{"title":"用人工神经网络分类器与决策树进行肺癌检测的准确性、敏感性、特异性和精密度的比较","authors":"D. Preethi, K. Ganapathy","doi":"10.1109/iciptm54933.2022.9754184","DOIUrl":null,"url":null,"abstract":"The aim of this work is to predict the performance of the Artificial Neural Network algorithm for novel lung cancer detection. A total of 1339 samples are collected from two lung cancer datasets found in Kaggle. The G power for samples is calculated from clincalc which contains two different groups from which group 1 is taken as ($\\mathrm{n}1=670$) and for group 2 ($\\mathrm{n}2= 670$), alpha (0.05), power (80%) and enrollment ratio. The collected samples are divided into training dataset $(\\mathrm{n}=937 [75\\%])$ and test dataset $(\\mathrm{n}=402\\ [25\\%])$. Accuracy, sensitivity, specificity and precision score values are calculated for evaluating the performance of the Artificial Neural Network algorithm. By comparing these two algorithms Artificial Neural Network had given better accuracy, specificity, sensitivity and precision of 97.95%, 96.55%, 98.55% and 98.55% than Decision Tree of 61.22%, 40.90%, 67.10% and 71.68%. By using the SPSS tool, the Significance value is calculated as 0.02. From this proposed work it is observed that the Artificial Neural Network (ANN) had given better accuracy than the Decision Tree algorithm.","PeriodicalId":6810,"journal":{"name":"2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM)","volume":"14 1","pages":"528-534"},"PeriodicalIF":0.0000,"publicationDate":"2022-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Novel lung cancer detection using ANN classifier in comparison with Decision Tree to measure the Accuracy, Sensitivity, Specificity and Precision\",\"authors\":\"D. Preethi, K. Ganapathy\",\"doi\":\"10.1109/iciptm54933.2022.9754184\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The aim of this work is to predict the performance of the Artificial Neural Network algorithm for novel lung cancer detection. A total of 1339 samples are collected from two lung cancer datasets found in Kaggle. The G power for samples is calculated from clincalc which contains two different groups from which group 1 is taken as ($\\\\mathrm{n}1=670$) and for group 2 ($\\\\mathrm{n}2= 670$), alpha (0.05), power (80%) and enrollment ratio. The collected samples are divided into training dataset $(\\\\mathrm{n}=937 [75\\\\%])$ and test dataset $(\\\\mathrm{n}=402\\\\ [25\\\\%])$. Accuracy, sensitivity, specificity and precision score values are calculated for evaluating the performance of the Artificial Neural Network algorithm. By comparing these two algorithms Artificial Neural Network had given better accuracy, specificity, sensitivity and precision of 97.95%, 96.55%, 98.55% and 98.55% than Decision Tree of 61.22%, 40.90%, 67.10% and 71.68%. By using the SPSS tool, the Significance value is calculated as 0.02. From this proposed work it is observed that the Artificial Neural Network (ANN) had given better accuracy than the Decision Tree algorithm.\",\"PeriodicalId\":6810,\"journal\":{\"name\":\"2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM)\",\"volume\":\"14 1\",\"pages\":\"528-534\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-02-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/iciptm54933.2022.9754184\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 2nd International Conference on Innovative Practices in Technology and Management (ICIPTM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/iciptm54933.2022.9754184","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Novel lung cancer detection using ANN classifier in comparison with Decision Tree to measure the Accuracy, Sensitivity, Specificity and Precision
The aim of this work is to predict the performance of the Artificial Neural Network algorithm for novel lung cancer detection. A total of 1339 samples are collected from two lung cancer datasets found in Kaggle. The G power for samples is calculated from clincalc which contains two different groups from which group 1 is taken as ($\mathrm{n}1=670$) and for group 2 ($\mathrm{n}2= 670$), alpha (0.05), power (80%) and enrollment ratio. The collected samples are divided into training dataset $(\mathrm{n}=937 [75\%])$ and test dataset $(\mathrm{n}=402\ [25\%])$. Accuracy, sensitivity, specificity and precision score values are calculated for evaluating the performance of the Artificial Neural Network algorithm. By comparing these two algorithms Artificial Neural Network had given better accuracy, specificity, sensitivity and precision of 97.95%, 96.55%, 98.55% and 98.55% than Decision Tree of 61.22%, 40.90%, 67.10% and 71.68%. By using the SPSS tool, the Significance value is calculated as 0.02. From this proposed work it is observed that the Artificial Neural Network (ANN) had given better accuracy than the Decision Tree algorithm.