A machine learning method for improving liver cancer staging.

J Biomed Inform

Center for Statistical Science, Tsinghua University, Beijing, China; Department of Industrial Engineering, Tsinghua University, Beijing, China. Electronic address:

Published: January 2023

Liver cancer is a common malignant tumor, and its clinical stage is closely related to the clinical treatment and prognosis of patients. Currently, the BCLC staging system revised by the BCLC group of University of Barcelona is the globally recognized staging system for liver cancer. However, with the deepening of related research, the current staging system can no longer fully meet the clinical needs. In this work, we propose a novel machine learning method for constructing an automatic hepatocellular carcinoma staging model that incorporates far more clinical variables than any existing staging system. Our model is based on random survival forests, which generates a unique hazard function for each patient. B-splines are used to embed hazard functions into vectors in low-dimensional space and hierarchical clustering method groups similar patients to form staging cohorts. The resulting staging system significantly outperforms the BCLC system in terms of distinctiveness between patients in different stages.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jbi.2022.104266DOI Listing

Publication Analysis

Top Keywords

staging system
20
liver cancer
12
machine learning
8
learning method
8
staging
8
system
6
method improving
4
improving liver
4
cancer staging
4
staging liver
4

Similar Publications

Characteristics of patients with undiagnosed stage 3 chronic kidney disease: results from an observational study (REVEAL-CKD) in China.

Lancet Reg Health West Pac

January 2025

Division of Nephrology, National Clinical Research Centre for Kidney Disease, State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China.

Background: Early diagnosis of chronic kidney disease (CKD) is crucial for timely intervention to delay disease progression and improve patient outcomes. However, data for clinical characteristics of Chinese patients with undiagnosed, early-stage CKD are lacking.

Methods: REVEAL-CKD is a multinational, observational study using real-world data in selected countries to describe factors associated with undiagnosed stage 3 CKD, time to diagnosis, and CKD management post diagnosis.

View Article and Find Full Text PDF

Insect farming: A bioeconomy-based opportunity to revalorize plastic wastes.

Environ Sci Ecotechnol

January 2025

Global Centre for Environmental Remediation (GCER), College of Engineering, Science and Environment, University of Newcastle, Callaghan, NSW, 2308, Australia.

Managing plastic waste is one of the greatest challenges humanity faces in the coming years. Current strategies-landfilling, incineration, and recycling-remain insufficient or pose significant environmental concerns, failing to address the growing volume of plastic residues discharged into the environment. Recently, increasing attention has focused on the potential of certain insect larvae species to chew, consume, and partially biodegrade synthetic polymers such as polystyrene and polyethylene, offering novel biotechnological opportunities for plastic waste management.

View Article and Find Full Text PDF

Study based on bibliometric analysis: potential research trends in fluid management for sepsis.

Front Med (Lausanne)

January 2025

Department of Critical Care Medicine, Qilu Hospital, Shandong University, Qingdao, China.

Objective: To investigate the potential and evolving trends in fluid management for patients with sepsis, utilizing a bibliometric approach.

Methods: Scholarly articles pertaining to fluid therapy for sepsis patients were extracted from the Web of Science (WoS) database as of June 1, 2024. The R software package, "Bibliometrix," was utilized to scrutinize the primary bibliometric attributes and to construct a three-field plot to illustrate the relationships among institutions, nations, and keywords.

View Article and Find Full Text PDF

The cellular and molecular mechanisms underlying lymphocyte development are diverse among teleost species. Although recent scRNA-seq analyses of zebrafish hematopoietic cells have advanced our understanding of teleost hematopoiesis, comparative studies using another genetic model, medaka, which is evolutionarily distant among teleosts, is useful for understanding commonality and species-specificity in teleosts. In order to gain insight into how different molecular and cellular mechanisms of lymphocyte development in medaka and zebrafish, we established a () mutant medaka, which exhibited defects in V(D)J rearrangement of lymphocyte antigen receptor genes, accordingly lacking mature B and T cells.

View Article and Find Full Text PDF

Background: The presence of level IV/V metastasis is a significant prognostic factor for patients with oral and oropharyngeal cancer, while level IV lymphadenopathy defines the N3 stage in nasopharyngeal carcinoma. However, the current staging system for hypopharyngeal squamous cell carcinoma (HPSCC) does not consider the location of involved nodes.

Objectives: To evaluate the risk factors and prognostic impact of level IV/V metastasis in patients with HPSCC.

View Article and Find Full Text PDF

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!