Care models for prostate cancer desperately need personalization, declared Shyam Natarajan, co-founder and CEO of Avenda Health.
To address this issue, his Culver City, California-based company built an AI-powered cancer management platform centered on personalization. On Wednesday, it earned 510(k) clearance from the FDA.
With the Rise of AI, What IP Disputes in Healthcare Are Likely to Emerge?
Munck Wilson Mandala Partner Greg Howison shared his perspective on some of the legal ramifications around AI, IP, connected devices and the data they generate, in response to emailed questions.
The cloud-based platform, named iQuest, uses a patient’s own diagnostic data to define the extent of the disease and create a cancer probability map with optimal treatment margins.
Existing AI products for prostate cancer are primarily used to aid diagnosis, usually via digital radiology or digital pathology, Natarajan pointed out. But iQuest is aimed at urologists for use after a patient has already gotten diagnosed to help them decide how to best treat the disease based on each specific patient’s tumor.
Once a patient receives an MRI and biopsy, their data is uploaded into iQuest. A physician then confirms the uploaded information, and the platform creates a 3D cancer estimation map that shows the patient’s extent of tumor within the prostate, Natarajan explained.
“That map and 3D information is now actionable and can aid physicians in making treatment decisions. If they are planning a targeted therapy, they can also use iQuest to generate a virtual treatment plan,” he said.
A Personalized Approach to Medication Nonadherence
At the Abarca Forward conference earlier this year, George Van Antwerp, managing director at Deloitte, discussed how social determinants of health and a personalized member experience can improve medication adherence and health outcomes.
Currently, the standard of care for prostate cancer uses a one-size-fits-all approach. The healthcare system treats the cancer like a whole-gland disease, even though prostate cancer is incredibly localized, Natarajan pointed out.
Prostate cancer’s current standard of care includes surgery and radiation, and in some cases, urologists simply monitor the disease via annual biopsies to ensure it doesn’t spread aggressively. But those treatments harm bodily structures that are critical to sexual and urinary function, and some require additional therapy within five years, Natarajan said.
“iQuest aids the urologist in determining the best course of action for the patient by showing them the likely extent of disease and margin for targeted therapy, which is not possible with the standard of care,” he said.
Avenda validated its algorithms in two main ways, Natarajan explained. The first was by comparing iQuest’s cancer estimation maps to surgical pathology slides of prostates removed after surgery. The company also had physicians review cases using both the standard of care (imaging, pathology and clinical reports) as well as iQuest for the same patient and compared their assessments.
The platform’s algorithms were trained on hundreds of thousands of diagnostic patient data points, including MRI data, pathology data and other clinical information.
“In order to minimize bias, algorithms are validated by using held-out datasets from wholly separate institutions from the training dataset,” Natarajan said.
Avenda was founded in 2017 as a UCLA spinout. In August, it closed a $10 million Series B financing round, bringing its total funding to date to more than $19 million.
Photo: Public domain image by the National Cancer Institute
