Breast Cancer Prediction using Machine Learning Models

Abstract

Breast cancer is a type of cancer that develops in the cells of the breast. Treatment for breast cancer usually involves X-ray, chemotherapy, or a combination of both treatments. Detecting cancer at an early stage can save a person's life. Artificial intelligence (AI) plays a very important role in this area. Therefore, predicting breast cancer remains a very challenging issue for clinicians and researchers. This work aims to predict the probability of breast cancer in patients. Using machine learning (ML) models such as Multilayer Perceptron (MLP), K-Nearest Neightbot (KNN), AdaBoost (AB), Bagging, Gradient Boosting (GB), and Random Forest (RF). The breast cancer diagnostic medical dataset from the Wisconsin repository has been used. The dataset includes 569 observations and 32 features. Following the data analysis methodology, data cleaning, exploratory analysis, training, testing, and validation were performed. The performance of the models was evaluated with the parameters: classification accuracy, specificity, sensitivity, F1 count, and precision. The training and results indicate that the six trained models can provide optimal classification and prediction results. The RF, GB, and AB models achieved 100% accuracy, outperforming the other models. Therefore, the suggested models for breast cancer identification, classification, and prediction are RF, GB, and AB. Likewise, the Bagging, KNN, and MLP models achieved a performance of 99.56%, 95.82%, and 96.92%, respectively. Similarly, the last three models achieved an optimal yield close to 100%. Finally, the results show a clear advantage of the RF, GB, and AB models, as they achieve more accurate results in breast cancer prediction.

Categorization of tweets for damages: infrastructure and human damage assessment using fine-tuned BERT model

“…Their model outperformed the baselines. Another study handled the classification of disaster tweets by exploring bag-of-words and several ML models ( Iparraguirre-Villanueva et al, 2023 ). The highest performance achieved is 87% accuracy.…”

Evaluation of machine learning algorithms in the early detection of Parkinson's disease: a comparative study

“…Moreover, it is based on identifying the k nearest k data points within the training set, after that, it performs the prediction or classification of the data based on the majority class of the nearest neighbors [66]. To measure the distance between its neighbors, the model uses the Euclidean equation for continuous variables, as shown in (5), and for discrete variables, it uses the overlap metric [67], [68] The model is widely used in the prediction of some diseases such as type 2 diabetes or for movie recommendations [69], [70]. (5)…”

Traces of Augmented Reality in Learning Mathematics: A Survey

“…Results demonstrated not only children belonging to the experimental group enjoyed learning through AR, but teachers also found the AR designs to be attractive to make children learn.GeoGebra(a free Math Tool) [12] when integrated with AR provided a good learning experience and better performance to school students. This experimental method was carried out by IparraguirreVillanueva, Orlando, et al [29], where they studied 78 students and found that 70% of the experimental group had outstanding performance while the remaining 30% students could reach the expected level of learning. Considering the controlled group that were taught without AR integration 10% achieved expected level performance, 85% were progressing and 5% were still in their initial stage.…”