Background: Exploration of the population profile and management of female breast cancer in Alexandria, Egypt, to identify system inefficiencies. Aims: To identify barriers to full implementation of international guidelines in female breast cancer patients. Methods: Data extraction and analysis from records of 3 public oncology services in Alexandria, Egypt in 2007–2016. Results: A total of 5236 of 7125 records were usable. Median patient age was 54 years, and 522 (31.5%) had a positive family history. Median duration of prediagnosis complaint was 3.1 months. For tumour stage, 2527 (55.2%) were early, 1717 (37.6%) were locally advanced and 331 (7.2%) were stage IV. Estrogen receptor, progesterone receptor and HER2 were positive in 3869 (85%), 3545 (78%) and 461 (15.3%) patients, respectively. Chemotherapy started after a median 1.03 months. Adjuvant chemotherapy was given to 3667 (91.7 %) patients and neoadjuvant chemotherapy to 333 (8.3%); 3686 (92.1%) received anthracycline-based combination chemotherapy, and 3613 (86%) received hormonal treatment. One hundred and eighty of 317 eligible patients received trastuzumab. Local and/or distant recurrence was seen in 1109 (21.2%) patients. In nonmetastatic cases, median overall and disease-free survival was 149.1 and 77.1 months, respectively. In metastatic cases, median progression-free survival was 19.6 months. Conclusion: There were defects in the record system, delayed diagnosis and treatment, and nonadherence to targeted therapy in many patients. Promotion of national and hospital-based registries is needed, along with targeted information, education and communication strategies, and a robust patient navigation system. Continuous monitoring of outcomes and adaptation to implementation needs must be sustained.

No abstract

e13558 Background: Artificial intelligence (AI) and machine learning (ML) have outstanding contributions in oncology. One of the applications is the early detection of breast cancer. Recently, several ML and data mining techniques have been used for both detection and classification of breast cancer cases. It is found that about 25% of breast cancer cases have an aggressive cancer at diagnosis time, with metastatic spread. The absence or presence of metastatic spread largely determines the patient’s survival. Hence, early detection is very important for reducing cancer mortality rates Methods: This study aims at applying ML and data mining, using AI techniques, for exploring and preprocessing breast cancer dataset, before building the ML classification Model for breast cancer metastasis prediction. The model will be implemented for mass screening, to prioritize patients who are more likely to develop metastases. A dataset of breast cancer cases was provided by the Oncology and Nuclear Medicine Department, Faculty of Medicine, Alexandria University. It contains clinical records of 5236 patients, diagnosed with breast cancer. ML libraries in Python programming language was used to explore the dataset and determine ratio of missing data, define data types, redundant data, and specify class label and predictors that to be used for the classification model. Results: In this work, the results showed that missing data ratio in some columns exceeds 90%, there are redundant features to be eliminated, data type conversion and feature reduction should be applied to prepare the data. Conclusions: Based on the previous findings, it is recommended to use ML preprocessing python libraries to prepare the dataset before building ML classification model of breast cancer metastasis prediction.

No abstract

Purpose: Exploration of the population profile and management of female breast cancer in a representative sample from Alexandria, Egypt, to identify system inefficiencies and barriers preventing full implementation of international guidelines, negatively impacting the outcome. Methods: The study surveyed 7125 records from three major public oncology services at Main University Hospital, Gamal Abd-elnasser Hospital and Ayadi Almostakbel Oncology Center, between 2007 and 2016. Results: 73.4% (5236 records) of the records contained usable information. The median age was 54 years, with positive family history in 31.5%. The median duration of complaint before diagnosis was 3.1 months (IQR 1.6-7.5). 55.2% were early stage, 37.6% were locally advanced and 7.2% were stage IV. Breast surgery was performed for 4976 cases. Axillary surgery was done for 4945 cases. Most cases were hormone receptor positive. 15.3% were HER2 positive. The median duration to start chemotherapy was 1.03 months (IQR 0.7-1.6). Adjuvant chemotherapy was given to 3667 and neoadjuvant chemotherapy was given to 333. Anthracycline-based combination chemotherapy, with or without Taxanes was the commonest. 86% received hormonal treatment. 180/317 trastuzumab-eligible patients received trastuzumab. 69.5% started radiotherapy > 6 months from presentation. Conventionally and hypofractionated regimens were used in 46.6% and 53.5%, respectively. 1109 developed relapse (local in 155, distant in 130 and 794 had both). In non-metastatic cases, median overall and disease free survivals were 149.1 and 77.1 months respectively. In metastatic cases, the median progression free survival was 19.6 months. Conclusion: The study revealed defects in the record system, delayed diagnosis and treatment, and inadherence to targeted therapy protocols in a significant part of eligible patients. Suggested implementation strategies include promotion of national or hospital based registries, information, education and communication with target populations and health carers, establishing a patient navigation system and monitoring outcomes of the interventions. Citation Format: Yousri Rostom, Salah Abdelmonem, Marwa Shaker, Nayera Mahmoud, Nevine Labib, Abdelsalam A. Ismail, Maher Soliman. Presentation and Management of Egyptian Female Breast Cancer In Alexandria, Egypt: An Implementation Study [abstract]. In: Proceedings of the 9th Annual Symposium on Global Cancer Research; Global Cancer Research and Control: Looking Back and Charting a Path Forward; 2021 Mar 10-11. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2021;30(7 Suppl):Abstract nr 16.