In March 2022, researchers at Memorial Sloan Kettering Cancer Center published a landmark study in Nature Biomedical Engineering demonstrating that an array of quantum-defect-modified carbon nanotube sensors, analyzed by machine learning, could detect high-grade serous ovarian carcinoma from blood serum with 87% sensitivity and 98% specificity, outperforming conventional biomarkers for the deadliest form of ovarian cancer.
The study was led by first author Mijin Kim, PhD, and senior author Daniel A. Heller, PhD, across a cohort of 269 patients. The platform employed single-walled carbon nanotubes functionalized with quantum defects, engineered modifications that expand the nanotube’s surface chemistry and fluorescence diversity, to generate a disease fingerprint distinguishable from both healthy controls and patients with other gynecological conditions including endometriosis. Rather than targeting a single known biomarker, the platform captured a composite spectral signal that machine learning interpreted as a disease signature, enabling cancer detection without prior knowledge of which specific proteins or metabolites to measure.
The distinction carries clinical importance. Existing blood-based ovarian cancer tests such as CA-125 have limited sensitivity, particularly at early disease stages, and frequently produce false positives in patients with benign gynecological conditions. The nanosensor array approach sidesteps that limitation by reading an emergent pattern across the serum proteome rather than measuring any single analyte. The study established the foundation for a generalizable platform with potential application across multiple cancer indications and disease types.
The methodology described in this paper, quantum-defect-modified carbon nanotube arrays combined with machine learning disease fingerprinting, forms the scientific foundation of Nine Diagnostics, which Kim and Heller co-founded in 2024 alongside Freddy T. Nguyen, MD, PhD. Read the paper.
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.