Hybridized Paradigms for The Clinical Prediction of Lung Cancer

The rise of health/medical informatics has created new opportunities for diagnosing different diseases. This is due to its cost-effectiveness and reliable ability to provide clear and understandable information that specialists and policymakers can use. This study aims at screening and predicting clinical lung cancer using a combination of socio-demographic and clinical input factors by implementing hybridized-novel paradigms integrated with multi-model single techniques. Four distinct multimodal single approaches combined with three hybridized novel paradigms were applied to predict lung cancer in a clinical setting. Both the quantitative and graphical performance of the individual methods demonstrate the superior capability of the Gaussian process regression (GPR) model compared to the other three models: Least-square boost (L-Boost), Step-wise-linear regression (SWLR), and Support Vector Regression (SVR). As a result of the inadequate performance and decreased effectiveness of individual procedures, three hybridized novel paradigms were introduced, namely; Stepwise-linear regression- Gaussian process regression (SWLR-GPR), Stepwise-linear regression- Least-square boost (SWLR-L-BOOST) and Stepwise-linear regression- Support Vector Regression (SWLR-SVR) to enhance the predictive abilities of individual methodologies in the clinical prediction of lung cancer by using regression methods. The comparative examination of the hybridized paradigms revealed that SWLR-GPR outperforms all other hybridized paradigms and single approaches in predicting lung cancer. Based on the results of this research and the efficacy of the suggested algorithms, this methodology may be used as a reliable method by medical professionals and policymakers for predicting Lung cancer.