http://rdf.ncbi.nlm.nih.gov/pubchem/patent/AU-2021105553-A4
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_03fd76e545b8f19cc2a6b4ffb005322b http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_5d9fead3aa19d5c30aca868b3601fc6e http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e29de530ea927d713bf11c70b0f02b57 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_46fab7083e1ca93c83ae5007b2520ffc http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d7a11d3bb7f6a9bc658d934af4d6dde5 http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_9ace00bde50afa5e71f0863f8ee71e1f http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_e0b0bf7d1ee978da377439e1b256a9cf |
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q2600-112 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q2600-158 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-80 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16B25-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/C12Q1-70 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/C12Q1-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16B25-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-80 |
filingDate | 2021-08-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2021-11-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a9a9db6deed59f9b4b187a20bb59bace http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b771f0fb7e1e025becc76a6bd44af486 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_20463970239421d86538c67bd6f92a40 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4711f70915a77109d50cfed91707d269 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9d97f2e824541eca2d3cc583be8b0067 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0ea29705d1cdc001a26eccbce2415706 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c9d6e0254e0edd58f09d980a7567bc21 |
publicationDate | 2021-11-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | AU-2021105553-A4 |
titleOfInvention | Method for identifying covid infection using gene expression level and machine learning model |
abstract | Method for identifying covid infection using gene expression level and nmachine learning model nABSTRACT nThe present invention is related to a method and system for remotely and automatically nidentifying the covid infection using gene expression level and machine learning model. In nthe present situation and outbreak of covid pandemic, where people are getting infected in nmass level, there is a need of a system which can identify the covid infection efficiently nwhile having sample in a speedy manner and automatically. The proposed invention nprovides a system which requires a smaller number of human resources and computing nresources also to quickly and automatically determines the covid infection and the system is nalso fully equipped and learn itself with the time as more samples are analyzed by the nsystem. The present invention comprises a central server which is based on machine nlearning model. The said central server is first trained using data related to gene expression nlevel and test cases. The proposed invention also comprises a sample scanner which is used nto scan the blood sample of the subject and the scanned data is sent to the central server. nThe said method is performed by a computing device having a processor, a memory, ninput/output device and communication unit. The sample scanner is attached to the said ncomputing device. As and when the peripheral blood cell sample of the subject is collected nand scanned using the sample scanner, the computing device is used to put additional ninformation of the subject/patient via user interface to the computing device. The ncollected/scanned data of the blood sample along with other details of the subject/patient nis transmitted to the central server via communication network. The said communication nnetwork may be wired or wireless communication network. The transmitted data is stored nin the database at the central server. The scanned data is analyzed and the gene expression nlevels of the sample subject is determined by the central server. The central server machine nthen compares the determined gene expression level with the standard gene expression nlevel via machine learning model. The said machine learning model then determines the nresult of comparison via the trained machine learning model and the difference of the gene nexpression level and the trained data helps the central server to reach the conclusion i.e., nwhether the sample subject is infected with the covid or not. The results are automatically nfed to the database along with the patient details which can be automatically fetched by the nsystem though user interface on any computing device. The results of the submitted sample nsubject are determined within a couple of minutes without much human intervention, nremotely and automatically. The said machine learning model is fully equipped to learn itself nbased on the data that is analyzed by the system, initial database related to gene expression nlevel and test cases. Thus, the said system greatly helps in this covid pandemic to quickly nand remotely provide the results of covid infection automatically. n1 |
priorityDate | 2021-08-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 118.