Data-Driven Modeling of Smartphone-Based Electrochemiluminescence Sensor Data Using Artificial Intelligence

Abstract

Understanding relationships among multimodal data extracted from a smartphone-based electrochemiluminescence (ECL) sensor is crucial for the development of low-cost point-of-care diagnostic devices. In this work, artificial intelligence (AI) algorithms such as random forest (RF) and feedforward neural network (FNN) are used to quantitatively investigate the relationships between the concentration of Ru ( bpy ) 3 2 + luminophore and its experimentally measured ECL and electrochemical data. A smartphone-based ECL sensor with Ru ( bpy ) 3 2 + /TPrA was developed using disposable screen-printed carbon electrodes. ECL images and amperograms were simultaneously obtained following 1.2-V voltage application. These multimodal data were analyzed by RF and FNN algorithms, which allowed the prediction of Ru ( bpy ) 3 2 + concentration using multiple key features. High correlation (0.99 and 0.96 for RF and FNN, respectively) between actual and predicted values was achieved in the detection range between 0.02 µM and 2.5 µM. The AI approaches using RF and FNN were capable of directly inferring the concentration of Ru ( bpy ) 3 2 + using easily observable key features. The results demonstrate that data-driven AI algorithms are effective in analyzing the multimodal ECL sensor data. Therefore, these AI algorithms can be an essential part of the modeling arsenal with successful application in ECL sensor data modeling.

Best practices and current implementation of emerging smartphone-based (bio)sensors – Part 1: Data handling and ethics

“…In one example, on-smartphone ML algorithms, such as a random forest (RF) and an ANN, were used to investigate how analyte concentration influenced electrochemical signal development [114]. In yet another demonstration of ML applied to an SbS platform, screening for disease in orchids was performed by training an algorithm using optical data and results from polymerase chain reaction (PCR) assays, resulting in an algorithm with 89% result prediction accuracy [115].…”

A Hybrid Approach: Dynamic Diagnostic Rules for Sensor Systems in Industry 4.0 Generated by Online Hyperparameter Tuned Random Forest

“…In this recent work [14], RF is used in a hybrid fashion with Feedforward Neural Network (FNN) to investigate the relationship(s) among multi-modal signals, extracted from electrochemiluminescence (ECL) sensors located in a smartphone and the concentration of Ru(bpy) 2+ 3 luminophore and its electrochemical data. Establishing such a correlation is essential for building optimized and cheaper diagnostic devices.…”

A Machine Learning-based approach for Simultaneous Detection of Interfering Analytes in Electrochemical Nanobiosensors

“…ML has been previously used in electrochemical biosensors, although its use has still been limited [13]. Aiassa et al [14] and Rivera et al [15] used ML to detect a single analyte to reduce the effect of background noise. Qian et al [16], used statistical machine learning to quantify E.Coli concentration from water samples.…”