A new study has been conducted by investigators from the Mass General Cancer Center in collaboration with researchers at the Massachusetts Institute of Technology (MIT) to develop and test an Artificial Intelligence tool called as Sybil. Sybil accurately predicted the lung cancer risk with or without smoking history. The results of the study were published in the Journal of Clinical Oncology. These results were based on the analyses of LDCT scans of lung cancer patients in U.S. and Taiwan. Also, the U.S. Preventive Service Task Force recommends for annual LDCTs for people above the age of 50 years with a history of 20 pack per year and who are either currently smoking or have quit smoking within last fifteen years. LDCT has demonstrated to lower deaths caused by lung cancer by up to 24 percent. But, only a fraction of target population gets screened as per the recommendations and this creates the need for timely treatment of more people.
In the study, Sybil was able to accurately predict risk of lung cancer. It predicted cancer within an year with Area Under the Curve (AUC) of 0.92 of participants. It predicted lung cancer within six years with AUCs of 0.75,0.81 and 0.80 for three datasets.
“Lung cancer rates continue to rise among people who have never smoked or who haven’t smoked in years, suggesting that there are many risk factors contributing to lung cancer risk, some of which are currently unknown,” said corresponding author Lecia Sequist, MD, MPH, director of the Center for Innovation in Early Cancer Detection and a lung cancer medical oncologist at the Mass General Cancer Center. “Instead of assessing individual environmental or genetic risk factors, we’ve developed a tool that can use images to look at collective biology and make predictions about cancer risk.”
This research team has identified deep learning as a way to solve this problem and worked on a model thar analyzes scans and predicts lung cancer risk for the next one to six years. The team concluded that further studies will be needed to determine if Sybil can accurately predict lung cancer among diverse populations. It will help the radiologists to set personalized screening for the patients.
The information shared in this blog is for educational purposes only and is certainly not a substitute for medical advice. Please consult with your healthcare professional for any medical needs.