Artificial intelligence (AI) can determine the course and severity of Merkel cell carcinomas (MCC), enhancing clinical decision making, a new study suggests.
For the study, researchers combined machine learning with clinical expertise to develop a web-based system called “DeepMerkel” which offers the power to predict MCC treatment-specific outcomes based on personal and tumour specific features.
“DeepMerkel is allowing us to predict the course and severity of a Merkel cell carcinoma enabling us to personalize treatment so that patients are getting the optimal management,” says study author Dr. Tom Andrew, a Plastic Surgeon and CRUK-funded PhD student at Newcastle University in Newcastle, U.K. “Using AI allowed us to understand subtle new patterns and trends in the data which meant on an individual level, we are able to provide more accurate predictions for each patient. This is important as in the 20 years up to 2020, the number of people diagnosed with this cancer has doubled and while it is still rare it is an aggressive skin cancer which is increasingly affecting older people.”
Dr Aidan Rose, Senior Clinical Lecturer, Newcastle University and Consultant Plastic Surgeon at Newcastle Hospitals NHS Foundation Trust, adds, “Being able to accurately predict patient outcomes is critical when guiding clinical decision making. This is particularly important when treating aggressive forms of skin cancer in a complex patient group which typically results in difficult, and sometime life-changing, choices being made regarding treatment options. The developments we have made using AI allow us to provide personalized survival predictions and inform a patient’s medical team of the optimal treatment.”
In two complementary publications in Nature Digital Medicine and the Journal of the American Academy of Dermatology, the team describe how using advanced statistical and machine learning methods they developed the web-based prognostic tool for MCC.
In Nature Digital Medicine, the team describe how they employed explainability analysis and the data of to reveal new insights into mortality risk factors for MCC. They then combined deep learning feature selection with a modified XGBoost framework, to develop a web-based prognostic tool for MCC which they termed DeepMerkel.
Analyzing the data from nearly 11,000 patients in two countries, the researchers describe in the Journal of the American Academy of Dermatology how DeepMerkel was able to accurately identify high-risk patients at an earlier stage of the cancer. This allows medics to make more informed decisions about when to use radical treatment options and intensive disease monitoring.
“With further investment, the exciting next step for our team is to further develop DeepMerkel so that the system can present options to help advise clinicians on the best treatment pathway open to them,” says Dr. Andrew. The next step is to integrate the DeepMerkel website into routine clinical practice and broaden the scope of its use into other tumour types.
PHOTO CREDIT: DermNet
