The study, led by investigators from the Mass General Cancer Center, a member of Mass General Brigham, along with researchers from the Massachusetts Institute of Technology (MIT), developed and tested an artificial intelligence tool known as Sybil. Based on analyzes of LDCT scans of patients in the United States and Taiwan, Sybil accurately predicted lung cancer risk for individuals who were or were not significant smokers. The results are published on the website

“Lung cancer rates continue to rise among people who have never smoked or who have not smoked for years, suggesting that there are many risk factors that contribute to lung cancer risk, some of which are currently unknown,” said author Lecia Sequist, MD. , MPH, director of the Center for Innovations in Early Cancer Detection and lung cancer medical oncologist at Mass General Cancer Center. “Instead of assessing individual environmental or genetic risk factors, we developed a tool that can use images to look at collective biology and make predictions about cancer risk.”

Application of Artificial Intelligence in Lung Cancer

The US Preventive Services Task Force recommends annual LDCTs for people over age 50, with a history of 20 pack-years, who are current smokers or who have quit smoking within the past 15 years. However, less than 10 percent of eligible patients are screened each year. To improve the effectiveness of lung cancer screening and provide personalized assessments, Sequist and colleagues at the Mass General Cancer Center teamed up with investigators at the Jameel Clinic at MIT. Using data from the National Lung Screening Trial (NLST), the team developed Sybil, a deep learning model that analyzes scans and predicts lung cancer risk over the next one to six years.

Advertising



“Sybil requires only one LDCT and does not depend on clinical data or radiologist annotations,” said co-author Florian Fintelmann, Department of Radiology, Division of Thoracic Imaging and Interventions, Massachusetts General Hospital. “It is designed to run in real-time in the background of a standard radiology reading station, enabling clinical decision support at the point of care.”

The team validated Sybil using three independent data sets – scans of more than 6,000 NLST participants that Sybil had never seen before; 8,821 LDCTs from Massachusetts General Hospital (MGH); and 12,280 LDCTs from Chang Gung Memorial Hospital in Taiwan. The latter set of scans included people with varying smoking histories, including never smokers.

Sybil was able to accurately predict lung cancer risk among these sets. The researchers determined how accurately Sybil used the Area Under the Curve (AUC), how well the test could differentiate between diseased and normal samples, and that 1.0 was a perfect score. Sybil predicted cancer within one year with an AUC of 0.92 for the additional NLST participants, 0.86 for the MGH data set, and 0.94 for the Taiwan data set. The program predicted lung cancer within six years with AUCs of 0.75, 0.81, and 0.80 for the three data sets, respectively.

“I am excited about the translational efforts led by the MGH team that aim to change outcomes for patients who would otherwise develop advanced disease,” said co-author and Jameel Clinic faculty member Regina Barzilay, PhD, member of the Koch Integrative Institute for Cancer Research.

The researchers note that this is a retrospective study, and prospective studies that follow patients are needed to confirm Sybil. In addition, the majority of US participants in the study were white (92 percent), and future studies will be needed to determine whether Sybil can accurately predict lung cancer among different populations. Sequist and colleagues will launch a prospective clinical trial to test Sybil in the real world and understand how it complements the work of radiologists. The code has also been released to the public.

“In our study, Sybil was able to detect risk patterns from LDCT that are invisible to the human eye,” Sequist said. “We’re excited to test this program further to see if it can add information that helps radiologists diagnose and guide us to personalize screening for patients.”

Source: Eurekalert

Source link

Share.

Leave A Reply