Color Health uses OpenAI to develop a cancer screening copilot for physicians
Color Health, a genetic testing company, uses OpenAI’s latest, lower-cost, large language model to equip physicians with pretreatment expertise, accelerating cancer screening diagnostic prior authorization requests and getting patients into treatment faster.
The company is also working with the University of California San Francisco to investigate how the cancer copilot tool performs in unearthing early warning signs, seemingly incongruous warning signs and other relevant details that may be deeply dispersed in electronic health records and other patient information .
WHY IT MATTERS
While the decision factors vary for different types of cancer, a trial of the technology helped providers analyze patient records in five minutes, the company said.
“Primary care physicians don’t tend to have the time or sometimes even the expertise to adjust people’s screening guidelines,” said Othman Laraki, co-founder and CEO of Color Health, in a Wall Street Journal report Monday.
The UCSF Helen Diller Family Comprehensive Cancer Center is testing Color’s copilot for pre-cancer diagnostic studies by comparing it to retrospective analyzes of cancer patient charts.
While that research is still in its early stages, according to a Color spokesperson, it will be a win for patient care if AI can ultimately reduce wait times for cancer treatment by connecting the dots.
In color announcement On Monday, Laraki said the company designed the tool to address the supply gap in oncology expertise to decide on pre-treatment for a patient with a confirmed malignancy.
The goal is to offer primary care physicians and other physicians an AI service that can determine what tests are needed to inform the patient’s cancer treatment, without waiting for the patient to visit an oncologist before ordering pretreatment diagnostics and completing the process prior consent is initiated. he explained.
“That way, by the time the patient meets her oncologist for the first time, the patient has a much better chance of being ready to start treatment and, we hope, saving weeks of valuable time.”
Laraki also emphasized the role of the physician in decision-making when using the tool.
“One of the key design decisions behind our work is that the tools were built from the ground up to be based on a human-in-the-loop model,” he said.
The company said it will first share the results of the first tested use case – which focuses on automating the analysis of a person’s background risk factors and then applying the guidelines that customize their screening plan – with individuals in its cancer program and will subsequently provide primary care. doctors the opportunity to assess the information.
Color estimates that physicians using the cancer copilot will have supported more than 200,000 patient cases in generating personalized AI care plans by the end of the year.
THE BIG TREND
Before focusing on tools to help physicians improve outcomes for cancer patients, Color launched its model of patient-initiated proactive testing in 2015. The tests focused on genes known to increase an individual’s cancer risk, such as BRCA1 and BRCA2 for breast, ovarian and pancreatic cancer. .
Within a few years the unicornalong with 23andMe and other companies, shattered patient barriers to cancer screening that were previously not possible by offering low-cost, over-the-counter home testing kits that could highlight important genetic risk factors.
Using AI for a new decision support service that enables PCPs to get their cancer patients into treatment faster is a burgeoning area in healthcare AI, where automating physician note-taking and reducing clinical administrative burden the majority of mainstream LLM use cases have been.
However, applying machine learning to health data offers a great opportunity to improve health outcomes for individuals and populations.
AI could play an important role in disease management, says Xin Wang, assistant professor at the University at Albany’s department of epidemiology and biostatistics.
“By analyzing patient data over time, AI algorithms can predict individual patient risks, suggest personalized treatment plans and even alert healthcare providers to early signs of complications,” he shared. Healthcare IT news in January.
“This proactive approach can lead to earlier interventions, better disease management and ultimately better health outcomes.”
ON THE RECORD
“We see a perfect match for AI technology, for language models,” said Brad Lightcap, Chief Operating Officer of OpenAI, in the WJ story. “They can give physicians more tools to understand medical records, to understand data, to understand labs and diagnostics.”
Andrea Fox is editor-in-chief of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.
The HIMSS AI in Healthcare Forum will take place September 5-6 in Boston. More information and registration.