Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent analysis and assessment system for disease management in hospital

A technology of intelligent analysis and evaluation system, applied in the field of intelligent analysis and evaluation system of hospital disease management, can solve the problems of increasing model instability, artificially high cost treatment, deviation of judgment results, etc., to improve medical quality and operational efficiency, increase Patient Satisfaction, Improve the Effect of Clinical Research

Active Publication Date: 2015-09-30
中科厚立信息技术(成都)有限公司
View PDF5 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the calculation method based on CMI has its inherent deficiencies in evaluating medical quality, operating efficiency, and rational drug use. First, this model does not take into account the characteristics of the disease itself and other clinically relevant factors, and does not conform to medical laws; Secondly, the inflated cost of treatment itself caused by over-examination and treatment will also increase the instability of the model, resulting in biased judgment results
[0006] The existing hospital management system cannot rely on professional medical big data analysis to assist hospital management decision-making support, let alone realize the comparison of medical management data between different dimensions or the same dimension in lean hospital management, and cannot clarify the ranking and positioning of hospital management, including The position and ranking of comparison objects among diseases, doctors, departments, and hospitals cannot compare the advantages and disadvantages of objects in industries, which is not conducive to focusing on the development of superior specialties and making up for weaker disciplines
In addition, for hospital management and regulatory agencies, it is impossible to customize hospitals, clinical disciplines, discharge departments, disease DRGs, discharge time periods, primary and secondary diagnoses or operations, patient age, gender, category, and aggregate patient satisfaction in the region. For dynamic query, it is impossible to conduct compound comparison query through different combinations of conditions across hospitals, and it is difficult to carry out scientific and effective management and supervision of hospitals

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent analysis and assessment system for disease management in hospital
  • Intelligent analysis and assessment system for disease management in hospital
  • Intelligent analysis and assessment system for disease management in hospital

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0093] Example 1: Categorical variables for disease coding and population information

[0094]

[0095] Bacterial endocarditis complex group (ICD9 code)

[0096] The patient's basic demographic information and admission status variables (partial) are as follows:

[0097]

[0098]

[0099] S5: Within the same DRG cohort, statistically significant comorbidities and other categorical variables were pretreated by statistical tests for patient mortality, length of hospital stay, and cost.

[0100] S6: In the step of establishing a statistical model, regression analysis is performed on the model to quantify the degree of influence of variables;

[0101] Use the independent variables to quantitatively describe the predictive variables. In the disease risk adjustment, the predictive variables are patient mortality, hospitalization days and hospitalization costs, and the independent variables are combined complication variables and other variables; the regression analysis of ...

example 2

[0104] Example 2: DMIAES Mortality Model #22: (patient age ≥ 18) acute ischemic stroke and use of thrombolytic agents with severe complications (MSDRG 61), with complications (MSDRG 62), without complications ( MSDRG 63).

[0105] Data source: Memorial Hermann Hospital, Texas Medical Center, USA

[0106] Number of patients in modeling sample: 996 Sample time 7 / 1 / 2004-6 / 30 / 2014

[0107] Model Category: Logistic Regression Model

[0108] Explanatory variables for combined complications

correlation coefficient

intercept

-4.159

pressure on the brain

2.272

Female, aged 75-80 years

1.547

endotracheal tube

1.488

On a ventilator within 48 hours of admission

1.392

give up rescue

1.388

epilepsy

1.344

Acidosis

1.285

Female, over 85 years old

1.092

Brain edema

0.943

Arrhythmia

0.906

[0109] acute respiratory failure

0.322

atri...

example 3

[0117] Example 3: Model quality verification results and comparative analysis

[0118] 1. Mortality rate

[0119] Model #22: Acute Ischemic Stroke DRG 61,62,63

[0120] Data source: Memorial Hermann Hospital, Texas Medical Center, USA

[0121] Test Sample Patient Number: 66 Discharge Time 7 / 1 / 2004-6 / 30 / 2014

[0122] Comparing models: our DMIAES model and the American equivalent model (referred to as U model)

[0123] C-Index test of model fit: DMIAES model in modeling data: 0.890, DMIAES model in test data: 0.964, U model: 0.933.

[0124]

[0125]

[0126] Model #328: Multiple Surgical Trauma DRG 957,958,959

[0127] Data source: Memorial Hermann Hospital, Texas Medical Center, USA

[0128] Number of test samples: 212 Discharge time 7 / 1 / 2004-6 / 30 / 2014

[0129] Comparing models: our DMIAES model and the American equivalent model (referred to as U model)

[0130] C-Index test of model fit: DMIAES model in modeling data: 0.955, DMIAES model in test data: 0.987, U mod...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an intelligent analysis and assessment system for disease management in a hospital. A user inquiry terminal is used for in-hospital hospital lean management and contrast assessment among hospitals in terms of four dimensions including medical treatment quality, medical treatment efficiency, medical treatment benefit and satisfaction of patients according to assessment results of a hospital management quality assessment module. Various screening, free combination and 360-degree omni-directional dynamic contrast among different dimensions are realized, various screening, combination and omni-directional contrast in the same dimension are also realized, problems of hospital management, ranking and positioning are made clear by big data professional analysis of the hospital, hospital management policy supporting and hospital management contrast in different dimensions, comprehensive contrast and ranking in terms of ICD (international classification of diseases) diagnosis, diagnosis related grouping (DRG) diseases, clinical doctors, clinical departments and hospitals in a region are realized, advantages and disadvantages of contrasted objects in the industry are made clear, clear positioning can be realized, lean management of the hospital is promoted, and comprehensive competition capacity of the hospital is improved.

Description

technical field [0001] The invention relates to the fields of lean hospital quality management, medical big data analysis and hospital management decision support, in particular to an intelligent analysis and evaluation system for hospital disease management. Background technique [0002] Compared with foreign advanced hospital management, domestic hospital management is basically still in its infancy. It not only lacks high-quality management personnel, but also lacks scientific quality and efficiency evaluation standards, which leads to the aimless expansion of hospitals and the shortage of medical resources. Huge waste. In recent years, due to the rapid development of IT technology in domestic hospitals, the accumulation of raw data of patients and diseases has been preliminarily completed. Most of the data can only be stored in the hospital's data warehouse, wasting resources. If we can fully learn from the US government's successful model and excellent methodology of ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06Q10/06G06Q50/22
Inventor 李涛杨思坦陈霞陶金蓝
Owner 中科厚立信息技术(成都)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products