CHAPTER ONE

1.0 INTRODUCTION

Operation Research (OR) existed as a scientific discipline since 1930’s. It is a discipline

of applying appropriate analytical methods for decision making. OR has been studied in health
care settings since 1952. One of the major uses of operational research in healthcare is in the
form of Queuing theory. Queuing theory describes basic phenomena such as the waiting time,
the throughput, the losses, the number of queuing items, etc. in queuing systems. Following
Kleinrock (1975), any system in which arrivals place demands upon time capacity resource can
be broadly termed a queuing system.

Time is always a valuable asset for patients in seeking treatment at any healthcare center‚
either public or private, and even more valuable for patients who are in critical conditions.
Doctors” and specialists need to maximize their service time since some of them are assigned
administrative works, reading medical reports, and keep moving from one department to another.
Waiting idly in the waiting room is not a productive situation where patients can spend their
waiting time to do other activities that might benefit them rather than sitting for nothing.

A queuing process consists of customers arriving at a service facility, waiting in a line

(queue) if all servers are busy, then receiving service and finally departing from the facility. A
queuing system is a set of customers, a set of servers and an order where by customers arrive and
processed. Queues (waiting lines) are a part of everyday life. We all wait in queues to buy a
movie ticket, make a deposit, mail a package, obtain food in cafeteria, pay for goods, etc. queues
are formed because resources are limited.

The study is designed to help the management of Diagnostic Hospital about the employee
adequacy and also help to reduce patient waiting time for services. Improving service delivery at
the Medical Centre is the primary objective of the study. Hence, this chapter critically discusses
the background to the study. The chapter also looks at the statement of the problem, the objective
of the study and the significance of the study. It also highlights on the research methodology
used, the scope, limitations and the organization of the study

1
1.1 BACKGROUND TO THE STUDY

A queue is a waiting line, whether of people; signals or things (Ashhley, 2000). Queuing
time is the amount of time a person, signal or a thing spends before being attended to for services

Queuing theory is the Mathematical study of waiting lines. Queuing theory is generally
considered as a branch of operations research because its results are often used when making
business decisions about the resources needed to provide services. The theory seeks to determine
how best to design and operate a system usually under conditions requiring allocation of scarce
resources.

Queuing models are those-where a facility performs a service. A queuing problem arises
when the current service rate of a facility falls short of the current flow rate of customers. If the
size of the queue happens to be a large one, then at times it discourages customers who may
leave the queue and if that happens, then a sale is lost by the concerned business unit. Hence, the
queuing theory is concerned with the decision making process of the business unit which
confronts with queue questions and makes decisions relative to the numbers of service facilities
which are operating.

The earliest use of queuing theory was in the design of a telephone system. A queue can
be studied in terms of the source of each queued item, how frequently items arrive on the queue,
how long the item can or should wait, whether some items should jump ahead in the queue, how
multiple queues might he formed and managed, and rules by which items are queued or de-
queued.

The queuing theory enables mathematical analysis of several related processes, including
arriving at the (back of the) queue, waiting in the queue (essentially a storage process), and being
served at the front of the queue. The queuing theory permits the derivation and calculation of
several performance measures including the service, and the probability of encountering the
system in certain states such as empty, full, having an available server or having to wait a certain
time to be served. (Vohra, 2010).

The subject of queuing theory can be described as follows: consider a service center and
the population of customers, which at sometimes enter the system in order to obtain service. It is

2
often the case that the service center can only serve a limited number of customers. If a new
customer arrives and the service is exhausted, he/she enters a waiting line and waits until the
service facility becomes available. So we can identify three main elements of service center: a
population of customers, the service facility and the waiting line.

Queues are formed because of limited resources and they are experienced almost every
day. Thus queuing theory calculates the average time a customer spends in a system, the average
time a customer Spends in a line, and the average time customer spends in service queuing
theory is applicable to intelligent transportation systems, call centers, advanced
telecommunications.

Queuing Theory tries to answer questions like e.g. the mean waiting time in the queue,
the mean system response time (waiting time in the queue plus service times), mean utilization of
the service facility‚ distribution of the number of customers in the queue, distribution of the
number of customers in the system and so forth. These questions are mainly investigated in a
stochastic scenario‚ where e.g. the inter arrival times of the customers or the service times are
assumed to be random

1.1.1 THE OUT-PATIENT DEPARTMENT (OPD)

A hospital is an integral part of a social and medical organization, the function of which
is to provide for the population complete healthcare, both curative and preventive, and whose
out-patient services reach out to the family and its home environment. The out-patient
department in any hospital is considered to be the shop window of the hospital and it is the most
important service provided by all hospitals as it is the point of contact between a hospital and the
community.

Nowadays, Out-Patient Department (OPD) services of the majority of hospitals are

having queuing and waiting time problems. Patients" waiting time refers to the time from the
registration of the Patient for appointment with doctor till they enter the doctors chamber.

The main objective of the‚ out-patient department of a hospital should include the
reduction of patients" time in the system, improvement on customer service, better resource
utilization and reduction of operating costs.

3
 Waiting time in out-patient departments is a problem throughout the world. One
consistent feature of patient dissatisfaction has been expressed with the lengths of waiting time in
the out-patient department. Various functions affecting the services of an OPD are:

i. Arrival pattern or input rate of patients at the central waiting room.

ii Services time at various clinics of OPD.

iii. Queue lengths at waiting rooms of clinics of OPD.

The out-patient department provides health care to infants, children, adolescents, adults,
and geriatric patients in need of non-emergency physician care. The waiting time is particularly
important for a hospital, since the “customers” are patients.

Long wait creates customer dissatisfaction on one hand and resources inefficiencies on
the other hand. (Bharali, 2010).

1.2 STATEMENT OF PROBLEM

Queuing of patients at the healthcare system has some health and economic Implications.
Queuing create negative impression about the service delivery of an organization. Queues occur
in the hospital, banks, ATM terminal, at the petrol pumps and other settings. This study assesses
the queuing problem associated with the patients flow in the healthcare setting with Diagnostic
Hospital, Anyigba “as the case study. This study would assess the queuing situation at the Out-
Patient Department (OPD) of Diagnostic Hospital, Anyigba taken cognizance of the arrival rate,
inter arrival time, service rate and the inter-service time. This study would address the cost
associated with waiting time by recommending the number of doctors that give efficient
performance at the OPD.

1.3 AIM AND OBJECTIVES OF THF STUDY

i. The aim of this study is to determine an efficient queuing system for health care
organization of Diagnostic Hospital, Anyigba that will improve efficiency.
The objectives of the study are as follows:

4
 ii. To study the existing system of an efficient queuing system for health care
organization
iii. To design interface for an efficient queuing system for health care organization
iv. To design database for an efficient queuing system for health care organization
v. To evaluate the entire system and its functionality.

1.4 SIGNIFICANCE THE STUDY

This study has a theoretical significance because it has added to the frontiers of
knowledge as both scholars and student in the area of queuing system and its application.

The finding of this study is hope to assist the hospital administrators and management to
reduce the waiting time of patients in the system (outpatient clinic), improve on customer
service, and maximize the utilization of its resources (doctors, nurses, hospital beds, etc.).

The findings could also be used for appropriate staffing and facilities design.

1.5 SCOPE OF THE STUDY

The study looked at the outpatient department of Diagnostic Hospital, Anyigba. It

focused on the number of patients who came to the out-patient department ward for healthcare
delivery from March to August, 2022 between the hours of 8:00 am 2:00pm.

It looked at the waiting and service times of patients to see how much time they spend in
the out-patient department before they leave to their homes. These were done to achieve the
objectives of the study and to know the number of minutes or hours the service providers in the
hospital spend on their patients.

1.6 DEFINITION OF KEY TERMS

Arrival Process: includes number of customers arriving, several types of customers, and one
type of customers’ demand, deterministic or stochastic arrival distance, and arrival intensity.

Queuing Theory: is a collection of mathematical models of various queuing systems. It is used

extensive to analyze production and service processes exhibiting random variability in market
demand (arrival times) and service times.
5
Queue: this comprises those customers waiting to be served and does not include the one being
served.

Server Process: includes a type of a server, serving rate and serving time. This includes the
event “customer served” which prompts the next event “start serving next customer from queue”
(Troitzsch, 2006).

Simulation: is the replication of a real world process or system over time.

System: this comprises those customers waiting to be served as well as those being served.

Traffic Intensity: this is also called the proportion of time the server is busy or the probability
the system is busy.

Waiting Process: includes length of queues, servers’ discipline (First-In-First-Out). This

includes the event “start serving next customer from queue” which takes this customer from the
queue into the server, and at the same time schedules the event “customer served” at some time
in the future.

1.7 LIMITATION OF THE STUDY

The research is limited only to the out - patient department of the Diagnostic Hospital,
Anyigba. The data collection is limited to patients who arrived at the department before 2:00 pm.

The data gathered should have been every patient who attended the hospital during the
time that the study was conducted but due to time and financial constraints, the researcher was
limited to patients who arrived at the hospital at 12:00 pm on the number of days that the study
was conducted.

The researcher could not follow the patients while they moved from one section of the
department to the other. Preferably, the number of patients whose data were collected in the
record section should have been the same number of patients whose data were gathered in the
other two sections: Thus, the patients used in the record section are not the same patients used in
the history and consulting room sections. This happened because of the time limit put on the
study. It is however hoped that these shortfalls would not affect the findings of the study.

6
 CHAPTER TWO

LITERATURE REVIEW

2.0 INTRODUCTION

Because patient waiting is undesirable, limiting waiting time is an important objective

when designing a healthcare’ system. This section reviews work on queuing problems which are
most common features not only in our daily life situations such as healthcare centers, in
manufacturing, computer networking and telecommunications. Whenever customers arrive at a
service facility, some of them have to wait before they receive the desired service. It means that
the customer has to wait for his/her turn may be in a line.

However, this chapter reviewed relevant and adequate literature on queuing theory. It
contains other research findings that will assist the researcher and serve as a guide for future
research. The chapter also highlights on the history behind the theory being used and the basics
of queuing theory. Queuing theory application is an attempt to minimize the cost of providing
health care services through minimization of efficiencies and delays in the system (Singh, 2006).

McClain (1976) reviewed research on queuing models for evaluating bed assignment
policies on utilization, waiting time and the probability of turning away patients. Katz et al.,
(1991) put forward that hospitals, airline companies, banks, manufacturing firms etc., try to
minimize the total waiting cost, and the cost of providing service to their customers. Therefore,
speed of service is increasingly becoming a very important competitive parameter.

Green (2006) presented the theory of queuing as applied in health care. She discussed the
relationship among delays, utilization and the number of servers; the M/M/c models, its
assumptions and extensions and the application of the theory to determine the required number
of servers. Nosek et ‚al (2001) reviewed the used queuing theory in pharmacy applications with
particular attention to improving customer satisfaction. Customer satisfaction is improved by
predicting land reducing waiting time and adjusting staffing.

The provision of ever-faster service, with the ultimate goal of having zero customer
waiting time, has recently received managerial attention for several reasons (Davis et
al.,2003).1n the more highly ‚developed countries, where standards of living are high, time

7
becomes more valuable as a commodity and consequently, customers are less willing to wait for
service. This is a growing realization by organizations that the way they treat their customers
today significantly impact on whether or not they will remain loyal customer’s tomorrow.

Advances in technology such as computers, internet etc., have provided firms with the
ability to provide faster services. For these reasons hospital administrators, physicians and
managers are continuously finding means to deliver faster services, believing that the waiting
will affect after service evaluation negatively. Understanding the inefficiencies in the hospital
and improving them is crucial for making health care policy and budgeting decisions (Wilson et
al, 2004).

Agnihothri et al (1991) sought the optimal staffing a hospital scheduling department that
handles phone calls whose intensity varies throughout the day. There are known peak and non-
peak period of the day. The authors grouped the periods that receive similar call intensity and
determines the necessary staffing varies dynamically with call intensity. As a result of
redistributing server capacity over time, customer complaints immediately reduced without an
addition of staff. Davis et al (1990) stressed that patients’ evaluation of service quality is affected
not only by the actual waiting time but also by the perceived waiting time. The act of waiting has
significant impact on patient satisfaction. The authors concluded that the amount of time
customers must spend waiting can significantly influence their satisfaction.

Shimshak et al, (1981) considered a pharmacy queuing system with preemptive service of
prescription order suspends the processing of lower priority prescriptions. Different costs are
assigned to wait-times for prescriptions of different priorities. Queuing theory uses queuing
models or mathematical' models and performance measures to assess and hopefully improve the
flow of customers through a queuing system (Gorney, l98l; Bunday, 1996).

A good patient flow means that the patient queuing is minimized while a poor patient
flow means patients-suffer considerable queuing delays (Hall, 1999); Siddhartan et al., (1996)
analyzed the effect on patient waiting time when primary care patients use the Emergency
Department. The authors proposed a priority discipline for different categories of patients and
then a First-In-First-Out discipline for each category. The authors found that the priority

8
discipline reduces the average wait time for all patients. However, while the wait time for higher
priority patients reduces, lower priority patients endure a longer average waiting time.

2.1 QUEUING THEORY

Queuing theory as part of probability theory has evolved from classic telegraphic
engineering in the last decades. In 1909, Erlang, & Danish telegraphic engineer published a
paper called The Theory of Probabilities and Telephone conversations. In the early 1920s Erlang
developed the famous model to evaluate loss probabilities of multi-channel point-to-point
conversations. The author observed that a telephone system was generally characterized by
either (i) Poisson input (number of calls), Exponential holding (service) time, and multiple
channels (servers) or (ii) Poisson input, constant holding time and a single channel. The Erlang
model was extended to allow for calculation in finite source input situations by Engset several
years later leading to the Engest model.

The “Application of the Theory of Probabilities to Telephone Trucking Problems” was

soon published by Molina in 1927. The uses of the queuing theory to telephone. were soon used
by many. A year after Molina’s publications, Thornton Fry, published a book on “Probability
and its Engineering Uses”. This book expands much of the work done by Erlang.

Further work was done on the Poisson input, arbitrary output, and single and multiple
channel problems by Felix Pollazeck in the 1930s. Names such as Kolmogorov and Khintchine
in Russia, Coromnelin in France and Palm in Sweden also started in the same field of Felix
Pollazeck.

In 1951, Kendall published his work about embedded Markov chains, which is the basis
for the calculation of queuing systems under fairly general input conditions. The author also
defined a naming convention for queuing systems which is still used. Nearly at the same time
Lindley developed an equation allowing for results of a queuing system under fairly general
input and service conditions.

In 1957, Jackson started the investigation of networked queues thus leading to so called
queuing network models. With the appearance of computers and computer networks, queuing

9
system and queuing networks have been identified as a powerful analysis and design tool for
various applications.

It was only after the Second World War, however, that queuing theory was boosted
mainly by the introduction of computers and the digitalization of the telecommunications
infrastructure. For engineers, the two volumes by Kleim rock (1975,1976) are perhaps the most
Well kriown, while m applied mathematics, apart from the penetrating influence of Feller
(1970,1971), the Single Server Queue of Cohen (1969) is regarded as a landmark. Since Cohen’s
book, which incorporates most of the important work before 1969, a wealth of books and
excellent papers have appeared, an evolution that is still continuing today.

Queuing theory is the study of waiting in all these various situations. It uses queuing
models to represent the various types of queuing systems that arise in practice. The models
enable finding an appropriate balance between the cost of service and the amount of waiting
time.

2.2 CHARACTERISTICS OF QUEUING SYSTEM

Conceptually, the simplest queuing model is the single server queue. The system models
the flow of customers as they arrive, wait in the queue if the server is busy, receive service, and
eventually leave.

Arrivals Waiting space Serve departures

r
A queuing system consists of customers who have a certain arrival pattern, and are served at a
station consisting of a number of servers with a specific service pattern. In this respect we can
see that a basic queuing system, one that consists of a single service station, can be described by
the following characteristics.

i. Arrival Pattern: This is specified by the distribution of inter-arrival time of customers. An

important related quantity is the mean inter-arrival time. The reciprocal of the mean inter-arrival
time is referred to as the arrival rate.

ii. Service Pattern: It is specified by the distribution of the time taken to complete service. The
reciprocal of the mean service time is referred to as the service rate.

10
iii. Number of Servers: A number of servers may work in parallel, and an arriving unit can
choose randomly between any of the free servers. If all servers are busy, the unit joins a queue
common to all the servers. iv. System Capacity: There might be situations in which a queuing
system can only accommodate & limited number of Waiting units. In this case, if the number of
waiting customers plus those in service exceeds the system capacity, any further arrival does not
join the system and is lost.

v. Queue Discipline: If a customer arrives at the system at a time when the server(s) is(are)
unavailable to provide service, he/she is forced to wait in the queue temporarily if there is more
than one customer waiting in the queue at a time the server becomes available, one of the
customers in the queue is selected to start receiving service. The manner in which waiting
customers are taken in for service when a new server becomes available is referred to as the
service discipline.

In this work First Come First Served (FCFS) is assumed as the service discipline.

The multi-server queues (M/M/C): (/FCFS):

This refers to queuing systems in which there are two or more Servers. In these systems, all the
assumptions of the simple queue hold except that out one queue is now being served by two or
more servers. Customers of these systems form Single queue and whichever of the servers next
becomes idle takes on the person at the head of the queue. The full assumptions of the multi-
server queues are as follows.

(i) There is no limit to the permissible length of the queue

(ii) No customer leaves the queue without being served

(iii) Customers form a single queue waiting to be served by any of the servers who next become
free

(iv) The arrival of the customers to the service facility occurs according to the Poisson process

(v) The service time for each server follows the negative exponential distribution with same
mean

11
(vi) There is a first-in-first-served discipline for the queue.

Comments regarding the validity of each of the assumptions above are similar to those made for
the single queue except for assumption (v) which assumes that all the servers serve at the same
average rate.

The formulae for computing the basic parameters of the multi-server queuing systems become
more complicated if different service rates are assumed for the servers. The result given
assuming equal rates of service for all the servers are normally adequate approximation to
reality.

Assumption: The First-In-First-Out discipline for the queue will not necessarily mean First-In-
First-Out for the system since not all customers are served by the same server. A later arrival to
the system may well leave before an earlier customer who went to a different server and had a
longer service time. lf there are “C” servers or service channels in the system, and the mean
service rate in each of those channels is µ then it follows that the average service rate for the
whole system is Cµ.

2.3 QUEUE DISCIPLINE

Discipline of a queuing system means the rule that a server uses to choose the next customer
from the queue (if any) when the server completes the service of the current customer. The most
common used queue disciplines are:

i. First-Come-First-Serve (FCFS) Customers are served on first-in-first-served basis. This is

the most common discipline used in queuing Systems. For example, with a queue at the bus stop,
the people who came first will have their tickets first and Board the bus first.

ii. First-In-First-Out (FIFO) Customers are served on a First-In-First-Out basis. For example,
with a queue at the hospital, a patient who comes in first is served and leave before the others.

iii. Last-Come-First-Serve (LCFS)customers who come in last are Served first. Here, the
customers are serviced in an order reverse of the order in which they enter so that the ones who
join the last are served first. For Example, the people who join an elevator last are the first ones
to leave, it also assumes that letters to be typed, or order forms to be processed accumulate in a

12
pile, each new addition being put on the top of them. Thus, a just arriving task would be the next
to be serviced provided that no fresh task arrives before it is picked up

iv. Priority – the customers in a queue might be rendered service on a priority basis.
Thus, customers may be called according to some identifiable characteristics for
service. Example is treatment given to a very important personality in preference to
other patients in a hospital.

McQuarrie (1983) showed that it is possible, when utilization is high, to minimize waiting times
by giving priority to clients who require shorter service times. Thus rule is a form of the shortest
processing time rule that is known to minimize waiting times. It is found infrequently in practice
due to the perceived unfairness (unless that class of customers is given a dedicated server, as in
supermarket check-out systems) and the difficulty of estimating service times accurately.

2.4 THE SYSTEM CAPACITY (SIZE OF THE SOURCE POPULATION)

The system capacity is the maximum number of customers, both those in service and
those in the queues(s), permitted in the service facility at some time. Whenever a customer
arrives at a facility that is full, the arriving customer is denied entrance to the facility. Such a
customer is not allowed to wait outside the facility (since that effectively increases the capacity)
but is forced to leave without receiving service.

A system that has no limit on the number of customers permitted inside the facility has
infinite capacity. Examples of infinite capacities include shoppers arriving at a supermarket, cars
arriving at a highway toll booth, students arriving to register courses at a large University. Most
queuing models assume such infinite arrival population. A system with a limit on the number of
customers has finite capacity.

2.5 ATTITUDE OF CUSTOMERS IN THE QUEUING SYSTEM

Customers in the queuing system can be classified as being patient or impatient. If a

customer joins a queue if it exists, and wait till they enter the service station for getting service,
they are called patient customers. On the other hand, the queuing systems may enjoy customer
behavior in the form of defections from the queue. There may be jockeying among the many
queues that is a customer may switch to the queues which are moving fast. Reneging is also

13
possible in the queue. Here a customer stands in the queue for some time and then leaves the
system because it is working slowly. The probability that a patient renege usually increases with
the queue length and the patient’s estimate of how long he must wait to be served. In systems
where demand exceeds server capacity, reneging is the only way that a system attains a “state of
dysfunctional equilibrium” (Hall et al, 2006).

Some customers on the other hand, may decide not to join the queue for some reason and
may decide to return for the service later and this situation is known as balking. Blocking occurs
when a queuing system places a limit on queue length. For example, an outpatient clinic may
turn away walk-in patients when its waiting room is full. In a hospital, where in-patients can wait
only in a bed, the limited number of beds may prevent a unit from accepting patients.

Nasroallah (2004), McManus et al., (2004) presented a medical-surgical intensive care

unit where critically ill patients cannot be put in a queue and must be turned away when the
facility is fully occupied. This is a special case where the queue length cannot be greater than
zero, which is called a pure loss model (Green, 2006).

Koizumi et al, (2005) found that blocking in a chain of extended care, residential and
assisted housing facilities results in upstream facilities holding patients longer than necessary.
They analyze the effect of the capacity in downstream facilities. System-wide congestion could
be caused by bottlenecks at only one downstream facility.

2.6 QUEUING SIMULATION

The queuing system is when classified as M/M/c with multiple queues where number of
customers in the system and in a queue is infinite, the solution for such models are difficult to
compute. When analytical computation of T is very difficult or almost impossible, a Monte Carlo
simulation is appealed in order to get estimations. A standard Monte Carlo simulation algorithm
fix a regenerative system and generate a sample of regenerative cycles, and then use this sample
to construct a likelihood estimator of state. Nasroallah (2004), Although supermarket sales do
not have regenerative situation but simulation here issued to generate estimated solutions.

Simulation is the replication of a real world process or system over time. Simulation
involves the generation of artificial events or processes for the system and collects the

14
observations to draw any inference about the real system. A discrete-event simulation simulates
only events that change the state of a system. Monte Carlo simulation uses the mathematical
models to generate random variables for the artificial events and collect observations. (Banks,
2001)

2.7 LIMITATIONS OF QUEUING THEORY

The assumptions of classical queuing theory may be too restrictive to be able to model
real-world situations exactly. The complexity of production lines with product-specific
characteristics cannot be handled with those models. Therefore, specialized tools have been
developed to simulate, analyze, visualize and optimize time dynamic queuing line behavior.

For example, the mathematical models often assume infinite numbers of customers,
infinite queue capacity, or no bounds on inter-arrival or service times, when it is quite apparent
that these bounds must exist in reality. Often, although the bounds do exist, they can be safely
ignored because the differences between the real-world and theory is not statistically significant,
as the probability that such boundary situations might occur is remote compared to the expected
normal situation. Furthermore, several studies show the robustness of queuing models outside
their assumptions. In other cases, the theoretical solution may either prove intractable or
insufficiently informative to be useful.

Alternative means of analysis have thus been devised in order to provide some insight
into problems that do not fall under the scope of queuing theory, although they are often
scenario-specific because they generally consist of computer simulations or analysis of
experimental data. See network traffic simulation.

As discussed at several places earlier, queuing models have several limitations and are
used in conjunction with the other decision analysis methods like simulation and regression.
Most of these limitations are the basic assumptions for application of queuing models. Some of
the limitations of queuing models are enumerated below:

15
 i. Takes average of all variables rather than the real numbers itself
ii. Assumes steady state
iii. Based on assumption that service time is known
iv. Service times are independent from one another
v. Service rate is known
vi. Service rate is greater than arrival rate
vii. Service time is described by negative exponential probability distribution

2.8 MEASURING THE PERFORMANCE AND THE QUALITY OF QUEUING

SYSTEMS

Queuing system can be studied in so many ways to see the rate at which it is performing
and also used to judge the quality of services. We judge the quality of the service at least in parts
– by the time customers have to wait and the length of the queue which depends on three things

(i) The rate at which customers arrive

(ii) The time taken to serve each customer
(iii) The number of servers available
(iv) The performance of the queue can also be measured by:
(v) The time customers spend waiting
(vi) The average number of customers in the waiting line
(vii) The utilization rate of the server

Management uses these to make decisions or plans for improving upon the waiting line
operations.

2.9 HEALTH SERVICE CAPACITY PLANNING

It is common for health care managers to project workload for physical infrastructure and
manpower planning. This may be done at different departments, hospitals or even national level.

It is a common method to look at past trends, estimate the historical-year-on-year growth

and extrapolate this growth rate to the future. However, there are two potential problems. Firstly,
we seldom see a definitive trend and the estimate of “growth rate” is highly dependent upon the
start and the end points of time intervals. Secondly, the assumption of a long lasting trend is also

16
unrealistic. A health care utilization is often closely related to age, a more robust way to project
is to use population based drivers. We can first drive the age specific utilization rate, which is the
number of encounters (E.g. emergency or patient attendances, hospital admissions) as per
population specific to each age group.

With rapid change and realignment of health care system, new lines of services and
facilities to render the same service, financial pressure on the health care organizations and
extensive use of expanded managerial skills in health care setting, use of queuing models has
become quite prevalent in it. Queuing models are used to achieve a balance or tradeoff between
capacity and service delays.

2.10 COST ASSOCIATED IN QUEUING THEORY

2.10.1 Cost associated with patients or customers having to wait for the service

i. Loss of business to HCO, as some patients might not be willing to wait for the service
and may decide to go to the competing organizations.
ii. Costs incurred by society for example increased intervention and cost due to delay in
career the value of patient’s time.
iii. Decreased patient satisfaction and quality of care.

2.10.2 Costs of Providing the Service (Capacity Costs)

i. Salaries paid to employees

ii. Salaries paid to employees or servers while they wait for service from other server, for
example waiting for the pathology report, radiology report, labs, etc.
iii. Fixed costs – cost of waiting space, facilities, equipment, and supplies.
iv. If the organization decides to increase the level of service provided, cost of providing
services would increase, if it decides to limit the same, costs associated with waiting for
the services would increase. So the manager has to balance the two costs and make a
decision about the provision of optimum level of service

2.11 QUEUING THEORY AND HEALTHCARE

17
 The health systems should have an ability to deliver safe, efficient and smooth services to
the patients. Several key reimbursement changes, increasing critiques and cost pressures on the
system and increasing demand of quality and efficacy from highly aware and educated patients
due to advances in technology and telecommunications have started putting more pressure on the
healthcare managers to respond to these concerns. Queuing theory is an example of the use in
healthcare. It essentially deals with patient flow through the system, if patient flow is good then
patient queuing is minimized, if it is bad then the system may suffer loss of business and patients
may suffer considerable queuing delays. Health care system can be visualized as a complex
queuing network in which delays can be reduced through the following ways:

i. Synchronization of work among service stages (e.g., coordination of tests, treatments,

discharge processes)
ii. Scheduling of resources (e.g. doctors and nurses) to match patterns of arrival
iii. Constant system monitoring (e.g. tracking number of patients waiting by location,
diagnostic grouping and acuity) linked to immediate actions.

18
 CHAPTER THREE

3.0 RESEARCH DESIG

The research method used in this work is a quantitative research approach. The data
gathered is the daily record of queuing system over six months. The method used in this research
work will be the analysis of queuing systems and techniques and also the development of
queuing model for the analysis of queuing method and establish a method that will solve the
problem of customer’s arrival rate. The model will establish the actual time it takes to serve the
customer as at when due and estimate the actual working serves necessary in the organization.
This model developed was used to predict the actual number of servers and time it takes to solve
the problem of queuing or waiting before customers are been served as and at when due in the
establishment.

The project will be structured in phases, which will include gathering requirement, designing the
system, implementing it, conducting tests, and finally deploying it.

PHP will be the programming language. It will be complemented by other web technologies like
HTML and CSS. In terms of database management, Microsoft Access will be employed in
conjunction with MySQL as the database server.

Front- end technologies:

 HTML stand for (Hypertext Markup Language): Is the main markup language for
creating and saving web documents and other information that can be displayed in a web
browser. It provides a means to create structured documents by denoting structural
semantics for text such as headings, paragraphs, lists, links, quotes and other items.
 CSS stand for (Cascading Style Sheets): Is a style sheet tool used for describing the look
and formatting of a document written in a markup language. While most often used to
style web pages and interface written in HTML and XML, SVG and XUL.
 PHP stand for (People Home Page): Is an open source server –side programming
language that can be used to create websites, applications, customer relationship
management systems and more.

19
 Back- end technologies:

 MySQL stand for (Structured Query Language): Is a database management system

commonly used for querying accessing, updating and managing data.
 MS Access stand for (Microsoft Access) Is used to store large amounts of data in an
organized and efficient manner. It allows to create tables, forms, queries, and reports
to manage your data.

3.1 POPULATION OF THE STUDY

The study adopts a descriptive, observational and ex post factor case study approach. In depth
review of hospital OPD attendance records from March to August, 2022 was made. Interviews
with management, doctors, and records staff were conducted to validate the secondary data and
to gather information required to construct the structural model of the routings in and out of
OPD. Direct observations were used to model patient average arrival and length of stay.
Questionnaires were also used to gather information on daily arrival rates, patients’ view on
queuing at the hospital, waiting time to consult a doctor, etc.

The survey population of the study was the entire out-patients of Diagnostic Hospital
Anyigba during the period of the study. Purposive sampling, a non-probability sampling
technique in which the researcher selects a group of people because they have particular traits
that the researcher wants to study was used. The out-patient department was selected because it
had the greatest queuing challenge compared to the other units in the hospital.

3.2 SOURCES OF DATA COLLECTION

The source of data collection main used in this study was primary and secondary source
of data.

Primary Source: This deals with the data expressly collected for a specific purpose usually
through field research, questionnaire, observation and personal interview

Secondary Source: The secondary data is gotten from consultation of past records, textbooks,
medical registers, journals, periodic magazines, newspaper and other relevant literature on
queuing theory simulation.

20
3.3 METHOD OF DATA COLLECTION

3.3.1 Data Collection Procedure

The researcher visited the Diagnostic Hospital Anyigba and personally communicated
with the administrator of the hospital. The researcher was taken through all the various section of
the hospital. He sat among the patients at the various sections and recorded the data.

A stop watch was used to calculate the number of minutes spent by each patient from the
recorded section where patients collected their folders through to the last section (the consulting
room section). Data was collected on Monday to Friday from the hours of 8:00 am to 2:00 pm.
The number of arrivals (i.e. number of patients) from Out-Patient Department was taken.

3.3.2 Personal Interview

This is a step by step process of seeking information through asking of questions and
getting answers in return. Here, the question to be asked by researcher from the targeted
population (e.g. doctors, patients, nurses and ward attendants) on some selected subject matter of
the study.

3.3.3 Observation

This entails having a close contact with the phenomenon and obtains information by
seeing, hearing, feeling, touching etc.

3.4 METHOD OF DATA ANALYSIS

Data collected for the study were analyzed by the use of table, queuing models and an
application developed in Microsoft Access for the purpose.

The queuing model i.e M/M/c parameter in a steady-state condition is expressed below:

meanarrivlrate(Ω)
Traffic intensity ρ =
meanservicerate(Cμ)

Ω
Therefore, ρ =
Cμ

21
The following formulae also apply for the multi-server queue

(i) The probability of the system being empty (i.e. all servers are idle) is:

1
P0 =
M

where M = ∑ ❑ j¿ 0 ¿ ¿ + ¿ ¿.
c

(ii) The probability of “n” customers in the system (i.e. the probability there are “n”
customers in the system) is:

1
¿
Pn = ¿
c
c n 1
(iii) ρ
The average forallin ≤c
c ! number
M, of customers in the system E(Ls) is:

ρ¿¿

(iv) The average number of customers in the queue E(Lq) is:

ρ¿¿

(v) The average time customer spends in the system E(Ws) is:

ρ¿¿

(vi) The average time a customer spends in the queue E(Ws) is:

ρ¿¿

(vii) The probability (W>0) is: ( Ωμ ) c ρ0

c ! (1−ρ)

22
 CHAPTER FOUR

DATA PRESENTATION AND ANALYSIS

4.1 INTRODUCTION

This chapter deals with tabular data presentation as well as analysis of arrival rate,
service rate and optimizing the number of servers.

4.2 DATA PRESENTATION

This is a convenient way of summarizing the data in an orderly form so that result can be
represented consistently and effectively. The use of tabulation shall be consider for this project
work in order to reduces and simplify the data details in such a way that essential features are
easy to interpret and understand.

Table 1: Daily Count in DHA Out-Patient Department (March-August 2022)

DAY MARCH APRIL MAY JUNE JULY AUGUS TOTAL

T

1 104 - 99 96 - 94 326

2 114 93 95 - 113 96 481

3 - 98 85 - 97 112 371

4 - 93 106 91 87 - 360

5 106 105 - 103 105 - 289

6 107 96 - 98 94 117 442

7 118 - 108 81 - 111 320

8 119 - 117 113 - 88 367

9 110 103 90 - 88 91 441

23
10 113 74 89 - 95 84 514

11 - 85 111 92 118 - 406

12 86 97 - 100 84 - 327

13 84 98 - 87 107 118 494

14 109 - 115 105 - 120 360

15 80 - 98 100 - 115 357

16 101 101 97 - 102 107 448

17 - 96 105 - 75 94 370

18 - 76 107 115 90 - 388

19 88 82 - 80 96 - 346

20 103 113 - 92 88 114 480

21 83 - 96 83 - 95 337

22 108 - 108 102 - 98 346

23 94 99 91 - 98 116 438

24 - 117 112 - 86 109 319

25 - 100 99 117 93 - 400

26 89 97 - 87 81 - 324

27 103 109 - 80 118 93 493

28 97 - 118 105 - 85 365

29 85 - 99 104 - 117 358

24
 30 109 93 97 - 110 95 444

31 - - 101 - - 104 185

Source: Out-Patient Diagnostic Hospital Anyigba (March-August, 2022)

4.3 DATA ANALYSIS

This section deals with the analysis of data collected from all the three sections (records,
history and consulting room) of the out-patient department of the Diagnostic Hospital Anyigba.
The data for this analysis were collected on Monday, Tuesday, Wednesday, Thursday and
Friday.

The mean arrival rates and the mean service rates would be calculated from the data
collected and their results would be used to measure the performance of the entire system as
objected in chapter one.

25
Table 2: Input Parameter for QM in developed MS Access Application

Parameter M/M/c Values

Arrival Mate ( ) 20

Service Rate (mu) 12

Number of server (c i.e. doctors) 2,3,4 and 5 depending on the scenario

Figure 1 Queue Model Data Processing Form

26
Figure 2 Result of Sensitivity Analysis of 5 Model Scenarios from application

From the results of the sensitivity analysis for the modeling, scenario 4 with 5 doctors at post
produces inferior performance in comparison to the others with average number in the system
being 5.4545 (Ls), average time in queue (Wq) 0.1894, average number in the queue (Lq)
3.7879, and average time in the system (Ws) being 0.2727. Scenario 2 (3 doctors at post)
provides optimal performance of the system with average number in the system (Ls) being
2.0414, average time in queue (Wq) 0.0187 which is about 1 minute, yielding the productivity,
average number in the queue (Lq) 0.3747, and average time in the system (Ws) being 0.1021. the
change in time spend in the queue from three doctors (Scenario 2) four doctors at post (Scenario
3) is very appreciable. The average number in the queue (Lq) drops from 0.3747 with 3 doctors
to 0.0732 with 4 doctors. Similarly average time in the queue (Wq) drops from 0.1894 to 0.0197
respectively

27
At Diagnostic Hospital Anyigba, there are a total of ten doctors (servers) that provide service to
patient at the OPD department. However, five of these doctors, start the day by spending in
average of one hours seeing cases on the wards before starting the work at the outpatient clinic.
They also take one hour lunch break. The other five doctors also take one hour lunch break and
so effectively consult for six hours.

28