Machine learning for optical chemical multi-analyte imaging

• Published in: Analytical and bioanalytical chemistry 2023-06, Vol.415 (14), p.2749-2761
• Main Authors: Zieger, Silvia E, Koren, Klaus
• Format: Article
• Language: English
• Subjects: Algorithms; Chemical perception; Chemical sensors; Chemoreception; Data analysis; Decision analysis; Decision trees; Dissolved oxygen; Identification and classification; Image acquisition; Learning algorithms; Machine learning; Metabolites; Methods; Multilayers; pH effects; Position measurement; Properties; Sensors; Two dimensional analysis
• ISSN: 1618-2642; 1618-2650
• DOI: 10.1007/s00216-023-04678-8

Simultaneous sensing of metabolic analytes such as pH and O.sub.2 is critical in complex and heterogeneous biological environments where analytes often are interrelated. However, measuring all target analytes at the same time and position is often challenging. A major challenge preventing further progress occurs when sensor signals cannot be directly correlated to analyte concentrations due to additional effects, overshadowing and complicating the actual correlations. In fields related to optical sensing, machine learning has already shown its potential to overcome these challenges by solving nested and multidimensional correlations. Hence, we want to apply machine learning models to fluorescence-based optical chemical sensors to facilitate simultaneous imaging of multiple analytes in 2D. We present a proof-of-concept approach for simultaneous imaging of pH and dissolved O.sub.2 using an optical chemical sensor, a hyperspectral camera for image acquisition, and a multi-layered machine learning model based on a decision tree algorithm (XGBoost) for data analysis. Our model predicts dissolved O.sub.2 and pH with a mean absolute error of < 4.50·10.sup.-2 and < 1.96·10.sup.-1, respectively, and a root mean square error of < 2.12·10.sup.-1 and < 4.42·10.sup.-1, respectively. Besides the model-building process, we discuss the potentials of machine learning for optical chemical sensing, especially regarding multi-analyte imaging, and highlight risks of bias that can arise in machine learning-based data analysis.