Clinical data mining process helps the clinicians to provide diagnosis, therapy and prognosis of different diseases. A description of patient conditions should consists of the changes in and combination of clinical measures. The clinical outcome prediction has been increased by using multiple measurement data instead of using single measurement data. The multiple measurement data are gathered from different time period and dataset and it is very sensitive to analysis and predicts the disease. For prediction of Hepatocellular Carcinoma (HCC) disease, the multiple measurement data were merged by using merging algorithm and the distribution of data is determined by statistical measurement. Then those data are fed into the classifier to classify the data as patients with HCC and patients without HCC. In order to reduce the false prediction rate and to enhance the prediction rate, efficient methods are introduced in this paper. In this paper, frequency based measurement feature is calculated based on wavelet transform and it can be added as additional feature with multiple measurement data. Then, the optimal features are selected based on Firefly optimization algorithm which reduces the classification overhead. The selected optimal features are learned by using the Support Vector Machine (SVM) classifier to predict the patients with HCC and patients without HCC. The experimental results are conducted in terms of accuracy and balanced accuracy to prove the effectiveness of the proposed prediction method.
