Unlock instant, AI-driven research and patent intelligence for your innovation.

A method for complementing the missing data of medical indicators in patients with peptic ulcer

A technology for peptic ulcer and missing data, which is applied in the medical field and can solve problems such as only considering time series

Active Publication Date: 2021-09-14
SUN YAT SEN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The shortcoming of this method is that it only considers the dimension of time series

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
  • A method for complementing the missing data of medical indicators in patients with peptic ulcer
  • A method for complementing the missing data of medical indicators in patients with peptic ulcer
  • A method for complementing the missing data of medical indicators in patients with peptic ulcer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Such as figure 1 , figure 2 , image 3 As shown, a method for completing the missing data of medical indicators of peptic ulcer patients includes the following steps:

[0031] Step S1: read the measurement data of the ulcer patient,

[0032] Step S2: Preprocessing the collected data;

[0033] The main purpose of medical big data preprocessing is to reduce the impact of noisy data on the overall data. Noisy data includes the following types, errors in the entry process, outliers that deviate from most data, and data duplication caused by the merger of heterogeneous data sources.

[0034] In this example, the statistical method is used to detect numerical attributes, and the possible range interval of the attribute is considered to identify outliers, or clustering can be used to identify outliers. The outlier data are then mode corrected.

[0035] Step S201: time aligning the data

[0036] The time of each patient's visit is different. The principle of alignment is...

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 present invention relates to a method for complementing the missing data of medical indicators of patients with peptic ulcer. The present invention decomposes the original sparse matrix into the product of two matrices with correlation, which overcomes the problem that only one dimension is considered in the prior art for complementing. The shortcoming of comprehensiveness not only considers the dimension of correlation between patients, but also considers the dimension of correlation between time series; the present invention uses the method of matrix decomposition to complete the missing data of measurement indicators of ulcer patients within one year, increasing The accuracy of the data is guaranteed, which can provide a reference for doctors to make clinical decisions, and can also use the complete medical data to monitor the patient's condition in time to improve the cure rate of the patient.

Description

technical field [0001] The invention relates to the medical field, and more specifically, to a method for supplementing missing data of medical indicators of patients with peptic ulcer. Background technique [0002] The medical record records the patient's historical health data, including the patient's basic situation, each visit to the doctor, medication and treatment, etc. In the era of big data, rational mining of information hidden behind a large number of medical records can help doctors make clinical decisions. However, due to the different visit times of different patients and the specificity of each person's body in medical big data, medical indicators that change over time generally have the problem of missing data. Therefore, it is an important research direction to complete missing indicators in medical records, and many data completion algorithms have emerged. [0003] In 2013, Liu et al. proposed a tensor completion method for estimating missing values ​​in v...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/20G16H50/70
CPCG16H50/20G16H50/70
Inventor 贾晓玉马锦华
Owner SUN YAT SEN UNIV