In the modern era of data-driven decision-making, advanced technologies such as artificial intelligence (AI) and metaheuristic algorithms have become essential tools in feature selection, marking a significant advancement in data analytics. These techniques play a crucial role in identifying the most relevant features from large and complex datasets. Their importance is especially evident when working with real-world data, particularly in medical data analysis and disease diagnosis. AI and metaheuristic algorithms are capable of detecting intricate patterns and relationships within complex medical datasets, allowing healthcare professionals to make more precise and timely diagnoses. By leveraging these technologies, researchers can fully utilize the potential of their data, ultimately enhancing patient care and saving lives. As the field progresses, the integration of AI and metaheuristic methods in feature selection continues to be fundamental in achieving higher accuracy and efficiency, not only in healthcare but also across various other domains.
Professor Nadimi and his research team have focused extensively on applying metaheuristic algorithms to subset feature selection. Their main objective has been to identify the most relevant features while keeping computational and implementation costs low. A key strength of their work lies in the use of authentic, real-world datasets, which has significantly improved the reliability and applicability of their findings. Their contributions cover a wide range of areas, including the collection and development of genuine medical datasets, addressing critical data challenges, and selecting key features from large-scale medical data. By employing their own innovative metaheuristic algorithms alongside well-established techniques, they have effectively tackled the feature selection problem. These methods enable the removal of redundant and irrelevant features, ensuring that only the most meaningful and necessary attributes are retained. This careful and systematic approach highlights their commitment to maximizing the value of medical data and improving the accuracy of disease diagnosis. Their research demonstrates a strong dedication to advancing healthcare through data-driven methodologies, with notable achievements in developing cost-effective diagnostic models for diseases such as coronary artery disease, diabetes, leukemia, prostate cancer, and colon cancer. Their work has made a lasting impact on the fields of medical feature selection and disease diagnosis.
Related Papers
- An improved binary quantum-based avian navigation optimizer algorithm to select effective feature subset from medical data: A COVID-19 case study (2023)
- Binary starling murmuration optimizer algorithm to select effective features from medical data (2023)
- Enhanced whale optimization algorithm for medical feature selection: A COVID-19 case study (2022)
- Binary approaches of quantum-based avian navigation optimizer to select effective features from high-dimensional medical data (2022)
- Binary Aquila optimizer for selecting effective features from medical data: A COVID-19 case study (2022)
- Boosting atomic orbit search using dynamic-based learning for feature selection (2021)
- B-MFO: A binary moth-flame optimization for feature selection from medical datasets (2021)
- Binary sine cosine algorithms for feature selection from medical data (2019)
- A binary metaheuristic algorithm for wrapper feature selection (2019)
- Comparative analysis of transfer function-based binary Metaheuristic algorithms for feature selection (2018)
- Feature selection based on whale optimization algorithm for diseases diagnosis (2016)
- Presentation of hybrid genetic algorithm for effective feature selection (2015)
- A low cost model for diagnosing coronary artery disease based on effective features (2015)