Application of whole blood cell counting in prediction of 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A blood cell counting and sars-cov-2 technology, applied in the biological field, can solve problems such as unpublished data reports
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031]Example 1, Patient Data Set Collection
[0032]The data sets include anonymous data for patients during hospitalization in Sao Paulo Hospital, Brazil, which have been studied by SARS-COV-2RT-PCR and other laboratory studies. All data is collected in accordance with the best international practice and anonymous. In order to have the difference between zero and the unit standard, all clinical details were standardized.
[0033]The data set includes RTPCR SARS-COV-2 test results and normal total blood cell count: blood cell accompanying, hemoglobin, red blood cell (RBC), lymphocyte, average platelet volume (MPV), white blood cells, basophils, neutrophils , Mean red blood cell hemoglobin (MCH), eosinophil, platelet, melocyte volume (MCV), monocytes, red blood cell distribution width (RBCDW) and flat erytocyte hemoglobin concentration (MCHC). 5,644 individual patients inspected between March 28, 2020, January 3, 2020, included the released integrated data set, 597 whole blood cell count ...
Embodiment 2
[0034]Example 2, Model definition classification
[0035]For our SARS-COV-2 positive and negative classification, we use machine learning models to compare, machine learning models, Decision Tree, K N-neighbor Algorithm (KNN), Support Vector Machine (SVM) and Simple Bayes (Bayes) Classified. Decision tree is an automatic learning technology for resolving classification and regression tasks. It extracts rules from a set of objects, which are represented by various attributes in the class; KNN is the easiest way to instance-based supervision classification One of the learning algorithms, classify the consistency between the recent K neighbors of unknown objects; the SVM classifier depends on the dimension of Vapnik-Chervonenkis (VC), and follows soft boundary assumptions; Springs, simple Bayesian classifiers are particularly suitable for high-dimensional data sets, taking into account its obvious simplicity, the method can be more complex classification system.
[0036]The performance of ea...
Embodiment 3
[0044]Example 3, k (double cross-validation
[0045]K / fold cross-validation is performed, which is a re-sample program for evaluating a machine learning model on a limited data sample. The process has a single parameter called K, which indicates the number of groups that split a given data sample, which is referred to as k-fold cross-validation. When a particular value for K is selected, it can be used instead of K in the reference model, taking K = 10, i.e., 10 times cross-validation.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More