Risk Detection in Medical Data Using Artificial Afterimage Algorithm

Metaheuristic algorithms have become a frequently used methodology in many fields such as genetics, bioinformatics, microbiology, etc. related to human health. Metaheuristic methods provide efficient solutions when classical approaches fail or are computationally expensive. In this study, Artificial Afterimage Algorithm was applied to 4 different medical data sets obtained from Kaggle. There is no previous study in the literature that models the afterimage algorithm as a heuristic method. Its mathematical infrastructure is simpler than many other methods. Using the Artificial Afterimage Algorithm, clusters of test samples taken from healthy individuals and patients were tried to be detected. Accuracy, precision, recall and F1 values of the clusters were calculated. The highest Accuracy value was obtained as 0.85, Precision value as 0.9, Recall value as 1 and F1 score value as 0.86. The study shows that the method can perform a good rate of risk detection in medical data.