Artificial neural network processed linear-light tristimulus and hue parameters of fluorescence for smartphone assisted point-of-care testing device

Chen, Huiting; Zhuang, Zehong; Guo, Siyun; Xie, Shangfang; Yu, Xin; Chen, Yuying; Ouyang, Sixue; Zhao, Wei; Shen, Kui; Tao, Jia; Zhao, Peng

doi:10.1016/j.snb.2023.133659

Cited by 10 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensor array is composed of multiple sensing modules with different properties that can generate fingerprint-like response patterns to multiple target objects. − This response patterns can be further applied to generate algorithms for discrimination and determination of targets in complex samples. Taking advantages of its pattern-based detection strategy, the sensor array has great potential in the diagnosis of diseases such as tumors, , Alzheimer, , meningitis, and COVID-19. , Data processing plays a crucial role in obtaining accurate assay results from sensor arrays, and artificial intelligence (AI) based on machine learning (ML) has proven to be a reliable and efficient tool for processing large volumes of data .…”

Section: Introductionmentioning

confidence: 99%

Intelligent Identification of Cerebrospinal Fluid for the Diagnosis of Parkinson’s Disease

Chen,

Guo,

Zhuang

et al. 2024

Anal. Chem.

Self Cite

View full text Add to dashboard Cite

Cerebrospinal fluid (CSF) biomarkers are more sensitive than the Movement Disorder Society (MDS) criteria for detecting prodromal Parkinson's disease (PD). Early detection of PD provides the best chance for successful implementation of diseasemodifying treatments, making it crucial to effectively identify CSF extracted from PD patients or normal individuals. In this study, an intelligent sensor array was built by using three metal−organic frameworks (MOFs) that exhibited varying catalytic kinetics after reacting with potential protein markers. Machine learning algorithms were used to process fingerprint response patterns, allowing for qualitative and quantitative assessment of the proteins. The results were robust and capable of discriminating between PD and non-PD patients via CSF detection. The k-nearest neighbor regression algorithm was used to predict MDS scores with a minimum mean square error of 38.88. The intelligent MOF sensor array is expected to promote the detection of CSF biomarkers due to its ability to identify multiple targets and could be used in conjunction with MDS criteria and other techniques to diagnose PD more sensitively and selectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Intelligent Identification of Cerebrospinal Fluid for the Diagnosis of Parkinson’s Disease

Chen,

Guo,

Zhuang

et al. 2024

Anal. Chem.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In view of these limitations of traditional diagnostic systems, microfluidic-based point-of-care (POC) diagnostic platforms could be a solution to improving health surveillance and administration. Compared to the bulky conventional diagnostic systems, POC platforms are inexpensive, easy to use, fast, and operable with small sample volumes. − …”

Section: Introductionmentioning

confidence: 99%

Integrated Point-of-Care Immune Cell Analyzer with Rapid Blood Sample Reaction and Wide Field-of-View Detection

Imran,

Shourav,

Kim

2024

Anal. Chem.

View full text Add to dashboard Cite

The development of affordable, reliable, and rapid diagnostic devices is crucial for monitoring immunological responses using a drop of blood. However, conventional automated diagnostic devices typically involve expensive and impractical robotic fluid-handling approaches. Herein, we developed an integrated cell analyzer comprising a cylindrical sample cartridge connected to a direct current motor and a compact fluorescence imaging module. Sample mixing and loading are performed automatically by a programmable sequence of single motor rotation controlled by an Android application. Two distinct stained immune cell samples can be identified by using two types of fluorescence imaging modes. The effectiveness of mixing performance in antigen−antibody (Ag−Ab) reactions was assessed through a compound objective lens that collects weak fluorescence emitted by the cell membrane. Active mixing with bidirectional rotation of the cartridge in a confined space shortened the Ag−Ab reaction time by a factor of 3.3 and achieved cell counting with higher accuracy while reducing reagent consumption by 4 times compared to the conventional incubation method. High-intensity fluorescence images of cells labeled with a nucleic acid stain were acquired through a single-lens-based fluorescence imaging module with a large field of view (FOV) in an unconventional detection chamber with a curved substrate. Compared with a flat chamber, the curved detection chamber reduces the effects of field curvature and provides aberration-free wide-FOV images, even with a simple lens. Our integrated cell analyzer thus offers a practical and cost-effective solution for monitoring patient immune responses in pointof-care settings.

show abstract

A Sensitive MOF⊃Dye Hydrogel for Visual Recognition of Fluoroquinolones

Jiang,

Zhou,

Kong

et al. 2024

Advanced Optical Materials

View full text Add to dashboard Cite

Development of new multi‐ratiometric fluorescence probes has been a popular research field. This approach provides richer and more accurate information for the recognition of different substances which have similar chemical and physical properties. In this work, a ratiometric fluorescence sensor UIO‐66⊃FL/RhB is successfully constructed by incorporating fluorescein (FL) and rhodamine B (RhB) to the UIO‐66. With the addition of fluoroquinolones (FQs), the prepared UIO‐66⊃FL/RhB sensor can be used for the 2D emission‐fingerprint map, the linear discriminant analysis (LDA) and hierarchical clustering analysis (HCA) in recognition the presence of each FQs. The fluorescence probe offers a broad linear range (0‐8 µM) and a low detection limit (3.7 nM) in sensing ofloxacin. In addition, a smartphone‐assisted portable sensing platform and a portable UIO‐66⊃FL/RhB hydrogel test material are constructed successfully for screening before fluorescence detection. This study proposes a novel multi‐ratiometric fluorescence probe, which can recognize different FQs. Besides, the UIO‐66⊃FL/RhB‐based hydrogel beads are construction for screening before the detection of FQs, which established a promising strategy for the simple and accurate discrimination of FQs.

show abstract

Artificial neural network processed linear-light tristimulus and hue parameters of fluorescence for smartphone assisted point-of-care testing device

Cited by 10 publications

References 43 publications

Intelligent Identification of Cerebrospinal Fluid for the Diagnosis of Parkinson’s Disease

Intelligent Identification of Cerebrospinal Fluid for the Diagnosis of Parkinson’s Disease

Integrated Point-of-Care Immune Cell Analyzer with Rapid Blood Sample Reaction and Wide Field-of-View Detection

A Sensitive MOF⊃Dye Hydrogel for Visual Recognition of Fluoroquinolones

Contact Info

Product

Resources

About