Ovary Cancer Detection using Decision Tree Classifiers based on Historical Dataof Ovary Cancer Patients

This research implements decision tree classifiers and artificial neural network to predict whether the patient will live with ovary cancer or not. Dataset was obtained from Danish Cancer Register and contains five Input parameters. Dataset contains some missing values and a noticeable improvement in accuracy was detected after removing them. Three features of the original dataset were shown to be the most significant: Mobility of the cancer, Surface of the cancer, and the Consistency of the cancer. The addition of the other two features (Size of the cancer and age of the patient) did not improve the results significantly. It was noticed that the patients with a cystic, but fixed and even cancer have always died from the ovary cancer. In contrast, the patients with uneven, but fixed and solid cancer have always survived the cancer. It is recommended to include more information about either the cancer or the patient to increase the chance of predicting the output of such patients.

[1]  Alexander G. Gray,et al.  Ovarian cancer detection from metabolomic liquid chromatography/mass spectrometry data by support vector machines , 2009, BMC Bioinformatics.

[2]  D. Armstrong,et al.  Recent progress in the diagnosis and treatment of ovarian cancer , 2011, CA: a cancer journal for clinicians.

[3]  Ron Kohavi,et al.  Wrappers for feature selection , 1997 .

[4]  Vijay Mishra,et al.  Feed Forward Artificial Neural Network: Tool for Early Detection of Ovarian Cancer , 2011, Scientia Pharmaceutica.

[5]  P. Sasieni,et al.  Estimating the workload associated with symptoms-based ovarian cancer screening in primary care: an audit of electronic medical records , 2014, BMC Family Practice.

[6]  H. Peters,et al.  The Ovary: A Correlation of Structure and Function in Mammals , 1980 .

[7]  Eibe Frank,et al.  Logistic Model Trees , 2003, Machine Learning.

[8]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[9]  N. Urban,et al.  Development of an ovarian cancer symptom index , 2007 .

[10]  T. Peters,et al.  Risk of ovarian cancer in women with symptoms in primary care: population based case-control study , 2009, BMJ : British Medical Journal.

[11]  Lingxi Peng,et al.  An Automated Diagnosis System of Liver Disease using Artificial Immune and Genetic Algorithms , 2013, Journal of Medical Systems.

[12]  G. Lyratzopoulos,et al.  Variation in number of general practitioner consultations before hospital referral for cancer: findings from the 2010 National Cancer Patient Experience Survey in England. , 2012, The Lancet. Oncology.

[13]  Marianne Lundkjær Gjerstorff,et al.  The Danish Cancer Registry , 2011, Scandinavian journal of public health.

[14]  J. Shelley,et al.  High prevalence of symptoms associated with ovarian cancer among Australian women , 2011, The Australian & New Zealand journal of obstetrics & gynaecology.

[15]  Sabine Van Huffel,et al.  Bayesian networks in ovarian cancer diagnosis: potentials and limitations , 2000, Proceedings 13th IEEE Symposium on Computer-Based Medical Systems. CBMS 2000.

[16]  Wenbin Chen,et al.  An immune-inspired semi-supervised algorithm for breast cancer diagnosis , 2016, Comput. Methods Programs Biomed..

[17]  Sheng-Hsiung Chiu,et al.  A Decision Tree Based Classifier to Analyze Human Ovarian Cancer cDNA Microarray Datasets , 2015, Journal of Medical Systems.

[18]  S. Ghafouri-Fard,et al.  The Role of Long Non-Coding RNAs in Ovarian Cancer , 2017, Iranian biomedical journal.