Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

Joint modelling of longitudinal and survival data on breast cancer

Tese de Doutoramento em Ciências (Especialidade em Matemática)

Stage at presentation of breast cancer in Luanda, Angola - a retrospective study

Background: It is expected that, by 2020, 15 million new cases of cancer will occur every year in the world, one million of them in Africa. Knowledge of cancer trends in African countries is far from adequate, and improvements in cancer prevention efforts are urgently needed. The aim of this study was to characterize breast cancer clinically and pathologically at presentation in Luanda, Angola; we additionally provide quality information that will be useful for breast cancer care planning in the country. Methods: Data on breast cancer cases were retrieved from the Angolan Institute of Cancer Control, from 2006 to 2014. For women diagnosed in 2009 (5-years of follow-up), demographic, clinical and pathological information, at presentation, was collected, namely age at diagnosis, parity, methods used for pathological diagnoses, tumor pathological characteristics, stage of disease and treatment. Descriptive statistics were performed. Results: The median age of women diagnosed with breast cancer in 2009 was 47 years old (range 25–89). The most frequent clinical presentation was breast swelling with axillary lymph nodes metastasis (44.9 %), followed by a mass larger than 5 cm (14.2 %) and lump (12.9 %). Invasive ductal carcinoma was the main histologic type (81.8 %). Only 10.1 % of cancer cases had a well differentiated histological grade. Cancers were diagnosed mostly at advanced stages (66.7 % in stage III and 11.1 % in stage IV). Discussion: In this study, breast cancer was diagnosed at a very advanced stage. Although it reports data from a single cancer center in Luanda, Angola it reinforces the need for early diagnosis and increasing awareness. According to the main challenges related to breast cancer diagnosis and treatment herein presented, we propose a realistic framework that would allow for the implementation of a breast cancer care program, built under a strong network based on cooperation, teaching, audit, good practices and the organization of health services. Conclusion: Angola needs urgently a program for early diagnosis of breast cancer.