http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113257422-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_aaadcd534c1edeab62f85ec7991cb759 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-241 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-30 |
filingDate | 2021-06-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7435f1e92b5f3888436f311610af9239 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_43547dfb449acfd87e2466d01d688e12 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8cbb319fe5cab22126f72aed6c9fcf48 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_eb039547b91fa9bc4b094ab02d869223 |
publicationDate | 2021-08-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113257422-A |
titleOfInvention | Construction method and system of disease prediction model based on glucose metabolism data |
abstract | The present invention relates to a method for constructing a disease prediction model based on glucose metabolism data, comprising the following steps: step S1: acquiring glucose metabolism data of a sample population, and constructing a first sample data set; step S2: comparing the obtained initial sample data The set is preprocessed to obtain a second sample set; Step S3: the second sample set is sorted and screened by the LightGBM algorithm for feature importance, and the top N important features are extracted to form a third sample set, and Divided into training set and verification set according to the preset ratio; Step S4: take the training set as the input of the LightGBM model, train the LightGBM model until the deviation between its output value and the true value is lower than the threshold, and obtain a disease prediction model. The present invention effectively improves the model accuracy and generalization ability, can quickly predict the probability of the test subject suffering from a disease related to abnormal glucose metabolism, and saves tense medical resources. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113851216-A |
priorityDate | 2021-06-04-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 156.