US EditionScientists Develop AI Method to Predict Overall Survival Rate of Prostate Cancer Patients
- Researchers at the University of Sharjah and Near East University in Turkey created an AI-based approach in 2025 that utilizes a combination of eight ensemble models to predict overall survival in patients diagnosed with prostate adenocarcinoma.
- They applied machine learning due to clinical challenges in survival prediction caused by the disease's diverse nature, coexisting conditions, and limits of conventional diagnostic markers.
- The study used data from the Cancer Genome Atlas PanCancer Atlas and evaluated models including Gradient Boosting, Random Forest, AdaBoost, LightGBM, Hard Voting Classifier, and Support Vector Classifier through key performance metrics.
- Gradient Boosting outperformed other models by achieving perfect scores of 1.0 in accuracy, recall, precision, and F-1 score, a 0.99 ROC AUC, and predicted a 70.6% overall survival rate.
- The findings indicate that ensemble models like Gradient Boosting could improve clinical decision-making if incorporated into workflows, though further research and clinical application remain necessary.
5 Articles
5 Articles
Medical Xpress
MSNScientists develop AI method to predict overall survival rate of prostate cancer patients
Scientists say they have worked out a machine learning method with the ability to provide close to precise survival estimates of patients afflicted with prostate adenocarcinoma, which is by far the most common type of prostatic cancer cases.
Scientists develop AI method to predict overall survival rate of prostate cancer patients - Journal of Cyber Policy
Machine learning prediction of overall survival in prostate adenocarcinoma using ensemble techniques. Copyright: Computers in Biology and Medicine. Doi: https://doi.org/10.1016/j.compbiomed.2025.110008 The dataset on prostate adenocarcinoma on an ensemble ML model for the prediction of the OS of PAC patients. The models are also evaluated based on the evaluation metrics. Copyright: Computers in Biology and Medicine. Doi: https://doi.org/10.1016/…
Coverage Details
Bias Distribution
- 50% of the sources lean Left, 50% of the sources are Center
To view factuality data please Upgrade to Premium
Ownership
To view ownership data please Upgrade to Vantage
