Optimal feature selection using novel flamingo search algorithm for classification of COVID-19 patients from clinical text

Abstract

<abstract> <p>Though several AI-based models have been established for COVID-19 diagnosis, the machine-based diagnostic gap is still ongoing, making further efforts to combat this epidemic imperative. So, we tried to create a new feature selection (FS) method because of the persistent need for a reliable system to choose features and to develop a model to predict the COVID-19 virus from clinical texts. This study employs a newly developed methodology inspired by the flamingo's behavior to find a near-ideal feature subset for accurate diagnosis of COVID-19 patients. The best features are selected using a two-stage. In the first stage, we implemented a term weighting technique, which that is RTF-C-IEF, to quantify the significance of the features extracted. The second stage involves using a newly developed feature selection approach called the improved binary flamingo search algorithm (IBFSA), which chooses the most important and relevant features for COVID-19 patients. The proposed multi-strategy improvement process is at the heart of this study to improve the search algorithm. The primary objective is to broaden the algorithm's capabilities by increasing diversity and support exploring the algorithm search space. Additionally, a binary mechanism was used to improve the performance of traditional FSA to make it appropriate for binary FS issues. Two datasets, totaling 3053 and 1446 cases, were used to evaluate the suggested model based on the Support Vector Machine (SVM) and other classifiers. The results showed that IBFSA has the best performance compared to numerous previous swarm algorithms. It was noted, that the number of feature subsets that were chosen was also drastically reduced by 88% and obtained the best global optimal features.</p> </abstract>

Binary modified Cat and Mouse based Optimizer for medical feature selection: A COVID-19 case study

“…The number of selected features is another objective of the FS problem addressed in Eq. (10). The statistical results of the Avg, Min, and Max values of the selected features for each MA are displayed in Fig.…”

“…According to the majority of similar studies in the research literature, the mean squared error (MSE) is utilized to quantify the classification error, denoted as Err in Eq. (10). Its value is computed using Eq.…”

“…Evaluation of Binary Cats Based on New Positions and Updating Their Positions Once the new binary position of each cat is calculated, this search agent is evaluated in terms of this binary response vector using the cost function by Eq. (10) to determine its fitness level in the new position. Then, this fitness value is compared with its value from the previous iteration.…”

“…In different fields, e.g., economics [3], engineering [4], and medicine [5], large datasets containing an array of features have been created as a result of rapid advances in science [6 , 7, 8]. With advances in medical science and technology over the past few years, many applications now rely on large datasets with many features [9,10]. ML and data mining techniques for exploring and extracting useful information from these medical data can increase the success rate of treating patients and significantly reduce mortality rates [11][12][13].…”

A Novel COVID-19 Diagnosis Approach Utilizing a Comprehensive Set of Diagnostic Information (CSDI)

“…A novel diagnostic model for COVID-19 has been developed that significantly improves the overall prediction accuracy [49]. The datasets encompass a range of critical information, including demographic data such as age, gender, and comorbidities, alongside essential diagnostic details and related tests.…”