Article
Medicine, General & Internal
Abdulqader M. Almars, Majed Alwateer, Mohammed Qaraad, Souad Amjad, Hanaa Fathi, Ayda K. Kelany, Nazar K. Hussein, Mostafa Elhosseini
Summary: A new hybrid model for cancer classification was proposed, using feature selection mRMRe and distributed hyperparameter optimization for gradient boosting ensemble methods. The optimized CatBoost classifier outperformed the optimized XGBoost in cross-validation 5, 6, 8, and 10.
Article
Biochemistry & Molecular Biology
Luca Zanella, Pierantonio Facco, Fabrizio Bezzo, Elisa Cimetta
Summary: The classification of high dimensional gene expression data is crucial for the development of effective diagnostic and prognostic tools. This study compared different combinations of feature selectors and classification learning algorithms, and evaluated their performance through empirical studies. The results showed that the quality of data related to the target classes is essential for successful classification of cancer phenotypes, and simple, well-established feature selectors combined with optimized classifiers can achieve good performance without the need for complicated and computationally demanding methods.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Biochemical Research Methods
Fengsheng Wang, Leyi Wei
Summary: In this study, we propose a novel multi-scale end-to-end deep learning model, MSTLoc, for identifying protein subcellular locations in the imbalanced multi-label immunohistochemistry (IHC) images dataset. We demonstrate that the proposed MSTLoc outperforms current state-of-the-art models in multi-label subcellular location prediction. Through feature visualization and interpretation analysis, we show that the multi-scale deep features learned from our model exhibit better ability in capturing discriminative patterns underlying protein subcellular locations, and the features from different scales are complementary for the improvement in performance. Case study results indicate that our MSTLoc can successfully identify some biomarkers from proteins that are closely involved in cancer development.
Article
Engineering, Multidisciplinary
M. Shaheen, N. Naheed, A. Ahsan
Summary: Big data analytics uncovers hidden patterns through classification, prediction and reinforcement of big datasets. Relevant, important and informative features are selected using different filtration techniques. A new feature selection technique called Relevance-diversity algorithm and a new supervised classification algorithm based on Naive Bayes classification are proposed. The performance of these techniques is evaluated using various datasets, and the results show improvements in terms of feature selection, accuracy, and time complexity.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Biochemical Research Methods
Xudong Zhao, Tong Liu, Guohua Wang
Summary: Molecular signatures play a crucial role in cancer diagnosis, but currently there are issues with identifying false positive signatures. Researchers proposed a new feature selection framework and a data transformation process to address these problems, and experimental results demonstrated the effectiveness of their method.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biotechnology & Applied Microbiology
Abhibhav Sharma, Pinki Dey
Summary: A machine learning approach was used to explore genetic risk factors of Alzheimer's disease, revealing novel and highly predictive biomarkers.
Article
Computer Science, Artificial Intelligence
JinFeng Wang, ZhenYu He, ShuaiHui Huang, Hao Chen, WenZhong Wang, Farhad Pourpanah
Summary: Dealing with high-dimensional gene expression data, using a fuzzy measure with regularization (FMR) can quickly solve the fuzzy measure issue and effectively select important genes. The genes selected by FMR are consistent with clinical studies and produce comparable results in terms of accuracy.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
Article
Computer Science, Information Systems
Haitham Elwahsh, Medhat A. Tawfeek, A. A. Abd El-Aziz, Mahmood A. Mahmood, Maazen Alsabaan, Engy El-shafeiy
Summary: It is known that various factors contribute to cancer, making a doctor's opinion insufficient for classification. Intelligent algorithms are necessary for medical assistance. Many researchers have employed these algorithms to estimate patient survival and predictive methodologies like machine learning and deep learning to forecast cancer prognoses. The accuracy of predictive cancer prognosis is currently a widespread concern.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Engineering, Chemical
Waleed Ali, Faisal Saeed
Summary: Advancements in intelligent systems have greatly contributed to the fields of bioinformatics, health, and medicine. This paper proposes a hybrid filter-genetic feature selection approach to improve the performance of cancer classification by addressing the high-dimensionality and noisy nature of microarray data. Experimental results demonstrate that the proposed method outperforms common machine learning methods in terms of Accuracy, Recall, Precision, and F-measure.
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
Oncology
Xiaoyan Sun, Amin Qourbani
Summary: This study presents a new hybrid approach using data mining techniques for breast cancer diagnosis. The proposed method includes feature selection using an integrated filter-evolutionary search method and ensemble classification based on neural networks. Simulation results demonstrate that the proposed method outperforms existing methods by an average of 12%.
JOURNAL OF CANCER RESEARCH AND CLINICAL ONCOLOGY
(2023)
Article
Engineering, Electrical & Electronic
Sheng Liu, Yue Sun, Lanyong Zhang, Peng Su
Summary: A fault diagnosis method for shipboard medium-voltage DC power system is proposed based on NA-MEMD and MI-LightGBM, which achieves high-precision fault classification and shows advantages in practical engineering applications.
INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS
(2021)
Review
Computer Science, Artificial Intelligence
Sarah Osama, Hassan Shaban, Abdelmgeid A. Ali
Summary: This review explores the applications of machine learning-based data reduction and classification algorithms in microarray gene expression data. It summarizes various data preprocessing methods, reviews different feature selection algorithms, and discusses feature extraction and hybrid methods. It also examines widely used machine learning algorithms for tumor and nontumor classification. Finally, the challenges and unanswered questions in accurate cancer classification and detection are highlighted.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Heyam H. Al-Baity, Nourah Al-Mutlaq
Summary: A new optimized wrapper gene selection method based on simulated annealing algorithm was proposed to assist in breast cancer prediction, showing superior performance in accuracy and execution time through experiments.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Computer Science, Artificial Intelligence
Asmaa H. Rabie, Ahmed I. Saleh
Summary: The world is battling viral diseases like Covid-19 that have overwhelmed medical systems and caused negative impacts on health and economies, especially in poorer countries. Monkeypox is a new potential pandemic that requires accurate diagnosis. This paper presents a precise diagnosing strategy called Accurate Monkeypox Diagnosing Strategy (AMDS).
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)