⏳ AI Sees Cancer 6 Years Ahead—Game Changer

PLUS: MIT’s Sybil model uses CT scans to forecast lung cancer risk long before symptoms appear.

In partnership with

AIHealthTech Insider: Issue #65

September 08, 2025

This week’s edition captures some of the boldest frontiers in AI and medicine — from non-invasive brain–computer interfaces to foundation models reshaping cancer care. We’re also spotlighting breakthroughs unveiled at ESC Congress 2025.

Here’s what’s inside ⬇️

  • 🧠 AI copilots giving paralyzed patients robotic control and independence

  • 💻 Foundation models trained on millions of scans, diagnosing cancers more accurately

  • 🩺 AI predicting breast & lung cancer risks years earlier than doctors

  • ⚡ Radiotherapy planning cut from 2 hours to 2 minutes

  • ❤️ Massive heart-health breakthroughs showcased at ESC 2025

As AI goes deeper into diagnosis, treatment planning, and recovery, healthcare’s future is being redefined.

Summaries for education, not medical advice. Verify locally before clinical use.

Source: MIT Jamel Clinic

MIT professor Dr. Regina Barzilay was named to TIME100 AI 2025 for her groundbreaking cancer-detection tools:

  • Mirai (2019): Predicts breast cancer risk 5 years in advance from a single mammogram

  • Sybil (2022): Predicts lung cancer risk 6 years ahead from low-dose CT scans

  • Validated in 2M+ mammograms (70 hospitals, 22 countries) and 25 hospitals (11 countries)

  • Designed to catch cancers earlier, reduce unnecessary screenings, and boost survival rates

This recognition highlights how AI is reshaping oncology by shifting detection from late-stage to early, actionable prevention.

Sponsored

Go from AI overwhelmed to AI savvy professional

AI keeps coming up at work, but you still don't get it?

That's exactly why 1M+ professionals working at Google, Meta, and OpenAI read Superhuman AI daily.

Here's what you get:

  • Daily AI news that matters for your career - Filtered from 1000s of sources so you know what affects your industry.

  • Step-by-step tutorials you can use immediately - Real prompts and workflows that solve actual business problems.

  • New AI tools tested and reviewed - We try everything to deliver tools that drive real results.

  • All in just 3 minutes a day

Image generated by AI

Researchers at UCLA combined a non-invasive brain–computer interface (BCI) with an AI co-pilot, enabling a paralysed man to control a robotic arm:

  • Conventional BCI: captured brain signals but struggled with precision

  • With AI: boosted task accuracy and speed by inferring user goals

  • Robotic arm trial: paralysed participant succeeded 93% of the time at moving blocks

  • Screen tasks: performance improved over standard BCI use

By sharing autonomy between human intent and AI inference, the system shows how BCIs can evolve into practical tools for independence and improved quality of life.

Image generated by AI

Researchers in China built an MRI–pathology foundation model (MRI-PTPCa) to noninvasively diagnose and grade prostate cancer:

  • Trained on 1.3M MRI–pathology pairs from 5,500+ patients

  • Achieved AUC >0.978 and 89.1% grading accuracy

  • Outperformed standard clinical measures and prior AI models

  • Delivered consistent results across discovery, external, and prospective cohorts

This approach reduces reliance on invasive biopsies, offering a scalable tool for more accurate and less risky prostate cancer care.

Sponsored

Used by Execs at Google and OpenAI

Join 400,000+ professionals who rely on The AI Report to work smarter with AI.

Delivered daily, it breaks down tools, prompts, and real use cases—so you can implement AI without wasting time.

If they’re reading it, why aren’t you?

This year’s European Society of Cardiology Congress wasn’t just about stents and statins it was a showcase of how AI is reshaping cardiovascular care. From real-time diagnostics to predictive rehab and genetic screening, the fusion of machine learning and medicine is accelerating faster than ever. Here’s a list of the most impactful AI-driven innovations unveiled in Madrid.

  • ESC Chat → First ESC-approved generative AI tool delivers instant, guideline-based answers to cardiologists.

  • AI Stethoscopes → Detect heart failure, arrhythmias, and valve disease in <15 seconds, showing 2–3× higher accuracy than traditional methods.

  • Cheek-Swab Test → Predicts pediatric arrhythmogenic cardiomyopathy 5 years earlier than current standards.

  • Stroke Rehab AI → Tripled recovery outcomes by personalizing intensity and adapting therapy in real time.

  • AI-Ready Phenotypes → ESC’s digital committee building a machine-readable library to integrate with EHRs for reproducible AI decision support.

Why it matters: ESC 2025 highlights how AI is transforming cardiovascular care from early prediction to rehab making cardiology one of the fastest-moving fields in AI adoption.

Source: Financial Times

Addenbrooke’s Hospital oncologist Dr Raj Jena, the UK’s first clinical professor of AI in radiation oncology, is using AI to cut cancer treatment prep times.

  • Osairis, co-developed with Microsoft, reduces radiotherapy planning from 2 hours to minutes

  • Trained on thousands of cases for prostate, head, and neck cancers

  • Patients now complete treatment in half the time

  • Frees oncologists to see more patients amid rising demand

  • New Apollo platform will let doctors safely test early AI models

This breakthrough is helping hospitals accelerate care, shorten waits, and link clinicians directly with AI innovators.

Sponsored

AI leaders only: Get $100 to explore high-performance AI training data.

Train smarter AI with Shutterstock’s rights-cleared, enterprise-grade data across images, video, 3D, audio, and more—enriched by 20+ years of metadata. 600M+ assets and scalable licensing, We help AI teams improve performance and simplify data procurement. If you’re an AI decision maker, book a 30-minute call—qualified leads may receive a $100 Amazon gift card.

For complete terms and conditions, see the offer page.

🔎 Do You Know?

Image generated by AI

Did you know that psychiatric disorders often “run in couples” — not just families?

A study of 14.8M spousal pairs across Taiwan, Denmark, and Sweden found:

  • Consistent spousal correlations across 9 psychiatric disorders

  • Patterns remained stable across cultures and generations

  • Having two parents with the same disorder more than doubles offspring risk

AI + genetics research may soon reveal how much of this is biology vs shared environment.

🧩 Curious Corner Poll

Did you know that spouses often share similar risks for psychiatric disorders?

👉 Which explanation do you find most fascinating?

Login or Subscribe to participate in polls.

Stay Ahead: AI Healthcare News!

This is just a glimpse of the AI healthcare revolution. Subscribe for exclusive updates on medicine’s future!