A team of researchers has developed an AI-based cancer survival calculator that goes beyond simply assessing cancer stage to offer a more precise and personalized estimate. A real instrument of hope, with surprisingly accurate results.
Artificial intelligence changes the game in predicting cancer survival
Imagine a future where the diagnosis of cancer is no longer an inevitable verdict, but a starting point for a broader and more personalized conversation. This future may be closer than you think, thanks to a new AI-powered tool that promises to revolutionize the way we see and deal with this disease.
The problem
Until now, survival estimates for cancer patients mainly depended on the stage of the cancer. However, as the doctor points out Lauren Janczewski, lead author of the study, “it's not just that. There are a multitude of other factors that can influence a patient's survival beyond just the stage of the cancer."
And this is where artificial intelligence comes in. Using a type of AI known as machine learning, the research team created a prototype tool called a “cancer survival calculator.” Find the original paper here. This tool has been tested on a huge tumor database, and provides initial five-year survival estimates for patients with breast, thyroid and pancreatic cancer.
The details of the research
The study aimed to identify the patient, tumor and treatment characteristics that most influence survival hope for each cancer type.
The data collected was part of the gigantic National Cancer Database (NCDB), which contains records of 72% of new cancer cases diagnosed in the United States. The researchers found that several factors specific to patients, tumors, and treatments for all three types of cancer significantly influenced survival. For example, for breast cancer, the top four factors were: Whether the patient had undergone cancer surgery. The age of the patient at the time of diagnosis. The size of the tumor. The time from diagnosis to treatment.
“Intelligent” hope
The Cancer Survival Calculator differs in several ways from tools already in use.
- Includes specific tumor biomarkers and treatment variables known to influence a patient's estimated prognosis.
- Use new data models, such as machine learning, that speed up processing.
- Improves forecast accuracy.
The next steps? Dr. Janczewski herself identified them: they are the finalization of a user interface that will allow the use of the Cancer Survival Calculator in clinical practice, and tests of the calculator in selected oncology centers.
This AI-powered cancer survival calculator offers a glimmer of hope and a new perspective. Not only does it provide more accurate estimates, it also encourages a more holistic and personalized view of the disease, allowing patients and doctors to make more informed decisions.
A step forward towards a future in which cancer will no longer be an "invincible enemy", but a challenge to be faced with greater awareness and hope.
Comments are closed.