KR20240065904A - Falling risk prevention system and method using electric medical record - Google Patents

Abstract

The present invention relates to a fall risk prevention system, and more specifically, a fall risk prevention system using electronic medical records that can effectively prevent the risk of falls by predicting a patient's fall and calculating the risk using electronic medical records. It's about. A fall risk prevention system using electronic medical records according to the present invention includes a data storage unit storing patient medical record data; a data extraction unit that extracts necessary medical records from the data storage unit; A data preprocessing unit that preprocesses the extracted data for analysis; a data classification unit that classifies preprocessed data; A data analysis unit that analyzes classified data and calculates a fall risk score; and a control unit that controls the operations of the data extraction unit, data preprocessing unit, data classification unit, and data analysis unit.

Description

Falling risk prevention system and method using electric medical record}

The present invention relates to a fall risk prevention system and prevention method. More specifically, the present invention relates to a fall risk prevention system and method, and more specifically, to a fall risk using electronic medical records that can effectively prevent the risk of falls by predicting a patient's fall and calculating the risk using electronic medical records. It is about risk prevention systems and prevention methods.

Currently, various fall risk prevention systems are being developed and used in clinical settings to predict and manage patients who fall.

Representative fall risk assessment tools include Morse Fall Risk (hereinafter referred to as 'MFS'), Hendrich Ⅱ, and St Thomas's Risk Assessment Tool in Falling Elderly Inpatient (hereinafter referred to as 'STRATIFY').

The evaluation items of the MFS assessment tool are ① history of falls in the past 3 months (past fall experience), ② secondary diagnosis (subdiagnosis), ③ walking assistance (whether or not to use devices), ④ intravenous fluid therapy/heparin lock, ⑤ gait/mobility ( It consists of gait disturbance and weakness), ⑥ consciousness/mental state, and each item is given a minimum score of 10 points and a maximum score of 20 points. If the score is 0 to 24 points, it is classified as having almost no risk of falling, if it is 25 to 44 points, it is classified as having a low risk of falling, and if it is 45 to 125 points, it is classified as having a high risk of falling. If the risk of falling is high, the patient is classified into a high-risk group and managed separately.

The evaluation items of the Hendrich Ⅱ assessment tool are ① confusion/disorientation/impulsivity, ② depression, ③ changes in urination/defecation, ④ dizziness/lightheadedness, and ⑤ for men, whether or not they are taking psychotropic drugs (benzodiazepines) and when they get up from their seats. It is composed of 0 to 4 points for each item. If the score is 5 or more, you are classified as a fall risk group.

The evaluation items of the STRATIFY assessment tool consist of ① being hospitalized due to a fall/falling in the hospital, ② disorientation/dizziness, ③ visual impairment, ④ frequency of using the bathroom, and ⑤ decline in mobility score. The score is given on a scale of 1 to 10, and if the score is 2 or higher, the patient is classified as a fall risk patient.

The risk of falling using the above assessment tools is measured daily or when necessary through surveys or simple tests, and the results are applied to nursing.

Currently, in clinical practice, the tools described above are used to predict and manage patients who fall, but not only is there no tool that can consistently maintain high predictive validity, but it has the disadvantage of having to be evaluated through separate tests (sitting and standing, etc.). there is.

Accordingly, the need for research and development to overcome the shortcomings and limitations of currently used fall risk assessment tools and to increase fall risk prediction is continuously being raised.

The present invention was developed to solve the problems of the prior art as described above, and maintains consistently high predictive validity for predicting fall risk, and does not require a separate test to predict fall risk, thereby effectively preventing fall risk. The purpose is to provide a fall risk prevention system and prevention method.

In particular, the present invention is a fall risk assessment tool that accurately and objectively reflects patient data measured every day to confirm the risk of falling, utilizing electronic medical records that allow qualitatively written contents to be generated into quantitative numbers. The purpose is to provide a fall risk prevention system and prevention method.

A fall risk prevention system using electronic medical records according to a preferred embodiment of the present invention for achieving the above object includes: a data storage unit storing patient medical record data; a data extraction unit that extracts necessary medical records from the data storage unit; A data preprocessing unit that preprocesses the extracted data for analysis; a data classification unit that classifies preprocessed data; A data analysis unit that analyzes classified data and calculates a fall risk score; and a control unit that controls the operations of the data extraction unit, data preprocessing unit, data classification unit, and data analysis unit.

Logistic regression analysis is used in the data analysis department.

The fall risk score calculation performed in the data analysis department uses the Exponential for each variable calculated through logistic regression to calculate the odds ratio, uses this as the weight of the variable, and calculates the fall risk based on Equation 1. I guess this.

[Equation 1]

A fall risk prevention method using electronic medical records according to a preferred embodiment of the present invention to achieve the above object includes the steps of: (a) extracting data from a data storage unit where the patient's medical record data is stored; (b) a data preprocessing step of preprocessing the extracted data for analysis; (c) classifying the preprocessed data; and (d) calculating a fall risk score using the classified data.

Calculation of the fall risk score in step (d) uses the Exponential for each variable calculated through logistic regression to calculate the odds ratio and use it as the weight of the variable, based on Equation 1 above. Predict the risk of falling.

[Equation 1]

In step (c), the preprocessed data is classified into training/verification data at a ratio of 8:2, and in step (d), statistical significance is analyzed using the training data.

In step (d), variables for which significance has not been tested are deleted and statistical significance analysis is performed again to calculate β for each variable.

According to the fall risk prevention system and prevention method using electronic medical records of the present invention, the fall risk prediction can be maintained consistently high by accurately and objectively reflecting patient data measured every day to confirm the risk of falling.

In addition, according to the present invention, the weight can be changed at any time by utilizing patient data that is added in real time or regularly and can be reflected without any special code modification. Therefore, the time and cost used for separate maintenance and repairs can be reduced.

In addition, by displaying the fall risk and predicted fall probability estimated using a calculation formula on the interface used within the hospital, medical staff can use it to determine the patient's fall risk and provide care.

Figure 1 is a configuration diagram of a fall risk prevention system utilizing electronic medical records according to a preferred embodiment of the present invention.
Figure 2 is a fall risk prevention process using electronic medical records according to a preferred embodiment of the present invention.
Figure 3 is a diagram showing preprocessing items performed in the data preprocessing step.

Hereinafter, a fall risk prevention system and method using electronic medical records according to a preferred embodiment of the present invention will be described in detail with reference to the attached drawings.

Figure 1 of the attached drawing is a configuration diagram of a fall risk prevention system utilizing electronic medical records according to a preferred embodiment of the present invention.

The fall risk prevention system using electronic medical records according to the present invention includes a data storage unit (10), a data extraction unit (20), a data preprocessing unit (30), a data classification unit (40), and a data analysis unit (50). and a control unit 60.

The data storage unit 10 stores various medical record data of hospitalized patients. The data storage unit 10 may be part of an electronic medical record system being built by a medical institution.

Data extracted through the data extraction unit 20 includes basic measurement information such as patient registration number, height, weight, age, stab wound code, and injury code, and the patient's fall history for the past 3 months as measured by the fall risk tool (MFS). (past fall experience), secondary diagnosis (sub-diagnosis), walking assistance (use of devices or not), intravenous fluid therapy/herapin lock, gait/mobility (gait disturbance and frailty), consciousness/mental status and nursing needs, tools Measured/written by urination/defecation, respiratory care, non-invasive oxygen administration, position change, moving out of bed, meal intake, presence of bedsores and nutritional status through bedsore tool, pain intensity extracted through pain tool, and prescribed to the patient every day. drug extraction, etc. Extraction is done through the API reflected on the development server.

In the data pre-processing unit 30, the extracted data is pre-processed by a method such as dummy for analysis.

In the data classification unit 40, the preprocessed data is classified into training/verification data.

The data analysis unit 50 calculates a fall risk score using a logistic regression method, a regression analysis method using log rose, etc.

The control unit 60 automatically controls the operations of the data extraction unit 20, data preprocessing unit 30, data classification unit 40, and data analysis unit 50.

Figure 2 of the attached drawings is a fall risk prevention process using electronic medical records according to a preferred embodiment of the present invention, and Figure 3 is a diagram showing pre-processing items performed in the data pre-processing step.

The fall risk prevention method using electronic medical records according to a preferred embodiment of the present invention includes a data collection step (S10), a data preprocessing step (S20), a variable selection step (S30), a machine learning step (S40), and statistical significance. It includes a test step (S50), a variable deletion step for which significance is not tested (S60), and a fall risk score calculation step (S70).

In the data collection step (S10), the hospital's database (DB) is accessed to extract necessary data.

In the data preprocessing step (S20), the extracted data is preprocessed so that it can be used for research. All contents extracted as strings, such as nursing care tools, fall risk tools, bedsores, and pain, are converted into dummies. Calculate the Charlson Comorbidity Index (CCI) using major illness and injury codes. The drugs taken are clustered using the ATC code and then dummied.

In the variable selection step (S30), data on fall patients and non-fall patients are extracted/collected/preprocessed for machine learning, and classified into training/verification data at a ratio of 8:2.

In the machine learning step (S40), logistic regression analysis, which is used when the dependent variable is categorical, is utilized. Logistic regression is a statistical model used to determine the probability of an event occurring, showing relationships between characteristics and calculating the probability of a specific outcome.

In the statistical significance test step (S50), the prediction rate is confirmed through machine learning and the significance of each variable is tested. Analyze statistical significance using the training data set used in the previous step.

In the step of deleting variables whose significance has not been tested (S60), variables whose significance has not been tested in the previous step are deleted and machine learning and statistical significance analysis are performed again.

In the fall risk score calculation step (S70), the odds ratio is calculated by using the Exponential for each variable calculated through logistic regression analysis, and this is used as the weight of the variable. The regression analysis equation using log odds is shown in Equation 1 below.

As described above, the fall risk prevention system and prevention method using electronic medical records according to a preferred embodiment of the present invention have been described in detail with reference to the attached drawings, but the present invention is not limited to the above-described embodiment, and the scope of the patent claims Various modifications can be made within it.

10: data storage unit 20: data extraction unit
30: data preprocessing unit 40: data classification unit
50: data analysis unit 60: control unit
S10: Data collection phase
S20: Data preprocessing step
S30: Variable selection step
S40: Machine Learning Phase
S50: Statistical significance test step
S60: Step of deleting variables whose significance is not tested
S70: Fall risk score calculation step

Claims (7)

A data storage unit where the patient's medical record data is stored;
a data extraction unit that extracts necessary medical records from the data storage unit;
A data preprocessing unit that preprocesses the extracted data for analysis;
A data classification unit that classifies preprocessed data;
A data analysis unit that analyzes classified data and calculates a fall risk score; and
A fall risk prevention system utilizing electronic medical records, including a control unit that controls the operation of the data extraction unit, data preprocessing unit, data classification unit, and data analysis unit. According to claim 1,
A fall risk prevention system using electronic medical records, in which the data analysis department uses logistic regression analysis. According to clause 2,
The fall risk score calculation performed in the data analysis department uses the Exponential for each variable calculated through the logistic regression analysis to calculate an odds ratio and use it as a weight for the variable.
A fall risk prevention system using electronic medical records that estimates the fall risk based on Equation 1.
[Equation 1]
(a) extracting data from a data storage unit where the patient's medical record data is stored;
(b) a data preprocessing step of preprocessing the extracted data for analysis;
(c) classifying the preprocessed data; and
(d) Calculating a fall risk score using classified data; a fall risk prevention method using electronic medical records. According to clause 4,
The fall risk score calculation performed in step (d) above is,
An odds ratio is calculated using the Exponential for each variable calculated through logistic regression analysis, and this is used as the weight of the variable. Electronic medical records are used to predict the risk of falling based on Equation 1. How to prevent the risk of falling.
[Equation 1]
According to clause 5,
In step (c), the preprocessed data is classified into training/verification data at a ratio of 8:2, and in step (d), electronic medical records are used to analyze statistical significance using the training data. How to prevent the risk of falling. According to clause 6,
In step (d), variables for which significance has not been tested are deleted and statistical significance analysis is performed again to calculate β for each variable. A fall risk prevention method using electronic medical records.