Medical researchers in Boston are hopeful about a new AI tool that could help detect early signs of lung cancer years before doctors would typically spot them. The tool, called Sybil, is an artificial intelligence (AI) system that was developed by scientists at the Massachusetts Institute of Technology in Cambridge and the Mass General Cancer Center. Reports say the tool was shown to accurately predict whether a person would develop lung cancer in the next year between 86% and 94% of the time in one study.
A Game-changer!
This new development could be especially vital for people who are at high risk of lung cancer. The Centers for Disease Control and Prevention (CDC) recommends that adults in this category should undergo a low-dose CT scan annually to screen for the disease. However, even the most skilled radiologist cannot spot everything with the naked eye, which is where Sybil comes in.
According to Dr. Lecia Sequist, the program director of the Cancer Early Detection and Diagnostics Clinic at Massachusetts General Hospital, “the AI that we developed is looking at the scan in a completely different way than a human radiologist looks at it.” This new tool could be a game-changer in the early detection of lung cancer, a leading cause of cancer death.
Although Sybil has not yet been approved by the Food and Drug Administration (FDA) for use outside clinical trials, it could potentially play a unique role in the detection and treatment of lung cancer. Currently, there are over 300 AI tools approved by the FDA for use in radiology. Most of these are used to assist doctors in the diagnosis and treatment of cancer, but not for predicting someone’s future cancer risk, as Sybil does.
How does Sybil work?
Sybil works by analyzing a single CT scan to predict cancer risk. It examines the three-dimensional image, looking for signs of abnormal growth in the lungs and other patterns or nuisances that are not fully understood. Based on its findings, Sybil provides predictions for whether a person will develop lung cancer in the next one to six years.
Early detection is crucial when it comes to lung cancer. The only way to spot it early is with a CT scan, as the lungs cannot be seen or felt. Past research has shown that screening with low-dose CT scans can reduce the risk of death from lung cancer by 24%. However, an AI tool like Sybil could potentially increase the rates of early detection of lung cancer, leading to higher survival rates.
Far from perfect…
Despite the potential benefits of AI tools in the field of radiology, there are still concerns about over-diagnosis and the lack of diversity in the data used to train these systems. Doctors may put patients through a potentially unnecessary biopsy for a nodule that may end up being benign. There are also concerns that the data used to develop AI tools does not represent the diversity of the country, which could lead to biased outcomes. It is essential to ensure that AI tools are developed in a way that is tailored to help people of all races and backgrounds.
The development of Sybil is a promising breakthrough in the medical field, offering us hope in the fight against cancer. Although there are still challenges to overcome, it is important that we continue to refine and develop AI tools like Sybil in a way that benefits all individuals, regardless of their race, ethnicity, or socioeconomic status. With continued research and development, AI tools could play a unique role in the fight against cancer, bringing us one step closer to a future where cancer is a treatable and even preventable condition.
