The Common Causes Of Of Breast Cancer - 1104 Words

Breast cancer is one of the most common causes of death in women worldwide and statistics reveals that India ranks top in the world in breast cancer deaths. This alarming fact necessitates early detection and treatment of the disease. Development of automated systems to process and analyze regional breast cancer data would help the medical experts to understand the severity of the disease and the nature of the patient population. Most of the Medical reports in India are hard copies with natural language descriptions. Processing natural language text has many challenges as it requires handling of varied reporting formats, language style, and diversified representation of facts within the content. A few specific processing requirements†¦show more content†¦Even if limited data are available for processing as in this work, developing an automated system for the medical domain necessitates frequent and extensive support from medical experts for meaningful implementation, analysis and inference from the results. The corpus used in this work is a set of breast cancer pathology reports obtained from a hospital in South India. The parameters – Tumour (T), Lymph node (N) and metastases (M) were extracted from the natural language text and the cancer stage of patients (S) was derived in the earlier phase of this work. In the work presented here, the presence of a list of malignant and benign conditions in patients is extracted from the text. The list of conditions was derived from standard medical documents, in consultation with the domain experts. The Gold standard values to evaluate the extraction process were obtained through manual scrutiny of the reports by the Pathologists. The system compares the extracted data with the Gold standard values, to derive the evaluation parameters namely Precision, Recall, Specificity and Accuracy. In the past, data mining approaches have been applied to the medical domain, especially on breast cancer data because these approaches are effective for classification and prediction of breast cancer-related parameters. As part of this work, EM (Expectation-Maximization) algorithm and Simple K-Means algorithm are used to cluster the extracted data on patient status (Malignant / Benign)