Information visualization and machine learning driven methods for impedimetric biosensing

This review addresses the convergence of impedimetric biosensing technologies and computational methods facilitating data information visualization. The literature brings various methodologies and analytical techniques associated with impedance measurements for biosensing, ranging from versatile testing platforms to management decisions according to the reported detection level. To this end, there has been a growing need for multivariate methods in data analysis, with a steady increase in machine learning methods to determine biosensing parameters. It has been expanded to calibration, analysis, classification, regression procedures, and more recently, calibration space and data inspection rules to optimize the device performance. Consequently, there has been a significant improvement in the automation and accuracy of data, with immediate impacts on diagnostics and protocols in recent years. We focus here on impedimetric biosensing and how multivariate methods combined with machine learning tools (artificial neural network, random forest, decision three, support vector machine, etc.) contribute to the outstanding performance of these devices.

Automated summary

This review discusses the convergence of impedimetric biosensing technologies and computational methods for data information visualization. Various methodologies and analytical techniques associated with impedance measurements for biosensing are presented, including versatile testing platforms and management decisions based on detection level. The application of multivariate methods in data analysis, particularly machine learning methods, has seen steady growth in determining biosensing parameters. These methods have been applied to calibration, analysis, classification, regression procedures, and optimization of device performance. As a result, there has been significant improvement in data automation, accuracy, and its impact on diagnostics and protocols.