Pfizer, Merck, J&J to release cancer drug data

Think a friend or colleague needs to be getting this text? Share this link with them to enroll.

Good afternoon! That is Annika, and I will be on the bottom on the American Society of Clinical Oncology annual meeting in Chicago in the approaching days. 

So will hundreds of cancer researchers and clinicians, who expect to see encouraging latest science and data that would advance cancer treatments, health equity and patient care. 

Greater than 5,000 research abstracts will probably be presented or published at ASCO, which starts on Friday and lasts until Tuesday. There will probably be data on existing drugs from pharmaceutical corporations, experimental treatments in early to mid-stage testing from biotech corporations and even AI tools. 

I will be specializing in a few of the larger names within the industry. Here’s a few of the data I’m taking a look at:

• Merck and Moderna will present three-year data from a phase two study on their experimental vaccine, used together with the therapy Keytruda, in patients with severe versions of probably the most deadly type of skin cancer.
• Pfizer‘s antibody-drug conjugates, or ADCs: The corporate will present data on some medications acquired through its $43 billion buyout of Seagen last 12 months. That features an experimental ADC called sigvotatug vedotin in a form of lung cancer, and one other already approved treatment, Adcetris, for a typical form of blood cancer.
• Johnson & Johnson will present mid-stage and late-stage data on a more convenient type of its targeted antibody drug, Rybrevant, in patients with a form of lung cancer.
• J&J has also released early-stage data on a radiopharmaceutical drug, which showed signs of efficacy in prostate cancer patients. But 4 trial participants died.
• Merck and its partner Kelun-Biotech have released positive phase three trial data on an antibody-drug conjugate in a form of breast cancer. 

I plan on writing up some data, together with a wrap-up or two after the conference, so stay tuned for my coverage. In the event you see me at ASCO this weekend, don’t hesitate to say hello! 

Be at liberty to send any suggestions, suggestions, story ideas and data to Annika at annikakim.constantino@nbcuni.com.

Software vendor Epic Systems is attempting to make it easier for health systems to chop through the bogus intelligence noise. 

The corporate last week released a free latest tool set called the AI Trust and Assurance Suite, which health systems can use to judge the performance of an AI model that integrates with an electronic health record, or EHR.

An EHR is an electronic version of a patient’s medical history. Epic is maybe one of the best known vendor within the space, because it houses medical records for greater than 300 million people. 

Epic released the suite as an open-source tool on the favored developer platform GitHub. Meaning it’s available for anyone on the earth to make use of. The suite will help health systems assess an AI model’s equity, fairness and performance, in addition to the way it is affecting outcomes for patients, said Corey Miller, vice chairman of research and development at Epic.

As an illustration, a health system could use the suite to check several different models and determine which one works best for that community’s local patient population. The tool set may perform a “fairness audit,” which may search for bias across race, sex and age inside a bunch of patients, Miller said. 

The suite is specifically designed to judge health-care AI, and Miller said it would work no matter whether a health system is using Epic’s EHR. The tools should not specifically built for Epic’s AI models, he added.

“We saw this as a possibility to create something that wasn’t on the market today,” Miller told CNBC in an interview. 

The discharge of Epic’s suite comes because the health-care sector has been reckoning with the way to establish guard rails and best practices around AI. Several organizations just like the Coalition for Health AI, Microsoft’s Trustworthy & Responsible AI Network and the Health AI Partnership have been created with these objectives in mind, but there are not any hard and fast rules about the way to use the technology.

Within the interim, Miller said he thinks Epic’s suite will make it easier for health systems to have a look at how an AI model performs with their local populations, particularly inside rural community hospitals which may not have data scientists on staff.

He said the suite has been within the works since late last 12 months. It evaluates models based on existing standards developed by “healthcare systems, health IT software developers, third-party experts, and the federal government,” in response to the post on GitHub. Epic plans to update the tool as best practices evolve, Miller said. 

Epic’s suite currently works with binary classification models, or typical predictive models, and Miller said generative AI models will probably be up next.  

“We expect to make this tool something that may really have a look at that whole spectrum of AI,” Miller said.  

Be at liberty to send any suggestions, suggestions, story ideas and data to Ashley at ashley.capoot@nbcuni.com.