Article
Health Care Sciences & Services
Marianna Inglese, Matteo Ferrante, Tommaso Boccato, Allegra Conti, Chiara A. Pistolese, Oreste C. Buonomo, Rolando M. D'Angelillo, Nicola Toschi
Summary: Traditional imaging techniques such as X-rays and MRI have limitations in breast cancer diagnosis and prediction, leading to the emergence of PET as a more effective tool. This study used dynamic PET scans to extract radiomic features and trained a model for classification and prognosis prediction. The results showed superior performance of the dynamic radiomics approach, outperforming standard PET imaging in accuracy. This study demonstrates the enhanced clinical utility of dynomics in improving breast cancer diagnosis and prognosis.
JOURNAL OF PERSONALIZED MEDICINE
(2023)
Article
Oncology
Saba Zarean Shahraki, Mehdi Azizmohammad Looha, Pooya Mohammadi Kazaj, Mehrad Aria, Atieh Akbari, Hassan Emami, Farkhondeh Asadi, Mohammad Esmaeil Akbari
Summary: This study aims to predict the time-related survival probability of breast cancer patients in different molecular subtypes over a 30-year follow-up period. The results revealed that the Luminal A subtype had the highest predicted survival probabilities, while the triple-negative and HER2-enriched subtypes had the lowest predicted survival probabilities.
FRONTIERS IN ONCOLOGY
(2023)
Article
Oncology
Lichen Ji, Wei Zhang, Xugang Zhong, Tingxiao Zhao, Xixi Sun, Senbo Zhu, Yu Tong, Junchao Luo, Youjia Xu, Di Yang, Yao Kang, Jin Wang, Qing Bi
Summary: The risk of osteoporosis is higher in breast cancer patients compared to healthy populations. Machine learning models can be used to predict the risk of osteoporosis, fracture occurrence, and prognosis. These models show better performance than current models and can improve decision making.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Run Fan, Yufan Chen, Sarah Nechuta, Hui Cai, Kai Gu, Liang Shi, Pingping Bao, Yu Shyr, Xiao-Ou Shu, Fei Ye
Summary: Robust and reliable prognosis prediction models have been developed for Asian patients with breast cancer, incorporating age, tumor characteristics, treatment information, and lifestyle factors. The models showed high prediction accuracy and generalizability, particularly in Asian American women, after internal and external validation.
Article
Oncology
Zoe Guan, Theodore Huang, Anne Marie McCarthy, Kevin Hughes, Alan Semine, Hajime Uno, Lorenzo Trippa, Giovanni Parmigiani, Danielle Braun
Summary: BRCAPRO is a breast cancer risk prediction model that does not consider non-genetic risk factors. We expand BRCAPRO by combining it with BCRAT, a model that uses mostly non-genetic risk factors, and show improved prediction accuracy. Accurate risk stratification is essential for targeted screening and prevention of cancer.
Article
Computer Science, Artificial Intelligence
Babymol Kurian, V. L. Jyothi
Summary: Breast cancer is the most common cancer worldwide. Machine learning techniques are used to improve the prognosis of breast cancer at an earlier stage. The research focuses on using an ensemble of machine learning classifiers to predict breast cancer using genetic sequences of BRCA1 and BRCA2. Five ensemble models from six machine learning classifiers were combined for the prediction, and the soft voting classifiers achieved the highest classification performance metrics with a classification precision of 94%.
Article
Biochemistry & Molecular Biology
Xinkang Li, Lijun Tang, Zeying Li, Dian Qiu, Zhuoling Yang, Baoqiong Li
Summary: In this study, machine learning algorithms including PLS-DA, AdaBoost, and LGBM were applied to establish models for predicting the ADMET properties of anti-breast cancer compounds. The LGBM algorithm yielded the best results compared to the other two algorithms, with high accuracy, precision, recall, and F1-score. The findings suggest that LGBM can be a reliable tool for predicting molecular ADMET properties in virtual screening and drug design research.
Article
Computer Science, Information Systems
Varshali Jaiswal, Preetam Suman, Dhananjay Bisen
Summary: Breast cancer is a common malignancy in women, and machine learning techniques, such as the I-XGBoost algorithm, have shown high accuracy in predicting the malignancy of breast cancer cells.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Medical Informatics
Jialong Xiao, Miao Mo, Zezhou Wang, Changming Zhou, Jie Shen, Jing Yuan, Yulian He, Ying Zheng
Summary: This study compared the performance of breast cancer prognostic prediction models based on machine learning and Cox regression. The results showed that the random survival forest (RSF) model slightly outperformed the other models in terms of discriminative ability, indicating the potential of the RSF method as an effective approach to building prognostic prediction models in the context of survival analysis.
JMIR MEDICAL INFORMATICS
(2022)
Article
Engineering, Multidisciplinary
V. Nanda Gopal, Fadi Al-Turjman, R. Kumar, L. Anand, M. Rajesh
Summary: Breast cancer is the most common disease among women worldwide, and early diagnosis is crucial for reducing mortality. This paper proposes a method for early diagnosis of breast cancer using IoT and machine learning, achieving high accuracy and low error rates. The results show that the MLP classifier outperforms LR and RF in terms of accuracy and error rate.
Article
Health Care Sciences & Services
Jiande Wu, Chindo Hicks
Summary: The study proposed a new approach to classify triple negative breast cancer and non-triple negative breast cancer patients using machine learning methods, with the Support Vector Machine algorithm demonstrating higher accuracy and fewer misclassification errors in classifying breast cancer types.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Computer Science, Information Systems
Sukhendra Singh, Sur Singh Rawat, Manoj Gupta, B. K. Tripathi, Faisal Alanzi, Arnab Majumdar, Pattaraporn Khuwuthyakorn, Orawit Thinnukool
Summary: Breast cancer is a leading cause of death in women worldwide, and early diagnosis is crucial for effective treatment. This paper proposes a hybrid model using transfer learning to study histopathological images and improve the detection and rectification of the disease at a low cost. Experimental results show that the proposed model outperforms baseline methods in terms of F-scores on the dataset of histopathological images.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Operations Research & Management Science
Kamyab Karimi, Ali Ghodratnama, Reza Tavakkoli-Moghaddam
Summary: Breast cancer has become a leading cause of mortality among women in recent decades. Machine learning can be used to improve treatment outcomes and reduce costs and time. This research proposes two novel feature selection methods based on imperialist competitive algorithm and bat algorithm, aiming to enhance diagnostic models' efficiency.
ANNALS OF OPERATIONS RESEARCH
(2023)
Review
Oncology
Milad Rahimi, Atieh Akbari, Farkhondeh Asadi, Hassan Emami
Summary: This study systematically investigates the use of machine learning to predict survival in patients with cervical cancer. Combining heterogeneous multidimensional data with machine learning techniques can play a very influential role in predicting cervical cancer survival. However, the challenges of interpretability, explainability, and imbalanced datasets need to be addressed for machine learning algorithms to be considered standard for survival prediction.
Article
Computer Science, Information Systems
Zahra Sedighi-Maman, Alexa Mondello
Summary: This study presents a two-stage data analytic framework for breast cancer survival prediction, focusing on both deceased patients and their survival lengths. By using data preparation techniques and a Generalized Linear Model (GLM), the study demonstrates the accuracy and interpretability of the predictions, surpassing complex models like Extreme Gradient Boosting (XGB) and Multilayer Perceptron based on Artificial Neural Networks (MLP-ANNs). The findings highlight the importance of data preprocessing in improving model performance, and showcase the application of GLM in predicting survival status and lengths for deceased cancer patients.
INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS
(2021)