Open AccessMachine learning-based LIBS spectrum analysis of human blood plasma allows ovarian cancer diagnosis
Author(s) -
Zengqi Yue,
Chen Sun,
Fengye Chen,
Yuqing Zhang,
Weijie Xu,
Sahar Shabbir,
Long Zou,
Weiguo Lü,
Wei Wang,
Zhenwei Xie,
Lili Zhou,
Yan Lu,
Jianhua Yu
Publication year - 2021
Publication title -
biomedical optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.362
H-Index - 86
ISSN - 2156-7085
DOI - 10.1364/boe.421961
Subject(s) - ovarian cancer , cancer , population , computer science , oncology , artificial intelligence , medicine , environmental health
Early-stage screening and diagnosis of ovarian cancer represent an urgent need in medicine. Usual ultrasound imaging and cancer antigen CA-125 test when prescribed to a suspicious population still require reconfirmations. Spectroscopic analyses of blood, at the molecular and atomic levels, provide useful supplementary tests when coupled with effective information extraction methods. Laser-induced breakdown spectroscopy (LIBS) was employed in this work to record the elemental fingerprint of human blood plasma. A machine learning data treatment process was developed combining feature selection and regression with a back-propagation neural network, resulting in classification models for cancer detection among 176 blood plasma samples collected from patients, including also ovarian cyst and normal cases. Cancer diagnosis sensitivity and specificity of respectively 71.4% and 86.5% were obtained for randomly selected validation samples.