Background: Previous studies mostly use single-type features to establish a prediction model. We aim to develop a comprehensive prediction model that effectively identify patients with poor prognosis for single hepatocellular carcinoma (HCC) based on artificial intelligence (AI). : 236 single HCC patients were studied to establish a comprehensive prediction model. We collected the basic information of patients and used AI to extract the features of magnetic resonance (MR) images.
Results: The clinical model based on linear regression (LR) algorithm (AUC: 0.658, 95%CI: 0.5021-0.8137), the radiomics model and deep transfer learning (DTL) model based on light gradient-boosting machine (Light GBM) algorithm (AUC: 0.761, 95%CI: 0.6326-0.8886 and AUC: 0.784, 95%CI: 0.6587-0.9087, respectively) were the optimal prediction models. A comparison revealed that the integrated nomogram had the largest area under the receiver operating characteristic curve (AUC) (all P < 0.05). In the training cohort, the integrated nomogram was predictive of recurrence-free survival (RFS) as well as overall survival (OS) (C-index: 0.735 and 0.712, P < 0.001). In the test cohort, the integrated nomogram also can predict RFS and OS (C-index: 0.718 and 0.740, P < 0.001) in patients.
Conclusion: The integrated nomogram composed of signatures in the prediction models can not only predict the postoperative recurrence of single HCC patients but also stratify the risk of OS after the operation.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11761343 | PMC |
| http://dx.doi.org/10.1016/j.heliyon.2025.e41735 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Predicting Carbonic Anhydrase Binding Affinity: Insights from QM Cluster Models.
J Phys Chem B
January 2025
School of Chemistry, The University of New South Wales, Sydney, NSW 2052, Australia.
A systematic series of QM cluster models has been developed to predict the trend in the carbonic anhydrase binding affinity of a structurally diverse dataset of ligands. Reference DLPNO-CCSD(T)/CBS binding energies were generated for a cluster model and used to evaluate the performance of contemporary density functional theory methods, including Grimme's "3c" DFT composite methods (rSCAN-3c and ωB97X-3c). It is demonstrated that when validated QM methods are used, the predictive power of the cluster models improves systematically with the size of the cluster models.
View Article and Find Full Text PDFScreening of Oncogenic Proteins and Development of a Multiepitope Peptide Vaccine Targeting AKT1 and PARP1 for Breast Cancer by Integrating Reverse Vaccinology and Immune-Informatics Approaches.
Asian Pac J Cancer Prev
January 2025
Parul Institute of Applied Sciences, Parul University, Vadodara, India.
Background: Breast cancer remains a significant global health challenge, requiring innovative therapeutic strategies. In silico methods, which leverage computational tools, offer a promising pathway for vaccine development. These methods facilitate antigen identification, epitope prediction, immune response modelling, and vaccine optimization, accelerating the design process.
View Article and Find Full Text PDFAnalyzing Secondary Cancer Risk: A Machine Learning Approach.
Asian Pac J Cancer Prev
January 2025
Department of Physics, Faculty of Sciences, Arak University, Arak, Iran.
Objective: Addressing the rising cancer rates through timely diagnosis and treatment is crucial. Additionally, cancer survivors need to understand the potential risk of developing secondary cancer (SC), which can be influenced by several factors including treatment modalities, lifestyle choices, and habits such as smoking and alcohol consumption. This study aims to establish a novel relationship using linear regression models between dose and the risk of SC, comparing different prediction methods for lung, colon, and breast cancer.
View Article and Find Full Text PDFNew Genetic Variations in RNA-binding Protein Gene and Breast Cancer Risk: A Case-Control Study.
Asian Pac J Cancer Prev
January 2025
Department of Biology, Faculty of Science, University of Sistan and Baluchestan, Zahedan, Iran.
Background: LIN28, a highly conserved RNA-binding protein, regulate a wide variety of post-transcriptional cellular processes. The current study aimed to identify genetic variants of five single nucleotide polymorphisms (SNPs) in the LIN28B gene (rs221634, rs22163, rs314276, rs9404590, and rs12194974) and their association with Breast cancer.
Method: 220 patients and 230 controls were genotyped by the RFLP assay for Lin28B gene variants.
F-18 FDG PET/CT based Preoperative Machine Learning Prediction Models for Evaluating Regional Lymph Node Metastasis Status of Patients with Colon Cancer.
Asian Pac J Cancer Prev
January 2025
Department of Nuclear Medicine, Busan Paik Hospital, University of Inje College of Medicine, Busan, Republic of Korea.
Objective: This study aimed to develop a simple machine-learning model incorporating lymph node metastasis status with F-18 Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) and clinical information for predicting regional lymph node metastasis in patients with colon cancer.
Methods: This retrospective study included 193 patients diagnosed with colon cancer between January 2014 and December 2017. All patients underwent F-18 FDG PET/CT and blood test before surgery.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!