Despite major advances in treatment and diagnosis over the past decades, cancer remains one of the most deadly diseases worldwide.
Early detection and care are the best tools doctors have against the disease. However, challenges—including high false-positive rates and difficult predicting treatment success—can slow down the process.
Now, healthcare professionals and medical researchers are finding ways to apply the latest developments from outside of medicine—like artificial intelligence—to the diagnosis and treatment of cancer. Here are five of these innovative technologies.
1. Improving lung cancer screening
Lung cancer screening with the use of computed tomography (CT) is highly effective in reducing the mortality rate of lung cancer. By some estimates, screening can cut back this mortality rate by 20 percent.
However, there are still significant challenges that reduce the effectiveness of CT screening. Even trained radiologists can miss evidence of lung cancer in some scans, delaying a diagnosis and the care patients need.
Now, a team of researchers at Google has developed an AI algorithm that can use CT to screen for lung cancer. In a study testing the effectiveness of the algorithm, it was found to be even more accurate than radiologists at correctly identifying tumors and malignant growths in scans. It also reduced the rates of false positives and false negatives in CT screening.
The algorithm, once ready for public use, could help increase the accuracy of CT screening in diagnosing lung cancer. It could also reduce the time to diagnosis by acting as an assistant to radiologists, automatically flagging scans that are likely to show tumors or other growths.
2. Ruling out false positives and negatives
Breast cancer has extremely high five-year survival rates when caught early, before it becomes invasive. However, unlike cervical cancer, which is rare, breast cancer is much more common. False positives and negatives in diagnosis have impacts on significantly larger populations.
Mammograms, the current gold standard detection method for breast cancer, still have high false-negative rates that can lead to delayed treatment for patients with breast cancer. Other popular methods, like genetic tests, have similar issues with both false positives and negatives. They have led patients to pursue major surgeries — like double mastectomies — when they may not have been necessary.
As with lung cancer, new AI-based algorithms may help reduce false positives and negatives in the diagnosis of breast cancer. The algorithms work in tandem with doctors, drawing attention to regions on a mammogram that look like they could contain tumors or evidence of malignant tissue.
So far, they've been demonstrated to reduce false positives by 6 percent and false negatives by 9 percent.
These AI-boosted detection methods may result in quicker treatment for the patients that need it, while sparing those who may have been incorrectly considered at high risk for breast cancer with previous diagnostic methods.
3. Predicting immunotherapy success
Immunotherapy is a relatively new treatment for cancer that uses drugs to boost the human immune system and help it fight off malignant cells. This method can be highly effective in treating the disease, and often has fewer side effects than other treatments like chemotherapy and radiation therapy. However, not all patients react the same, and there's no way of knowing whether or not immunotherapy will work.
A new AI tool may change this. In combination with regular CT scans, an algorithm could be used to identify patients who are most likely to respond well to immunotherapy. This would allow doctors to provide them with treatment and move other patients to alternatives, like chemotherapy, quicker than they would have otherwise.
4. Improving radiation therapy
Radiation therapy is one of the most effective treatments available for many different types of cancer. However, it is extremely hard on the body, and it is often difficult to predict how patients will react.
Recently, artificial intelligence was successfully used to help doctors plan where to target radiation therapy and forecast how well a patient is likely to hold up to the effects. The new technology may allow doctors to better plan radiotherapy treatment, as well as begin to look for alternatives earlier in the treatment process if necessary.
5. Personalized cancer treatment
The Cleveland Clinic has started using AI to personalize patient treatment plans. The AI model used by the clinic works with a combination of medical records and patient health history, along with CT scans. It builds customized programs for each patient based on a mathematical model that estimates how well they would respond to certain treatments.
With the right information, the model can help doctors determine the correct dose of radiation for a patient. It can help ensure patients receive the most effective treatment as soon as possible, and ideally, spend less time in the hospital.
How AI can improve cancer treatment
Cancer remains one of the most deadly diseases, despite major advancements in treatment and diagnosis methods. Soon, AI may change this. Its pattern-finding abilities can improve false positive and negative rates and help doctors better plan treatments, which could lead to potential cancer cure news in the future.
While many of these applications are still experimental, some are already being used to improve the effectiveness of cancer care.
Kayla Matthews is a MedTech journalist and writer. Her work has also been featured on Medical Economics, HIT Consultant, HealthIT Outcomes and Health IT Answers. To read more from Kayla, please visit her blog here.
