ANALYSIS OF THE EFFECT OF CHEMOTHERAPY IN OVARIAN CANCER TREATMENT USING DATA MINING
Principal Investigator
Name
Kezban Alpan
Degrees
Ph.D.
Institution
Middlesex University
Position Title
PhD Student
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-1089
Initial CDAS Request Approval
Nov 1, 2022
Title
ANALYSIS OF THE EFFECT OF CHEMOTHERAPY IN OVARIAN CANCER TREATMENT USING DATA MINING
Summary
Today, cancer research has turned into an interdisciplinary field, and many different types of studies have been started in this field. When it comes to analyzing the data produced in the research, different approaches that are believed to be more effective than traditional methods are needed. One of the approaches is data mining. Various data mining techniques are being developed to enable today's computers to analyze data and reveal key points which are hidden in large amounts of data. These techniques increase decision-making abilities and enable the development of support systems for experts in different fields.
When the literature is reviewed, we see that there are many studies on ovarian cancer and the effectiveness of chemotherapy. Many of these studies were conducted with a limited number of patients (150-200 patients at most), by using standard statistical and data analysis methods. In addition, studies using data mining and machine learning methods mostly focused just on first-line chemotherapy or on limited drug groups. The number of these studies is also not enough to give a brief literature sample. This study aims to apply data mining techniques and machine learning algorithms to find out the best first-line and second-line therapy for ovarian cancer patients using a large and detailed patient group, without any drug limitations.
When the literature is reviewed, we see that there are many studies on ovarian cancer and the effectiveness of chemotherapy. Many of these studies were conducted with a limited number of patients (150-200 patients at most), by using standard statistical and data analysis methods. In addition, studies using data mining and machine learning methods mostly focused just on first-line chemotherapy or on limited drug groups. The number of these studies is also not enough to give a brief literature sample. This study aims to apply data mining techniques and machine learning algorithms to find out the best first-line and second-line therapy for ovarian cancer patients using a large and detailed patient group, without any drug limitations.
Aims
* Finding the best possible first-line treatment according to the patient's demographic features and screening results.
* Finding the best possible second-line treatment according to the patient's demographic features and screening results.
* Analyzing the effect of ovarian screening results on the success of the treatment.
* Analyzing the effect of ovarian screening abnormalities on the success of the treatment.
* Analyzing the relationship of procedure types and results with ovarian screening abnormalities.
* Analyzing the relationship of medical complications with ovarian cancer treatment success.
Collaborators
Professor Xiaohong Gao - Middlesex University
Dr Britta Stordal * Middlesex University