Communications of the ACM
ML Technique Better at Predicting Cancer Cure Rates
The new SVM-integrated PCM model is developed builds upon a simple interpretation of covariables to predict which patients will be uncured at the end of their initial treatment and need additional medical interventions.
Credit: toolbox-studio.com
A machine learning model developed by University of Texas at Arlington (UTA) researchers can better predict cancer cure rates.
The new model combines the existing promotion time cure model (PCM) with a support vector machine (SVM) algorithm to account for non-linear or complex relationships between cure probability and covariates.
The PCM-SVM model was found to be 30% more effective than the PCM model in tests involving real survival data for leukemia patients.
Said UTA's Suvra Pal, "With our improved predictive accuracy of cure, patients with significantly high cure rates can be protected from the additional risks of high-intensity treatments. Similarly, patients with low cure rates can be recommended timely treatment so that the disease does not progress to an advanced stage for which therapeutic options are limited. The proposed model will play an important role in defining the optimal treatment strategy."
From University of Texas at Arlington
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, D.C., USA
No entries found