Wiring the pieces together for better care.
getty
Viz.ai is moving deeper into neurodegenerative disease through a partnership with Cortechs.ai that will bring quantitative brain MRI analysis into the clinical coordination workflows already used by hospitals.
The collaboration, announced July 9, will begin with multiple sclerosis, a disease impacting more than 1.8 million people worldwide, according to the WHO. Cortechs.ai’s NeuroQuant MS software measures and tracks lesion burden and brain volumes, while Viz.ai’s platform is intended to deliver those results directly to the clinicians coordinating a patient’s care.
That distinction matters. Healthcare AI has no shortage of algorithms capable of producing additional measurements. Its persistent weakness is turning those outputs into information that reaches the right clinician early enough to influence a decision.
“At the initial launch sites, an MS patient’s MRI is run through NeuroQuant MS, and the resulting lesion and volume data flows directly into the same care coordination platform the clinical team already uses instead of sitting in a separate report the neurologist has to go find,” Dr. Tim Showalter, chief medical officer at Viz.ai, tells me.
In MS, small changes can be difficult to evaluate consistently across serial scans. “MS is notoriously hard to monitor consistently,” says Showalter. “Lesion burden and brain volume changes that matter for treatment decisions can be subtle, and subjective visual reads make it difficult to reliably track disease activity over time. That means it is also difficult to get that information to the treating neurologist quickly.” New or enlarging lesions may indicate inflammatory disease activity, while loss of brain volume can provide another view of accumulated neurodegeneration. Quantitative analysis could make these changes more reproducible, but it does not replace clinical interpretation—or automatically prove that treatment should change.
“Quantitative analysis does not replace the radiologist’s read; it adds an objective, reproducible layer of decision support,” Showalter notes.
The partnership also reveals Viz.ai’s platform strategy. Rather than developing every disease-specific capability internally, the company can use its footprint of approximately 2,000 U.S. hospitals and health systems to bring external technologies into established clinical workflows. “We’re focused on being the platform that brings the best solutions together and delivers them where care actually happens,” Showalter says.
For specialized AI companies, this model could address a familiar commercialization problem. A technically strong point solution may still struggle with hospital integration, clinician adoption and distribution. Viz.ai provides access to workflow infrastructure; Cortechs.ai contributes a dedicated quantitative-imaging layer.
Kyle Frye, CEO of Cortechs.ai, describes the goal as making quantitative imaging “an active part of care delivery, not a static report that lives in the PACS.”
What outcome measures will Viz.ai and Cortechs.ai track after deployment? “We’ll be looking at outcomes such as earlier diagnosis, faster treatment initiation, more consistent longitudinal disease monitoring, and ultimately better clinical decision-making that can positively influence disease progression and patient care,” replies Frye.
Those endpoints will be crucial. Faster delivery of more precise imaging data is valuable only if it appropriately changes care, avoids unnecessary treatment escalation, and ultimately improves patient outcomes.
The longer-term ambition extends beyond MRI. “Imaging is the starting point, not the ceiling,” Showalter says, pointing to the potential future incorporation of other biomarkers as the evidence matures.
We are facing an era in which rapid implementation will drive guideline changes. As advanced data points become accessible in routine workflow, they will inevitably become part of routine patient care management.