Artificial intelligence (AI) has already taken the healthcare industry by storm and it’s only just begun scratching the surface of its capabilities.
This technology has enabled doctors to better detect conditions like epilepsy and Alzheimer’s disease, and may transform the field of oncology more than any prior advancement. Although there is still much work to be done before AI becomes mainstream within medicine, professionals are considering this opportunity to be a major step toward advancing cancer care in the future.
Success with Oncology
A challenge oncologists often face is learning how to effectively treat tumors over time. In an effort to combat this issue, a team of scientists from the University of Edinburgh have recently developed an approach known as “REVOLVER,” which directly addresses evolving tumors that can become resistant to treatment over time.
Through the use of AI, they have discovered a connection between repeated tumor mutations and survival rate, suggesting that specific patterns of DNA mutations could predict how cancers may progress in the future. This is a powerful illustration of how AI may not only be able to predict the progression of cancers, but prompt doctors to take preventive action and make better choices surrounding treatment.
In addition to predicting how a patient’s cancer may unfold, scientists have also utilized AI to speed up the diagnostic process altogether. A study conducted by NYU researchers found that AI could detect both adenocarcinoma and squamous cell carcinoma with 97 percent accuracy.
The same study demonstrated how this technology is able to detect 6 different genetic mutations linked to lung cancer with substantial success. There is much untapped potential of AI, which extends a new sense of hope for those at risk or unknowingly suffering from lung cancer.
Fighting Rare Diseases
While early detection is a major priority, AI is also playing an important role in assisting those suffering from rare cancers that require extensive treatment and targeted therapies.
With the help of an artificial immune system, for example, doctors were able to detect malignant pleural mesothelioma (MPM) with nearly 98 percent accuracy. Through the study, it was found that the artificial immune system outperformed the multi-layer neural network algorithm, an approach that has been commonly used to diagnose disease. MPM is responsible for over 70% of diagnoses and the prognosis is grim, making early detection absolutely key to treating the disease.
This particular form of cancer has stumped medical experts for decades, inspiring researchers to band together worldwide to advance diagnostics and treatment. Scotland is taking charge through their Cancer Innovation Challenge, a program dedicated to helping Scotland become a world leader in cancer care. This program awarded £35,000 to three inspiring projects focused on data science solutions within healthcare, one surrounding the potential of artificial intelligence in diagnosing MPM. Although mesothelioma is quite rare, this is an issue that remains close to the hearts of local residents, as Scotland has an unusually high rate of asbestos-related illnesses nationwide.
Mesothelioma isn’t the only fatal cancer being researched, Dr. Elliot Fishman, a diagnostic radiologist at John Hopkins University, is dedicated to fighting pancreatic cancer through GPU-accelerated deep learning. Working with one of the largest centers for pancreatic cancer treatment in the world, Fishman has developed niche experience in diagnosing pancreatic cancer and acknowledges that AI may be able to detect what the human eye can easily overlook.
Despite positive results, researchers are battling with regulatory organizations to install artificial intelligence throughout hospitals. Logistical issues such as cost, training, and the possibility of AI replacing jobs have hindered its progress. Regardless of these obstacles, the healthcare industry is beyond hopeful for what the future has in store and the evidence for success within research is remarkable.