Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Application of complete blood count in predicting sars-cov-2 infection

A blood cell counting and sars-cov-2 technology, applied in the biological field, can solve problems such as unpublished data reports, and achieve great value, attractiveness, and easy-to-measure effects

Active Publication Date: 2022-07-22
YANTAI ZHIYI MEDICINE TECH CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] To predict whether a person is positive or negative for SARS-CoV-2 early in their disease, using machine learning to predict SARS-CoV-2 (positive / negative) test results from complete blood counts has not yet been published

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Application of complete blood count in predicting sars-cov-2 infection
  • Application of complete blood count in predicting sars-cov-2 infection
  • Application of complete blood count in predicting sars-cov-2 infection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Example 1, Patient Data Set Collection

[0032] The dataset includes anonymized data from patients during hospitalization at the Iserletta Albert Einstein Hospital in São Paulo, Brazil, who have obtained samples for SARS-CoV-2 rt-PCR and other laboratory studies. All data was collected in accordance with best international practice and anonymously. All clinical details were normalized to have zero mean and unit standard deviation.

[0033] The dataset includes RtPCR SARS-CoV-2 test results and normal total blood counts: hematocrit, hemoglobin, red blood cells (RBC), lymphocytes, mean platelet volume (MPV), white blood cells, basophils, neutrophils , mean corpuscular hemoglobin (MCH), eosinophils, platelets, mean corpuscular volume (MCV), monocytes, red blood cell distribution width (RBCDW) and mean corpuscular hemoglobin concentration (MCHC). 5644 individual patients examined between March 28, 2020 and April 3, 2020 were included in the published comprehensive dataset...

Embodiment 2

[0034] Example 2, Model Definition Classification

[0035] For our SARS-CoV-2 positive and negative classification, we employ a machine learning model for comparison that applies Decision Tree, K-Nearest Neighbors (KNN), Support Vector Machines (SVM) and Naive Bayes ( Bayes) for classification. A decision tree is a supervised automatic learning technique for solving classification and regression tasks that extracts rules from a set of objects represented by various attributes in the class; KNN is the simplest instance-based supervised classification One of the learning algorithms, the classification is based on the agreement between groups of the nearest k neighbors of an unknown object; the SVM classifier is statistically dependent on the dimension of Vapnik-Chervonenkis (VC) and obeys the soft boundary assumption; based on Naive Bayes The naive Bayesian classifier is particularly well suited for high-dimensional datasets, and given its apparent simplicity, the method can ...

Embodiment 3

[0044] Example 3, K-fold cross-validation

[0045] Perform K-fold cross-validation, a resampling procedure for evaluating machine learning models on limited data samples. This process has a single parameter called k, which represents the number of groups to split a given data sample into, and the process is called k-fold cross-validation. When choosing a specific value for k, it can be used in the reference model instead of k, taking K = 10, i.e. 10-fold cross-validation.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of biotechnology, in particular to the application of complete blood count in predicting SARS-CoV-2 infection. The invention implements various models, applies decision tree, K-nearest neighbor algorithm, support vector machine and Naive Bayes for classification , these models can predict SARS‑CoV‑2, among which the AUC of non-hospitalized patients in the decision tree model can reach up to 90%, and the data of comprehensive inpatients in the support vector machine model can reach 96%, the present invention not only uses from Data collected from normalized complete blood counts were also compared with studies on the same dataset but using different models, which showed that support vector machines and decision trees outperformed models used in published studies, which can be useful in disease Early stages of manifestations use biomarkers for initial screening between SARS‑CoV‑2 positivity and negativity, the different parameters of the complete blood count are of great value and appeal due to their simplicity and easily measurable parameters.

Description

technical field [0001] The invention relates to the field of biotechnology, in particular to the application of complete blood count in predicting SARS-CoV-2 infection. Background technique [0002] The COVID-19 strain has caused public health concerns since December 2019. Infection causes fever, cough, exhaustion, and moderate to severe respiratory symptoms, which, if severe, can lead to death. On March 11, the World Health Organization declared the virus outbreak a pandemic. [0003] To confirm whether people with COVID-19 have successfully escaped SARS-CoV-2, methods based on reverse transcription polymerase chain reaction (rt-PCR) have become the main standard. However, a combination of factors, including insufficient tools for rt-PCR to monitor the presence of SARS-CoV-2, hinder large-scale patient studies. The conventional test used was 80 percent accurate compared to results from chest CT scans, also depending on the degree of viral shedding specific to each person...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G01N15/10G06K9/62G06N20/00G16H10/60
CPCG01N15/10G06N20/00G16H10/60G01N2015/1006G06F18/214
Inventor 魏冬青法哈德·胡玛云王恒王艳菁
Owner YANTAI ZHIYI MEDICINE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com