These New AI Blood Tests Can Detect Cancer

Artificial intelligence (AI) is making waves in medical research, unlocking new possibilities for detecting deadly diseases early and efficiently.

From pinpointing rare cancers to streamlining infection diagnosis, AI is proving to be a game-changer in healthcare innovation.

Spotting Ovarian Cancer Early with AI

In a recent report by the BBC, it was outlined that ovarian cancer is often called “rare, underfunded, and deadly,” according to Audra Moran, head of the Ovarian Cancer Research Alliance (Ocra), as she explained to Padraig Belton, BBC reporter. Detecting it early is critical, but challenging according to the news outlet. Most cases begin in the fallopian tubes, and by the time symptoms appear, the cancer may have already spread.

MORE: TikTok is turning Gen Z to botox too early

DISCOVER: Teens are using social media to diagnose themselves with mental health issues

“Five years prior to ever having a symptom is when you might have to detect ovarian cancer, to affect mortality,” Moran explains.

Dr. Daniel Heller and his team at Memorial Sloan Kettering Cancer Center are tackling this issue using nanotubes—tiny carbon tubes 50,000 times thinner than a human hair. These nanotubes fluoresce in response to specific molecules in blood samples, but the resulting data patterns are too subtle for humans to interpret.

This is where AI steps in. Machine learning algorithms analyse the nanotube data, learning to differentiate between samples from patients with ovarian cancer and those without. Even with limited data from only a few hundred patients, the AI achieved higher accuracy than current cancer biomarkers on its first attempt.

MORE: I Tried the World’s First AI-yurvedic Skin Scan: Here’s What Happened

DISCOVER: Dr. Miriam Al Adib lifted the lid on Almendralejo’s AI scandal, and we all need to pay attention

Dr. Heller envisions a future where this tech could triage all gynaecological diseases, helping doctors quickly determine if a case is likely cancer. “This may be three to five years away,” he says.

AI vs. Deadly Infections

AI isn’t just revolutionising cancer detection—it’s also speeding up the diagnosis of infections like pneumonia. With over 600 pathogens capable of causing pneumonia, traditional tests can take days and cost thousands.

MORE: Red Light Therapy Doesn’t Suit Everyone: What You Need to Know

DISCOVER: Researchers are training AI to detect breast cancer

California-based company Karius has developed an AI-powered blood test that identifies the precise pneumonia pathogen within 24 hours. Using a massive database of microbial DNA containing billions of data points, Karius compares patient samples to pinpoint the infection and recommend targeted antibiotics.

“Before our test, a patient with pneumonia would have 15 to 20 different tests in their first week—costing about $20,000,” says Karius CEO Alec Ford. Thanks to AI, this process is faster, cheaper, and more accurate.

Data Sharing: The Missing Link

While AI excels at detecting patterns in biomarkers, the lack of data sharing is a bottleneck. “People aren’t sharing their data, or there’s not a mechanism to do it,” Moran says. Ocra is funding a large-scale patient registry to bridge this gap and improve algorithm training.

MORE: This female-founded start up has developed an AI that can spot breast cancer

DISCOVER: AI Breakthrough Predicts Breast Cancer 5 Years Early—And We Finally Know How It Works

The Future of AI in Healthcare

From diagnosing diseases to improving treatment precision, AI is pushing the boundaries of what’s possible. “It’s still the wild west of AI now,” says Moran, but the potential for lifesaving breakthroughs has never been greater.