Modelling a Novel Linear Weighted Kernel Model for Thyroid Prediction

Fast-paced lives often lead to unhealthy food choices, work-life imbalances, social anxiety, hereditary anomalies, and increased diagnostic abilities have all been connected to the recent and noteworthy increase in the occurrence of thyroid disorders. Nonetheless, there is ongoing debate regarding these factors' exact role in thyroid illness. As such, obtaining a thorough understanding of the linked relationships is imperative to reduce the corresponding morbidity and mortality rates. Using Linear Weighted Kernel-Support Vector Machine (LWK-SVM) approaches, this study uncovered hidden correlations between various intricate and varied epidemiological relationships related to links to thyroid illness. Using digital health data, researchers developed the LWK-SVM method that simultaneously identifies frequent and exceptional risk variables associated with the disease by evaluating the proposed approaches. Mutual factors were preserved for interpretation, and unique approaches were employed for distinct datasets. The findings validated that thyroid illness history, age, and gender are risk factors that are positively associated with the development of thyroid cancer in the future. Moreover, the lack of underlying chronic illnesses, including obesity, diabetes, or hypertension, has been linked to a decreased risk of thyroid cancer diagnosis. The proposed LWK-SVM framework demonstrates that it is a sensible, workable answer and should be advanced for in-depth information finding on diverse illnesses.