New MMRF-Supported Tool Helps Predict Smoldering Multiple Myeloma Patients’ Risk of Developing Myeloma

When it comes to smoldering multiple myeloma (SMM), an asymptomatic precursor condition to active myeloma, one of the biggest decisions doctors and patients face is whether to undergo careful monitoring or begin treatment. To determine how likely it is that a case of SMM will progress to myeloma, doctors assess a patient’s risk status when they’re diagnosed.

Existing tools, like the widely used Mayo Clinic 20/2/20 Model and the IMWG Risk Stratification Model, can predict many cases of high-risk SMM that will progress to active myeloma within two years. But unfortunately, these tools can miss some patients whose SMM evolves to become high-risk or overestimate other patients’ risk.

This is why the Multiple Myeloma Research Foundation (MMRF) has long supported research to improve the field’s understanding and definition of high-risk SMM and to develop tools to better assess risk.

With MMRF funding, a team of investigators at Dana-Farber Cancer Institute co-led by Irene Ghobrial, MD have developed a new SMM risk prediction model called PANGEA-SMM. In a recent study of 2,344 patients with SMM published in Nature Medicine, investigators showed that PANGEA-SMM outperformed existing models.

Leveraging machine learning and mathematical models, PANGEA-SMM tracks changes in several biomarkers that are already part of routine SMM monitoring—M-protein levels, light chains, kidney function markers, and blood counts—and doesn’t require a recent bone marrow biopsy. This allows a patient’s risk to be assessed more regularly, potentially making it more predictive than other models.

PANGEA-SMM is the result of a $2 million, multi-year collaboration with Dr. Ghobrial’s lab to study SMM and optimize treatment for the condition.

“The MMRF has been an important collaborator over many years,” Dr. Ghobrial said. “The Foundation’s support was instrumental in advancing this work.”

Clinicians can immediately use the free PANGEA-SMM tool online alongside other risk stratification models, and as they enter data into it, the model will learn and improve. Dr. Ghobrial said she hoped that this tool would help patients have informed conversations with their doctors.

“This tool can open up a discussion between patients and their doctors about their personal risk and their options for therapy and clinical trials,” she said.

The MMRF has invested in other efforts to help high-risk SMM patients as well. With an MMRF Myeloma Accelerator Challenge grant, for example, Sagar Lonial, MD of Emory University’s Winship Cancer Institute is bringing together several leading institutions to generate and analyze new SMM patient data—including, uniquely, data about the immune system and function—and develop a better definition of high-risk SMM. By better defining which patients are high risk, investigators will uncover which patients will benefit most from early intervention, which interventions are most effective, and which patients can safely watch and wait.

“SMM patients live with a lot of uncertainty, and they urgently need better risk stratification,” said Hearn Jay Cho, MD, PhD the MMRF’s chief medical officer. “The MMRF supports innovative research, including PANGEA-SMM’s machine learning approach, to achieve better outcomes for SMM patients and to help them feel more confident in their treatment and monitoring plans.”