Approximately 2.3 million women worldwide had a new diagnosis of breast cancer in 2022, and the disease claimed about 670,000 lives.
As of right now, breast cancer has no known treatment. Treatment options for breast cancer may include hormone therapy, chemotherapy, radiation, specially-targeted drugs, and surgery, depending on the kind of cancer.
Furthermore, the likelihood of recurrence and metastasis—the transfer of the cancer to another area of the body—varies depending on the kind and stage of breast cancer.
Calvin Chao, MD, vice president of medical research at the digital health business Artera, told Medical News Today that “breast cancer is a complex disease with various treatment choices, including chemotherapy and different types and durations of hormone therapy.”
“In order to prevent both undertreatment and overtreatment, patients and doctors must determine which treatments will be most beneficial and comprehend their risks for recurrence.”
The ArteraAI Breast digital pathology-based risk assessment tool for patients with early-stage, hormone receptor-positive (HR+), HER2-negative invasive breast cancer has been approved by the U.S. Food and Drug Administration (FDA).
What is the function of ArteraAI?
The goal of ArteraAI Breast is to assist medical professionals in determining the degree of treatment for patients with early-stage HR+/HER2-breast cancer by predicting the chance of metastasis.
“ArteraAI Breast feeds the digital photos and some clinical characteristics into an AI model by scanning a patient’s pathology slides of the surgical resection tissue,” Chao clarified.
“To predict the probability of metastasis, or cancer recurrence, the multimodal AI (MMAI) model was trained on data from over 8,500 breast cancer patients from clinical trials.”
“This AI model can accurately forecast the probability of metastasis and sort patients into MMAI Low or MMAI High risk groups based on their AI risk score, as demonstrated in the FDA clinical validation,” he continued.
When oncologists are deciding how best to treat patients with breast cancer, ArteraAI Breast helps.
According to Chao, “oncologists routinely need to assess the best level of therapy intensification for their patients.”
“Patients with a lower risk profile do not require the same level of treatment intensity as patients with a higher risk profile since they have a significantly reduced possibility of cancer recurrence.”
“Oncologists and patients may make the best treatment decisions with the support of the ArteraAI Breast results, which include the individualized AI risk score and the corresponding MMAI risk groups.”
Possibly less expensive and time-consuming than the tests that are now offered
Richard Reitherman, MD, PhD, a board-certified radiologist and medical director of breast imaging at MemorialCare Breast Center at Orange Coast Medical Center in Fountain Valley, CA, was available to discuss this study with MNT.
According to Reitherman, a test known as Oncotype DX has been available to physicians since the early 2000s to help them assess a patient’s risk of systemic metastasis and if chemotherapy should be added to endocrine therapy.
He explained, “The Oncotype DX uses a patented methodology to analyze the histopathologic (the features of the tumor as represented on the slides) and provides what is called a recurrent score that separates women into a low, moderate, and high risk of systemic disease in the future and, therefore, consideration of adding chemotherapy to reduce this risk.”
“This test can be very essential, but it is rather expensive, not always available, and may take several weeks to process. Testing following surgery is typically covered by insurance, but not prior to it. Chemotherapy may be considered in some clinical circumstances before surgery, although the Oncotype recurrence score is not available.
“The potential breakthrough in the multi-modal artificial intelligence (MMAI) model for predicting distant metastasis in hormone positive (HR+) early-stage breast cancer is that it assigns patients into low and high risk metastasis groups using immediately available clinical and existing histopathologic features without the costs and time delays associated with currently available methodology,” Reitherman continued.
Possibility of protecting women from the harmful effects of chemotherapy
Additionally, MNT discussed this study with Donna McNamara, MD, a breast medical oncologist at the John Theurer Cancer Center at Hackensack University Medical Center in New Jersey. McNamara stated that she thought it was an amazing milestone using AI and digital pathology, marking a significant advancement in personalizing breast cancer therapy, especially for patients with HR+ early-stage disease.
According to McNamara, “it is vitally crucial to be able to better stratify patients who will benefit from chemotherapy vs those who can safely avoid it.”
Many patients, particularly postmenopausal women with node-negative tumors, are in a “gray region” where it is not always obvious whether chemotherapy is advised. In some circumstances, this technology might offer much-needed clarification.
“A big advantage is the ability to protect low-risk individuals from the considerable toxicities of chemotherapy,”
Neuropathy, an elevated risk of infection, and affects on fertility are just a few of the crippling short-term and long-term side effects of chemotherapy. We can spare patients needless financial, emotional, and physical hardships if we can safely identify those who will not gain much from this treatment.
McNamara stated that in order to begin using ArteraAI Breast with her patients, she would need a plethora of solid, peer-reviewed evidence, beginning with data from prospective, head-to-head clinical trials that directly assess its efficacy against established gold standards such as Oncotype DX.
She explained, “This data must include long-term follow-up showing that utilizing ArteraAI to guide medication leads to at least similar, if not superior, patient outcomes in terms of disease-free and overall survival across varied populations.”
“I would require precise answers on its practical implementation, including real-world turnaround times, cost, and insurance coverage, as well as how it integrates into our current workflow, beyond this crucial clinical validation.”
Additionally, McNamara stated, “I would need a degree of transparency into the AI model itself, moving beyond the “black box” to understand the key features driving its risk assessments, as I cannot base a patient’s treatment plan on a tool without thoroughly understanding its accuracy, reliability, and practical utility.”