Machine Learning-Assisted Janus Colorimetric Face Mask for Breath Ammonia Analysis.

Artificial olfactory systems have been widely used in medical fields such as in the analysis of volatile organic compounds (VOCs) in human exhaled breath. However, there is still an urgent demand for a portable, accurate breath VOC analysis system for the healthcare industry. In this work, we proposed a Janus colorimetric face mask (JCFM) for the comfortable evaluation of breath ammonia levels by combining the machine learning K-nearest neighbor (K-NN) algorithm. Such a Janus fabric is designed for the unidirectional penetration of exhaled moisture, which can reduce stickiness and ensure facial dryness and comfort. Four different pH indicators on the colorimetric array serve as recognition elements that cross-react with ammonia, capturing the optical fingerprint information on breath ammonia by mimicking the sophisticated olfactory structure of mammals. The Euclidean distance (ED) is used to quantitatively describe the ammonia concentration between 1 ppm and 10 ppm, indicating that there is a linear relationship between the ammonia concentration and the ED response (R2 = 0.988). The K-NN algorithm based on RGB response features aids in the analysis of the target ammonia level and achieves a prediction accuracy of 96%. This study integrates colorimetry, Janus design, and machine learning to present a wearable and portable sensing system for breath ammonia analysis.

Oriented Antibody-Assembled Metal-Organic Frameworks for Persistent Wearable Sweat Cortisol Detection.

The level of cortisol can reflect people's psychological stress, help diagnose adrenal gland diseases, and is also related to several mental diseases. In this study, we developed a cortisol monoclonal antibody-oriented approach to modify an immunosensor for wearable label-free and persistent sweat cortisol detection. On such an antibody-oriented immunosensor, the fragment crystallizable (Fc) region is partially inserted within the metal-organic framework (MOF), and antibody-binding regions of the cortisol monoclonal antibody (Cmab) were exposed on the MOF surface via selective growth and self-assembly. Such ordered and oriented embedding of antibodies in the MOF resulted in excellent antibody activity and improved stability and antigen-binding capacity. We also engineered the full integrated system for on-body sweat cortisol biosensing performance in several volunteers, and the results indicated that this wearable sensor is suitable for practical cortisol detection with a good linear detection range from 1 pg/mL to 1 µg/mL with a lower limit of detection of 0.26 pg/mL. Moreover, the wearable sensor demonstrated good persistence in detecting cortisol, with only 4.1% decay after 9 days of storage. The present work represents a simple oriented antibody assembling approach to improve the stability of antibodies, providing an important step toward long-term continuous sweat biomarker detection.

Integrated Ultrasound-Enrichment and Machine Learning in Colorimetric Lateral Flow Assay for Accurate and Sensitive Clinical Alzheimer's Biomarker Diagnosis.

The colloidal gold nanoparticle (AuNP)-based colorimetric lateral flow assay (LFA) is one of the most promising analytical tools for point-of-care disease diagnosis. However, the low sensitivity and insufficient accuracy still limit its clinical application. In this work, a machine learning (ML)-optimized colorimetric LFA with ultrasound enrichment is developed to achieve the sensitive and accurate detection of tau proteins for early screening of Alzheimer's disease (AD). The LFA device is integrated with a portable ultrasonic actuator to rapidly enrich microparticles using ultrasound, which is essential for sample pre-enrichment to improve the sensitivity, followed by ML algorithms to classify and predict the enhanced colorimetric signals. The results of the undiluted serum sample testing show that the protocol enables efficient classification and accurate quantification of the AD biomarker tau protein concentration with an average classification accuracy of 98.11% and an average prediction accuracy of 99.99%, achieving a limit of detection (LOD) as sensitive as 10.30 pg mL-1. Further point-of-care testing (POCT) of human plasma samples demonstrates the potential use of LFA in clinical trials. Such a reliable lateral flow immunosensor with high precision and superb sensing performance is expected to put LFA in perspective as an AD clinical diagnostic platform.

Machine learning-powered wearable interface for distinguishable and predictable sweat sensing.

The constrained resources on wearable devices pose a challenge in meeting the demands for comprehensive sensing information, and current wearable non-enzymatic sensors face difficulties in achieving specific detection in biofluids. To address this issue, we have developed a highly selective non-enzymatic sweat sensor that seamlessly integrates with machine learning, ensuring reliable sensing and physiological monitoring of sweat biomarkers during exercise. The sensor consists of two electrodes supported by a microsystem that incorporates signal processing and wireless communication. The device generates four explainable features that can be used to accurately predict tyrosine and tryptophan concentrations, as well as sweat pH. The reliability of this device has been validated through rigorous statistical analysis, and its performance has been tested in subjects with and without supplemental amino acid intake during cycling trials. Notably, a robust linear relationship has been identified between tryptophan and tyrosine concentrations in the collected samples, irrespective of the pH dimension. This innovative sensing platform is highly portable and has significant potential to advance the biomedical applications of non-enzymatic sensors. It can markedly improve accuracy while decreasing costs.

Machine Learning with Neural Networks to Enhance Selectivity of Nonenzymatic Electrochemical Biosensors in Multianalyte Mixtures.

Nonenzymatic biosensors hold great potential in the field of analysis and detection due to long-term stability, high sensitivity, and low cost. However, the relative low selectivity, especially the overlapped oxidation peaks of biomarkers, in the biological matrix severely limits the practical application. In this work, we introduce an intelligent back-propagation neural network into nonenzymatic electrochemical biosensing to overcome the limitation of low selectivity for glucose and lactate detection. After simple electrodeposition and dropping modification, three working electrodes with distinct characters are fabricated and integrated into electrochemical microdroplet arrays for glucose and lactic acid detection. By analyzing chronoamperometry data from a standard mixture of glucose and lactate in varying concentrations, a database of highly selective detection can be simply established. The trained neural network model can reliably identify and accurately predict the concentration of glucose and lactic acid in the range of 0.25-20 mM with a correlation coefficient of 0.9997 in multianalyte mixtures. More importantly, the predicted results of serum samples are precise, and the relative standard deviation is less than 6.5%, proving the possible applicability of this method in real scenarios. This innovative method to enhance selectivity can avoid complex material synthesis and selection, and the highly specific nonenzymatic electrochemical biosensing platform paves the way for intelligent and precise point-of-care detection in long-term and is of low cost.

Wireless USB-like electrochemical platform for individual electrochemical sensing in microdroplets.

The portable electrochemical platform can adapt to more usage scenarios, which is essential for drug discovery, toxicology, and cell biology. Here, we constructed the wireless USB-like electrochemical platform for simultaneous multi-channel electrochemical sensing in microdroplet array. On such platform, multi-channel mini-pillar arrays can anchor reagent droplet (a few microliters to dozens of microliters), and the wireless USB-like electrochemical platform can achieve simultaneously multi-channel detection. As a concept-of-proof for multi-channel, the 4∗4 channels are chosen as a model to proof the practicality of such portable electrochemical platform, the relative standard deviation (RSD) of such a platform in microdroplets sensing is below 5% level. The quantitative electrochemical analysis of multiple glucose concentrations in miniature workstation was also achieved, and only 0.97% difference between traditional electrochemical workstation. The wireless USB-like electrochemical platform with the characteristics of cloud data management and multi-channel, which enables remote detection and analysis and presents an opportunity for future portable high-throughput biomedical applications.