Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us
Guangdong Fapon Biotech Co., Ltd.

Download Mobile App




AI Model Improves Breast Cancer Survival Prediction

By LabMedica International staff writers
Posted on 26 Oct 2026

Predicting survival in breast cancer can be challenging because outcomes are influenced by a combination of clinical, biological, and genetic factors. More...

Traditional survival models can estimate risk but may not fully capture the complex relationships among these variables, limiting confidence in treatment and follow-up planning. Researchers have now developed an artificial intelligence-based survival model designed to provide more individualized prognostic information and support personalized breast cancer care.

The University of Cincinnati Cancer Center developed a hybrid statistical deep learning framework for breast cancer survival prediction. The model combines statistical methods with deep learning to identify complex patterns across patient data and stratify patients who may appear clinically similar into more specific risk groups. This approach could help physicians better tailor treatment decisions and discussions about prognosis.

The model also addresses the limited availability and cost of tumor genetic testing at some hospitals. Researchers generated simulated gene expression data and integrated these molecular features with clinical information. The framework transforms clinical data into a more informative representation of patient risk, accounts for similarities among patients, and incorporates uncertainty into its survival predictions.

The team evaluated the model using a publicly available dataset containing clinical and survival information from 1,980 patients with breast cancer. In this dataset, the model achieved greater accuracy in predicting survival outcomes than the comparison models evaluated in the study. The research was published in the Journal of Statistical Theory and Practice, and the team plans to further assess the model using larger and more diverse patient datasets.

“These deep learning–based models are not meant to replace physicians. They are tools that could help physicians understand complex patient information and support their decisions. This combination of statistics, machine learning and cancer research has been exciting for me to help us improve how we understand patient outcomes,” said Wedad Alatebi, doctoral student in the Department of Biostatistics, Health Information and Data Science in the University of Cincinnati College of Medicine.

Related Links
University of Cincinnati Cancer Center


Platinum Member
Automated Coagulation Analyzer
Hemolumi H6
βeta-Hydroxybutyrate Reagent
β-Hydroxybutyrate LiquiColor®
Portable POCT Blood Gas Analyzer
BD100
Gold Member
Nucleic Acid Extractor System
NEOS-96 XT
Read the full article by registering today, it's FREE! It's Free!
Register now for FREE to LabMedica.com and get access to news and events that shape the world of Clinical Laboratory Medicine.
  • Free digital version edition of LabMedica International sent by email on regular basis
  • Free print version of LabMedica International magazine (available only outside USA and Canada).
  • Free and unlimited access to back issues of LabMedica International in digital format
  • Free LabMedica International Newsletter sent every week containing the latest news
  • Free breaking news sent via email
  • Free access to Events Calendar
  • Free access to LinkXpress new product services
  • REGISTRATION IS FREE AND EASY!
Click here to Register








Channels

Clinical Chemistry

view channel
Image: Researchers combined a blood-based biomarker of Alzheimer’s disease with age, sex, and genetic risk to estimate future cognitive impairment risk in asymptomatic adults (Image Credit: Adobe Stock)

Blood Biomarker Model May Help Estimate Five- and 10-Year Cognitive Impairment Risk

Estimating future cognitive impairment risk remains challenging in cognitively healthy adults, particularly when biomarker findings are reduced to simple positive or negative results. Because mild cognitive... Read more

Molecular Diagnostics

view channel
Image Credit: Shutterstock

Lung Cancer Atlas Reveals Cellular Patterns Associated With Patient Prognosis

Lung cancer is a leading cause of cancer-related death worldwide and is characterized by substantial cellular heterogeneity. Even within a single tumor, cancer cells can vary in aggressiveness, while immune,... Read more

Immunology

view channel
Image: The panel expands Cepheid’s respiratory testing portfolio on the GeneXpert platform, offering laboratories greater flexibility in selecting tests based on clinical needs. (Photo courtesy of Cepheid)

Multiplex PCR Test Gains CE Marking to Support Respiratory Infection Diagnosis

Acute respiratory infections often present with overlapping symptoms, making it difficult to distinguish between viral and bacterial causes. Seasonal surges of influenza-like illness in Europe further... Read more

Microbiology

view channel
Image: Malaria is caused by Plasmodium parasites, primarily transmitted through the bites of infected female Anopheles mosquitoes (Image Credit: Adobe Stock)

Complete Malaria Genomes Could Improve Species Identification and Surveillance

Malaria remains a major global health challenge, with an estimated 282 million cases and 610,000 deaths worldwide in 2024. Although most research has focused on Plasmodium falciparum, Plasmodium ovale... Read more

Industry

view channel
Image: The TOMR trial uses Signatera-guided MRD testing to identify high-risk patients for curative-intent treatment.

Natera and Incyte Collaborate on MRD-Guided Colorectal Cancer Treatment Study

Natera (Austin, TX, USA) has entered into a clinical collaboration with Incyte (Wilmington, DE, USA) for a Phase II study evaluating molecular residual disease (MRD)-guided treatment in colorectal cancer.... Read more
Copyright © 2000-2026 Globetech Media. All rights reserved.