September 28, 2026

This week: What if a scan taken before cancer treatment could help flag a serious side effect before it happens? MD Anderson researchers found a possible warning in routine lung CT scans. We also look at an AI prediction for brain tumor recurrence, a newborn infection standard screening may miss, and a striking finding about glucose monitors.

Here’s what changed, in plain English.

^{Summaries are for education, not medical advice. Always verify locally before clinical use}.

👇 Later in this issue: A newborn can pass a hearing test and still have an infection that affects hearing later. Here’s what a large screening study found.

New here? Join 1,500+ readers getting one carefully sourced AI-healthcare briefing every Monday—written in plain English, without the hype.

🤎 Sponsored

“If I were a farmer, I would absolutely use AI.” 

That’s Jensen Huang, founder and CEO of NVIDIA. 

And he's pointing to one of AI’s biggest untapped opportunities: Farming. It’s an industry facing mounting pressure to produce more with less and it’s still massively under-automated. 

DIT AgTech brings AI, nutrition automation, and real-time data to livestock production, helping ranchers boost productivity and get more from every animal. 

And it’s already proven in one of the world's toughest livestock environments: 

Now expanding into the U.S. and Brazil, DIT AgTech is targeting a 300M+ head cattle market. And the biggest barrier to adoption? Gone. Ranchers get the technology for free when they sign up for a three-year nutrition plan. 

DIT AgTech can scale adoption faster, which means more data and more recurring revenue. 

Invest before this early-stage opportunity gets harder to access.

Invest in DIT AgTech Today

^{𝘐𝘯 𝘮𝘢𝘬𝘪𝘯𝘨 𝘢𝘯 𝘪𝘯𝘷𝘦𝘴𝘵𝘮𝘦𝘯𝘵 𝘥𝘦𝘤𝘪𝘴𝘪𝘰𝘯, 𝘪𝘯𝘷𝘦𝘴𝘵𝘰𝘳𝘴 𝘮𝘶𝘴𝘵 𝘳𝘦𝘭𝘺 𝘰𝘯 𝘵𝘩𝘦𝘪𝘳 𝘰𝘸𝘯 𝘦𝘹𝘢𝘮𝘪𝘯𝘢𝘵𝘪𝘰𝘯 𝘰𝘧 𝘵𝘩𝘦 𝘪𝘴𝘴𝘶𝘦𝘳 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘵𝘦𝘳𝘮𝘴 𝘰𝘧 𝘵𝘩𝘦 𝘰𝘧𝘧𝘦𝘳𝘪𝘯𝘨, 𝘪𝘯𝘤𝘭𝘶𝘥𝘪𝘯𝘨 𝘵𝘩𝘦 𝘮𝘦𝘳𝘪𝘵𝘴 𝘢𝘯𝘥 𝘳𝘪𝘴𝘬𝘴 𝘪𝘯𝘷𝘰𝘭𝘷𝘦𝘥. 𝘋𝘐𝘛 𝘈𝘨𝘛𝘦𝘤𝘩 𝘩𝘢𝘴 𝘧𝘪𝘭𝘦𝘥 𝘢 𝘍𝘰𝘳𝘮 𝘊 𝘸𝘪𝘵𝘩 𝘵𝘩𝘦 𝘚𝘦𝘤𝘶𝘳𝘪𝘵𝘪𝘦𝘴 𝘢𝘯𝘥 𝘌𝘹𝘤𝘩𝘢𝘯𝘨𝘦 𝘊𝘰𝘮𝘮𝘪𝘴𝘴𝘪𝘰𝘯 𝘪𝘯 𝘤𝘰𝘯𝘯𝘦𝘤𝘵𝘪𝘰𝘯 𝘸𝘪𝘵𝘩 𝘪𝘵𝘴 𝘰𝘧𝘧𝘦𝘳𝘪𝘯𝘨, 𝘢 𝘤𝘰𝘱𝘺 𝘰𝘧 𝘸𝘩𝘪𝘤𝘩 𝘮𝘢𝘺 𝘣𝘦 𝘰𝘣𝘵𝘢𝘪𝘯𝘦𝘥 𝘩𝘦𝘳𝘦: https://bit.ly/4bzuWCi​  ​}

⚡ Quick Hits

A system called FastGlioma showed promise in predicting glioblastoma recurrence from tumor tissue. Researchers developed it using data from 60 patients and tested it with 20 more.

The honest part: The test group was small, and the study has not shown that acting on the prediction helps patients live longer or receive better care.

👉 Explore the study →

In a study involving 857 parents, Washington State University researchers tested AI responses to HPV vaccine misinformation in a simulated social media setting. The most effective tone varied with how humanlike participants believed the AI to be.

Why it matters: Getting a medical fact right may not be enough; how a correction is delivered can affect whether people accept it. The result comes from a simulated setting, so real-world effects still need testing.

👉 See what the researchers found →

Know someone in healthcare, medicine, or AI? Forward this to them. They can subscribe free here →

🌍 Beyond AI

Researchers screened 48,556 newborns for congenital cytomegalovirus (CMV), an infection that can affect hearing or development later. They found 176 infected babies; 100 would not have qualified for the usual targeted screening, often because they appeared healthy at birth.

Why it matters: A baby can pass an initial hearing test and still need follow-up. The study shows how broader screening might find families who otherwise would not know.

The honest part: The research came from two hospitals in Jerusalem. It did not establish whether universal screening is cost-effective everywhere.

👉Read the newborn screening study →

🤎 Sponsored

Grocery store pods spend months going factory → warehouse → truck → shelf, losing the flavor oils that make coffee taste like coffee. Angelino's roasts, packs, and ships within days — 50+ flavors, compatible with Keurig®, from 39¢ a cup. New customers save 15%, no code needed.

Try Fresh-Roasted Pods

🧠 Brain in Brief

In a study of 197 people receiving lecanemab, researchers identified changes in 34 blood proteins during treatment. Those shifts could offer clues about how the drug affects the body beyond its intended target.

The honest part: This was a single-clinic study. The protein changes are research findings, not a validated way to tell whether an individual patient is benefiting.

👉 Read the research →

You don’t need an AI team to build an AI agent. With Skydive, the person who knows the work can create the agent to do it.

Start an agent off with a role, teach them how your team operates, connect your tools, and put them to work.

Make your first agent

🌿 Worth Knowing

Among people with type 2 diabetes taking basal insulin, researchers compared 13,935 people who started continuous glucose monitoring with the same number of matched nonusers. After one year, 1.16% of monitor users had died, versus 2.09% of nonusers.

Why it matters: The difference is large enough to warrant closer study of how glucose monitors might affect longer-term health, beyond day-to-day blood sugar control.

The honest part: This is preliminary observational research being presented at a conference. Even after matching patients on 29 characteristics, it cannot prove that the monitors caused the lower death rate.

👉Examine the findings →

This week’s takeaway: Earlier warnings are promising. The next test is whether finding them changes what happens to patients.

Get one carefully sourced AI-healthcare briefing every Monday.