Main Page
Deanship
The Dean
Dean's Word
Curriculum Vitae
Contact the Dean
Vision and Mission
Organizational Structure
Vice- Deanship
Vice- Dean
KAU Graduate Studies
Research Services & Courses
Research Services Unit
Important Research for Society
Deanship's Services
FAQs
Research
Staff Directory
Files
Favorite Websites
Deanship Access Map
Graduate Studies Awards
Deanship's Staff
Staff Directory
Files
Researches
Contact us
عربي
English
About
Admission
Academic
Research and Innovations
University Life
E-Services
Search
Deanship of Graduate Studies
Document Details
Document Type
:
Thesis
Document Title
:
A Comparison of Parametric and Non Parametric Methods for the Effectiveness of Wet Cupping Therapy
مقارنة بين الطرق المعلمية واللامعلمية لتأثير العلاج بالحجامة الرطبة
Subject
:
Faculty of Science
Document Language
:
Arabic
Abstract
:
Data mining is the process of noticing unknown and unseen useful information, it is aimed to gain beneficial and understandable information from the huge data sets. The classification is a supervised method used to classify the data by learning a part of it as sample then predicts other data to test the performance. The interpretation of data and the analysis are the most important parts in medical researches. This thesis evaluates the possibility of using both parametric and nonparametric methods in classification and prediction. This retrospective study applied on patients who did wet cupping, and objects to investigate the effect of wet cupping therapy (WCT) on some diagnosis using an artificial neural network, decision tree, discriminant analysis and logistic regression model. The proposed models determined the important variables for each data set and employed as a systems that give an accurate, inexpensive and suitable explanation to predict the effect of WCT on the patient additionally to forecast level of improvement. These models will help the practitioner to take the right decision of predicting the patients’ response for WCT. The investigated data set that have major impact on predicting the effect of WCT are liver function, the problems of cells that circulate in blood, thyroid function, kidney function, lipid, bone and calcium problems. The models constructed by dividing the data into 70% to train the model and 30% to test their performance using different classification assessments. The results of these models present the importance of WCT on patient’s health depending on the diagnosis, where there are significant difference on most of blood tests. The comparisons between models were made to identify a comprehensive evaluation about the models. The study conclude that WCT is an effective treatment in improving the quality of life and reducing pain. The proposed models identify the important features that have a major influence in each data set. These models will help the clinicians to predict the level of patients’ improvement. Any model which proposed could be applied as a supportive tool to make an early decision regarding the response of patient to the WCT. It would be helpful to apply a nonparametric method with a parametric method and identify the performance of each methods to select the optimal one for classification. The results would provide guidelines for the improvement levels by targeting some types of blood tests and select better method in prediction power.
Supervisor
:
Dr. Lamya Abdulbaset Baharith
Thesis Type
:
Master Thesis
Publishing Year
:
1442 AH
2020 AD
Added Date
:
Sunday, January 17, 2021
Researchers
Researcher Name (Arabic)
Researcher Name (English)
Researcher Type
Dr Grade
Email
هاجر صالح الجهني
Aljohani, Hajar Saleh
Researcher
Master
Files
File Name
Type
Description
46850.pdf
pdf
Back To Researches Page