ABSTRACT
Objective To establish a lung cancer risk prediction model using data mining technology and compare the performance of decision tree C5.0 and artificial neural networks in the application of risk prediction model, and to explore the value of data mining techniques in lung cancer risk prediction. Methods We collected the data of 180 patients with lung cancer and 240 patients with benign lung lesion which contained 17 variables of risk factors and clinical symptoms. Decision tree C5.0 and artificial neural networks models were established to compare the prediction performance. Results There were 420 valid samples collected in total and proportioned with the ratio of 7:3 for the training set and testing set. The accuracy, sensitivity, specificity, Youden index, positive predictive value, negative predictive value and AUC of artificial neural networks model were 65.3%, 61.7%, 73.3%, 0.350, 54.9%, 73.1% and 0.675 (95%CI: 0.628-0.720) in testing set; those of decision tree C5.0 model were 61.0%, 47.8%, 80.4%, 0.282, 35.3%, 80.6% and 0.641 (95%CI: 0.593-0.687) in testing set. Conclusion The artificial neural networks model is superior to the decision tree C5.0 model at overall performance and it has potential application value in the risk prediction of lung cancer.
ABSTRACT
Liver disorders such as hepatitis, cirrhosis and hepatocellular carcinoma are a series of the most life threatening diseases along with extensive inflammatory cellular infiltrations. Macrophage has been proved to be key regulators and initiators of inflammation, and long non-coding RNAs (lncRNAs) are recommended to play critical roles in the occurrence and development of a variety of diseases. To uncover the role of macrophage in liver disorders via lncRNA sequencing method, we first applied a lncRNA classification pipeline to identify 1247 lncRNAs represented on the Affymetrix Mouse Genome 430/430A 2.0 array. We then analyzed the lncRNA expression patterns in a set of previously published gene expression profiles of silica particle exposed macrophages and liver respectively, and identified and validated sets of differentially expressed lncRNAs shared by macrophages and liver. The functional enrichment analysis of these lncRNAs was processed on the basis of their expression signatures, three aspects including cis, trans and co-acting proteins were proposed. This is the first time to correlate macrophage with liver disorders via co-expressed lncRNAs. Our findings indicated that roles of macrophage in liver disorders were double-edged, the differentially expressed lncRNAs and their corresponding regulatory genes or proteins may serve as potential diagnostic biomarkers and therapeutic targets.