Color Health, a genetic testing company, is utilizing OpenAI’s latest, more affordable, large language model to provide doctors with expertise in pretreatment workup that could expedite prior authorization requests for cancer screening diagnostics and expedite patient treatment.

The company has partnered with the University of California San Francisco to research how the cancer copilot tool performs in identifying early warning signs, seemingly conflicting red flags, and other relevant details scattered throughout electronic health records and other patient information.


Although decision-making factors for different types of cancers vary, a trial of the technology enabled providers to analyze patient records in just five minutes, as reported by the company.

“Primary care physicians often lack the time or expertise to adjust individuals’ screening guidelines for risk,” stated Othman Laraki, co-founder and CEO of Color Health, in a Wall Street Journal report on Monday.

The UCSF Helen Diller Family Comprehensive Cancer Center is evaluating Color’s copilot for cancer pretreatment diagnostic work-ups by comparing it to retrospective analyses of cancer patient charts.

Although the study is still in its early stages, if AI can ultimately reduce wait times for cancer treatment by connecting relevant information, it would greatly benefit patient care.

In Color’s announcement on Monday, Laraki explained that the tool was designed to address the lack of oncology expertise in deciding on pretreatment workup for patients with confirmed malignancies.

The objective is to provide primary care physicians and other clinicians with an AI service that can determine necessary tests for informing the patient’s cancer treatment without waiting for the patient to see an oncologist first, streamlining pretreatment diagnostics and prior authorization processes.

“This way, by the time the patient meets with their oncologist, they are more prepared to begin treatment and, hopefully, save valuable time,” Laraki emphasized.

Laraki also highlighted the importance of clinician involvement in decision-making when using the tool.

“One of the key design decisions behind our work is that the tools were developed from the ground up to involve a human-in-the-loop model,” he stated.

The company plans to share the results of the initial use case, which focuses on automating the analysis of a person’s background risk factors and adjusting their screening plan based on guidelines, with individuals in its cancer program first, followed by primary care physicians for review.

Color estimates that by the end of the year, physicians using the cancer copilot will have assisted over 200,000 patient cases in creating personalized AI care plans.


Prior to focusing on tools to improve cancer patient outcomes, Color introduced its model of patient-initiated proactive testing in 2015, concentrating on genes associated with increased cancer risk like BRCA1 and BRCA2 for breast, ovarian cancer, and pancreatic cancer.

Within a few years, the unicorn company, alongside 23andMe and others, broke down barriers to cancer screening for patients by offering affordable, at-home test kits that could reveal key genetic risk factors.

Utilizing AI for a new decision support service empowering primary care providers to expedite cancer treatment for their patients is an emerging area in healthcare AI, where automation of physician documentation and reduction of clinical administrative burdens have been predominant use cases for large language models.

However, applying machine learning to health data represents a significant opportunity to enhance health outcomes for individuals and populations.

According to Xin Wang, assistant professor at the University at Albany department of epidemiology and biostatistics, AI can play a critical role in disease management.

“By analyzing patient data over time, AI algorithms can predict individual patient risks, suggest personalized treatment plans, and alert healthcare providers to early signs of complications,” he told Healthcare IT News in January.

“This proactive approach can lead to earlier interventions, improved disease management, and ultimately, better health outcomes.”


“We see AI technology, particularly language models, as a perfect fit for clinicians, providing them with more tools to interpret medical records, data, labs, and diagnostics,” stated Brad Lightcap, Chief Operating Officer of OpenAI, in the WSJ story.

Andrea Fox is the senior editor of Healthcare IT News.
Healthcare IT News is a HIMSS Media publication.


The HIMSS AI in Healthcare Forum is set to be held on September 5-6 in Boston. Learn more and register.



Please enter your comment!
Please enter your name here