Inpatient medical management quality assessment method
A technology for medical management and inpatients, applied in the field of lean hospital quality management, can solve problems such as increased model instability, deviation of judgment results, non-compliance with medical laws, etc., and achieve the effect of improving the level of medical quality management
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example 1
[0149] Example 1: Correlation Analysis of Predictor Variables in Renal Failure Mortality Model
[0150] Model #218: DRG682,683,684
[0151] Data source: Memorial Hermann Hospital, Texas Medical Center, USA
[0152] Number of patient samples: 2587 Discharge time 7 / 1 / 2004-6 / 30 / 2014
[0153] Number of Significant Variables Filtered: 37
[0154] Number of strongly correlated variables: 4
[0155] Statistical method: VarianceInflationFactor (VIF)
[0156]
[0157] Note: From the 37 variables that were screened out, the strong correlation test was carried out. The value below is the VIF value, and the variables with VIF>5 are marked.
example 2
[0158] Example 2: Importance list of predictor variables in the mortality model for patients with renal failure
[0159] Model #218: DRG682,683,684
[0160] Data source: Memorial Hermann Hospital, Texas Medical Center, USA
[0161] Number of patient samples: 2587 Discharge time 7 / 1 / 2004-6 / 30 / 2014
[0162] Total number of model variables: 280
[0163] Number of Significant Variables Filtered: 37
[0164] Statistical method: LASSO
[0165]
[0166] Note: The value below the variable represents the importance of the variable, and the higher the value, the greater the impact of the variable on the model.
example 3
[0167] Example 3: Predictor Variable Selection for a Renal Failure Mortality Model
[0168] Model #218: DRG682,683,684
[0169] Data source: Memorial Hermann Hospital, Texas Medical Center, USA
[0170] Number of patient samples: 2587 Discharge time 7 / 1 / 2004-6 / 30 / 2014
[0171] Total number of model variables: 280
[0172] Number of Significant Variables Filtered: 37
[0173] Statistical method: LASSO
[0174]
[0175]
[0176] Note: Combining the model and clinical experience, the variable rhabdomyolysis, chronic liver disease and later variables were deleted; the strongly correlated variable-organ internal tube was 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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com