Machine-learning-aided identification of steroid hormones based on the anisotropic galvanic replacement generated sensor array

• Published in: Sensors and actuators. B, Chemical Vol. 370; p. 132470
• Main Authors: Chen, Yuying, Lin, Peiru, Zou, Xun, Liu, Lina, Ouyang, Sixue, Chen, Huiting, Ren, Qingfan, Zeng, Ying, Zhao, Peng, Tao, Jia
• Format: Journal Article
• Language: English
• Published: Lausanne Elsevier B.V 01.11.2022; Elsevier Science Ltd
• Subjects: Algorithms; Anisotropic galvanic replacement; Copper; Copper oxides; Cost analysis; Gold; Hormones; Hydrogen peroxide; Machine learning; Palladium; Sensor array; Sensor arrays; Sensors; Steroid hormones; Steroids; Substrates; Anisotropic galvanic replacement; Sensor array; Steroid hormones; Machine learning
• ISSN: 0925-4005; 1873-3077
• DOI: 10.1016/j.snb.2022.132470

The conveniently simultaneous identification of steroid hormones is challenging due to their similar chemical structures. Herein, we have established a machine-learning-aided sensor array for accurate discrimination and determination of steroid hormones based on Cu@Cu2O (CC), Cu@Cu2O@Pd (CCP) and Cu@Cu2O@PdAu (CCPA). The Michaelis-Menten constant of CC, CCP and CCPA toward H2O2 were calculated as 2.61, 1.11 and 2.03 mM, respectively, indicating their different catalytic activities that were obtained from the anisotropic galvanic replacement of Cu@Cu2O with Pd (II) and Au (III). Five kinds of steroid hormones were selected as model targets and reacted with the sensor array before chromogenic reaction. The absorption of chromogenic substrate was used as learning data to train the k-nearest neighbors algorithm, the discrimination confidence was from 88.9% to 100% for different mixtures, and 100% for betamethasone of 1–50 μM in real sample. This work provides a quick analysis of steroid hormones in 1.5 h and low-cost strategy, its further application in the field of cosmetic safety is highly expected. •A sensor array consisting of 3 anisotropic Cu-based nanomaterials was constructed.•k-nearest neighbors (k-NN) algorithm was used to improve the analytical performance•Five kinds of steroid hormones can be accurately identified and determined using k-NN assisted sensor array.•A quick analysis of hormones in real samples was realized with 1.5 h as a sample to result time.