Search

There are five indicators used in the diagnosis of breast cancer classification. The indicators are a type of malignancy, location, topography, morphology, behavior, and grade. This study aimed to assess how the relationship between types of diagnostic classification was given to breast cancer patients. The research is a quantitative method and used the hospital medical records were collected in the form of anatomical pathology examination results for hospital patients in the year 2017. Data were obtained from 317 pathology examinations which included 282 breast cancer patients. Each patient is given a diagnosis according to the pathologist’s observations into various classifications according to location, topography, type, morphology, grade, and behavior. The result of the analysis showed a relationship between the location of cancer and the type of malignancy. Furthermore, there is a difference in the probability of a malignant or benign tumor-attacking the right or left breast. Correspondence analysis was carried out between the location of the tumor with topography, type of malignancy, morphology, grade, and behavior respectively. The results showed that there was a significant correspondence between topography with the type of malignancy, type of malignancy with morphology, morphology with grade, and grade with behavior. Each type of diagnosis of breast cancer diagnosis is entirely accurate and has a significant correspondence relationship with each other.

To classify the diagnosis of dengue fever is not easy, an accurate accuracy is needed for doctors and health workers in making a decision related to the diagnosis of dengue fever. In the classification of diagnosis of dengue fever, the Neural Network is used as the model applied. To implement the Neural Network there are several parameters that we must determine such as learning rate and momentum, the problem is the absence of standard guidelines in determining the parameters to be used in this method whom the experimental method is used. For this reason, a method that can solve the problem is needed, with the parameters obtained can be optimized. The solution that can be applied with applying the Genetic Algorithm (GA) on the Neural Network, in order to optimize the learning rate parameter value and momentum. The results obtained are apparently the application of optimization techniques with Genetic Algorithms which can make it easier to find parameter values optimally and can increase the accuracy value in the Neural Network algorithm, thus the model obtained can be used for doctors and health workers in determining the classification of dengue fever diagnosis.