Search

Background:The causes of hereditary breast cancer are classified in two groups as modifiable and non-modifiable (genetic) in our study.Some of the non-modifiable factors selected are breast density, menarche age, menopause, BRCA1 and BRCA2 genes, family history, height and weight of patients.On the other hand, oral contraceptive usage, alcohol consumption, hormone therapy, breastfeeding, exposure to radiation and smoking are among the modifiable factors.The risk of having hereditary breast cancer could be identified by BRCA1/BRCA2 gene tests which requires long lasting experiments and incurs high costs. Before performing the required genetic test, the modifiable and non-modifiable factors of the high risk patients are collected by geneticist or genetic counselor and then calculated risk score of the patients.After observing the test results, the effect of existing factors are analyzed.The aim of this study is to develop a hereditary breast cancer prediction algorithm by using data mining techniques for high risk breast cancer patients.Methods:Different applications may require different data mining methods.The current study involves the data classification technique for predicting hereditary breast cancer through a function that incorporates modifiable and non-modifiable factors. The data consists of 562 BRCA negative, and 68 BRCA positive instances with 117 categorical and numerical characteristics.The first step of this approach is preprocessing the data on hand.Individuals with incomplete data are excluded from the list, and some logical adjustments are performed.Results:As a result, 440 patients (392 BRCA negative, 48 BRCA positive), and 75 characteristics (3 numerical, 72 categorical attributes) are obtained.In the second step, important factors are determined by attribute selection algorithms. After applying 23 selection and 7 ranking methods, the important attributes are determined as: age, diagnosis, height, weight, menopause age, menarche age, FIB/FIB40, SEO, cancer status of the family, clinical stage, and pathological stage.As a result, three data sets are suggested for classification. Finally, a total of 182 data classification results are derived for the aforementioned data sets.All analyses are performed by employing WEKA software.Conclusion:Comparison of the results shows that, the best data classification method's predictions on the BRCA negative class has 100% accuracy.Hence, a new individual's situation can be assessed without undergoing detailed gene tests, resulting in cost and required workforce reduction.The results are found to be promising and applicable.As an extension of the study, a user friendly interface and a decision support tool can be developed. Citation Format: Seda Kilic, Ozge Sukruoglu, Demet Akdeniz, Mukaddes Avsar, Bugra Tuncer, Şimal Aysever, Suzan Güreli, Fadime Üney-Yüksektepe, Tulin Aktin, Hulya Yazici. Selection of BRCA1/2 negative cases using data mining analytical approach for hereditary breast cancer prediction in high risk breast cancer patients. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 3741. doi:10.1158/1538-7445.AM2015-3741

Background: The distribution of hereditary breast and ovarian cancer in Turkish population has been reported in earlier publications. However, the regional distributions of breast cancer and/or BRCA1/2 gene mutations frequency are not known for Balkan Turks who came to Turkey for the forced migration in 1989 and for general Turkish populations in Turkey. Materials and Method: We recruited 401 patients with a family history of breast and/or ovarian cancers, and 126 early-onset breast cancer cases below age 40 with/without a family history of cancer between 1994-2013. These patients were referred to Cancer Genetics Department of Oncology Institute in University of Istanbul. Families were selected from consecutive referrals to the above-listed hospital meeting specific family-history criteria (either multiple cases of breast and or ovarian cancer in the family or the presence of an individual with a young age at diagnosis). Mean age of patients in the study was 41, 18±10, 24. Results: The distributions of patients participating in the study were evaluated in total 8 groups such as seven geographic regions of Turkey and the Balkan Turks. Overall frequency of BRCA1/2 gene mutations in Turkish population was 10%. The distribution of patients according to 8 groups were 26.6% in the Black Sea Region, 21.5% in the Marmara Region, 17.6% in the Eastern Anatolia Region, 8.6% in Central Anatolia, 3.1% in Aegean Region, 3.9% in the Mediterranean region, 2.7% in South Eastern Anatolia and 16% in Balkan Turks. BRCA1 and BRCA2 positivity was evaluated in the study groups: BRCA1/2 mutations ratio were 20% in the Black Sea Region, 16% in the Marmara Region, 20% in the Eastern Anatolia Region, 12% in Central Anatolia, % 4 in Aegean Region and 28% in the Balkan Turks. None of mutations in both genes were found in the patients participating in the study from South Eastern Anatolia and the Mediterranean regions. The observed BRCA1/2 mutations rate was found almost two-fold according to the expected mutation rate in the group of Balkan Turks. The highest breast cancer rates were seen in the city of Giresun in the Black Sea Region and in the city of Malatya in the Eastern Anatolia Region, respectively. Conclusions: In our study, breast cancer was more frequent in the regions which were the Black Sea, the Marmara, Eastern Anatolia and the Balkan Turks group. Although the Marmara region was industrialized, Bulgaria where Balkan Turks lived before forced-migration and the Black Sea Region are not industrialized areas. However, in 1986, these regions were the most affected by the Chernobyl disaster and these interactions was described with scientific data. Therefore, it might be concluded that the high rates of breast cancer are associated with the Chernobyl disaster in these regions. In the study, BRCA1/2 gene mutation rates were examined in Balkan Turks who came to Turkey by forced-migration after Chernobyl disaster. In the group of Balkan Turks, almost two fold expected incidence for BRCA1/2 gene mutations was observed. The investigated society was a small community living as a minority in Bulgaria. Therefore, it was suggested that the society was isolated as a nature and has been had high BRCA1/2 mutations rate. On the other hand, in the study, BRCA1/2 gene mutations and clinical/pathological data were also compared and survival analysis was performed in the general Turkish population. The diagnosis age for breast cancer was found 10 years earlier when compared to the other populations (p Citation Format: Demet Akdeniz, Bugra S. Tuncer, Seda Kilic, Ozge Sukruoglu, Leyla Kilic, Kevser Altundag, Rumeysa Ciftci, Sevda Ozel, Senem Karabulut, Meltem Ekenel, Pinar Saip, Hasan Karanlik, Neslihan Cabioglu, Hulya Yazici. Distribution and frequency of BRCA gene mutations in Turkish population including Balkan Turks. [abstract]. In: Proceedings of the AACR Special Conference: Cancer Susceptibility and Cancer Susceptibility Syndromes; Jan 29-Feb 1, 2014; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2014;74(23 Suppl):Abstract nr 43. doi:10.1158/1538-7445.CANSUSC14-43