A Hybrid Model for Decision-Making in Interventional Medicine

Interventional medicine is considered as one of the mostpromising advancement in the medical field. It is a very useful technology for assisting different medical procedures such as diagnosis, therapy etc. Much research is being done in this area to improve the quality as well as decision making power of interventional medicine. But many of them failed to achieve better results. Hence, this work put forward a new approach for improvising the quality as well as decision making ability of interventional medicine through efficient heart disease classification procedure known as Ant Colony Optimized Deep Convolutional Neural Network (ACO-DCNN). This approach is implemented with the help of two different type dataset such as text and image. The text data processing consists of different procedures such as pre-processing, feature selection and classification. Similarly, the image data is processed by using different procedures such as pre-processing, extraction, selection and classification. In this work, ACO-DCNN classifier is used to classify both image and text data. The suggested technique is evaluated using two publically available datasets such as UCI text dataset and ECG image dataset by using PYTHON platform. The different performance measures considered are accuracy, precision, sensitivity, F1-score and specificity. From the evaluation results, the classification accuracy achieved for image dataset is 95.83% and for text dataset is 95.86%. Also, the comparison results showed that, the proposed method is better than other existing approaches.