Department of Electrical and Electronics Engineering Graduate Program, İzmir Katip Çelebi University, 35620 Turkey.
Department of Biomedical Engineering Graduate Program, İzmir Katip Çelebi University, 35620 Turkey.
Analyst. 2021 Nov 22;146(23):7336-7344. doi: 10.1039/d1an01888d.
In the present study, iodide-mediated 3,3',5,5'-tetramethylbenzidine (TMB)-HO reaction system was applied to a microfluidic paper-based analytical device (μPAD) for non-enzymatic colorimetric determination of HO. The proposed system is portable and incorporates a μPAD with a machine learning-based smartphone app. A smartphone app called "" capable of image capture, cropping and processing was developed to make the system simple and user-friendly. Briefly, circular μPADs were designed and tested with varying concentrations of HO. Following the color change, the images of the μPADs were taken with four different smartphones under seven different illumination conditions. In order to make the system more robust and adaptive against illumination variation and camera optics, the images were first processed for feature extraction and then used to train machine learning classifiers. According to the results, TMB + KI showed the highest classification accuracy (97.8%) with inter-phone repeatability at = 30 s under versatile illumination and maintained its accuracy for 10 minutes. In addition, the performance of the system was also comparable to two different commercially available HO kits in real samples.
在本研究中，采用碘介导的 3,3',5,5'-四甲基联苯胺（TMB）-HO 反应体系，应用于微流控纸基分析装置（μPAD），用于 HO 的非酶比色测定。该系统便携，结合了具有基于机器学习的智能手机应用程序的 μPAD。开发了一个名为“”的智能手机应用程序，能够进行图像捕获、裁剪和处理，使系统简单易用。简要地说，设计并测试了具有不同 HO 浓度的圆形 μPAD。在颜色变化后，使用四部不同的智能手机在七种不同的照明条件下拍摄 μPAD 的图像。为了使系统更加稳健，能够适应照明变化和相机光学，对图像进行了特征提取处理，然后用于训练机器学习分类器。结果表明，TMB+KI 在各种照明条件下具有最高的分类准确率（97.8%），手机间的重复性为 30 s，并且在 10 分钟内保持准确率。此外，该系统在实际样本中的性能也可与两种不同的市售 HO 试剂盒相媲美。
