KR20240065904A - Falling risk prevention system and method using electric medical record - Google Patents
Falling risk prevention system and method using electric medical record Download PDFInfo
- Publication number
- KR20240065904A KR20240065904A KR1020220147184A KR20220147184A KR20240065904A KR 20240065904 A KR20240065904 A KR 20240065904A KR 1020220147184 A KR1020220147184 A KR 1020220147184A KR 20220147184 A KR20220147184 A KR 20220147184A KR 20240065904 A KR20240065904 A KR 20240065904A
- Authority
- KR
- South Korea
- Prior art keywords
- data
- unit
- fall risk
- medical records
- analysis
- Prior art date
Links
- 230000002265 prevention Effects 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000007405 data analysis Methods 0.000 claims abstract description 14
- 238000013500 data storage Methods 0.000 claims abstract description 12
- 238000013075 data extraction Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 239000000284 extract Substances 0.000 claims abstract description 3
- 238000007477 logistic regression Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 208000004210 Pressure Ulcer Diseases 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 208000002173 dizziness Diseases 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 3
- 230000037230 mobility Effects 0.000 description 3
- 230000000474 nursing effect Effects 0.000 description 3
- 206010017577 Gait disturbance Diseases 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000013872 defecation Effects 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000005021 gait Effects 0.000 description 2
- 229920000669 heparin Polymers 0.000 description 2
- 239000003978 infusion fluid Substances 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 230000027939 micturition Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 238000000551 statistical hypothesis test Methods 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 208000036119 Frailty Diseases 0.000 description 1
- HTTJABKRGRZYRN-UHFFFAOYSA-N Heparin Chemical compound OC1C(NC(=O)C)C(O)OC(COS(O)(=O)=O)C1OC1C(OS(O)(=O)=O)C(O)C(OC2C(C(OS(O)(=O)=O)C(OC3C(C(O)C(O)C(O3)C(O)=O)OS(O)(=O)=O)C(CO)O2)NS(O)(=O)=O)C(C(O)=O)O1 HTTJABKRGRZYRN-UHFFFAOYSA-N 0.000 description 1
- 241000220317 Rosa Species 0.000 description 1
- 206010041899 Stab wound Diseases 0.000 description 1
- 206010047571 Visual impairment Diseases 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 206010003549 asthenia Diseases 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 229940049706 benzodiazepine Drugs 0.000 description 1
- 150000001557 benzodiazepines Chemical class 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229960002897 heparin Drugs 0.000 description 1
- 208000013433 lightheadedness Diseases 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 235000003715 nutritional status Nutrition 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229940001470 psychoactive drug Drugs 0.000 description 1
- 239000004089 psychotropic agent Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 208000029257 vision disease Diseases 0.000 description 1
- 230000004393 visual impairment Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19173—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
본 발명은 낙상위험 방지 시스템에 관한 것으로, 더욱 상세하게는 전자의무기록을 활용하여 환자의 낙상을 예측하고 위험도를 산출하여 낙상의 위험을 효과적으로 방지할 수 있는 전자의무기록을 활용한 낙상 위험 방지 시스템에 관한 것이다. 본 발명에 따른 전자의무기록을 활용한 낙상 위험 방지 시스템은, 환자의 의무기록 데이터가 저장된 데이터 저장부; 데이터 저장부로부터 필요한 의무기록을 추출하는 데이터 추출부; 추출된 데이터를 분석을 위해 전처리하는 데이터 전처리부; 전처리된 데이터를 분류하는 데이터 분류부; 분류된 데이터를 분석하여 낙상 위험도 점수를 산출하는 데이터 분석부; 및 데이터 추출부, 데이터 전처리부, 데이터 분류부 및 데이터 분석부의 작동을 제어하는 제어부;를 포함한다.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
본 발명은 낙상위험 방지 시스템 및 방지 방법에 관한 것으로, 더욱 상세하게는 전자의무기록을 활용하여 환자의 낙상을 예측하고 위험도를 산출하여 낙상의 위험을 효과적으로 방지할 수 있는 전자의무기록을 활용한 낙상 위험 방지 시스템 및 방지 방법에 관한 것이다.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.
현재 임상현장에서는 낙상환자를 사전에 예측하고 관리할 수 있도록 다양한 낙상 위험 방지 시스템이 개발되어 사용되고 있다.Currently, various fall risk prevention systems are being developed and used in clinical settings to predict and manage patients who fall.
대표적인 낙상 위험 사정 평가 도구로 Morse Fall Risk(이하, 'MFS'라고 한다), Hendrich Ⅱ, St Thomas's Risk Assessment Tool in Falling Elderly Inpatient(이하, 'STRATIFY'라 한다) 등이 사용되고 있다.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').
MFS 사정 도구의 평가 항목은 ① 지난 3개월간 낙상 이력(과거 낙상 경험), ② 이차 진단(부진단), ③ 보행보조(기구사용 여부), ④ 정맥 수액 요법/헤파린 록, ⑤ 걸음걸이/이동(걸음 장애 및 허약함), ⑥ 의식/정신상태로 구성되며, 각 항목에 최소 10점에서 최대 20점의 점수를 부여한다. 점수가 0~24점 일 경우에는 낙상 위험성의 거의 없는 것으로 분류하고, 25~44점 일 경우에는 낙상 위험이 있으나 낮은 것으로 분류하며, 45~125점 일 경우에는 낙상 위험이 큰 것으로 분류한다. 낙상 위험이 큰 경우에는 고위험군으로 분류하여 별도 관리하게 된다.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.
Hendrich Ⅱ 사정 도구의 평가 항목은 ① 혼란/방향 감각 상실/충동, ② 우울, ③ 배뇨/배변 변화, ④ 어지러움/현기중, ⑤ 남성인 경우 향정신성 의약품(Benzodiazepine) 복용 여부와 자리에서 일어날 때 등으로 구성되며, 각 항목에 0~4점을 부여한다. 점수가 5점 이상일 경우 낙상 위험군으로 분류한다.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.
STRATIFY 사정 도구의 평가 항목은 ① 낙상으로 인해 입원하거나/원내에서 낙상하는 경우, ② 방향감/어지러움, ③ 시각장애, ④ 화장실 이용 빈도, ⑤ 이동점수하락 등으로 구성된다. 1~10점 척도로 점수를 내며 2점 이상일 경우 낙상 위험 환자로 분류한다.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.
상기와 같은 사정 도구들을 이용한 낙상 위험도는 매일 혹은 필요할 때 설문조사를 하거나 간단한 검사를 통해 측정하게 되며, 그 결과를 간호에 적용하게 된다.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.
현재 임상현장에서는 낙상환자를 예측하고 관리하는데 상술한 바와 같은 도구들을 활용하고 있으나, 높은 예측 타당도를 일관되게 유지할 수 있는 도구가 없을 뿐만 아니라 별도의 시험(앉았다 일어나기 등)을 통해 평가해야 하는 단점이 있다. 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.
이에, 현재 사용되고 있는 낙상 위험 사정 도구들의 단점 및 한계를 극복하고 낙상 위험 예측도를 높이기 위한 연구 개발의 필요성이 지속적으로 제기되고 있는 실정이다. 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.
본 발명은 상기와 같은 종래 기술의 문제점을 해결하고자 안출된 것으로, 낙상 위험을 예측하는 예측 타당도를 일관되게 높게 유지하고, 낙상 위험 예측을 위해 별도의 시험이 필요치 않음으로써, 낙상 위험을 효과적으로 예방할 수 있는 낙상 위험 방지 시스템 및 방지 방법을 제공하는데 그 목적이 있다.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.
특히, 본 발명은 매일 측정되는 환자 데이터를 정확하고 객관적으로 반영하여 낙상 위험도를 확인할 수 있도록 하는 낙상 위험 사정 도구로서 정성적으로 작성된 내용을 정량적인 수치로 생성할 수 있도록 하는 전자의무기록을 활용한 낙상 위험 방지 시스템 및 방지 방법을 제공하는데 그 목적이 있다.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.
상기와 같은 목적 달성을 위한 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 시스템은, 환자의 의무기록 데이터가 저장된 데이터 저장부; 데이터 저장부로부터 필요한 의무기록을 추출하는 데이터 추출부; 추출된 데이터를 분석을 위해 전처리하는 데이터 전처리부; 전처리된 데이터를 분류하는 데이터 분류부; 분류된 데이터를 분석하여 낙상 위험도 점수를 산출하는 데이터 분석부; 및 데이터 추출부, 데이터 전처리부, 데이터 분류부 및 데이터 분석부의 작동을 제어하는 제어부;를 포함한다.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.
데이터 분석부에서는 로지스틱 회귀분석법이 사용된다.Logistic regression analysis is used in the data analysis department.
데이터 분석부에서 이루어지는 낙상 위험도 점수산출은 로지스틱 회귀분석을 통해 산출된 변수별 β에 Exponential 활용해 오즈비(odd ratio)를 산출하고 이를 변수의 가중치로 활용하며, 수학식1에 기초하여 낙상 위험도를 얘측한다.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.
[수학식1][Equation 1]
상기와 같은 목적 달성을 위한 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 방법은, (a) 환자의 의무기록 데이터가 저장된 데이터 저장부로부터 데이터를 추출하는 단계; (b) 추출된 데이터들을 분석을 위해 전처리하는 데이터 전처리 단계; (c) 전처리된 데이터들을 분류하는 단계; 및 (d) 분류된 데이터를 이용해 낙상 위험도 점수를 산출하는 단계;를 포함한다.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.
(d)단계에서 이루어지는 낙상 위험도 점수 산출은, 로지스틱 회귀분석을 통해 산출된 변수별 β에 Exponential 활용해 오즈비(odd ratio)를 산출하고 이를 변수의 가중치로 활용하며, 수학식1에 기초하여 상기 낙상 위험도를 예측한다. 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.
[수학식1][Equation 1]
(c) 단계에서는 전처리된 데이터를 8:2의 비율로 훈련용/검증용 데이터로 분류하며, (d) 단계에서는 훈련용 데이터를 활용하여 통계 유의성을 분석한다. 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.
(d) 단계에서는 유의성이 검정되지 않은 변수를 삭제하고 통계 유의성 분석을 재실시하여 변수별 β를 산출한다.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.
본 발명 전자의무기록을 활용한 낙상 위험 방지 시스템 및 방지 방법에 따르면, 매일 측정되는 환자 데이터를 정확하고 객관적으로 반영하여 낙상 위험도를 확인할 수 있도록 함으로써, 낙상 위험 예측도를 일관되게 높게 유지할 수 있다.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.
또한, 본 발명에 따르면, 실시간 또는 정기적으로 추가되는 환자 데이터를 활용하여 가중치가 수시로 변화할 수 있으며 별다른 코드의 수정 없이 반영할 수 있다. 따라서, 별도의 유지 및 보수에 사용되는 시간 및 비용을 절감할 수 있다.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.
또한, 병원 내에서 활용하고 있는 인터페이스에 산출식으로 추정한 낙상 위험도와 낙상 예측 확률을 표기함으로써, 의료진이 환자의 낙상 위험을 판단하고 간호하는데 활용할 수 있다.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.
도 1은 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 지스템의 구성도이다.
도 2는 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 프로세스이다.
도 3은 데이터 전처리 단계에서 이루어지는 전처리 사항들을 나타낸 도면이다.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.
이하, 첨부된 도면을 참조하여 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 시스템 및 방지 방법을 상세히 설명하기로 한다.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.
첨부된 도면의 도 1은 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지지스템의 구성도이다.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.
본 발명에 따른 전자의무기록을 활용한 낙상 위험 방지 시스템은, 데이터 저장부(10), 데이터 추출부(20), 데이터 전처리부(30), 데이터 분류부(40), 데이터 분석부(50) 및 제어부(60)를 포함한다.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.
데이터 저장부(10)에는 입원 환자들의 각종 의무기록 데이터들이 저장된다. 데이터 저장부(10)는 의료기관에서 구축하고 있는 전자의무기록시스템의 일부일 수 있다.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.
데이터 추출부(20)를 통해 추출되는 데이터에는 환자 등록번호, 키, 몸무게, 나이, 자상병코드, 부상병코드와 같은 기본 계측 정보와 낙상 위험도 도구(MFS)로 측정된 환자의 최근 3개월간 낙상 이력(과거 낙상 경험), 이차 진단(부진단), 보행보조(기구사용 여부), 정맥 수액 요법/헤라핀 록, 걸음걸이/이동(걸음 장애 및 허약함), 의식/정신상태와 간호 필요도, 도구로 측정/작성되 배뇨/배변, 호흡 간호, 비침습적 산소 투여, 체위변경, 침상 밖으로 이동, 식사 섭취, 욕창 도구를 통한 욕창 유무와 영양 상태, 통증 도구를 통해 통증 강도를 추출, 매일 환자에게 처방된 약물 추출 등이 있다. 추출은 개발 서버에 반영한 API를 통해 추출된다.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.
데이터 전처리부(30)에서는 추출된 데이터들이 분석을 위해 더미(dummy)화 등의 방법으로 전처리된다.In the data pre-processing unit 30, the extracted data is pre-processed by a method such as dummy for analysis.
데이터 분류부(40)에서는 전처리된 데이터들이 훈련용/검증용 데이터로 분류된다.In the data classification unit 40, the preprocessed data is classified into training/verification data.
데이터 분석부(50)에서는 로지스틱 회귀분석법, 로그 로즈를 이용한 회귀분석법 등을 이용하여 낙상 위험도 점수를 산출하게 된다.The data analysis unit 50 calculates a fall risk score using a logistic regression method, a regression analysis method using log rose, etc.
제어부(60)에서는 데이터 추출부(20), 데이터 전처리부(30), 데이터 분류부(40) 및 데이터 분석부(50)의 작동을 자동으로 제어한다.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.
첨부된 도면의 도 2는 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 프로세스이고, 도 3은 데이터 전처리 단계에서 이루어지는 전처리 사항들을 나타낸 도면이다.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.
본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 방법은, 데이터 수집 단계(S10), 데이터 전처리 단계(S20), 변수 선정 단계(S30), 기계 학습 단계(S40), 통계 유의성 검정 단계(S50), 유의성이 검정되지 않는 변수 삭제 단계(S60) 및 낙상 위험도 점수 산출 단계(S70)를 포함한다.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).
데이터 수집 단계(S10)에서는 병원의 데이터 베이스(DB)에 접근하여 필요한 데이터를 추출하게 된다. In the data collection step (S10), the hospital's database (DB) is accessed to extract necessary data.
데이터 전처리 단계(S20)에서는 추출된 데이터를 연구에 활용할 수 있게 전처리한다. 간호 필요 도구, 낙상 위험도 도구, 욕창, 통증 등 문자열(String)로 추출된 내용은 모두 더미(dummy)화한다. 주상병, 부상병코드를 활용하여 Charlson Comorbidity Index(CCI)를 산출한다. ATC 코드를 활용하여 복용약물을 클러스터링한 후 더미화한다.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.
변수 선정 단계(S30)에서는 기계학습을 위해 낙상환자와 비낙상환자의 데이터를 추출/수집/전처리하고, 8:2의 비율로 훈련용/검증용 데이터로 분류한다.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.
기계학습단계(S40)에서는 종속변수가 범주형일 때 사용하는 로지스틱 회귀분석을 활용한다. 로지스틱 회귀분석은 이벤트가 발생할 확률을 결정하는데 사용되는 통계모델로써 특성 간의 관계를 보여주고 특정 결과의 확률을 계산한다.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.
통계 유의성 검정 단계(S50)에서는 기계학습을 통해 예측률을 확인하고 변수별 유의성을 검정한다. 앞 단계에서 활용한 훈련용 데이터 세트를 활용하여 통계 유의성을 분석한다.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.
유의성이 검정되지 않는 변수 삭제 단계(S60)에서는 앞 단계에서 유의성이 검증되지 않은 변수를 삭제하고 기계학습과 통계적 유의성 분석을 재실시하도록 한다.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.
낙상 위험도 점수 산출 단계(S70)에서는 로지스틱 회귀분석을 통해 산출한 변수별 β에 Exponential 활용해 오즈비(odd ratio)를 산출하고 이를 변수의 가중치로써 활용하게 된다. 로그 오즈를 이용한 회귀분석식은 아래의 수학식1과 같다.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.
이상과 같이 본 발명의 바람직한 실시예에 따른 전자의무기록을 활용한 낙상 위험 방지 시스템 및 방지 방법을 첨부된 도면을 참조로 상세히 설명하였으나, 본 발명은 상술한 실시예에 한정되지 않으며, 특허청구범위 내에서 다양하게 변형 실시될 수 있다.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 : 데이터 저장부 20 : 데이터 추출부
30 : 데이터 전처리부 40 : 데이터 분류부
50 : 데이터 분석부 60 : 제어부
S10 : 데이터 수집 단계
S20 : 데이터 전처리 단계
S30 : 변수 선정 단계
S40 : 기계 학습 단계
S50 : 통계 유의성 검정 단계
S60 : 유의성이 검정되지 않는 변수 삭제 단계
S70 : 낙상 위험도 점수 산출 단계10: 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)
상기 데이터 저장부로부터 필요한 의무기록을 추출하는 데이터 추출부;
추출된 데이터를 분석을 위해 전처리하는 데이터 전처리부;
전처리된 데이터를 분류하는 데이터 분류부;
분류된 데이터를 분석하여 낙상 위험도 점수를 산출하는 데이터 분석부; 및
상기 데이터 추출부, 데이터 전처리부, 데이터 분류부 및 데이터 분석부의 작동을 제어하는 제어부;를 포함하는, 전자의무기록을 활용한 낙상위험 방지시스템.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.
상기 데이터 분석부에서는 로지스틱 회귀분석법이 사용되는, 전자의무기록을 활용한 낙상위험 방지시스템.According to claim 1,
A fall risk prevention system using electronic medical records, in which the data analysis department uses logistic regression analysis.
상기 데이터 분석부에서 이루어지는 낙상 위험도 점수산출은 상기 로지스틱 회귀분석을 통해 산출된 변수별 β에 Exponential 활용해 오즈비(odd ratio)를 산출하고 이를 변수의 가중치로 활용하며,
수학식1에 기초하여 상기 낙상 위험도를 얘측하는, 전자의무기록을 활용한 낙상위험 방지시스템.
[수학식1]
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]
(b) 추출된 데이터들을 분석을 위해 전처리하는 데이터 전처리 단계;
(c) 전처리된 데이터들을 분류하는 단계; 및
(d) 분류된 데이터를 이용해 낙상 위험도 점수를 산출하는 단계;를 포함하는, 전자의무기록을 활용한 낙상위험 방지 방법.(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.
상기 (d)단계에서 이루어지는 낙상 위험도 점수 산출은,
로지스틱 회귀분석을 통해 산출된 변수별 β에 Exponential 활용해 오즈비(odd ratio)를 산출하고 이를 변수의 가중치로 활용하며, 수학식1에 기초하여 상기 낙상 위험도를 예측하는, 전자의무기록을 활용한 낙상위험 방지 방법.
[수학식1]
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]
상기 (c) 단계에서는 전처리된 데이터를 8:2의 비율로 훈련용/검증용 데이터로 분류하며, 상기 (d) 단계에서는 상기 훈련용 데이터를 활용하여 통계 유의성을 분석하는, 전자의무기록을 활용한 낙상위험 방지 방법.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.
상기 (d) 단계에서는 유의성이 검정되지 않은 변수를 삭제하고 통계 유의성 분석을 재실시하여 상기 변수별 β를 산출하는, 전자의무기록을 활용한 낙상위험 방지 방법.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.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020220147184A KR20240065904A (en) | 2022-11-07 | 2022-11-07 | Falling risk prevention system and method using electric medical record |
PCT/KR2023/016826 WO2024101733A1 (en) | 2022-11-07 | 2023-10-27 | Fall risk prevention system and method using electronic medical record |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020220147184A KR20240065904A (en) | 2022-11-07 | 2022-11-07 | Falling risk prevention system and method using electric medical record |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20240065904A true KR20240065904A (en) | 2024-05-14 |
Family
ID=91032794
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020220147184A KR20240065904A (en) | 2022-11-07 | 2022-11-07 | Falling risk prevention system and method using electric medical record |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR20240065904A (en) |
WO (1) | WO2024101733A1 (en) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101611838B1 (en) * | 2013-05-30 | 2016-04-12 | 가톨릭대학교 산학협력단 | Method and system for predicting high risk based on patient safety |
KR101766335B1 (en) * | 2016-06-08 | 2017-08-08 | 건국대학교 글로컬산학협력단 | System and method for predicting risk for fall |
KR101883433B1 (en) * | 2016-11-07 | 2018-07-30 | 인하대학교 산학협력단 | System and method for tailored intervetion through prediction of inpatient falls |
WO2019022779A1 (en) * | 2017-07-28 | 2019-01-31 | Google Llc | System and method for predicting and summarizing medical events from electronic health records |
-
2022
- 2022-11-07 KR KR1020220147184A patent/KR20240065904A/en unknown
-
2023
- 2023-10-27 WO PCT/KR2023/016826 patent/WO2024101733A1/en unknown
Also Published As
Publication number | Publication date |
---|---|
WO2024101733A1 (en) | 2024-05-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102799794B (en) | The self-service evaluating system of life entity physiological situation | |
CN109841282A (en) | A kind of Chinese medicine health control cloud system and its building method based on cloud computing | |
MPhil et al. | Reviewing and selecting outcome measures for use in routine practice | |
US20060025931A1 (en) | Method and apparatus for real time predictive modeling for chronically ill patients | |
CN105260588A (en) | Health protection robot system and data processing method thereof | |
CA2565918A1 (en) | Method and apparatus for real time predictive modeling for chronically ill patients | |
Banerjee et al. | Telesurveillance of elderly patients by use of passive infra-red sensors in a'smart'room | |
JPWO2016120955A1 (en) | BEHAVIOR PREDICTION DEVICE, BEHAVIOR PREDICTION DEVICE CONTROL METHOD, AND BEHAVIOR PREDICTION DEVICE CONTROL PROGRAM | |
CN112669967A (en) | Active health medical decision-making assisting method and equipment | |
Bolton et al. | The impact of nursing interventions | |
CN103870673A (en) | Structured labelling method of medical research and development system using support documents | |
US20230298760A1 (en) | Systems, devices, and methods for determining movement variability, illness and injury prediction and recovery readiness | |
CN113744878A (en) | Chronic disease risk index assessment and intervention system based on mobile internet | |
CN111161820B (en) | Oral health management system | |
CN109545374A (en) | A kind of disease based on body gait feature big data automatically tracks, treats and supplying system | |
Baig et al. | Falls risk assessment for hospitalised older adults: a combination of motion data and vital signs | |
CN115714022A (en) | Neonatal jaundice health management system based on artificial intelligence | |
CN114068022A (en) | Early warning method and device for fall risk, storage medium and electronic equipment | |
CN113688205A (en) | Disease detection method based on deep learning | |
JP2011138376A (en) | Diagnosis support system | |
KR20240065904A (en) | Falling risk prevention system and method using electric medical record | |
CN111374651A (en) | Novel wisdom endowment system | |
KR101274431B1 (en) | Apparatus and method for determining health using survey information, apparatus and method for generating health sort function | |
Devriendt et al. | Comprehensive geriatric assessment in the emergency department | |
CN111986801A (en) | Rehabilitation evaluation method, device and medium based on deep learning |