김미진 (Memorial Sloan Kettering Cancer Center, 현 Georgia Institute of Technology)

한빛사논문

조회267

김미진Mijin Kim

Memorial Sloan Kettering Cancer Center, 현 Georgia Institute of Technology

CV File 387 kb

Nat. Biomed. Eng., Mar 2022, 6 (3) | https://doi.org/10.1038/s41551-022-00860-y Detection of ovarian cancer via the spectral fingerprinting of quantum-defect-modified carbon nanotubes in serum by machine learning

Mijin Kim ¹, Chen Chen ^1,2,3, Peng Wang ⁴, Joseph J. Mulvey ⁵, Yoona Yang ⁶, Christopher Wun ⁷, Merav Antman-Passig ¹, Hong-Bin Luo ⁴, Sun Cho ¹, Kara Long-Roche¹, Lakshmi V. Ramanathan ¹, Anand Jagota ⁶, Ming Zheng ⁸, YuHuang Wang ⁴ and Daniel A. Heller ^1,2

¹Memorial Sloan Kettering Cancer Center, New York, NY, USA.

²Weill Cornell Medicine, Cornell University, New York, NY, USA.

³Tri-Institutional PhD Program in Chemical Biology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.

⁴Department of Chemistry and Biochemistry, University of Maryland, College Park, MD, USA.

⁵Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, USA.

⁶Departments of Bioengineering, and Chemical and Biomolecular Engineering, Lehigh University, Bethlehem, PA, USA.

⁷Hunter College High School, New York, NY, USA.

⁸Materials Science and Engineering Division, National Institute of Standards and Technology, Gaithersburg, MD, USA.

Corresponding author

Correspondence to Daniel A. Heller.

Abstract

Serum biomarkers are often insufficiently sensitive or specific to facilitate cancer screening or diagnostic testing. In ovarian cancer, the few established serum biomarkers are highly specific, yet insufficiently sensitive to detect early-stage disease and to impact the mortality rates of patients with this cancer. Here we show that a 'disease fingerprint' acquired via machine learning from the spectra of near-infrared fluorescence emissions of an array of carbon nanotubes functionalized with quantum defects detects high-grade serous ovarian carcinoma in serum samples from symptomatic individuals with 87% sensitivity at 98% specificity (compared with 84% sensitivity at 98% specificity for the current best clinical screening test, which uses measurements of cancer antigen 125 and transvaginal ultrasonography). We used 269 serum samples to train and validate several machine-learning classifiers for the discrimination of patients with ovarian cancer from those with other diseases and from healthy individuals. The predictive values of the best classifier could not be attained via known protein biomarkers, suggesting that the array of nanotube sensors responds to unidentified serum biomarkers.

논문정보

형식Research article
게재일2022년 03월 (BRIC 등록일 2024-05-07)
연구진국외 연구진
분야 바이오·의료융합 > 바이오센싱 및 나노바이오물질

댓글 작성 로그인

CV 열람하기

연락처 보기