Deep ThyroidScan: Multilayer Recursive Neural Network (ML-RNN) for Accurate Detection and Classification

Abstract-Thyroid disease is one of the most prevalent illnesses worldwide, affecting over 42 million individuals in India alone. The thyroid gland, a small organ located in the neck, plays a crucial role in regulating metabolic processes by secreting essential hormones. Any dysfunction in the thyroid gland can significantly impact overall health. Accurate testing for thyroid disorders is vital for effective treatment, as early diagnosis can help balance hormone secretion and mitigate related complications.However, the increasing number of thyroid patients and the shortage of medical professionals pose challenges to traditional diagnostic methods. To address these issues, a deep learning-based Multi-Layer Recursive Neural Network (ML-RNN) is employed to enhance diagnosis. This approach focuses on preprocessing the input data, selecting relevant features from standard datasets, extracting key attributes, and classifying thyroid conditions into normal, hyperthyroid, and hypothyroid categories.The first stage of this process involves preprocessing, which includes data cleaning, splitting, and handling missing values to enhance data quality. Next, feature selection is performed using the Fisher score method to identify an optimal subset of features. Data analysis is then conducted based on Region-of-Interest (ROI) volumes. Finally, classification is carried out using ML-RNN, which improves accuracy in detecting thyroid disorders and assessing the risk of developing the disease. The model demonstrates high performance in terms of accuracy, recall, positive predictive value, and negative predictive value, making it a reliable tool for thyroid disease prediction.