DESIGN AND IMPLEMENTATION OF DATA MINING FOR MEDICAL RECORD SYSTEM

ABSTRACT

Data mining is the extraction of hidden predictive information from large database which helps in predicting future trend and behavior thereby helping management make knowledge driven decisions. The data mining tool designed is to aid in quick access and retrieval of patients information to avoid time wasted in retrieving of such data from hospitals data warehouse. The data mining tool was also designed to discover hidden pattern that helps in decision making by management. Structured System Analysis and Design Methodology were used in the analysis of the existing system which also provided a guide for the design of the proposed system.

PHP programming language and my SQL was used in the creation of a data warehouse for patient‟s information and data mining tool for the retrieval of such information when needed.

TABLE OF CONTENTS

CHAPTER ONE

INTRODUCTION

11  Background of Study

12   Statement of the Problem

13   Objectives of Study

14   Significance of Study

15   Scope of Study

16   Limitations of Study

17   Definition of related terms

CHAPTER TWO

REVIEW OF RELATED LITERATURE

21     Introduction

22  Review of related literature

CHAPTER THREE

SYSTEM ANALYSIS AND METHODOLOGY

31  System   analysis

32  Method of data collection

321 Interviewing key officer

322 Observation method

323 Examination of document

33  Analysis of the existing system

331 Organization profile chart

332  Advantages of the existing system

333 Disadvantage of the existing system

34  Analysis of the proposed system

341 Justification of the proposed system

35 Methodology

351 Recommended appropriate mode

CHAPTER FOUR

SYSTEM DESIGN AND IMPLEMENTATION

41 Overview of design

42 Main menu

43 Program modules specification

431 Database design and specification

432  Input/output specification

433 Input form

434 Output form

4341  Medical record system

44   Flowchart of the proposed solution

45 Choice and justification of programming language

46 System requirement

47 Implementation plan

471 Testing

4

72 Conversion

473 Training

48   Maintenance details

CHAPTER FIVE

SUMMARY, RECOMMENDATIONS, CONCLUSION

51     Summary

52  Review of achievements

53   Areas of application

54  Suggestion for further studies

55   Recommendation

56    Conclusion

REFERENCES

APPENDIX A (Program codes)

APPENDIX B (Sample, output forms)

CHAPTER ONE

INTRODUCTION

11    BACKGROUND OF STUDY

Data mining, is the extraction of hidden predictive information from large database, is a powerful new technology with great potential to help companies focus on the most important information in their data warehouses Data mining tools predict future trends and behaviors, allowing businesses to make proactive, knowledge driven decisions The automated, prospective analysis offered by data mining move beyond the analyses of past events provided by retrospective tools typical of decision support systems Data mining tools can answer business questions that traditionally were too time consuming to resolve The scour databases for hidden patterns, finding predictive information those experts may miss because it lies outside their expectations

Most companies already collect and refine massive quantities of data Data mining techniques can be implemented rapidly on existing software and hardware platforms to enhance the value of existing information resources, and can be integrated with new products and system as they are brought on-line Which implemented on high performance client/server or parallel processing computers, data mining tools can analyze massive database to deliver answers to questions such as “Which client are most likely to respond to my next promotional mailing, and Why?”

Data mining techniques are result of a long process research and product development This evolution began when business data was first stored on computers, continued with improvement in data access, and more recently, generated technologies that allow users to navigate through their data in real time Data mining takes this evolutionary process beyond retrospective data access and navigation to prospective and proactive information delivery

Data mining is ready for application in the business community because it is supported by three technologies that are sufficiently mature: massive data collection, powerful multiprocessor computers and data mining algorithms In this evolution from business data to business information, each new step has built upon the previous one For example, dynamic data access is critical for drill-through in data navigation applications, and the ability to store large database is critical to data mining

The file management is obsolete in developed countries like the United States where and in developing countries like Nigeria the file system is still processed manually in most medical centers; this is as a result of low standard of technology It was clear that computer is everywhere in Nigeria These computers are for money making and as a result of this, our hospitals lack computerized services, but with the help of data mining we can also computerize our hospitals

12    STATEMENT OF THE PROBLEM

The problem of data mining has become very crucial in areas of privacy of data Specifically regarding the source of the data analyzed for certain purpose My research in Owerri General Hospital here reveals that patients visit the hospital and they waste a lot of time The patients waits for the nurses or the attendants to get their data and there are volumes of files to search through before the patients files is finally retrieved or the patients might forget his/her card when visit the hospital

It there means that the patient‟s data cannot be found due to the fact that the Nurse does not know the patients number In this case it is either that the patients is denied treatment by the Doctor or the Nurses will check through the volumes of files in order to retrieved his/her data, this is time consuming problem There is a problem of misplacing of patients data, the non-availability of relevant forms like x-ray/laboratory forms and chats (pressure chats temperature) and requirement of more workers to carry the folders into the consulting rooms as an evident

Moreover, there are mistakes in entering patient‟s records Two patients might be given the same number and there could be wrong spelling and loss of important information There is also lack of space for storing all the files and also due to carelessness on the part of staff

Furthermore, volume of work for the hospital staff is much; this is because the ratio of patients to staff of Owerri General Hospital is so much So staffs are over worked and they hurry through their duty, hence they carry out such duties lousily which makes the Doctors unfriendly to their patients

13    OBJECTIVE OF STUDY

Objectives of this research work are to:

Create a data warehouse for storage of patient‟s information thereby eliminating manual file storage of patient‟s records

Design a good data mining tool that will help in easy retrieval of patient information thereby reducing time wastage and improve service delivery

The data mining tool will be able to discover hidden pattern in large volume of data which will help in good decision making

14    SIGNIFICANCE OF STUDY

This research will cover the creation of good database system for the management of patient‟s records in Owerri general hospital and also provide efficient data mining tool for easy retrieval of data and discovery of hidden patterns in large volume of data

15    SCOPE OF STUDY

This research work will be carried out on data mining for medical record system of Owerri General Hospital The work reported in this research could be viewed as a step towards enhancing databases with functionalities

16    LIMITATION OF STUDY

Data mining record is limited in that; some manual operation will still be needed to carry out the operation effectively There was some constraints encountered during collection of data, poor data collection becomes apparent due to interviewing of hospital representatives like the consultants Nurses, Doctors, Hospital attendants who were reluctant to disclose important information and statistical data which otherwise would have been relevant to this research, due to hospital secret which breeds some indifferent attitudes towards that

It takes a long time and large commitment of resources to get a good result, unavailability of text and materials on this topic, made gathering of facts very difficult, some of the facts were gathered from the internet, which is quite expensive

17    DEFINITION OF TERMS

Data Mining: Can be defined as “The nontrivial extraction of implicit, previously unknown, and potentially useful information from data, and “The science of extracting useful information from large data set or databases”

It involves sorting through large amounts of data and picking out relevant information

Information Retrieval: The act of locating quantities of data stored in a Database and producing useful information from the data

Information Processing: A method of organizing, processing and extracting information to be easily stored, retrieved, searched and updated

Record: It is a unit of data representing a particular transaction or a basic element of a file consisting in turn a number of interrelated data elements

Hospital: A hospital is an institution of medical treatment of the sick and injured people

Model: Is a pattern or mathematical/symbolic representation of real life

System and or abstract system behaviors

Artificial Intelligence: It is a branch of computer science that is dedicated to the study of the ways in which computers can be used to emulate or duplicate most human function

Knowledge Base: Is an organized collection of declarative and procedural relationships that represents expertise in a focused area