Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study
AimThis study aims to develo\p a population-adapted machine learning-based prediction model for hepatocellular carcinoma (HCC) lymph node metastasis (LNM) to identify high-risk patients requiring intensive surveillance.MethodsData from 23511 HCC patients in the SEER database and 57 patients from our...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1601985/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839633057645068288 |
|---|---|
| author | Li Yuqin Li Yuqin Li Hongyan Li Hongyan Li Hongyuan Li Tingting He Kun Fang Jie Han Yunhui |
| author_facet | Li Yuqin Li Yuqin Li Hongyan Li Hongyan Li Hongyuan Li Tingting He Kun Fang Jie Han Yunhui |
| author_sort | Li Yuqin |
| collection | DOAJ |
| description | AimThis study aims to develo\p a population-adapted machine learning-based prediction model for hepatocellular carcinoma (HCC) lymph node metastasis (LNM) to identify high-risk patients requiring intensive surveillance.MethodsData from 23511 HCC patients in the SEER database and 57 patients from our hospital were analyzed. Seven LNM risk indicators were selected. Four machine learning algorithms—decision tree (DT), logistic Regression (LR), multilayer perceptron (MLP), and extreme gradient boosting (XGBoost)—were employed to construct prediction models. Model performance was evaluated using area under the curve, accuracy, sensitivity, and specificity.ResultsAmong 23511 SEER patients, 1679 (7.14%) exhibited LNM. Race, Sequence number, Tumor size, T stage and AFP were identified as independent predictors of LNM. The LR model achieved optimal performance (area under the curve: 0.751; accuracy: 0.707; sensitivity: 0.711; specificity: 0.661). External validation with 57 patients from our hospital confirmed robust generalizability (area under the curve: 0.73; accuracy: 0.737; sensitivity: 0.829; specificity: 0.5), outperforming other models.ConclusionsThe LR-based model demonstrates superior predictive capability for LNM in HCC, offering clinicians a valuable tool to guide personalized therapeutic strategies. |
| format | Article |
| id | doaj-art-291e92aecc444f30b94a4f9d6ee1c81c |
| institution | Matheson Library |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-291e92aecc444f30b94a4f9d6ee1c81c2025-07-11T05:23:26ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-07-011510.3389/fonc.2025.16019851601985Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based studyLi Yuqin0Li Yuqin1Li Hongyan2Li Hongyan3Li Hongyuan4Li Tingting5He Kun6Fang Jie7Han Yunhui8Department of Obstetrics and Gynecology, Jinan Central Hospital, Jinan, ChinaSchool of Clinical Medicine, Southwest Medical University, Luzhou, Sichuan, ChinaDepartment of Anesthesiology, The Affiliated Traditional Chinese Medicine Hospital, Southwest Medical University, Luzhou, ChinaLuzhou Key Laboratory of Research for Integrative on Pain and Perioperative Organ Protection, Luzhou, ChinaSchool of Clinical Medicine, Southwest Medical University, Luzhou, Sichuan, ChinaDepartment of Health Management Center, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, ChinaClinical Research Institute, The Affiliated Hospital, Southwest Medical University, Luzhou, ChinaDepartment of Respiratory Medicine, Dezhou People’s Hospital, Dezhou, Shandong, ChinaDepartment of Obstetrics and Gynecology, Jinan Central Hospital, Jinan, ChinaAimThis study aims to develo\p a population-adapted machine learning-based prediction model for hepatocellular carcinoma (HCC) lymph node metastasis (LNM) to identify high-risk patients requiring intensive surveillance.MethodsData from 23511 HCC patients in the SEER database and 57 patients from our hospital were analyzed. Seven LNM risk indicators were selected. Four machine learning algorithms—decision tree (DT), logistic Regression (LR), multilayer perceptron (MLP), and extreme gradient boosting (XGBoost)—were employed to construct prediction models. Model performance was evaluated using area under the curve, accuracy, sensitivity, and specificity.ResultsAmong 23511 SEER patients, 1679 (7.14%) exhibited LNM. Race, Sequence number, Tumor size, T stage and AFP were identified as independent predictors of LNM. The LR model achieved optimal performance (area under the curve: 0.751; accuracy: 0.707; sensitivity: 0.711; specificity: 0.661). External validation with 57 patients from our hospital confirmed robust generalizability (area under the curve: 0.73; accuracy: 0.737; sensitivity: 0.829; specificity: 0.5), outperforming other models.ConclusionsThe LR-based model demonstrates superior predictive capability for LNM in HCC, offering clinicians a valuable tool to guide personalized therapeutic strategies.https://www.frontiersin.org/articles/10.3389/fonc.2025.1601985/fullhepatocellular carcinomamachine learningpredictive modellymph node metastasislogistic regression |
| spellingShingle | Li Yuqin Li Yuqin Li Hongyan Li Hongyan Li Hongyuan Li Tingting He Kun Fang Jie Han Yunhui Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study Frontiers in Oncology hepatocellular carcinoma machine learning predictive model lymph node metastasis logistic regression |
| title | Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study |
| title_full | Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study |
| title_fullStr | Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study |
| title_full_unstemmed | Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study |
| title_short | Lymph node metastasis in patients with hepatocellular carcinoma using machine learning: a population-based study |
| title_sort | lymph node metastasis in patients with hepatocellular carcinoma using machine learning a population based study |
| topic | hepatocellular carcinoma machine learning predictive model lymph node metastasis logistic regression |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1601985/full |
| work_keys_str_mv | AT liyuqin lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT liyuqin lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT lihongyan lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT lihongyan lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT lihongyuan lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT litingting lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT hekun lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT fangjie lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy AT hanyunhui lymphnodemetastasisinpatientswithhepatocellularcarcinomausingmachinelearningapopulationbasedstudy |