Comparison of machine learning models for breast cancer diagnosis

Abstract

<p><span lang="EN-US">Breast cancer is the most common cause of death among women worldwide. Breast cancer can be detected early, and the death rate can be reduced. Machine learning techniques are a hot topic for study and have proved influential in cancer prediction and early diagnosis. This study's objective is to predict and diagnose breast cancer using machine learning models and evaluate the most effective based on six criteria: specificity, sensitivity, precision, accuracy, F1-score and receiver operating characteristic curve. All work is done in the anaconda environment, which uses Python's NumPy and SciPy numerical and scientific libraries, and pandas and matplotlib. This study used the Wisconsin diagnostic breast cancer dataset to test ten machine learning algorithms: decision tree, linear discriminant analysis, forests of randomized trees, gradient boosting, passive aggressive, logistic regression, naïve Bayes, nearest centroid, support vector machine, and perceptron. After collecting the findings, we performed a performance evaluation and compared these various classification techniques. Gradient boosting model outperformed all other algorithms, scoring 96.77% on the F1-score.</span></p>

Chronic Diseases Prediction Using Machine Learning With Data Preprocessing Handling: A Critical Review

“…gini, max_depth: none, n_estimators: 150 Effectively addressing class imbalance through techniques such as weighted classes AdaBoost [? ], [120] n_estimators: 50, learning_rate: 0.5, algorithm: SAMME Addressing the issue of class imbalance by assigning greater weight to prediction errors on samples from the positive class XGBoost [113], [115], [120], [128], [196], [197] n_estimators: 300, scale_pos_weight: 1, max_depth: 4, Sampling method: uniform, eta: 0.3, booster: gbtree Provides numerous parameters that can be optimized Bagging [125] n_estimators: 20, base_estimator: decision tree Becoming more robust to outliers SVM [7], [40], [108], [120], [160], [172] Kernel: rbf, gamma: 1, C: 10 Effective in high-dimensional feature space KNN [76], [108], [120], [124], [145], [199] Algorithm: ball_tree, p:2, n_neighbors: 14 Capturing non-linear and complex patterns in data MLP [115] Optimizer: Adam, learning rate: 0.001 Identifying complex patterns that may be associated with cancer CNN [96] Learning rate: 0.01, Epochs: 100, Optimizer: Adam…”

“…Machine learning can be used for data mining in the healthcare sector [4]. Applying machine learning in health data can help predict if a patient might have six chronic diseases: diabetes mellitus [5], [6]; cancer [7], [8]; stroke [9], [10]; hypertension [11], [12]; kidney failure [13], [14]; and heart issues [15], [16].…”

Breast Cancer Prediction using Machine Learning Models

“…ML models have demonstrated their contribution to the prediction and early diagnosis of cancer. For example, in [27] they conducted a study to predict and diagnose breast cancer using ML models, for which they used parameters such as specificity, sensitivity, precision, accuracy, precision, and F1 score. The GBDT model obtained a score of 96.77 outperforming all other models.…”

Lung Infection Detection via CT Images and Transfer Learning Techniques in Deep Learning

“…AI systems have shown significant progress in the domain of image identification, which plays a crucial role in the diagnosis and detection of illnesses. Recent studies have shown that AI-assisted imaging systems have exhibited comparable diagnostic performance to that of human medical professionals in some medical conditions [3,4]. SARS-CoV-2, an emerging coronavirus responsible for the onset of COVID-19 disease in human beings, first manifested in Wuhan, China, in December 2019 [5].…”