The COVID-19 pandemic has underscored the urgent demand for fast and reliable detection of the SARS-CoV-2 virus. In response, artificial intelligence and metaheuristic algorithms have proven to be powerful tools for enhancing COVID-19 screening and diagnosis. One of the main challenges lies in selecting the most relevant features from vast clinical, epidemiological, and biochemical datasets to support early detection. Metaheuristic algorithms address this by efficiently exploring high-dimensional data and identifying optimal subsets of features. This capability is essential for developing AI models that are robust, scalable, and capable of generalization. These algorithms have been successfully used to extract meaningful features from CT images, laboratory results, and patient-related data, reducing model complexity while improving prediction accuracy. The combination of AI and metaheuristic techniques offers significant potential for building accurate and interpretable COVID-19 detection systems, making feature selection a vital component in early diagnosis, controlling disease spread, and saving lives during current and future pandemics.
During the COVID-19 outbreak, Professor Nadimi and his team demonstrated a strong commitment to advancing technological solutions for disease detection, achieving notable progress in COVID-19 diagnosis. Their objective was to design optimized AI-based methods capable of delivering early and accurate detection using real-world patient data. Through careful examination of extensive and reliable medical datasets, they developed innovative approaches to identify the most impactful features for precise diagnosis. To tackle this challenge, they introduced intelligent feature selection strategies driven by metaheuristic algorithms. These approaches analyze laboratory data and patient metadata to determine the most influential predictive features. By automating the process of selecting optimal feature subsets, their methods enabled the creation of highly accurate AI models for COVID-19 screening and diagnosis. Their emphasis on real-world data has provided healthcare professionals with effective tools for rapid and informed decision-making, ultimately improving patient outcomes. Their contributions to applying metaheuristic algorithms for robust feature selection have played a crucial role in developing AI systems capable of swift COVID-19 detection, helping to save lives during the pandemic and strengthening preparedness for future outbreaks.
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)
- Enhanced whale optimization algorithm for medical feature selection: A COVID-19 case study (2022)
- Binary Aquila optimizer for selecting effective features from medical data: A COVID-19 case study (2022)