{"title":"使用机器学习解读与两种侵袭性肝细胞癌表型相关的基因模型的预后和治疗价值。","authors":"Junhan Pan, Cong Zhang, Huizhen Huang, Yanyan Zhu, Yuhao Zhang, Shuzhen Wu, Yan-Ci Zhao, Feng Chen","doi":"10.2147/JHC.S480358","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Macrotrabecular-massive (MTM) and vessels encapsulating tumor clusters (VETC)-hepatocellular carcinoma (HCC) are aggressive histopathological phenotypes with significant prognostic implications. However, the molecular markers associated with MTM-HCC and VETC-HCC and their implications for clinical outcomes and therapeutic strategies remain unclear.</p><p><strong>Methods: </strong>Utilizing the TCGA-LIHC cohort, we employed machine learning techniques to develop a prognostic risk score based on MTM and VETC-related genes. The performance of the risk score was assessed by investigating various aspects including clinical outcomes, biological pathways, treatment responses, drug sensitivities, tumor microenvironment, and molecular subclasses. To validate the risk score, additional data from the ICGC-JP, GSE14520, GSE104580, GSE109211, and an in-house cohort were collected and analyzed.</p><p><strong>Results: </strong>The machine learning algorithm established a 4-gene-based risk score. High-risk patients had significantly worse prognosis compared to low-risk patients, with the risk score being associated with malignant progression of HCC. Functionally, the high-risk group exhibited enrichment in tumor proliferation pathways. Additionally, patients in the low-risk group exhibited improved response to TACE and sorafenib treatments compared to the high-risk group. In contrast, the high-risk group exhibited reduced sensitivity to immunotherapy and increased sensitivity to paclitaxel. In the in-house cohort, high-risk patients displayed higher rates of early recurrence, along with an increased frequency of elevated alpha-fetoprotein, microvascular invasion, and aggressive MRI features associated with HCC.</p><p><strong>Conclusion: </strong>This study has successfully developed a risk score based on MTM and VETC-related genes, providing a promising tool for prognosis prediction and personalized treatment strategies in HCC patients.</p>","PeriodicalId":15906,"journal":{"name":"Journal of Hepatocellular Carcinoma","volume":"11 ","pages":"2373-2390"},"PeriodicalIF":4.2000,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11614714/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deciphering the Prognostic and Therapeutic Value of a Gene Model Associated with Two Aggressive Hepatocellular Carcinoma Phenotypes Using Machine Learning.\",\"authors\":\"Junhan Pan, Cong Zhang, Huizhen Huang, Yanyan Zhu, Yuhao Zhang, Shuzhen Wu, Yan-Ci Zhao, Feng Chen\",\"doi\":\"10.2147/JHC.S480358\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Macrotrabecular-massive (MTM) and vessels encapsulating tumor clusters (VETC)-hepatocellular carcinoma (HCC) are aggressive histopathological phenotypes with significant prognostic implications. However, the molecular markers associated with MTM-HCC and VETC-HCC and their implications for clinical outcomes and therapeutic strategies remain unclear.</p><p><strong>Methods: </strong>Utilizing the TCGA-LIHC cohort, we employed machine learning techniques to develop a prognostic risk score based on MTM and VETC-related genes. The performance of the risk score was assessed by investigating various aspects including clinical outcomes, biological pathways, treatment responses, drug sensitivities, tumor microenvironment, and molecular subclasses. To validate the risk score, additional data from the ICGC-JP, GSE14520, GSE104580, GSE109211, and an in-house cohort were collected and analyzed.</p><p><strong>Results: </strong>The machine learning algorithm established a 4-gene-based risk score. High-risk patients had significantly worse prognosis compared to low-risk patients, with the risk score being associated with malignant progression of HCC. Functionally, the high-risk group exhibited enrichment in tumor proliferation pathways. Additionally, patients in the low-risk group exhibited improved response to TACE and sorafenib treatments compared to the high-risk group. In contrast, the high-risk group exhibited reduced sensitivity to immunotherapy and increased sensitivity to paclitaxel. In the in-house cohort, high-risk patients displayed higher rates of early recurrence, along with an increased frequency of elevated alpha-fetoprotein, microvascular invasion, and aggressive MRI features associated with HCC.</p><p><strong>Conclusion: </strong>This study has successfully developed a risk score based on MTM and VETC-related genes, providing a promising tool for prognosis prediction and personalized treatment strategies in HCC patients.</p>\",\"PeriodicalId\":15906,\"journal\":{\"name\":\"Journal of Hepatocellular Carcinoma\",\"volume\":\"11 \",\"pages\":\"2373-2390\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2024-11-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11614714/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Hepatocellular Carcinoma\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.2147/JHC.S480358\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Hepatocellular Carcinoma","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2147/JHC.S480358","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
Deciphering the Prognostic and Therapeutic Value of a Gene Model Associated with Two Aggressive Hepatocellular Carcinoma Phenotypes Using Machine Learning.
Background: Macrotrabecular-massive (MTM) and vessels encapsulating tumor clusters (VETC)-hepatocellular carcinoma (HCC) are aggressive histopathological phenotypes with significant prognostic implications. However, the molecular markers associated with MTM-HCC and VETC-HCC and their implications for clinical outcomes and therapeutic strategies remain unclear.
Methods: Utilizing the TCGA-LIHC cohort, we employed machine learning techniques to develop a prognostic risk score based on MTM and VETC-related genes. The performance of the risk score was assessed by investigating various aspects including clinical outcomes, biological pathways, treatment responses, drug sensitivities, tumor microenvironment, and molecular subclasses. To validate the risk score, additional data from the ICGC-JP, GSE14520, GSE104580, GSE109211, and an in-house cohort were collected and analyzed.
Results: The machine learning algorithm established a 4-gene-based risk score. High-risk patients had significantly worse prognosis compared to low-risk patients, with the risk score being associated with malignant progression of HCC. Functionally, the high-risk group exhibited enrichment in tumor proliferation pathways. Additionally, patients in the low-risk group exhibited improved response to TACE and sorafenib treatments compared to the high-risk group. In contrast, the high-risk group exhibited reduced sensitivity to immunotherapy and increased sensitivity to paclitaxel. In the in-house cohort, high-risk patients displayed higher rates of early recurrence, along with an increased frequency of elevated alpha-fetoprotein, microvascular invasion, and aggressive MRI features associated with HCC.
Conclusion: This study has successfully developed a risk score based on MTM and VETC-related genes, providing a promising tool for prognosis prediction and personalized treatment strategies in HCC patients.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
