How AI May Help Treat Metastatic Cancer

By Sherry Baker and Temma Ehrenfeld @SherryNewsViews
November 08, 2023
How AI May Help Treat Metastatic Cancer

It’s difficult to cure cancer once it spreads. But AI-directed precise, individualized treatments may raise your odds. Here’s what you should know.

The big fear with any cancer is that it can spread. Malignant cells in one spot may metastasize to nearby normal lymph nodes, tissues, or organs and continue to other parts of your body.

Once the problem has traveled far from its origin, cancer is generally classified as stage IV (4), the hardest kind to fight.

Artificial intelligence (AI), however, may empower doctors to save the lives of people with a metastatic cancer. AI has already shown promise in detection, screening for risk, diagnosing the origin of cancer, and tailoring treatment.


YOU MIGHT ALSO LIKE: Our Cancer Care section


How AI could target metastasized cancer

Current treatments, which include surgery, radiation, hormone therapy, and chemotherapy, can stop or slow the growth of many types of cancer. But finding the right recipe is tough. A treatment that worked on malignant cells in the origin of the cancer may not work with cells in another part of your body after the cancer spreads.  

A treatment may work for only a while. Cancer doctors, called oncologists, are often forced to try one treatment after another.

One treatment may produce so many risky or unpleasant side effects that a patient chooses not to pursue it. But you can’t know precisely in advance how unpleasant or effective it will be.

No two patients are the same. As medicine advances, the hope is that it will become personalized, drawing upon an individual’s genetic makeup, history, and sensitivity to medication, as well as general rules from medical experience.

Doctors will always make choices based upon patterns they’ve seen in other patients. But the more details the better.

AI analyzes enormous databases to recognize and document patterns that scientists and doctors may not have previously seen. Feeding the process with more detailed information about an individual patient can help doctors fine-tune their approach.

For example, the field of radiomics uses AI to extract more useful details from medical images of tumors.

In one investigative project, scientists at five institutions across Europe are applying radiomics with 600 lung cancer patients. A separate group has used AI to create a model that predicts the prognosis of lung cancer patients with 75 percent accuracy, but it did not have radiomic information.

In patients with colon cancer, the malignancy spreads to their livers about half the time. Columbia University researchers used radiomics to analyze a set of images from nearly 670 colon cancer patients.

Half of them had received a cocktail of drugs that included one called cetuximab. The other half didn’t get the cetuximab. The project identified details in images of the colon that outperformed other known markers used for predicting response to treatment.

"Patients respond to chemotherapy differently from one another. Even a single patient's response to therapy can vary substantially over the course of treatment. In fact, many patients do not respond at all to the drug combination because the dosages, which can profoundly impact efficacy, are not suitable for them,” said Dean Ho, director of the Institute for Digital Medicine at the National University of Singapore (NUS).

NUS engineers have developed CURATE.AI, which compiles data about metastatic cancer patients, including chemotherapy types, dosages, and subsequent changes in the size of a tumor or levels of biomarkers in the blood.

The program creates a profile, or “map,” for each patient’s treatment, projecting expected responses. It also identifies specific drug doses that may require frequent changes to maximize results.

"No two patients' profiles are alike, and as a patient's body and the cancer itself evolve during treatment, the CURATE.AI profile evolves as well, enabling the clinical and engineering teams to optimize care for the entire duration of treatment, an unprecedented advance for combination therapy," Ho said.

Evidence AI may help treat metastatic cancer successfully

When researchers tested the CURATE.AI map on a man with advanced, stage IV, treatment-resistant prostate cancer, he received a novel drug combination that included an investigational drug, ZEN-3694, and enzalutamide, a widely used prostate cancer drug.

The researchers used the CURATE.AI patient treatment map to identify and raise and lower the optimal doses of each drug, a strategy known as dynamic dosing.

"Dynamic dosing in cancer therapy is not commonly used. In fact, drug dosing changes in oncology are typically performed only to reduce toxicity. CURATE.AI uniquely modifies drug dosing to increase efficacy,” Ho said.

It worked. The man’s metastatic cancer was halted, and he returned to his previously active life.

The study provides hope when a drug that worked before seems to fail, noted urologist and prostate cancer expert Allan Pantuck, MD, at University of California in LA, the lead clinician of the study. It may work again with dynamic dosing.  


YOU MIGHT ALSO LIKE: Blood Test Accurately Detects Over 50 Kinds of Cancer


November 08, 2023

Reviewed By:  

Janet O'Dell, RN