Accuracy Improvement for the Diagnosis of Breast Cancer using Different Techniques of Machine Learning

One of the most widespread diseases among women is breast cancer. Almost 20% of women across the globe are suffering from this deadly dangerous disease (DDD). The death ratio of women suffering from DDD is around 55%. Nowadays, this disease is prevalent among women. Detection and timing of the detection of this disease are critical during the phase of treatment and rehabilitation. Early-stage detection of this disease results in recovery, whereas if the condition is detected after some time, it causes severe damage. Its detection is not an easy task as sometimes the machines used for the detection do not prove to be as accurate as they could be. Techniques like thermography and computer-aided diagnosis (CAD) are used to detect this DDD. Nowadays, a lot of work is being carried out on ways that could help accurately detect this DDD. To accurately detect this disease, different types of machine learning (ML) techniques and their algorithms are carried out to develop the tools that could help doctors diagnose this DDD efficiently. In this paper, the most popular and common types of ML techniques to diagnose this disease are discussed and their accuracy is improved. K Nearest Neighbours (KNN), Random Forest (RF), Decision Tree (DT), and XG Boost machine learning techniques are used to train and test the data. The accuracy of the disease diagnosis is increased with the training and testing of the dataset.