A BBC News feature by Technology reporter Padraig Belton, the third in a six-part series examining how AI is changing medical research and treatments, highlights the work of Daniel A. Heller, PhD, Co-Founder and Chief Science Officer of Nine Diagnostics and Head of the Cancer Nanomedicine Lab at Memorial Sloan Kettering Cancer Center (MSKCC). The article focuses on Dr. Heller’s development of a carbon nanotube nanosensor blood test that uses AI to detect ovarian cancer at earlier stages than currently possible.
Ovarian cancer is “rare, underfunded, and deadly,” according to Ovarian Cancer Research Alliance (OCRA) President and CEO Audra Moran, who is quoted in the BBC feature. Most cases begin in the fallopian tubes, and by the time symptoms appear, the disease may have already spread. Moran notes that detection as many as five years before symptoms emerge may be necessary to meaningfully reduce mortality.
Dr. Heller’s team developed a testing technology using nanotubes, tiny carbon tubes approximately 50,000 times smaller than the diameter of a human hair. Discovered roughly two decades ago for their ability to emit fluorescent light, nanotubes can now be tuned to respond to almost anything in blood. Millions of nanotubes placed in a blood sample emit different wavelengths of light based on what binds to them, generating a complex molecular fingerprint too subtle for any human analyst to interpret.
“We can look at the data and we will not make sense of it at all. We can only see the patterns that are different with AI.”
Daniel A. Heller, PhD
The algorithm was trained on samples from a limited number of patients, including blood from people with other cancers and other gynaecological diseases that could be confused with ovarian cancer. Despite the small training set, the AI achieved accuracy exceeding the best cancer biomarkers currently available. Further studies are underway using larger sensor arrays and broader patient datasets. Prior peer-reviewed validation from the Heller Lab, published as Kim et al. (2022) in Nature Biomedical Engineering, achieved 87% sensitivity and 98% specificity for high-grade serous ovarian cancer across 269 patient samples.
“What we’d like to do is triage all gynaecological disease – so when someone comes in with a complaint, can we give doctors a tool that quickly tells them it’s more likely to be a cancer or not, or this cancer than that.”
Daniel A. Heller, PhD
Dr. Heller estimates a clinical triage tool may be three to five years away. He notes that while the sensor is known to respond to proteins and small molecules in blood, identifying precisely which of those molecules are specific to cancer remains an open research question – one the AI approach is helping to answer.
The BBC feature also covers other AI applications in blood diagnostics, including AI-assisted identification of the precise pneumonia pathogen within 24 hours and a machine learning platform developed at AstraZeneca that uses biomarkers from the UK Biobank to identify over 120 diseases with greater than 90% accuracy. A recurring theme across all three examples is the role of AI in decoding complex biological patterns that no conventional diagnostic method can resolve, and the challenge of limited, siloed data that constrains how quickly these tools can be trained and validated.
Nine Diagnostics is built on this same scientific foundation, extending the nanosensor and AI platform to generate multi-omic fingerprints for cancer diagnostics and treatment monitoring across oncology applications.
About Nine Diagnostics
Nine Diagnostics is an AI-enabled multi-omic nanosensor company advancing precision medicine. The platform simultaneously captures proteomic, metabolomic, and lipidomic signals alongside patient clinical context to generate a multi-omic fingerprint, using machine learning to identify disease-relevant patterns without requiring prior knowledge of which biomarkers matter. This enables pre-treatment patient stratification, on-treatment response monitoring, and post-treatment minimal residual disease detection. Founded by Freddy T. Nguyen, MD, PhD (CEO), Daniel A. Heller, PhD (CSO), and Mijin Kim, PhD (Scientific Advisor), Nine Diagnostics is based in Cambridge, Massachusetts.