AI Tool Personalizes Immunotherapy for Better Results, Fewer Risks! 

United States: An Alternative to chemotherapy, immunotherapy has been showcasing promising results in the treatment of cancer. However, a new artificial intelligence tool is designed to make sure the patient receives the best possible experience. 

More about the Immunotherapy 

According to Fox News, it was first approved in 2011, and it takes the help of the cancer patient’s own immune system in order to attack the cancer. 

However, according to the experts, the method is not conducive for every individual, as the reports reveal that only 15 percent to 20 percent of those who have used it have experienced its life-saving results. 

Moreover, similar to other kinds of medications, immunotherapy also shows certain side effects that can be lethal at times, as the reports stated. 

As per the studies, there are 10 percent to 15 percent of the patients developed “significant toxicities.” 

AI Tool Personalizes Immunotherapy for Better Results, Fewer Risks. Credit | Shutterstock
AI Tool Personalizes Immunotherapy for Better Results, Fewer Risks. Credit | Shutterstock

More about the AI model 

For the past five years, the model’s development has been in progress by GE HealthCare in collaboration with Vanderbilt University Medical Center (VUMC) in Nashville, Tennessee, where the model was trained on thousands of patients’ electronic health records (EHRs). 

It is done to recognize various patterns in how they have to respond to immunotherapy while focusing on safety and effectiveness. 

Jan Wolber, global digital product leader at GE HealthCare’s pharmaceutical diagnostics segment, stated, “The model predicts which patients are likely to derive the benefit from immunotherapy versus those patients who may not,” as Fox News reported. 

Moreover, “It also predicts which patients have a likelihood of developing one or more significant toxins,” he added. 

How was the model training conducted? 

While extracting data from the patient’s health record, the model analyzed the demographic information, imaging scans, preexisting diagnoses, lifestyle habits (such as smoking), medication history, and more. 

Travis Osterman, a medical oncologist and associate chief medical information officer at Vanderbilt University Medical Center, said, “All of these data are already being collected by the patient’s oncologist, or they’re filling out a form in the waiting room ahead of time,” as the Fox News reported. 

“We’re not asking for additional blood samples or complex imaging. These are all data points that we’re already collecting — vital signs, diagnoses, lab values, those sorts of things,” Osterman said. 

The study findings were published in the Journal of Clinical Oncology Clinical Cancer Informatics. 

As per the study reports, the AI model showed 70 to 80 percent accuracy in forecasting the patients’ responses to immunotherapies. 

Wolder added, “While the models are not perfect, this is actually a very good result,” and, “We can implement those models with very little additional effort because there are no additional measurements required in the clinic.”