대학병원 직원의 환자정보보호행동 분석

신아미 ( A Mi Shin ),이인희 ( In Hee Lee ),이경호 ( Kyung Ho Lee ),윤경일 ( Kyung Il Youn ) 한국병원경영학회 2010 병원경영학회지 Vol.15 No.2

Ensuring the confidentiality of patient records is critical requirement for quality of care and in fulfilling legal obligation of healthcare organizations. This study analyzed the behavior of hospital employees who are dealing with confidential patient information in a hospital. Theory of Planned Behavior(TPB) model and TPB expanded models that add habit concept to TPB are tested for the validity in explaining the predisposing factors that affect the behavior of hospital employee in ensuring the confidentiality of patient records. Data were collected by administrating a survey to the 350 employee of a tertiary care hospital. Of the 350 questionaries distributed, 321 were responded resulting 92% of response rate. The mean differences among the groups classified by age, years of experience, gender, and occupation were analysis using ANOVA. The relationships among the concepts suggested in the models were analysed by applying the Structural Equations Modeling method. The results of ANOVA indicated significant mean differences in the frequency of confidentiality ensuing behavior. Administrative staff and medical technicians show higher frequency of ensuing behavior compared to the physicians and the nurses. And more experienced employee show more confidentiality ensuring behavior. The results of Structural Equations analysis showed that the strong effect of habit and attitude in predicting the behavior. However, the effect of perceived behavioral control was not significant. Based on the results the theoretical and practical implications are discussed.

종이의무기록과 전자의무기록의 기재 충실도 및 일치도 비교 연구: 의사의 입원,퇴원기록지와 간호사의 입원,퇴원간호정보기록지를 중심으로

신아미 ( A Mi Shin ),정선주 ( Sun Ju Jung ),이인희 ( In Hee Lee ),손창식 ( Chang Sic Son ),박희준 ( Hee Joon Park ),김윤년 ( Yoon Nyun Kim ),윤경일 ( Kyung Il Youn ) 한국병원경영학회 2010 병원경영학회지 Vol.15 No.1

This study was tried to evaluate the level of completeness and the accordance in electronic medical records by comparing paper-based medical record in doctor`s admission records, discharge summary, and nursing information records. Medical records of inpatients of neurology department that the 100 paper-based medical records in 2004 and 100 electronic medical records in 2006 were targeted. Existence of record items and doctor-nurse record accordance were evaluated in doctor`s admission record, discharge summary, admission nursing information record, and discharge nursing information record. There were not any differences between electronic medical records and paper-based medical records in doctor`s admission record and discharge summary. Electronic medical records had less missing records than paper-based medical records in admission and discharge nursing information records. Electronic medical records showed higher accordance than the paper-based medical record in doctor-nurse record generally, but there were statistically differences in only medication, allergy, smoking, and drinking(p<0.05). In this study, it was verified that the quality of electronic medical records are better than paper-based records in nursing information record and doctor-nurse record agreement.

호흡곤란환자의 입-퇴원 분석을 위한 규칙가중치 기반 퍼지 분류모델

손창식,신아미,이영동,박형섭,박희준,김윤년,Son, Chang-Sik,Shin, A-Mi,Lee, Young-Dong,Park, Hyoung-Seob,Park, Hee-Joon,Kim, Yoon-Nyun 대한의용생체공학회 2010 의공학회지 Vol.31 No.1

A rule weight -based fuzzy classification model is proposed to analyze the patterns of admission-discharge of patients as a previous research for differential diagnosis of dyspnea. The proposed model is automatically generated from a labeled data set, supervised learning strategy, using three procedure methodology: i) select fuzzy partition regions from spatial distribution of data; ii) generate fuzzy membership functions from the selected partition regions; and iii) extract a set of candidate rules and resolve a conflict problem among the candidate rules. The effectiveness of the proposed fuzzy classification model was demonstrated by comparing the experimental results for the dyspnea patients' data set with 11 features selected from 55 features by clinicians with those obtained using the conventional classification methods, such as standard fuzzy classifier without rule weights, C4.5, QDA, kNN, and SVMs.

비선형 시간이력해석을 통한 철근콘크리트 벽식구조 건물의 내풍 성능 평가

정승용(Jeong, Seung Yong),강현구(Kang, Thomas H.-K.) 한국콘크리트학회 2020 한국콘크리트학회 학술대회 논문집 Vol.32 No.1

대구일 종합병원 전자간호기록 시스템에 대한 사용자 만족도 조사

신아미 ( A Mi Shin ),박희준 ( Hee Joon Park ),정선주 ( Sun Ju Jung ),박명화 ( Myong Hwa Park ),윤경일 ( Kyung Il Yoon ),김윤년 ( Yoon Nyun Kim ) 한국보건통계학회 2009 보건정보통계학회지 Vol.34 No.1

Objective: This study was tried to survey nurse`s satisfaction on the ENR(electronic nursing record) system in general hospital in Daegu. Methods: 250 nurses who were working in the A general hospital in Daegu participated to survey through Questionnaire for User Interaction Satisfaction about satisfaction of electronic nursing record system. Results: Mean score of Questionnaire for User Interaction Satisfaction was 3.18 and this result was statistically higher than middle score of 3. Score of terminology & message was the highest and score of capabilities was lowest in all categories of Questionnaire for User Interaction Satisfaction. Results of stepwise multiple regression between overall evaluation and other categories were that categories of learning, capabilities, screen influenced category of overall evaluation and category of learning was the biggest influence variable. Conclusion: Users seem to be satisfied with the electronic nursing record system and this results could help to modify better electronic nursing record system in A hospital.

데이터 마이닝을 활용한 뇌경색증과 동반되는 질환의 연관성 분석

이인희,신아미,손창식,박희준,김중휘,박상영,최진호,김윤년,Lee, In-Hee,Shin, A-Mi,Son, Chang-Sik,Park, Hee-Joon,Kim, Joong-Hwi,Park, Sang-Young,Choi, Jin-Ho,Kim, Yoon-Nyun 대한물리치료학회 2010 대한물리치료학회지 Vol.22 No.1

Purpose: The purpose of this study was to apply association rule mining to explore the labyrinthine network of cerebral infarction comorbidity and basic data supply to develop cutting-edge physical therapy protocols for cerebral infarction with comorbidity Methods: From clinic records of enrollees of A Hospital in D city, patients over 18 years of age with cerebral infarction and cerebral infarction comorbidity were recruited as a case group. All diagnoses of that hospital were categorized according to the "International Classification of Disease (ICD)" diagnosis system. We extracted code I63 from the "Korea Classification of Disease (KCD)-4". Associated rule mining was done with a priori modeling and Web nodes to examine the strengths of associations among those diagnoses. The support and confidence values of associated rule mining results were examined. Results: The subjects of this study were 2,267 cerebral infarction patients. E11 (Non-insulin-dependent diabetes mellitus), E78 (Disorders of lipoprotein metabolism and other lipidaemias), G81 (Hemiplegia), I10 (Essential hypertension), and K29 (Gastritis and duodenitis) were high frequency diagnoses, being found in 10% or more of total diagnoses of cerebral infarction from frequency analysis results. The highest frequency diagnosis was 1,042 (46.0%) for I10. The second most frequent diagnosis was for E11(21.5%) while the third most frequent diagnosis was E78 (20.2%). Results from a priori modeling and Web nodes indicated that cerebral infarction has a strong association withessential hypertension, non-insulin-dependent diabetes mellitus, disorders of lipoprotein metabolism and other lipidaemias. Conclusion: Cerebral infarction is associated with hypertension, diabetes mellitus, and disorders of lipoprotein metabolism and other lipidaemias. The result of this study will be helpful to clinicians treating patients with cerebral infarction.

물리치료를 받은 선천성 근성 사경 환아의 최종 종괴 지름 예측 모형 개발

이인희,신아미,이경호,박희준,김윤년,Lee, In-Hee,Shin, A-Mi,Lee, Gyeong-Ho,Park, Hee-Joon,Kim, Yoon-Nyun 대한물리치료학회 2009 대한물리치료학회지 Vol.21 No.2

Purpose: The pathophysiology of congenital muscular torticollis (CMT) is that the sternoclavicularmastoid (SCM) is shortened on the involved side by fibrosis, leading to an ipsilateral tilt and contralateral rotation of the face and chin. The aim of this study was to examine the effect of physical therapy and develop a mass diameter prediction model for infants with CMT. Methods: Fifty six patients were diagnosed with CMT between April 2003 and December 2008. Infants with neurological complications, and spasmodic and ocular torticollis were excluded. Physical therapy was applied to those masses in the SCM muscles of those infants after checking their physical findings and the diameter of the mass with ultrasonography. Their physical findings and mass diameter was reevaluated when their neck tilt was under $5^{\circ}$. Results: The mean age when physical therapy was started was 35 days. After a mean 90 days of treatment, the subjects showed improvement in the neck tilt. Subjects whose neck tilted above $15^{\circ}$ showed significant improvement in neck tilt decreased their mass diameter (p<0.01). Facial symmetric infants showed a shorter recovery duration than the facial asymmetric infants (p<0.05). A mass decreasing model based on the diameter of the mass, facial symmetry or not and the physical therapy start day after birth was developed by linear regression. Conclusion: Physical therapy is an effective treatment for CMT. The change in the diameter of the mass on the SCM muscles after treatment can be predicted.

데이터의 공간적 분포를 고려한 퍼지 이산화와 특징선택에의 응용

손창식(Chang-Sik Son),신아미(A-Mi Shin),이인희(In-Hee Lee),박희준(Hee-Joon Park),박형섭(Hyoung-Seob Park),김윤년(Yoon-Nyun Kim) 한국지능시스템학회 2010 한국지능시스템학회논문지 Vol.20 No.2

임상 데이터마이닝에서 최적의 특징 집합을 선택하는 것은 주어진 데이터로부터 생성된 모델의 복잡성을 줄일 뿐만 아니라 유용성을 향상시키는 데에 매우 중요하고, 선택된 특징들의 임계값은 질병의 감별진단을 위해 임상 전문가의 결정기준으로 사용된다. 본 논문에서는 데이터의 공간적인 분포, 즉 중첩영역에서 중복 속성값을 포함하는 데이터의 분리성 정도를 평가함으로써 연속형 속성을 가진 데이터에 대한 퍼지 이산화기법을 제안한다. 제안된 방법에서 중복 속성값의 가중치 평균값은 각 특징의 임계값(즉 경계값)을 결정하기 위해서 사용되었고, 러프집합은 전체 특징들 중에서 중요특징들의 집합을 선택하기 위해서 이용하였다. 제안된 방법의 타당성을 검증하기 위해 호흡곤란을 주호소로 내원한 668명의 환자 데이터를 근거로 3가지 이산화방법과 제안된 이산화방법에 대한 실험을 수행하였다. 실험결과, 퍼지분할을 기반으로 한 이산화방법이 하드분할을 기반으로 한 이산화방법에 비해서 평균 분류정확도와 G-mean 성능에서 보다 좋은 결과를 제공함을 확인하였다. In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.

일부 물리치료사와 작업치료사의 환자 의료정보보호 행동 이해

이인희,신아미,손창식,박상영,박희준,윤경일,김윤년,Lee, In-Hee,Shin, A-Mi,Son, Chang-Sik,Park, Sang-Young,Park, Hee-Joon,Yoon, Kyung-Il,Kim, Yoon-Nyun 대한물리치료학회 2010 대한물리치료학회지 Vol.22 No.2

Purpose: The purpose of this study was to use the theory of planned behavior, past habit and moral obligation to better understand the behavior of physical therapists (PTs) and occupational therapists (OTs) in protecting the medical information of patients. Methods: We conducted a survey using self-writting questionnaires structured within the framework of the theory of planned behavior to understand to analyze information from 103 clinical PTs and OTs in their efforts to protect patient medical information. Results: The PTs and OTs' medical information protecting behavior was 2.85 mean points. That point failed to reach 1.0 points. Behavior intention was 3.83 mean points. That was judged to be improved. Behavioral intention was closely correlated with behavior, behavioral attitude, subjective norms, behavior control, and past habit. Variables related to the theory of planned behavior, attitude, subjective norms, and perceived behavior control all explained 50% of the behavioral intention of PTs and OTs regarding future divulgence of patient information. The past habits of PTs and OTs were also a significant predictor in explaining the behavioral intention to protect a patient's medical information (p<0.01). Conclusion: Revising the behavioral attitudes, subjective norms, perceived behavior control, and past habits of PTs and OTs helped improve their behavior regarding protection of the medical information of patents.

응급실 급성 충수염 환자의 임상경로 개발

박철용,김윤년,최현석,신아미,Park, Cheol-Yong,Kim, Yoon-Nyun,Choi, Hyun-Seok,Shin, A-Mi 한국데이터정보과학회 2010 한국데이터정보과학회지 Vol.21 No.3

이 논문에서는 응급실 급성 충수염 환자의 치료와 검사 항목에 대한 임상경로를 개발하였다. 임상경로 개발을 위해 먼저 Park과 Kim (2010)에 의해 제시된 처방 선택 방법을 이용하였으며, 그 다음에 이렇게 선택된 처방들을 연관성이 있는 처방끼리 묶어서 그림으로 표시하였다. 구체적으로 사용된 처방 선택 방법은 향상도에 근거하고 있으며 빈도가 높은 처방부터 출발하여 이것과의 향상도가 0.9에 못 미치는 음의 연관성 처방들을 순차적으로 제거하였다. 이렇게 선택된 처방들에 대해 연관성이 있는 처방들을 묶는 방법도 처방 선택 방법과 비슷하다. 구체적으로 선택된 처방 중 빈도가 높은 처방부터 출발하여 순차적으로 이것과의 향상도가 1.1을 넘는 처방들을 연관성 있는 처방으로 고려하여 해당 처방 오른쪽에 표시하였다. 따라서 임상경로 그림에는 제일 왼쪽에는 연관성이 낮은 처방들을 빈도순으로 위에서 아래로 배치하고, 제일 왼쪽에 있는 각 처방의 오른쪽에는 이것과 연관성이 높은 처방들을 왼쪽에서 오른쪽으로 역시 빈도순으로 배치하는 것을 원칙으로 하였다. In this study, we develop clinical pathways for test and medical treatment items of acute appendicitis patients in emergency room. In order to develop the clinical pathways, we first employ the order selection method by Park et al. (2010), and then display the selected orders in such a way that associated orders are tied together. More specifically the order selection method that we employ is based on lift and, starting from the orders with higher frequencies, sequentially removes the negatively associated orders with lift values less than 0.9. The way associated orders are selected and tied together is similar to that of the order selection method. More specifically, starting from the selected orders with higher frequencies, the orders with lift values greater than 1.1 are considered associated and displayed to the right of the corresponding order. Therefore, in the diagram of clinical pathways, the orders at the left hand side, in principle, are not associated with each other and upper orders have higher frequencies, and associated orders are located to the right of corresponding order at the left hand side and more left orders, in principle, have higher frequencies.