Advanced searches left 3/3
Search only database of 8 mil and more summaries

Biocheck Cardiac-1 Crp Rapid Test Model Bc-804114

Summarized by PlexPage
Last Updated: 02 July 2021

* If you want to update the article please login/register

General | Latest Info

Imagine you are a physician or paramedic called to emergency. Patient presented with acute chest pain, shortness of breath, maybe nausea. It looks like a heart attack, but it can also be acute heart failure, cocaine abuse, something as banal as indigestion, or else. 1 Perhaps you can record electrocardiogram on site to help you differentiate, Perhaps you cannot. What you know is that in the case of heart attack, time is muscle and time waste is muscle lose! 2 by intervening promptly you can save a patient's life and limit the amount of damage to his or her heart. 3 Luckily, you have a kit of Troponin rapid tests at hand. You prick the patient's finger, apply a bit of blood to the device and yes, you see test line appear within minutes, telling you that with high probability this is a heart attack. You can start managing patients for adequate treatment immediately. A heart attack is a serious emergency that requires immediate medical attention. 1 Most heart attacks happen suddenly when one of the arteries leading to the heart becomes Block, usually by blood clot, and cuts off blood flow. Lack of blood restricts supply of oxygen and nutrients. Without these, cells of the heart start to die. That is why every second counts when it comes to heart attack treatment. Extensive blockage, especially in major blood vessel, can cause large heart attack. A large heart attack that is not treated early can lead to heart failure, life-threatening condition. Coronary artery disease-build-up over time of plaque from fat and other substances that make arteries grow narrower or harder-is most often at the root of MI. Rapid diagnosis of heart attack is critical for early treatment. The extent of permanent damage to the heart resulting from occlusion of the coronary artery can largely be avoided by timely reperfusion therapy. Reperfusion therapy includes drugs and surgery. Drugs apply to counter MI dissolve clot blocking artery. Blood flow can also be restored surgically by opening up artery at clogged site or grafting new artery around blockage. 6 rapid diagnosis of acute MI is critical for early treatment. Unfortunately, typical symptoms associated with MI-acute chest pain often accompanied with pain in the upper body, shortness of breath, nausea, tiredness, sweating-are not necessarily present in each case, nor are they unique to this condition. 7 clinical assessment, even when combined with electrocardiogram, is thus often not sufficient to diagnose or exclude MI. Blood tests to measure concentration of cardiac Troponin form cornerstone for early diagnosis of MI. 8 Troponin is a regulatory protein complex involved in the functionality of muscle cells. It is composed of three subunits: Troponin I, T and C. 9 Heart muscle cells express isoforms of cTnI and cTnT that are structurally distinct from their skeletal counterparts.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions

Introduction

Table

LOINCLOINC Display Name
76485-2CRP
48421-2CRP (BldC)
1988-5CRP
14634-0CRP
11039-5CRP Ql

Computation has great potential for improving diagnostics. By identifying complex and nonlinear patterns from noisy inputs, computational tools present an opportunity for automated and robust inference of medical data. For example, several studies have show deep learning as a method to automatically identify tumors from image, potentially enabling diagnostics in low-resource settings that lack trained diagnostician 1-3. Additionally, computational solutions have been demonstrated earlier in diagnostics pipelines to virtually stain pathology slides and enhance image resolution through use of convolutional neural networks 4-6. Though much of this recent success is within the field of imaging, diagnostics that rely on biosensing can similarly leverage computational tools to improve sensing results and design future systems. Point-of-care testing can especially benefit from computational sensing approaches. Due to their low-cost materials, compact designs, and requirement for rapid and user-friendly operation, POC tests are often less accurate when compared to traditional laboratory tests and assay 7-12. For example, paper-base immunoassays such as rapid diagnostic tests offer affordable and user-friendly class of POC tests which have been developed for malaria, HIV-1 / 2, and cancer screening, among other uses 13-17. However, these RDTs lack sensitivity and specificity needed for certain diagnostic applications largely due to issues of reagent stability, fabrication, and operational variability, as well as matrix effects present in complex samples such as blood 15 16 18. Additionally, well-know competitive binding phenomenon called hook-effect can lead to false reporting of results, specifically in instances where sensing analyte can be present over large dynamic range 19-24. Therefore, computational tools alongside portable and cost-effective assay readers present a unique opportunity to compensate for some of these constraints 25-34. By quantifying signals generated on paper-base substrates, machine learning algorithms have the potential to significantly improve performance of POC sensors, without significant hardware cost or increasing complexity of assay protocol. As demonstration of this emerging opportunity at the intersection of computational sensing and machine learning, we report computational paper-base vertical flow assay for cost-effective high-sensitivity C-reactive protein testing, also referred to as cardiac CRP testing 35. Here, we implement a deep learning-base computational sensing framework to jointly develop CRP quantification algorithm with multiplexed sensing membrane of VFA, selecting the most robust subset of sensing channels via feature selection methods in order to accurately infer CRP concentration. Recent work by our group investigates the use of neural networks for POC Lyme disease diagnostics using the VFA format, achieving competitive results compared to gold-standard clinical testing. 32 However, in contrast to this previous report, here we uniquely demonstrate precise quantification of protein biomarker as opposed to binary decision, incorporation of test fabrication information into learning model to improve quantitative sensing performance, and significantly extend sensing dynamic range through computational analysis of multiplexed immunoreaction spots, all targeting same analyte in uniquely different ways.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions

Results

Table

LOINCLOINC Display Name
76485-2CRP
48421-2CRP (BldC)
1988-5CRP
14634-0CRP
11039-5CRP Ql

From selected samples, 17 were in the low-risk group, 19 were in the moderate-risk group, and 26 were in the high-risk group. Four samples had hs-CRP levels > 10 mg / liter, indicating unspecific inflammation. All applied POC rapid tests go technically well and deliver results feasible for immediate visual analysis. In general, all three investigators had high agreement between their reading and the results from laboratory analysis. One investigator classified 2 / 66 samples to be in a higher risk group than indicated by reference measurement. Two other investigators classified four samples into a higher risk group. Results of laboratory reference values and readings by better investigator are provided in Figure 2. When combining moderate-and high-risk group samples, all three investigators classify all samples to be in either of groups achieving sensitivity for elevated risk assessment of 100 %. All samples with unspecifically elevated hs-CRP were correctly classified by all investigators. One investigator wrongly classified one of samples < 1 mg / liter to be in moderate-risk groups achieving a specificity of 95 %.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions

Discussion

Table

LOINCLOINC Display Name
76485-2CRP
48421-2CRP (BldC)
1988-5CRP
14634-0CRP
11039-5CRP Ql

Our VFA-base hsCRP test benefits from machine learning in several ways. Firstly, using neural networks to select optimal spots and infer analyte concentration from highly multiplexed sensing channels greatly improves our quantification accuracy when compared to eg, standard multi-variable regression, which yields an average % CV of 47 % with an R 2 value of 0. 79. Deep learning algorithms such as fully-connect network architecture used in this work, contain a much larger number of learned / trained coefficients along with multiple layers of linear operations and non-linear activation functions when compared to standard linear regression models. These added degrees of freedom enable neural networks to converge to robust models which can learn non-obvious patterns from confounding set of variables, making them powerful computational tool for assay interpretation and calibration. However, one concern with deep learning approaches is the possibility of overfitting to give training set, especially in the instance of limited data. To mitigate this issue, we incorporate regularization terms in hyper-parameter search, and find via cross-validation that the lowest error model employs a maximum degree of dropout regularization of 50 51. However, we observe better quantification results in blindly test samples when compared to cross validation analysis, suggesting that our model appropriately generalize over the operational range of hsCRP sensor. Secondly, by incorporating fabrication information using RID and FID input features, neural network was able to learn from batch-specific patterns and signals. This resulted in 12. 9 % reduction in blindly tested MSLE when compared to the performance of network train without these fabrication batch input features. Similarly, incorporating fabrication information reduces the overall % CV from 16. 6 % to 11. 2 % and increase R 2 value from 0. 92 to 0. 95. It is important to note that these VFA tests were fabricated without the use of industry-grade production equipment such as humidity and temperature control chambers, and in addition, several fabrication steps involve manual assembly. Take together, these simple input features can benefit performance and quality assurance of future computational POC tests following the methodology of this work. For example, fabrication information could be included for each test in form of Quick Response code or could alternatively be logged into GUI by user before measurement data is sent to the quantification network. Another benefit of our computational VFA platform is mitigation of false sensor Response due to hook effect. The VFA format Importantly enables rapid computational analysis of highly multiplexed immunoreaction spots with minimal cross talk or interference among spots, which is inevitable in the case of standard lateral flow assays or RDTs. Multiplexed information reported by different spotting conditions therefore allows for unique combinatorial signals to be generated over a large dynamic range. 3b. The hook effect is clearly seen in our raw sensor data, exhibited by capture antibody Ab condition see Supplementary Figs. 2 and 3, illustrating how this condition alone can lead to false reporting of high analyte concentrations, ie in case of ACUTE inflammation.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions.

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions

Sources

* Please keep in mind that all text is machine-generated, we do not bear any responsibility, and you should always get advice from professionals before taking any actions

logo

Plex.page is an Online Knowledge, where all the summaries are written by a machine. We aim to collect all the knowledge the World Wide Web has to offer.

Partners:
Nvidia inception logo

© All rights reserved
2021 made by Algoritmi Vision Inc.

If you believe that any of the summaries on our website lead to misinformation, don't hesitate to contact us. We will immediately review it and remove the summaries if necessary.

If your domain is listed as one of the sources on any summary, you can consider participating in the "Online Knowledge" program, if you want to proceed, please follow these instructions to apply.
However, if you still want us to remove all links leading to your domain from Plex.page and never use your website as a source, please follow these instructions.