No 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.

Introduction: Studies conducted in our laboratory on proteomic profiling of breast cancer serum among women by shotgun LC-MS methodology have identified several biomarkers for early detection of breast cancer. However, not all of the identified biomarkers have been validated due to costs involved with validation tests. The development of a reliable, cost-effective highly sensitive portable system, the Electrochemiluminescence (ECL) biosensor will enable us to validate identified biomarkers that have valuable diagnostic applications. The purpose of this study was to detect dopamine, which has been identified as a biomarker in advanced breast cancer. Dopamine and its receptors act as novel therapeutic agents in advanced breast cancer. Dopamine significantly enhances the efficacy of commonly used anticancer drugs through its antiangiogenic action. Methods: In this work, a compact, mobile phone-based ECL sensor apparatus was developed using the phone cameras, screen-printed electrodes (SPE), and mobile app for dopamine detection. Methods of DC voltage application for ECL reaction were comprehensively studied from the mobile phone itself or external power. Under optimized sensing conditions, with disposable carbon SPE and 20 mM coreactant tri-n-propylamine (TPrA), acceptable repeatability and reproducibility were achieved in terms of relative standard deviation (RSD) of intra- and interassays, which were 6.7 and 5.5 %, respectively. The biochemical compound dopamine was measured due to its ECL quenching characteristics and its clinical significance in breast cancer detection and therapeutic properties. The quenching mechanism of Ru(bpy)32+/TPrA by dopamine was investigated based on the estimation of the constants of the Stern-Volmer equations. Results: The linear range for detectable dopamine concentration was from 1.0 to 50 µM (R2 = 0.982). As the developed mobile phone-based ECL sensor is simple, small and assembled from low-cost components, it offers new opportunities for the development of inexpensive analytical methods and compact sensors. Conclusion: The ECL sensor demonstrated that a new instrumentation with mobile technology in the point-of-care diagnostics of breast cancer could provide reliability and sensitivity of a high-end equipment. This project is funded by the NSF CBET division. Citation Format: Hyun J. Kwon, Padma P. Tadi Uppala, Elmer C. Rivera, Mabio R. Neto, Daniel Marsh, Jonathan J. Swerdlow, Rodney L. Summerscales. Development of a smartphone-based electrochemiluminescence biosensor for dopamine detection in advanced breast cancer [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 871.