Researchers from The University of Texas claim to have developed a machine learning model that is 30 per cent more accurate than previous methods.
Machine learning (ML) techniques are becoming increasingly prevalent in medical settings as a way to predict survival rates and life expectancies among patients diagnosed with diseases such as cancer, heart disease, stroke and, more recently, Covid-19.
A professor and his doctoral student at The University of Texas at Arlington have published a new model of predicting survival from cancer that they say is 30 per cent more effective than previous models in predicting who will be cured of disease.
The model can help patients avoid treatments they don’t need while allowing treatment teams to focus instead on others who need additional interventions, the authors state.
“Previous studies modelling the probability of a cure, also called the cure rate, used a generalised linear model with a known parametric link function such as the logistic link function,” said principal investigator Suvra Pal, associate professor of statistics in the Department of Mathematics.
“However, this type of research doesn’t capture non-linear or complex relationships between the cure probability and important covariates, such as the age of the patient or the age of a bone marrow donor.
“Our research takes the previously tested promotion time cure model (PCM) and combines it with a supervised type of ML algorithm called a support vector machine (SVM) that is used to capture non-linear relationships between covariates and cure probability.”
Supported by a grant from the National Institute of General Medical Sciences, the new SVM-integrated PCM model (PCM-SVM) is developed in a way that 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.
To test the technique, Pal and his student Wisdom Aselisewine took real survival data for patients with leukaemia, a type of blood cancer that is often treated with a bone marrow transplant.
The researchers chose the condition because it is caused by the rapid production of abnormal cancerous, white blood cells. Since this does not happen in healthy people, they were able to clearly see which patients in the historic data set were cured by treatments and which were not.
Both statistical models were tested and the newer PCM-SVM technique was found to be 30 per cent more effective at predicting who would be cured by the treatments compared to the previous technique.
“These findings clearly demonstrate the superiority of the proposed model,” Pal said.
“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.”
