the hospital.

The service performance in any given medical institution is a function of how

effective the working system of that institution is. Students will always fall sick at

irregular interval and hence the clinic should always function at all time because

15
nobody can tell when illness would come. The manner to which these students are

attended to determines the effectiveness of the staffs and other facility been used in

the hospital Johnson W.L, Rosenfeld L.S. (2008).

Legal liability in all aspects of healthcare was an increasing problem in the

1990s and 2000s. The surge in the per capita number of attorneys and changes in the

tort system caused an increase in the cost of every aspect of healthcare, and

healthcare technology was no exception. Failure or damages caused during

installation or utilization of an automated hospital management system has been

feared as a threat in lawsuits. Some smaller companies may be forced to abandon

markets based on the regional liability climate. Larger EHR providers (or

government-sponsored providers of EHRs) are better able to withstand legal

assaults.

In some communities, hospitals attempt to standardize EHR systems by

providing discounted versions of the hospital's software to local healthcare

providers. A challenge to this practice has been raised as being a violation of Stark

rules that prohibit hospitals from preferentially assisting community healthcare

providers. In 2006, however, exceptions to the Stark rule were enacted to allow

hospitals to furnish software and training to community providers, mostly removing

this legal obstacle. Health Care services delivery especially in developing nations

such as Nigeria is continually hampered by very weak information infrastructure to

16
support data collection, collation, analysis and interpretation. This has led to a

myriad of problems such as poor and inadequate information for clinical care of

patients, education, research, and planning, budgeting and report generation amongst

others. The burdens of poor information infrastructure are missing and misfiled

patient’s records which are gradually becoming a norm while data reporting are

either absent or delayed to the point of un-usefulness. Hospitals are still groaning

with the burden of manual health records, absence of good health library and long

patient waiting time for documentation. They are still struggling to benefit from the

gains of information and communication technology, hence the need for Hospital

Management System.

2.4 Summary of the review

Having considered the above and other problems besetting information

management in our hospitals, this project aims at developing a model of controlling

the traffic encountered due to patient who patronise the hospitals. The goal is to

satisfactorily integrate all efforts to ensure successful design and implementation of

the hospital management system, which must result to precision, cost cutting and

efficient management. The product (Hospital Management System) must be very

accurate and suit all environments including large, medium or small-scale hospitals.

17
 CHAPTER THREE

RESEARCH METHODOLOGY

3.1 Research Design

The design adopted for this study is the descriptive survey. The researcher

considered this design appropriate for the study because it is conducted to have a

better understanding of the existing problem as stated in the objective of the study,

hence, it is difficult to manipulate variables instead the variables are only identified,

observed and measured.

3.2 Target Population of the study

The population of the study were the number of recorded hypertensive cases

in central hospital, during the study period (January 2015 – December 2020) in

Auchi. The available data contained is the sample frame from which the sample is to

be selected from. For the sake of this study the data were obtained from the records

of the central hospital Auchi.

3.3 Sample inclusion criteria

The observed case of hypertension during the period under study Jan 2015 –

Dec 2020 were utilized recorded cases of admitted hypertensive patient (inpatient)

18
and recorded cases of hypertensive visiting patient (outpatient) where the sampled

cases.

3.4 Method of data collection

The descriptive survey was employed and recorded data were used, which

signifies that the secondary method of data collection is appropriate for the study.

Separate records of inpatient and outpatient based on monthly attendance for six

years were extracted and the obtained data were used to plot the trend and also

understand the behaviour of plot and to create conclusion regarding the results

obtained to enable us deduce a valid recommendation to this effect.

3.5 Method of data Analysis

The method of data analysis adopted for this study is Time Series plot (Graph)

and model for the purpose of making forecast. Different methods and models are

adopted for the purpose of forecast and prediction but for this study, decomposition

method will be adopted to carry out the analysis. The decomposition method was

deemed accurate for the model because it creates an avenue for checking for the

presence of seasonal data and also forecast future occurrences.

Decomposition of time series: Decomposition of time series data is mainly

observation on monthly or quarterly data using additive or multiplicative model.

19
Decomposition using additive model: Decomposition using additive model helps

to eliminate cyclical component as cyclical fluctuations can only be observed in long

term data covering a long time. Therefore, it is not included in the model

Y t =T t + St + I t

The procedure involves in decomposition (Additive model)

Step 1: compute the time series data and check for seasonal component

Step 2: Deseasonalize the data by removing the seasonal component from the actual

value

Step 3: compute the trend from the deseasonalized data

Step 4: Deduct the trend figures from the deseasonalised data and remove the errors

(irregular variation).

Step 5: compute the MSE and MAD to adjudge whether the model is reasonable to

select the best from the different models.

n
1
MSE= ∑ e2
n i=1
n
1
MSD= ∑ ( e−e^ )2
n−1 i=1

( )
n
1
MAPE= ∑ e2 × 100
n i =1

3.5.1 Deseasonalized data

When we use smoothing we smooth out not only the seasonal variation but

also the random (irregular) variation that is always present throughout a time series.

20
What we might like to do is remove just the seasonal effect and leave any trend and

the random ups and downs back in the data. The resulting series gives us what is

known as “deseasonalized" data which may give us a clearer picture of what is

happening. To achieve this in a sensible manner we need a suitable model for the

process producing the original time series. We have already mentioned that two

possible models are an additive model and a multiplicative model, the latter being

converted into an additive model by taking logarithms. Our model takes the form

data=trend + cycle+error :

If we are interested in proportional or percentage changes then taking logarithms

may be more sensible. If the “height" variation of the irregular component or cycle

tends to increase as the trend increases then these components would appear to be

having a multiplicative effect so that we would try logarithms. Hence, this research

uses the Minitab 16 software to analyse the data collected.

21
 CHAPTER FOUR

DATA PRESENTATION, ANALYSIS, AND DISCUSSION

4.1 Data Presentation

The result of the data is represented based on the method of data analysis
described in chapter three. The data were also used to plot the time series graph and
also conduct a time series decomposition for the data which includes seasonal
indices and residual plot for both hypertensive inpatient and outpatient.
Table 4.1: Hypertensive outpatient Records
MONTH 2015 2016 2017 2018 2019 2020
January 10 14 22 21 23 12
February 12 11 21 18 19 21
March 14 12 11 19 12 18
April 15 12 16 11 12 10
May 15 22 10 17 15 17
June 21 12 16 19 14 17
July 19 15 20 20 20 19
August 17 13 19 16 15 11
September 10 20 19 20 13 20
October 14 12 12 21 15 22
November 12 10 20 20 13 19
December 21 19 13 18 12 13
Source: Central Hospital, Auchi, 2022

Table 4.2: Hypertensive inpatient Records

2015 2016 2017 2018 2019 2020
January 7 12 6 9 9 10
February 11 9 7 11 12 0
March 6 4 5 7 5 7
April 8 7 8 5 6 0
May 7 5 4 4 8 4
June 11 11 7 13 4 0
July 10 12 9 12 11 0
August 9 8 6 7 7 0
September 3 2 13 5 5 0
October 8 5 3 2 9 10
November 6 8 11 8 7 0
December 11 1 5 3 2 0

22
 Source: Central Hospital, Auchi, 2022

FIGURE 4.1: Original time series plot for hypertensive outpatient

FIGURE 4.2: Original time series plot of Hypertensive inpatient

The figure 4.1 shows the original time plot for hypertensive Outpatient. The

plot shows no specific pattern of increase and decrease but a random pattern. The

23
plot also shows evidence of seasonality which can be deseasonalized. The figure 4.2

shows the original time series plot Inpatient respectively. The hypertensive inpatient

plot also shows no specific pattern of increase and decrease but a random pattern.

The plot also shows evidence of seasonality which can be deseasonalized. The

inpatient data also have cases of no records which is as a result of no recorded cases

of hypertensive inpatient attending the hospital for that particular month or as a

result of strike action.

4.2 Data Analysis

The data as presented in 4.1 and 4.2 are analysed below using the component

decomposition method of time series. Showing the Residual data, seasonal data,

decomposition time plot were discussed.

FIGURE 4.3: Normal plot of Percentage response against residual for outpatient

24
Figure 4.4: Normal plot of Percentage response against residual for inpatient

The Figure 4.3 shows the normal probability plot for hypertensive outpatient

which indicates that the residuals from the analysis should be normally distributed,

meanwhile, the Hypertensive Outpatient data shows that the residuals appear to

follow a straight line. This shows some evidence of non-normality at the tails,

although it is not extreme.

The Figure 4.4 shows the normal probability plot hypertensive inpatient which

indicates that the residuals from the analysis should be normally distributed,

meanwhile, Hypertensive inpatient; residuals appears to follow a straight line with

some point around the tail end of the line. Hence, there exist some evidence of non-

normality at the tails, although it is not extreme.

25
 F
IGURE 4.5: plot of residual against fitted value for outpatient

F
IGURE 4.6: plot of residual against fitted value for inpatient
Based on the plot in figure 4.5, the residuals appear to be randomly scattered

about zero. Hence, no evidence of non-constant variance, missing terms, or the

26
existence outliers exists. Based on the figure 4.6, the residuals appear also appears to

be randomly scattered about zero. Therefore, there is no evidence of non-constant

variance, missing terms, or outliers exists. From the result of the plot above, it could

be said that the outpatient and inpatient attendance at the central hospital appears to

be random.

FIGURE 4.7: Histogram plot for hypertensive outpatient

FIGURE 4.8: Histogram plot for hypertensive inpatient

27
 The Figure 4.7 shows the histogram of the distribution of residuals for all

observation, the appearance of the histogram changes depending on the number of

intervals used to group the data, and hence, for Hypertensive Outpatient, there is

evidence of negative skewness and no evidence of existing of outliers.

The Figure 4.8 shows the histogram of the distribution of residuals for all

inpatient observation, the appearance of the histogram changes depending on the

number of intervals used to group the data, and hence, for Hypertensive Outpatient,

there is no-evidence of skewness and no evidence of existing of outliers.

FIGURE 4.9: plot of residual against observation order

28
FIGURE 4.10: plot of residual against observation order

The Figure 4.9 illustrates the graph plots of the residuals versus their expected

values of hypertensive outpatient when the distribution is normal. There is no

evidence that the error terms are correlated with one another. Hence, the Figure 4.9

also shows a plot of no evidence of non-constant variance, missing terms, or outliers

exists. Finally, the residuals appear to be randomly scattered about zero.

The Figure 4.10 illustrates the graph plots of the residuals versus their

expected values of hypertensive inpatient when the distribution is normal. The plot

shows no evidence that the error terms are correlated with one another. Hence, the

Figure 4.10 shows evidence of no non-constant variance, missing terms, or outliers

exists. Finally, the residuals appear to be randomly scattered about zero.

29
 F
IGURE 4.11: plot of component Analysis for Hypertensive outpatient

FIGURE 4.12: plot of component Analysis for Hypertensive inpatient

30
31
The decomposition procedure analyzes the trend and seasonal components of the

series that are in separate plots:

The top left chart shows the original observations of the time series while the second

chart shows the detrended data obtained by either dividing the data by the trend

component (multiplicative model), the third chart indicates the Seasonally adjusted

data obtained by either dividing the data by the seasonal indices (multiplicative

model). Seasonally adjusted and detrended data which is also represented by the

residuals. Hence, the hypertensive outpatient data, the figure 4.11 indicates the

detrended data and seasonally adjusted data are quite different from the original

observations, it could be concluded that a trend component and a seasonal

component were present in the data. The residuals graph also shows that the fitted

values are under predicted in part of the first annual cycle (the graph exhibits large

positive residuals in this regions).

The component analysis chart in figure 4.12 shows the original, detrend, seasonal

and seasonal adjusted data for hypertensive inpatient data. The top left chart shows

the original observations of the time series while the second chart shows the

detrended data obtained by either dividing the data by the trend component

(multiplicative model), the third chart indicates the Seasonally adjusted data

obtained by either dividing the data by the seasonal indices (multiplicative

model). Seasonally adjusted and detrended data which is also represented by the

32
residuals. Hence, the hypertensive inpatient data, the figure 4.12 indicates the

detrended data and seasonally adjusted data are quite different from the original

observations, it could be concluded that a trend component and a seasonal

component were present in the data.

F
IGURE 4.13: Seasonal analysis for hypertensive outpatient

F
IGURE 4.14: Seasonal analysis for hypertensive inpatient

33
 The figure 4.8 shows the plot for seasonal indices, the plot indicates that the

pattern of Hypertensive outpatient experiences an average downward movements in

the 3rd, 4th, 5th, 6th 10th and 11th months of the season and average experiences an

upward movements in the 1st, 2nd, 7th, 8th, 9th, and12th month. The chart of

percent variation by season shows that the 7th month has the least variation and the

1st month has the most variation. The boxplots of the detrended data by season show

that months where the absolute value of the seasonal effect is large--the 7th -- tend

to have less variation than months where the seasonal effect is smaller--the 1st, 2nd,

3rd, 4th, 5th, 6th, 8th, 9th, 10th, 11th, and 12th. There is an obvious effect of season

on the residuals in the boxplots of the residuals by season.

The figure 4.14 shows the plot for seasonal indices of hypertensive inpatient

data, the plot indicates that the pattern of Hypertensive inpatient experiences an

average downward movements in the 3rd, 4th, 5th, 9th 10th and 12th months of the

season and average experiences an upward movement in the 1st, 2nd, 6th, 7th, 8th,

and11th month. The chart of percent variation by season shows that the 5th month

has the least variation and the 10th month has the most variation. The boxplots of the

detrended data by season show that months where the absolute value of the seasonal

effect is large is the 5th and 6th and this tend to have less variation than months

where the seasonal effect is smaller--the 1st, 2nd, 3rd, 4th, 7th, 8th, 9th, 10th, 11th,

34
and 12th. There is an obvious effect of season on the residuals in the boxplots of the

residuals by season.

Figure 4.15: Actual, Fitted, Trends and forecast for hypertensive outpatient

FIGURE 4.16: Actual, Fitted, Trends and forecast for hypertensive inpatient

35
 From the figure 4.15, it is evident that there is an increasing rise in the trend of

hypertensive outpatient in the hospital as indicated by the fitted data. Based on the

accuracy measure for hypertensive inpatient by the decomposition result, it shows

that the mean average percentage error is 30.444 while the mean absolute deviation

is 2.971 and finally the mean standard deviation is at 13.507.

From the figure 4.16, it is evident that there is a good fit for the actual data as

indicated by the fit and a decreasing trend as indicated by the trend line for

hypertensive inpatient in the hospital as indicated by the fitted data. Based on the

accuracy measure for hypertensive inpatient by the decomposition result, it shows

that the mean average percentage error is 35.269 while the mean absolute deviation

is 2.3858 and finally the mean standard deviation is at 9.8066. The forecasted trend

also shows a decrease in the number of hypertensive inpatient indicating a reduction

of the hypertensive inpatient visit to the hospital.

4.3 Discussions

The result of the analysis as shown from the figure 4.1 and 4.2 indicated a

random movement in the trend pattern of hypertensive outpatient, this could be an

indication that seasonality also affects the manner in which patient visits the hospital

for hypertension treatment. The residuals in figure 4.3 should be normally

distributed, meanwhile, Hypertensive Outpatient; the residuals do not appear to

36
follow a straight line. Some evidence of non-normality exists at the tails, although it

is not extreme. Based on this plot, the residuals appear to be randomly scattered

about zero. Hence, no evidence of non-constant variance, missing terms, or outliers

exists. Finally, the residuals appear to be randomly scattered about zero. No

evidence exists that the error terms are correlated with one another. The forecasted

result also indicates a random pattern in hypertensive outpatient visit which signifies

that the month of July will record the highest number of hypertensive patient in the

hospital with the month of April experiencing the lowest case.

37
 CHAPTER FIVE

SUMMARY CONCLUSION AND RECOMMENDATIONS

5.1 Summary of findings

The research looks into the statistical analysis of Inpatient and Outpatient a

case study of Central hospital Auchi. The objective of the study is to evaluate the

trend based on the visit of the patients to the hospital and also use the decomposition

method of time series to forecast for future patients attendance of inpatients and

outpatients. To achieve the stated objectives, the original time series graph was

plotted and it shows a random pattern of movement which depicts that there is no

stable pattern of visit among inpatient and outpatient in the hospital as shown in the

figure 4.1 and 4.2. From the result as shown by the figure 4.15 shows that there is an

increase in the number hypertensive outpatient pattern of visits to the hospital while

the figure 4.16 shows hypertensive inpatient plot for the decomposition result, it

showed a decrease in the visiting pattern by the inpatient. The result of forecasted

trend showed an increasing number of outpatient while the forecasted result for

inpatient showed a decreasing attendance as shown by the decreasing trend line. The

trend result also showed that the mean absolute deviation (MAD) from the graph

will form a better fit as compared to the other two, because the MAD value is the

least among all three measure of accuracy. Hence since the mean absolute deviation

for inpatient have the least measure of accuracy, we conclude that the hospital

38
should be more concerned with patient who comes into the hospital receive

treatment and go back home.

5.2 Conclusion

Clinicians and administrators can collaborate to reduce hypertension. The

Success rate depends on an ability to understand health care as a system, including

the many interactions between patients, clinicians, support services and other

resources. The success rate also depends on an ability to pinpoint the bottlenecks and

system failures, particularly with respect to interactions between the patient and

doctors available for rendering service to available patients. This project work hence

presented the decomposition method of time series which have been used to model

and evaluate hypertensive inpatient and outpatient who visits the Central Hospital,

Auchi for treatment. As a result of the above findings, it is concluded that the

hospital should be more concerned with patient who comes into the hospital receive

treatment and go back home except for critical cases where the patient needs to be

admitted for proper care and examination.

5.3 Recommendations

At the end of the study after proper investigation the following

recommendation were proposed by the researcher.

39
 i. Following the declining nature of the trend in inpatient records, the researcher

recommends that the management of central hospital should put in place

corrective measure to check the way in which hypertensive inpatients are

attended to as it might be a drawback to why patient prefer outpatient visit

than been admitted for proper checks.

ii. The management should also try as much as possible to consider the time used

in attending to hypertensive inpatient and outpatient emergencies at the

hospital as this might be another drawback for the declining nature of patients.

iii. Drugs should be made readily available and proper administration of drugs

should be given to patients at the right time as delay can sometimes be

detrimental to the health of these patients.

iv. The administrators in the hospital should organize symposium for patients to

educate them on the need to visit the hospital frequently so as to help manage

their ailment.

40
 REFERENCES

Adesanya T, Gholahan O, (2012): Exploring the responsiveness of public and

private hospitals in Lagos. J Public Health Res. 2012; 1: e2.
American Heart Association (2021): sleep to cardiovascular health checklist.
American Heart Association. https://newsroom.heart.org/news/american-
heart-association-adds-sleep-to-cardiovascular-health-checklist. Accessed July
15, 2022.
Araoye M.A. (2003): Research methodology with statistics for health and social
sciences. 1st ed. Illorin: Nathadex Publishers. Sample size determination; pp.
115–21.
Bailey N.T.J & Welch J.D (2012) Appointment systems in hospital outpatient
departments. Lancet 259:1105–1108
Basile J, (2022): Overview of hypertension in adults. Libby P, (2021)., eds. Systemic
hypertension: Mechanisms, diagnosis, and treatment. In: Braunwald's Heart
Disease: A Textbook of Cardiovascular Medicine. 12th ed. Elsevier; Ask
Mayo Expert. Hypertension (adult). Mayo Clinic; 2021.
Brenner J, (2020). Mindfulness with paced breathing reduces blood pressure.
Medical Hypothesis. 2020;
Delone M & McLean J (2017): A dynamic approach for outpatient scheduling. J
Med Econ; 20(8): 786- 798.
Hahn-Goldberg S, Carter MW, Beck JC, Trudeau M, Sousa P, Beattie K. (2014):
Dynamic optimization of chemotherapy outpatient scheduling with
uncertainty. Health care Manag Sci 17(4):379-92.
Huang YL, Marcak J. (2015): Grid Patient Appointment Template Design to
Improve Scheduling Effectiveness. J Health C Eng 6(2):239-58.
Johnson W.L, Rosenfeld L.S. (2008): Factors Affecting Waiting Time in
Ambulatory Care Services. Health Services Research 3(4):286-295.
Klassen K. J, and Rohleder T. R. (2016): Scheduling outpatient appointments in a
dynamic environment. Journal of Operations Management.1996;14:83-101
Mann, J.F, (2022) Choice of drug therapy in primary (essential) hypertension.
https://www.uptodate.com/contents/search. Accessed July 18, 2022.

41
Mardiah F. P, Basri M. H (2013): The Analysis of Appointment System to Reduce
Outpatient Waiting Time at Indonesia’s Public Hospital. Human Resource
Management Research 3(1): 27-33
Mazaheri Habibi MR, Abadi FM, Tabesh H, Vakili-Arki H, Abu-Hanna A, Eslami
S. (2018): Evaluation of patient satisfaction of the status of appointment
scheduling systems in outpatient clinics: Identifying patients' needs. J Adv
Pharm Technol Res.9(2):51-55.
Thomas G, (2022): Blood pressure measurement in the diagnosis and treatment of
hypertension in adults. https://www.uptodate.com/contents/search. Accessed
July 18, 2022.

42
 Appendix
Table 4.1: Hypertensive outpatient Records
MONTH 2015 2016 2017 2018 2019 2020
January 10 14 22 21 23 12
February 12 11 21 18 19 21
March 14 12 11 19 12 18
April 15 12 16 11 12 10
May 15 22 10 17 15 17
June 21 12 16 19 14 17
July 19 15 20 20 20 19
August 17 13 19 16 15 11
September 10 20 19 20 13 20
October 14 12 12 21 15 22
November 12 10 20 20 13 19
December 21 19 13 18 12 13

Table 4.2: Hypertensive inpatient Records

2015 2016 2017 2018 2019 2020
January 7 12 6 9 9 10
February 11 9 7 11 12 0
March 6 4 5 7 5 7
April 8 7 8 5 6 0
May 7 5 4 4 8 4
June 11 11 7 13 4 0
July 10 12 9 12 11 0
August 9 8 6 7 7 0
September 3 2 13 5 5 0
October 8 5 3 2 9 10
November 6 8 11 8 7 0
December 11 1 5 3 2 0
Source: Central Hospital, Auchi

43
 Appendix 1
2015 2018
TREND DETREND SEAS DESE2 TREND DETREND SEAS DESE2
1.21 1.21
JAN 15.144 0.660 9 8.200 JAN 16.168 1.299 9 17.221
1.09 1.09
FEB 15.173 0.791 5 10.955 FEB 16.196 1.111 5 16.432
MA 0.83 0.83
R 15.201 0.921 8 16.710 MAR 16.225 1.171 8 22.678
0.72 0.72
APR 15.229 0.985 8 20.594 APR 16.253 0.677 8 15.103
0.95 0.95
MAY 15.258 0.983 5 15.706 MAY 16.282 1.044 5 17.800
0.95 0.95
JUN 15.286 1.374 7 21.950 JUN 16.310 1.165 7 19.860
1.21 1.21
JUL 15.315 1.241 7 15.612 JUL 16.339 1.224 7 16.434
1.04 1.04
AUG 15.343 1.108 7 16.233 AUG 16.367 0.978 7 15.278
1.10 1.10
SEP 15.372 0.651 1 9.086 SEP 16.395 1.220 1 18.173
0.94 0.94
OCT 15.400 0.909 2 14.861 OCT 16.424 1.279 2 22.292
0.87 0.87
NOV 15.429 0.778 7 13.680 NOV 16.452 1.216 7 22.800
1.02 1.02
DEC 15.457 1.359 3 20.525 DEC 16.481 1.092 3 17.593
2016 2019
1.21 1.21
JAN 15.485 0.904 9 11.480 JAN 16.509 1.393 9 18.861
1.09 1.09
FEB 15.514 0.709 5 10.042 FEB 16.538 1.149 5 17.345
MA 0.83 0.83
R 15.542 0.772 8 14.323 MAR 16.566 0.724 8 14.323
0.72 0.72
APR 15.571 0.771 8 16.476 APR 16.595 0.723 8 16.476
0.95 0.95
MAY 15.599 1.410 5 23.036 MAY 16.623 0.902 5 15.706
0.95 0.95
JUN 15.628 0.768 7 12.543 JUN 16.651 0.841 7 14.633
1.21 1.21
JUL 15.656 0.958 7 12.326 JUL 16.680 1.199 7 16.434
AUG 15.684 0.829 1.04 12.413 AUG 16.708 0.898 1.04 14.323

44
 7 7
1.10 1.10
SEP 15.713 1.273 1 18.173 SEP 16.737 0.777 1 11.812
0.94 0.94
OCT 15.741 0.762 2 12.738 OCT 16.765 0.895 2 15.923
0.87 0.87
NOV 15.770 0.634 7 11.400 NOV 16.794 0.774 7 14.820
1.02 1.02
DEC 15.798 1.203 3 18.571 DEC 16.822 0.713 3 11.729
2017 2020
1.21 1.21
JAN 15.827 1.390 9 18.041 JAN 16.850 0.712 9 9.840
1.09 1.09
FEB 15.855 1.324 5 19.171 FEB 16.879 1.244 5 19.171
MA 0.83 0.83
R 15.884 0.693 8 13.129 MAR 16.907 1.065 8 21.484
0.72 0.72
APR 15.912 1.006 8 21.967 APR 16.936 0.590 8 13.730
0.95 0.95
MAY 15.940 0.627 5 10.471 MAY 16.964 1.002 5 17.800
0.95 0.95
JUN 15.969 1.002 7 16.724 JUN 16.993 1.000 7 17.769
1.21 1.21
JUL 15.997 1.250 7 16.434 JUL 17.021 1.116 7 15.612
1.04 1.04
AUG 16.026 1.186 7 18.142 AUG 17.050 0.645 7 10.504
1.10 1.10
SEP 16.054 1.183 1 17.264 SEP 17.078 1.171 1 18.173
0.94 0.94
OCT 16.083 0.746 2 12.738 OCT 17.106 1.286 2 23.353
0.87 0.87
NOV 16.111 1.241 7 22.800 NOV 17.135 1.109 7 21.660
1.02 1.02
DEC 16.140 0.805 3 12.706 DEC 17.163 0.757 3 12.706

45