Disease risk regulation model establishment method
A technology for model establishment and disease risk, applied in the field of disease risk adjustment model establishment, which can solve the problems of artificially high cost treatment, biased judgment results, failure to consider disease characteristics and other clinically relevant influencing factors, and avoid overfitting. , the effect of improving accuracy and reliability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example
[0075] Example 1: Correlation analysis of predictive variables in the mortality model of renal failure
[0076] Model #218: DRG 682,683,684
[0077] Data source: Herman Memorial Hospital, Texas Medical Center
[0078] Number of patient samples: 2587 Discharge time 7 / 1 / 2004-6 / 30 / 2014
[0079] Number of significant variables selected: 37
[0080] Number of strongly correlated variables: 4
[0081] Statistical method: Variance Inflation Factor (VIF)
[0082]
[0083] Note: The strong correlation test is performed from the 37 variables selected. The lower value is the VIF value, and the variables with VIF>5 are marked.
Example
[0084] Example 2: Importance list of predictors of mortality model for patients with renal failure
[0085] Model #218: DRG 682,683,684
[0086] Data source: Herman Memorial Hospital, Texas Medical Center
[0087] Number of patient samples: 2587 Discharge time 7 / 1 / 2004-6 / 30 / 2014
[0088] Total model variables: 280
[0089] Number of significant variables selected: 37
[0090] Statistical method: LASSO
[0091]
[0092] Note: The value below the variable represents the importance of the variable. The higher the value, the greater the influence of the variable on the model.
Example
[0093] Example 3: Selection of predictors for the mortality model of renal failure
[0094] Model #218: DRG 682,683,684
[0095] Data source: Herman Memorial Hospital, Texas Medical Center
[0096] Number of patient samples: 2587 Discharge time 7 / 1 / 2004-6 / 30 / 2014
[0097] Total model variables: 280
[0098] Number of significant variables selected: 37
[0099] Statistical method: LASSO
[0100]
[0101]
[0102] Note: Combining the model and clinical experience, the variables rhabdomyolysis, chronic liver disease and later variables were deleted; the strongly correlated variable-organ internal ducts were also deleted.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap