A Deep Learning Approach to Organic Pollutants Classification Using Voltammetry

Research Progress of Electrochemical Biosensors for Diseases Detection in China: A Review

Disease diagnosis is not only related to individual health but is also a crucial part of public health prevention. Electrochemical biosensors combine the high sensitivity of electrochemical methods with the inherent high selectivity of biological components, offering advantages such as excellent sensitivity, fast response time, and low cost. The generated electrical signals have a linear relationship with the target analyte, allowing for identification and concentration detection. This has become a very attractive technology. This review offers a summary of recent advancements in electrochemical biosensor research for disease diagnosis in China. It systematically categorizes and summarizes biosensors developed in China for detecting cancer, infectious diseases, inflammation, and neurodegenerative disorders. Additionally, the review delves into the fundamental working principles, classifications, materials, preparation techniques, and other critical aspects of electrochemical biosensors. Finally, it addresses the key challenges impeding the advancement of electrochemical biosensors in China and examines promising future directions for their development.

Explainable AI for Chronic Kidney Disease Prediction in Medical IoT: Integrating GANs and Few-Shot Learning

According to recent global public health studies, chronic kidney disease (CKD) is becoming more and more recognized as a serious health risk as many people are suffering from this disease. Machine learning techniques have demonstrated high efficiency in identifying CKD, but their opaque decision-making processes limit their adoption in clinical settings. To address this, this study employs a generative adversarial network (GAN) to handle missing values in CKD datasets and utilizes few-shot learning techniques, such as prototypical networks and model-agnostic meta-learning (MAML), combined with explainable machine learning to predict CKD. Additionally, traditional machine learning models, including support vector machines (SVM), logistic regression (LR), decision trees (DT), random forests (RF), and voting ensemble learning (VEL), are applied for comparison. To unravel the "black box" nature of machine learning predictions, various techniques of explainable AI, such as SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME), are applied to understand the predictions made by the model, thereby contributing to the decision-making process and identifying significant parameters in the diagnosis of CKD. Model performance is evaluated using predefined metrics, and the results indicate that few-shot learning models integrated with GANs significantly outperform traditional machine learning techniques. Prototypical networks with GANs achieve the highest accuracy of 99.99%, while MAML reaches 99.92%. Furthermore, prototypical networks attain F1-score, recall, precision, and Matthews correlation coefficient (MCC) values of 99.89%, 99.9%, 99.9%, and 100%, respectively, on the raw dataset. As a result, the experimental results clearly demonstrate the effectiveness of the suggested method, offering a reliable and trustworthy model to classify CKD. This framework supports the objectives of the Medical Internet of Things (MIoT) by enhancing smart medical applications and services, enabling accurate prediction and detection of CKD, and facilitating optimal medical decision making.

Revolutionizing cesium monitoring in seawater through electrochemical voltammetry and machine learning

Monitoring radioactive cesium ions (Cs+) in seawater is vital for environmental safety but remains challenging due to limitations in the accessibility, stability, and selectivity of traditional methods. This study presents an innovative approach that combines electrochemical voltammetry using nickel hexacyanoferrate (NiHCF) thin-film electrode with machine learning (ML) to enable accurate and portable detection of Cs+. Optimizing the fabrication of NiHCF thin-film electrodes enabled the development of a robust sensor that generates cyclic voltammograms (CVs) sensitive to Cs⁺ concentrations as low as 1 ppb in synthetic seawater and 10 ppb in real seawater, with subtle changes in CV patterns caused by trace Cs⁺ effectively identified and analyzed using ML. Using 2D convolutional neural networks (CNNs), we classified Cs+ concentrations across eight logarithmic classes (0 - 106 ppb) with 100 % accuracy and an F1-score of 1 in synthetic seawater datasets, outperforming the 1D CNN and deep neural networks. Validation using real seawater datasets confirmed the applicability of our model, achieving high performance. Moreover, gradient-weighted class activation mapping (Grad-CAM) identified critical CV regions that were overlooked during manual inspection, validating model reliability. This integrated method offers sensitive and practical solutions for monitoring Cs+ in seawater, helping to prevent its accumulation in ecosystems.

Gas-Phase Biosensors (Bio-Sniffers) for Measurement of 2-Nonenal, the Causative Volatile Molecule of Human Aging-Related Body Odor

The molecule 2-nonenal is renowned as the origin of unpleasant human aging-related body odor that can potentially indicate age-related metabolic changes. Most 2-nonenal measurements rely on chromatographic analytical systems, which pose challenges in terms of daily usage and the ability to track changes in concentration over time. In this study, we have developed liquid- and gas-phase biosensors (bio-sniffers) with the aim of enabling facile and continuous measurement of trans-2-nonenal vapor. Initially, we compared two types of nicotinamide adenine dinucleotide (phosphate) [NAD(P)]-dependent enzymes that have the catalytic ability of trans-2-nonenal: aldehyde dehydrogenase (ALDH) and enone reductase 1 (ER1). The developed sensor quantified the trans-2-nonanal concentration by measuring fluorescence (excitation: 340 nm, emission: 490 nm) emitted from NAD(P)H that was generated or consumed by ALDH or ER1. The ALDH biosensor reacted to a variety of aldehydes including trans-2-nonenal, whereas the ER1 biosensor showed high selectivity. In contrast, the ALDH bio-sniffer showed quantitative characteristics for trans-2-nonenal vapor at a concentration range of 0.4-7.5 ppm (with a theoretical limit of detection (LOD) and limit of quantification (LOQ) of 0.23 and 0.26 ppm, respectively), including a reported concentration (0.85-4.35 ppm), whereas the ER1 bio-sniffer detected only 0.4 and 0.8 ppm. Based on these findings, headspace gas of skin-wiped alcohol-absorbed cotton collected from study participants in their 20s and 50s was measured by the ALDH bio-sniffer. Consequently, age-related differences in signals were observed, suggesting the potential for measuring trans-2-nonenal vapor.

Deep Learning Denoising Improves and Homogenizes Patient [18F]FDG PET Image Quality in Digital PET/CT

Given the constant pressure to increase patient throughput while respecting radiation protection, global body PET image quality (IQ) is not satisfactory in all patients. We first studied the association between IQ and other variables, in particular body habitus, on a digital PET/CT. Second, to improve and homogenize IQ, we evaluated a deep learning PET denoising solution (Subtle PETTM) using convolutional neural networks. We analysed retrospectively in 113 patients visual IQ (by a 5-point Likert score in two readers) and semi-quantitative IQ (by the coefficient of variation in the liver, CVliv) as well as lesion detection and quantification in native and denoised PET. In native PET, visual and semi-quantitative IQ were lower in patients with larger body habitus (p < 0.0001 for both) and in men vs. women (p ≤ 0.03 for CVliv). After PET denoising, visual IQ scores increased and became more homogeneous between patients (4.8 ± 0.3 in denoised vs. 3.6 ± 0.6 in native PET; p < 0.0001). CVliv were lower in denoised PET than in native PET, 6.9 ± 0.9% vs. 12.2 ± 1.6%; p < 0.0001. The slope calculated by linear regression of CVliv according to weight was significantly lower in denoised than in native PET (p = 0.0002), demonstrating more uniform CVliv. Lesion concordance rate between both PET series was 369/371 (99.5%), with two lesions exclusively detected in native PET. SUVmax and SUVpeak of up to the five most intense native PET lesions per patient were lower in denoised PET (p < 0.001), with an average relative bias of -7.7% and -2.8%, respectively. DL-based PET denoising by Subtle PETTM allowed [18F]FDG PET global image quality to be improved and homogenized, while maintaining satisfactory lesion detection and quantification. DL-based denoising may render body habitus adaptive PET protocols unnecessary, and pave the way for the improvement and homogenization of PET modalities.