Improved bio-inspired with machine learning computing approach for thyroid prediction

Thyroid illness is widely recognised as a prevalent health condition that can result in a range of health disorders. Thyroid illnesses, namely hypothyroidism and hyperthyroidism, are widespread worldwide and present considerable health consequences. These conditions have a particularly noticeable effect on women in places such as Asia, Latin America, and Africa. Precise and prompt identification of thyroid diseases is essential because of their significant impact on metabolism and general well-being. This study investigates the use of several machine learning (ML) and deep learning (DL) methods, such as random forest (RF), decision tree, SVM, and KNN, to improve the precision of predicting thyroid illnesses. The objective is to enhance the performance of these models by using more sophisticated optimization methods like particle snake swarm optimization (PSSO). The results of the analysis, assessed using parameters such as accuracy, recall, precision, F1-score, and Specificity, clearly show substantial improvements in predictive capability. The random forest with PSSO model attained an accuracy of 98.7%, an F1-score of 98.47%, a Precision of 98.51%, a Recall of 98.7%, and a Specificity of 98%. Notably, PSSO-RF outperformed a CNN-LSTM deep learning baseline by 2.98% (95.72%) in accuracy, highlighting the effectiveness of bio-inspired optimisation in improving conventional machine learning models. This research adds to the increasing data of research that uses computational innovations to improve healthcare outcomes. The results indicate that by using RF with PSSO optimiser, an accuracy score of 98.7% can be achieved. This performance surpasses that of current state-of-the-art models.