Cancer Prevention Gets a Boost from AI
February is National Cancer Prevention Month, which focuses on reducing cancer risk through research and education. Risk factors such as smoking, overexposure of skin to the sun, and unhealthy diet/exercise are best combated by educating as many people as possible about the consequences of cancer. Another branch of cancer prevention is the early detection of cancer through routine screening. This week’s Domain Knowledge highlights how AI improves cancer detection processes to help prevent cancer.
Although detection doesn’t prevent cancer as a whole, it prevents more severe, life-threatening stages of cancer by addressing it before it reaches that point. For example, over the past 20 years, there is nearly a 30% reduction in breast cancer mortality among women over 50 who underwent routine mammography vs those who did not. Lung Cancer is another prime example, where almost 9 in 10 lung cancer patients will survive their disease for at least a year if diagnosed at the earliest stage compared to around 1 in 5 people when diagnosed at the most advanced stage.
AI greatly improves the efficiency and accuracy of the screening and diagnosis processes. In the context of breast cancer, this is demonstrated in a recent study on AI for Digital Breast Tomosynthesis that shows how AI integrated into screening practice leads to an improvement in the diagnostic performance of radiologists in the detection of breast cancer.
Perhaps a less obvious way AI contributes to efficiency is in helping determine when patients would be best suited to be screened. Scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) are developing technology for creating risk-based screening guidelines for mammograms. This more personalized approach to cancer screening helps patients in higher-risk groups that are screened routinely, while also reducing costly and potentially traumatic overscreening and overtreatment.
Access to screenings with AI goes even further with tools that anyone can use on their phone to help self-diagnose certain types of skin cancer. The application called Skinvision accomplishes this by guiding users through skin checks using their phone camera and assessing lesions for skin cancer. Though physician intervention is needed if it does detect early skin cancer, this AI tool helps people be proactive in screening and prevention.
The next step in preventing cancer with AI will likely be assessing for precursors to cancer. Scott Leatherdale, a Public Health Professor at the University of Waterloo, suggests in a recent publication that it’s possible these big data assets can be adapted to have more impact on the future cancer burden through more focus on primary prevention efforts that incorporate artificial intelligence. In line with the theme of Cancer Prevention Month, reducing the risk of cancer as early as possible will have a significant impact.
That’s a wrap for this week’s review of news and happenings in the healthcare AI space. In closing, I’ll leave you with an invitation to learn more about the benefits of using an AI Hub to manage multiple applications across your clinical needs and offer you a personal demo of Ferrum’s platform and growing AI catalog.
If you have AI tips, suggestions, or resources you’d like to share leave us a note below, and please feel free to suggest topics you would like to see covered in future posts.