Diagnostic tests are starting to spot diseases far earlier with the help of artificial intelligence.

Why it matters: Many of today's diagnostics are limited by whether there is a known biological marker for a disease or a clinician knows precisely what to look for.

• But the ability of AI to use a vast array of data is helping researchers discover entirely novel ways to detect disease.
• In some cases, that might even be a disease that may not have turned out to harm someone.

Driving the news: On Tuesday, researchers from Peking University in Beijing reported finding that temperature patterns of the face — detected using thermal cameras and AI — are associated with various chronic illnesses, such as diabetes and high blood pressure.

• Last week, researchers at the University of British Columbia announced they pinpointed a distinct subtype of endometrial cancer that put patients at much greater risk of death but "would otherwise go unrecognized by traditional pathology and molecular diagnostic tests."
• In a study last month, researchers reported they could identify patients with Parkinson's disease far earlier — up to seven years before symptoms appear — using a blood test paired with AI.

The big picture: Advances in algorithms combined with greater availability of large datasets and improved access to cloud computing are supercharging diagnostics.

• "It's math, not magic," Mayo Clinic Platform president John Halamka told Axios.

Between the lines: A key benefit of using AI in diagnostics is its incidental findings.

• In an abdominal CT scan, a ton of data is gathered with a single test, but typically the radiologist zeroes in on what the physician ordered the test for, Elliott Green, CEO of AI database startup Dandelion Health, told Axios.
• But AI might also flag early markers for metabolic dysfunction-associated steatotic liver disease, often referred to as fatty liver disease, Green said.
• "AI goes where the evidence is, not where we think the evidence should be," Green said.

Yes, but: Data out is only as good as the data in. That means addressing issues around data transparency and the representation of diverse patients in datasets are critical for developing accurate, less biased, algorithms.

• While AI may reduce false positives, it also runs the risk of increasing the problem of overdiagnosis of disease that may never have turned into a problem.

The bottom line: Over time, patients should expect to see much more of this in their doctor's offices — and may even get information they weren't looking for — as they undergo even the most routine testing.

Share this

The FDA granted approval to Eli Lilly's Alzheimer's drug, which was found to slow progression of the disease by about one-third in patients with less advanced disease, the company announced Tuesday.

Why it matters: The approval of donanemab, which will be sold under the brand name Kisunla, makes the antibody the second drug of its kind to win FDA approval.

• The drug, which is infused once a month, was approved to treat mild cognitive impairment.

The big picture: Kisunla targets proteins in the brain known as amyloid plaques that are believed to contribute to the development of Alzheimer's disease, which afflicts nearly 7 million Americans.

• It will compete with Eisai and Biogen's Leqembi, which the FDA approved last year.

Catch up quick: In June, a key FDA advisory committee unanimously concluded that the drug donanemab benefits patients with early stages of the disease and that its benefits outweigh its risks.

• The drug faced some uncertainty earlier this year after some patients enrolled in a clinical trial experienced brain swelling, bleeding and other adverse events, prompting the FDA in March to call for an outside review of donanemab.

Go deeper: Where the future of Alzheimer's drugs is heading

Yesterday, we told you about the short supply of geriatricians. But experts warn that not enough new doctors are going into pediatrics, either.

Why it matters: Without enough pediatricians, kids may miss out on necessary health care that is key to improving overall health and ultimately lowering health costs.

• "Our children are the future, but we sure don't act like it when it comes to health care," Aaron Carroll, a pediatrician and president of health services research group AcademyHealth, wrote in a New York Times op-ed published Monday.

By the numbers: Although 99% of pediatric residency spots offered this year eventually filled up, 252 positions went unfilled during the initial matching process, according to the National Residency Matching Program.

• That's up from 88 unfilled spots during the 2023 matching process.

Between the lines: Increasing the number of doctors going into pediatrics could "prevent astronomical healthcare costs down the road," Alexandra Schumm, vice president of research at consulting group Chartis, wrote in April.

The Medicare Advantage market generated the largest average gross margins per enrollee for health insurers last year, according to a new analysis from KFF.

Zoom in: MA insurers' margins were virtually the same in 2023 as they were the previous year, despite reports that private Medicare insurers saw higher-than-expected utilization last year.

• Gross margins measure the amount of premium income an insurer takes in per enrollee, subtracted by the cost of their health care.

Reality check: High gross margins don't necessarily mean high profits, KFF notes.

• The figure doesn't account for administrative expenses or tax liabilities for insurers operating in these insurance markets.

🏛 The Supreme Court agreed to decide whether the FDA can refuse to approve flavored vapes. (USA Today)

💉 Moderna gets $176 million from the federal government to make a bird flu vaccine. (Axios)

💰 Federal officials want to protect providers from fraudulent catheter billings. (Washington Post)

🚨 Health officials in the Florida Keys issue a dengue fever alert. (NBC News)