Pfizer, Merck and J&J to publish data on cancer drugs

Do you think a friend or colleague should receive this newsletter? Share this link with them to register.

Good afternoon! I'm Annika and I'll be attending the American Society of Clinical Oncology annual meeting in Chicago in the coming days.

So will thousands of cancer researchers and doctors, who hope to see new science and encouraging data that could advance cancer treatments, health equity and patient care.

More than 5,000 research abstracts will be presented or published at ASCO, which begins Friday and runs through Tuesday. There will be data on existing drugs from pharmaceutical companies, experimental treatments in early and mid-stage trials from biotech companies, and even artificial intelligence tools.

I will focus on some of the biggest names in the industry. This is some of the data I'm seeing:

• merck and modern will present three years of data from a phase two study of its experimental vaccine, used in combination with the Keytruda therapy, in patients with severe versions of the deadliest form of skin cancer.
• PfizerAntibody-drug conjugates, or ADCs: The company will present data on some drugs acquired through its $43 billion purchase of Seagen last year. That includes an experimental ADC called sigvotatug vedotin in a type of lung cancer and another already approved treatment, Adcetris, for a common type of blood cancer.
• Johnson and Johnson will present mid- and late-stage data on a more desirable form of its targeted antibody drug, Rybrevant, in patients with a type of lung cancer.
• J&J has also published early-stage data on a radiopharmaceutical drug, which showed signs of effectiveness in patients with prostate cancer. But four trial participants died.
• Merck and its partner Kelun-Biotech have published positive data from the phase three trial of an antibody-drug conjugate in a type of breast cancer.

I plan to write up some facts, along with a recap or two after the conference, so stay tuned for my coverage. If you see me at ASCO this weekend, don't hesitate to say hello!

Feel free to send any tips, suggestions, story ideas, and facts to Annika at [email protected].

Software provider Epic Systems is trying to make it easier for health systems to cut through the AI ​​noise.

Last week, the company launched a new free toolset called AI Trust and Assurance Suite, which health systems can use to evaluate the performance of an artificial intelligence model that integrates with an electronic health record, or EHR.

An EHR is an electronic version of a patient's medical record. Epic is perhaps the best-known provider in this sector, hosting medical records for more than 300 million people.

Epic released the suite as an open source tool on the popular developer platform GitHub. That means it is available for anyone in the world to use. The suite can help health systems evaluate an AI model's fairness, equity and performance, as well as how it impacts outcomes for patients, said Corey Miller, vice president of research and development at Epic.

For example, a health system could use the suite to test several different models to determine which works best for that community's local patient population. The toolkit can also conduct an “equity audit,” which can look for biases between race, sex and age within a group of patients, Miller said.

The suite is designed specifically to evaluate AI in healthcare, and Miller said it will work regardless of whether a health system is using Epic's EHR. The tools are not designed specifically for Epic's AI models, she added.

“We saw this as an opportunity to create something that didn't exist today,” Miller told CNBC in an interview.

The launch of Epic's suite comes at a time when the healthcare industry has been looking at how to establish guardrails and best practices around AI. Several organizations such as the Coalition for AI in Health, the Microsoft Trustworthy and Responsible AI Network, and the AI ​​for Health Association have been created with these goals in mind, but there are no hard and fast rules for how to use the technology.

Meanwhile, Miller said he believes Epic's suite will make it easier for health systems to see how an AI model works with their local populations, particularly within rural community hospitals that might not have data scientists on staff.

He said the suite has been under construction since late last year. It evaluates models based on existing standards developed by “healthcare systems, health IT software developers, external experts, and the government,” according to the GitHub post. 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 be next.

“We hope to make this tool something that can really look at the entire spectrum of AI,” Miller said.

Please feel free to send any tips, suggestions, story ideas, or information to Ashley at [email protected].

Reimbursement is something that AI programs cannot yet generate

When I had my mammogram earlier this month, I was surprised that I had to pay cash for an AI-enhanced reading of my scan. I opted to pay, but wondered why my insurance company wouldn't cover it.

It turns out that most of the new FDA-approved AI diagnostic and radiology programs coming to market have not yet obtained billing codes for insurance reimbursement. Early forays into computer-assisted mammography in the late 1990s proved to be no more effective than conventional screening tests.

This time, medical societies along with government and private insurance plans are taking a more cautious approach to approving payment for new technology.

Please feel free to send any tips, suggestions, story ideas or information to Bertha at [email protected].