APPLICATION OF MULTIPLE REGRESSION ANALYSIS ON MEDICAL DATA

APPLICATION OF MULTIPLE REGRESSION ANALYSIS ON MEDICAL DATA.

(A case study of Aboh Mbaise General Hospital in Imo State)

 

Abstract

This project work is titled Application Of Multiple Regression Analysis On Medical Data, using Aboh Mbaise General Hospital in Imo State as the study area. Much time was given to obtain the secondary data used for the analysis of this research work. The data were subjected to descriptive analysis and Multiple  regression analysis and test at 5% significance level by the t-test. The results of the study indicated that blood pressure is 155.474 showing increase in blood pressure of patients. From the findings it indicates that 14.7% (144/981) were women and 9.9% (27/273) were men (P ¼ 0.046).  The study concludes that The blood pressure of patients is greatly related to the age groups and number of pregnancy of patients in the hospital. The study therefore recommends; The level of blood pressure is dependent upon age group of patients therefore treatments should be taken to control cases of hypertension and low hemoglobin level of patients admitted in hospitals, The analysis of medical data should be based on the use of multiple regression technique to vividly analyze the multiple variables of the study.

 

 

TABLE OF CONTENTS

 

CHAPTER ONE

This project work on; the application of multiple regression analysis on medical data, as collected from Aboh mbaise general hospital in Imo state Nigeria on the systolic blood pressure, age, hemoglobin level. In Nigeria, the negligence of substandard data source has been on the increase due to insufficient funding leading to poor analysis and uncultured decision making and planning in the global economy. This is essential due to the accelerated rate of research on improving income rate on civil and public servants within the country over the years. This section of this research study would be able to state the various objections, problem statement, significance and scope as well as its terminologies to be used in the process of this study for easy understanding of the concepts.

 

1.1    Background Of The Study

Important questions about health care are often addressed by analyzing health care utilization data. A finding that people with lower income or who live in certain areas of the country use fewer medical services can indicate problems with access to care and valuable data of their health. If patterns of use are found to vary by insurance plan, this may suggest positive or negative properties of managed care; Goodman, et al,(2000).

Ideally, we should all have a blood pressure below 120 over 80 (120/80). This is the ideal blood pressure for people wishing to have good health. At this level, we have a much lower risk of heart disease or stroke. If your blood pressure is optimal, this is great news. By following our healthy living advice, you will be able to keep it this way. If your blood pressure is above 120/80mmHg, you will need to lower it.

 

Most adults in Nigeria (Imo state) have blood pressure readings in the range from 120 over 80 (120/80) to 140 over 90 (140/90). If your blood pressure is within this range, you should be taking steps to bring it down or to stop it rising any further. The reason why people with blood pressure readings in this range should lower it, even though this is not classified as ‘high’ blood pressure, is that the higher your blood pressure, the higher your risk of health problems. For example, someone with a blood pressure level of 135 over 85 (135/85) is twice as likely to have a heart attack or stroke as someone with a reading of 115 over 75 (115/75).

Studies that show high variation among geographic areas in rates at which a surgical procedure is performed suggest that residents in some of those areas are not receiving optimal care. Another important area of research is prediction of total health care costs for a group of people for a year, so that providers can be paid appropriate rates for caring for those people.

Multiple regression methods are used extensively to adjust analyses for important patient characteristics or to predict future utilization for individuals. Utilization of data has several characteristics that make them a challenge to analyze particularly medical data. Over the years general approaches for analysis have evolved, and some new approaches are now possible because of advances in analytic methods and software. In this paper we discuss sources of data, the statistical properties of utilization data, common analytic methods, the use of newly available computing methods, study design, and methods for dealing with censored data.

In testing for independence, two variables are involved and the number of rows (r) and columns (c) would depend on the number of groups into which two variable are categorized. The table is called r x c contingency table. The intersection of rows and columns in the table form a total of r x c cells, which contain the observed frequencies Murray, R. (2008).

 

Finally, time series analysis and ANOVA will be employed. Time series is a set of observations on a variable measured at successive points in time or successive period of time. That is, time series forecasting models are based on assumption that past history is an indication of future expectation. It is a data generated in chronological order for the purpose of monitoring the performance of an aspect of the economy such as production and sales figures, stock levels, rainfall data and others.

There are four components of time series, they are: Trend component, Seasonal, Cyclical and Irregular variation Iwuagwu, E. (2004). For the purpose of this project work, the time series analysis used will be limited to estimation of the trend and forecasting for the next year only. This implies that the further application of time series will not be discoursed in this project work.

There exist limited studies which have exclusively studied the effect of family size on both savings and consumption expenses of the industrial workforce. Therefore, in this backdrop, the present study attempts to fill existing research lacunae through in-depth examination of the impact of family size on monthly savings and consumption expenditure of industrial and civil workers through the application of specific econometric tools. It further aims to study the pattern of savings and consumption expenses of workers by simultaneously analyzing and comparing their mean values across different family size groups in the area of Bori.

 

1.2    Statement Of Problem

The challenges of analyzing and collecting medical data is something worthwhile in the modern medical technology settings of today. This study therefore would determine how efficient the multiple regression analysis can be in analyzing the data on systolic blood pressure, number of pregnancies and age group of the patients could be efficiently analyzed using this statistical technique.. These data could involve age, blood pressure and hemoglobin level. How does number of ages causes blood pressure, does number of pregnancy affect or causes blood pressure. The increased use of multiple regression analysis in clinical research has many physicians usefulness and impact as it applies so many predictable variables. A better understanding of these regression techniques has become necessary the most commonly used regression analysis techniques is multiple regression. However, this study will be able to determine the relationship between

 

1.3   Aims And Objectives Of The Study.

Aims Of The Study

The study is aimed at examining the application of multiple regression in analysis of medical data, and to determine the efficiency of multiple regression in analyzing medical data.

Other objectives of this project work are stated below;

Objectives Of The Study

  1. To determine if the blood pressure of patients is related to their

age groups.

 

  1. To determine if the hemoglobin level of patients is  related to      their age groups

 

  1. To know if number of pregnancies is related to the age group of patients.

 

1.4   Statement Of Hypothesis

With the above objectives, the following null hypothesis is stated to guide the objectives of the study being achieved;

 

Ho1:   The blood pressure of patients is not related to the

age groups of patients in the hospital.

 

Ho2: The hemoglobin level of patients is not related to    the age      groups of patients.

Ho3The number of pregnancies is not related to the age group     of                patients.

 

1.5    Scope Of The Study

The scope of this project work covers multiple regression analysis on medical data in line with the respective procedures for ascertaining treatments to patients through the application of this concept. It covers the development of multiple influential factors that affect the analysis of medical related datasets. This study is designed to review the dependency of the various medical ailments mentioned in the objective above.

 

1.6    Significance Of The Study

The research study is designed to cover the application of multiple regression analysis on medical. This study is focuses on the following:

  • Tracking blood pressure during pregnancy.
  • To know when there is normal blood pressure.
  • To whether the age of a pregnant mother causes systolic blood pressure
    • Limitations of the study

Financial constraint– Insufficient fund tends to impede the efficiency of the researcher in sourcing for the relevant materials, literature or information and in the process of data collection.

More so, the issue of locating the historical data for the study is time consuming which affects the level of analysis. it is possible that the data used for the study is properly arranged , so it is assumed that the data is no consistent which took much for accuracy of the data to be collected.

Time constraint– The researcher will simultaneously engage in this study with other academic work. This consequently will cut down on the time devoted for the research work.

 

1.8    Definition Of Terms

Data: This is the set of unprocessed facts about an object or item in a population.

Regression: Is the technique of analysis that deals with only variables one depending on the other.

Multiple:    Is a statistical technique to analyze the difference between the mean values of multiple dependent variables across different categories (groups) of a single independent variable.

Analysis:  A method of simplifying the methods and properties or characteristics of a given parameter or substance.

Medical: Is a a practice of administering treatments  on registered or customized patients in a place.

Medical services: These are information’s or facts that require the control and care offered by medical personnel’s in a hospital custody.

 

  Order full material here