Hepatocellular carcinoma(HCC)ranks among the most prevalent cancers worldwide and represents a leading contributor to cancer-associated mortality.Curative strategies primarily include liver resection(LR)and liver tran...Hepatocellular carcinoma(HCC)ranks among the most prevalent cancers worldwide and represents a leading contributor to cancer-associated mortality.Curative strategies primarily include liver resection(LR)and liver transplantation(LT).However,in China,the fiveyear recurrence rate after curative-intent treatment is as high as 50%-70%,while overall survival(OS)remains below 15%,posing a significant clinical challenge.展开更多
1 Introduction In machine learning,it is often necessary to statistically compare the overall performance of two algorithms(e.g.,our proposed algorithm and each compared baseline)based on multiple benchmark datasets[1...1 Introduction In machine learning,it is often necessary to statistically compare the overall performance of two algorithms(e.g.,our proposed algorithm and each compared baseline)based on multiple benchmark datasets[1–3].In this case,our proposed algorithm is typically referred to as the control algorithm[4].However,in some cases,it is also essential to conduct pairwise statistical comparisons of multiple algorithms without a control algorithm[5].For instance,in an experimental study,there may be no novel algorithm being proposed[6,7].Alternatively,we might aim to statistically compare the performance of multiple implementations for one strategy in different configurations[8].展开更多
文摘Hepatocellular carcinoma(HCC)ranks among the most prevalent cancers worldwide and represents a leading contributor to cancer-associated mortality.Curative strategies primarily include liver resection(LR)and liver transplantation(LT).However,in China,the fiveyear recurrence rate after curative-intent treatment is as high as 50%-70%,while overall survival(OS)remains below 15%,posing a significant clinical challenge.
基金supported by the National Natural Science Foundation of China(62306131,62225602)the Fundamental Research Funds for the Central Universitiesthe Red Willow Outstanding Youth Talent Support Program of Lanzhou University of Technology.
文摘1 Introduction In machine learning,it is often necessary to statistically compare the overall performance of two algorithms(e.g.,our proposed algorithm and each compared baseline)based on multiple benchmark datasets[1–3].In this case,our proposed algorithm is typically referred to as the control algorithm[4].However,in some cases,it is also essential to conduct pairwise statistical comparisons of multiple algorithms without a control algorithm[5].For instance,in an experimental study,there may be no novel algorithm being proposed[6,7].Alternatively,we might aim to statistically compare the performance of multiple implementations for one strategy in different configurations[8].
