• 한국컴퓨터정보학회논문지
• /
• 제26권7호
• /
• pp.9-17
• /
• 2021

본 연구는 대장암 환자의 치료방법 중 하나인 항암화학요법을 분류할 수 있는 시스템인 CDSS연구의 일환으로 시행되었다. 대장암 치료에서 환자의 상태에 맞는 항암화학요법의 선택은 환자의 생존 기간과 직결되기 때문에 매우 중요하다. 따라서 본 연구에서는 대장암 환자의 개인적, 병리학적 특성을 사용해 기저 모델, 병리학적 모델, 그리고 환자의 두 가지 특성을 모두 사용한 결합 모델을 만들어 머신러닝 알고리즘으로 항암화학요법을 분류하였다. Top-n Accuracy와 ROC 곡선, AUC로 모델의 예측 정확도를 비교한 결과, 결합 모델에서 가장 우수한 예측 정확도를 보였으며, LGBM 알고리즘의 성능이 가장 우수한 것을 알 수 있었다. 본 연구에서는 머신러닝 알고리즘을 이용해 환자 특성별 모델을 분류함으로써 환자의 상태에 맞는 항암화학요법 분류 모델을 구축하였다. 향후 연구에서 본 연구 결과를 기초한다면 더 좋은 성능의 항암화학요법 분류 모델을 만들어 CDSS 연구에 도움이 될 것이다.

• Journal of Periodontal and Implant Science
• /
• 제49권2호
• /
• pp.76-89
• /
• 2019

Purpose: The purpose of this study was to evaluate the prognostic effect of patient compliance with supportive periodontal treatment (PC-SPT). Chronic periodontitis patients were classified based on their compliance level, and factors affecting PC-SPT and the prognosis of PC-SPT were investigated. Methods: This study selected 206 patients who started SPT after receiving periodontal treatment between 2010 and 2012. Patients who continued SPT through February 2016 were included. The patients were classified according to whether they exhibited complete compliance (100% of visits), excellent compliance (${\geq}70%$ of visits), incomplete compliance (<70% of visits), or non-compliance (only 2 visits). Patient characteristics that could affect PC-SPT, such as age, sex, distance of the clinic from their residence, implantation, and periodontal treatment, were investigated. The number of newly decayed and extracted teeth, alveolar bone level changes around the teeth and implants, and implant removal were examined to evaluate the prognosis of PC-SPT. Results: Sex and the presence of an implant significantly affected PC-SPT. Additionally, the number of newly decayed and extracted teeth and changes in alveolar bone levels around the teeth and implants were significant prognostic factors related to PC-SPT. Conclusions: PC-SPT in chronic periodontitis patients will help maintain periodontal health and prevent further periodontal disease.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.176-181
• /
• 2023

During cancer treatment, the patient's response to drugs appears differently at the cellular level. In this paper, an image-based cell phenotypic feature quantification and key feature selection method are presented to predict the response of patient-derived cancer cells to a specific drug. In order to analyze the viability characteristics of cancer cells, high-definition microscope images in which cell nuclei are fluorescently stained are used, and individual-level cell analysis is performed. To this end, first, image stitching is performed for analysis of the same environment in units of the well plates, and uneven brightness due to the effects of illumination is adjusted based on the histogram. In order to automatically segment only the cell nucleus region, which is the region of interest, from the improved image, a superpixel-based segmentation technique is applied using the fluorescence expression level and morphological information. After extracting 242 types of features from the image through the segmented cell region information, only the features related to cell viability are selected through the ReliefF algorithm. The proposed method can be applied to cell image-based phenotypic screening to determine a patient's response to a drug.

• 한국간호교육학회지
• /
• 제13권1호
• /
• pp.41-51
• /
• 2007

Purpose: This research studied the nurses' knowledge and attitude about pain management. Method: The research subjects were 465 nurses working at three university hospitals in Seoul and at one university hospital in Kyunggi-do. The survey results were collected between October 13 and 21 in 2004. Result: The overall mean score of correct answers on knowledge about pain management was 73.34, general knowledge 71.08, and cancer pain control was 93.93. Similarly, the mean score of correct answers on knowledge about the classification of analgesics was 75.89, while the knowledge of their use was only 52.48. The overall characteristics related to the degree of the nurses' knowledge about pain management were their educational background and their experiences of pain education. In a similar view, the overall characteristics related to the knowledge about the classification of analgesics were age and religion. Likewise, the use of analgesics was related to field of service and the experience of pain education. Finally, the overall characteristics related to the nurse's attitude toward pain management were their field of service and their position. Conclusion: The results of this study could be useful to institutions involved in the education and application of patient pain management.

• 종양간호연구
• /
• 제2권1호
• /
• pp.5-16
• /
• 2002

Purpose: This study was to develop a stress-adaptation model for family caregivers of cancer patients that could provide the basis of planning nursing intervention. Method: A hypothetical model was developed using the family adaptation model proposed by Haley et al. (1987). In the literature, the stressor was identified as patient's characteristics, caregiver's characteristics, duration of illness, and family life events. It affected stress appraisal, family resources, family coping and finally caregiver's adaptation. In this model, 18 paths were constructed. Data were collected from 241 caregivers, whose family members were in treatment between June and August 2000, at 3 university hospitals and were analyzed by SPSS and LISREL programs. Results: 1) The overall fitness indices of the hypothetical model were x 2=267.78 (P= .0), GFI= .92, AGFI= .87, NFI= .93, NNFI= .93, PNFI= .64, PGFI= .55, and RMR= .43. Ten of the eighteen paths proved to be significant. 2) To improve the model fitness, the hypothetical model was modified considering modification indices and the paths proved not significant. Final model excluded 3 paths demonstrated to be improved by x2=161.96 (P= .00), GFI= .95, AGFI= .91, NFI= .96, NNFI= .96, and RMR= .23. Twelve of fifteen paths proved to be significant. 3) Stress appraisal was influenced by disease related characteristics and duration of illness and was explained 22% of the variance. Family resources were influenced by stress appraisal and was explained 57% of variance. Family coping was influenced by disease related characteristics, caregiver's characteristics, duration of illness, family life event, and stress appraisal and was explained 57% of variance. Family caregiver adaptation was influenced by disease related characteristics, caregiver's characteristics, stress appraisal, and family coping and was explained 31% of variance. Twelve of fifteen paths were significant. Conclusion: Based on this study, to help family caregivers to adapt, individual intervention is necessary with consideration of disease related and caregiver's characteristics and duration of illness. The intervention should include efforts to raise the family resources and to identify positively the stress they encounter, and there is a need to establish an adaptation model that considers emotional aspects of family caregivers. Since there is a difference in emotional status depending on the disease stage, a study needs to be done to analyze the differences among the disease stages (diagnosis, treatment, recurrence, and terminal stages).

• 기본간호학회지
• /
• 제22권1호
• /
• pp.16-24
• /
• 2015

Purpose: This study was done to identify essential nursing diagnoses using NANDA and their related factors and defining characteristics of patients who were cared in an emergency room. Methods: The research checklist developed by the researcher consisted of 44 nursing diagnoses with defining characteristics and related factors and was applied to 235 patients who were admitted to an emergency room from November 1 to December 31, 2012. Results: Forty-one of forty-four nursing diagnoses were identified. The most frequent nursing diagnoses were acute pain, risk for falls, and activity intolerance. The most frequent defining characteristic for the nursing diagnosis of 'acute pain' was verbal report of pain. The agreement rate with NANDA (2009)'s defining characteristics was 66.7%. Conclusion: Results indicate that identification of essential nursing diagnoses and their defining characteristics and related/risk factors is important for emergency patient nursing care to facilitate use of NANDA taxonomy in the emergency nursing practice and documentation systems.

• 한국치위생학회지
• /
• 제12권4호
• /
• pp.665-674
• /
• 2012

Objectives : This study purposed to identify factors related to dental service quality perceived by dental clinic patients, and for this purpose. Methods : The data conducted a questionnaire survey of 362 patients who had visited a dental clinic in Daejeon twice or more in August 2010 and aged over 20 during the period from the 1st to 31st of August 2010 and obtained results as follows. Results : The patients' general characteristics, perceived dental service quality was higher in older ones, married ones, high school or lower school graduates, civil servants, self-employed ones, and housewives, and the differences were statistically significant. according to the patients' dental clinic use characteristics, perceived dental service quality was higher when the stay in dental clinic was short, and the difference was statistically significant. Conclusions : Perceived dental service quality was related to the patients' general characteristics and dental clinic use characteristics. therefore, dentists and dental hygienists should make efforts to be more patient-oriented and to create pleasant dental care environment.

• Child Health Nursing Research
• /
• 제30권3호
• /
• pp.176-186
• /
• 2024

Purpose: With the recent increase in interest in patient safety, prevention of falls in hospitalized children has become important. This study aimed to identify the incidence rate of falls among hospitalized children and explore fall-related characteristics. Methods: This retrospective descriptive study analyzed the medical information of 18,119 patients aged <18 years admitted to a general hospital in South Korea from electronic medical records and fall event reports between January 1, 2018, and September 30, 2023. The study variables included the general and clinical characteristics of the fall group and fall-related characteristics of the fall events. This study employed descriptive statistics and a chi-square test using IBM SPSS version 26.0. Results: Among the patients, 82 fall events were identified. Therefore, the fall incidence rate was 4.5 falls per 1,000 patients. Furthermore, a statistically significant difference was found concerning the type of injury sustained between children >1 year old and those <1 year old, and most cases had no damage or bruises. More cases were found in which falls occurred two days after hospitalization in winter and summer than on the day or the day after hospitalization, which was a statistically significant difference. In addition, fall prevalence was higher between 8 am and 4 pm, and when no caregiver was present. Conclusion: Based on the results of this study, education and interventions to prevent fall events in infants and toddlers should persist throughout hospitalization, and it is necessary to guide continuous management and observation of the caregivers.

• 한국직업건강간호학회지
• /
• 제9권1호
• /
• pp.18-29
• /
• 2000

Back injury is frequent in industry workers and is a common cause of productivity loss. It has been reported that the insured of industrial accident insurance tend to stay in hospital longer than that of other types of insurance. The purpose of this study was to identify factors affecting the length of hospital stay for the treatment of back injury in the workers under industrial accident insurance. The results of this study help insurers develop reasonable industrial accident insurance policy for back injury claims and prevention strategies of work-related back injury. A total of 2,949 patients whose industrial accident insurance claim has been approved for the treatment of work-related back injury from January to December 1999 were included in this study. Relationship between the length of hospital stay and characteristics of patient, work place, back injury, and hospital were assessed using ANOVA, t-test, simple linear regression and multiple resgression. The major findings of this study are as follows : 1. The average length of hospital stay(LOS) was 91.82 days, respectively. 2. Characteristics of Patient LOS of male patients was longer than that of female patients, there was positive correlation between age and LOS and between average wage and LOS. Working period was negatively correlated with LOS. Distance from resident to hospital was positively correlated with LOS and LOS was significantly different dependign on type of duty. 3. Characteristics of Work Place LOS was significantly different depending on types of industry and geographical region of work place. Size of work place was positively correlated with LOS. 4. Characteristics of Back Injury Occupational back pain required shorter LOS compared with back injury due to electric shock. Number of concomitant illnesses and severity of disability were positively correlated with LOS. 5. Characteristics of Hospital Patients treated in community hospitals required significantly longer LOS. Treatment in hospitals with rehabilitation program required decreased LOS. This was more prominent as number of physicians specialized in rehabilitation. 6. Multiple regression analysis revealed that distance form resident to hospital, geographical region of work place, size of work place, number of concomitant illnesses, severity of disability, and type of hospital were factors affecting LOS.

• 대한간호학회지
• /
• 제11권1호
• /
• pp.7-17
• /
• 1981

The purpose of this study is to investigate the relationship between family attitude about mental illness and their general characteristics. The subjects for this study were a sample of 120 families selected from psychiatric ward of one university hospital, which is one national hospital in Seoul. Data was collected from July 1th to August 10th in 3980 used by Opinion about Mental Illness Scale (O.M.I.). The materials were analized by S.P.S.S. program. The findings of the study were as follows: A. Families' attitude toward mental illness shown ay this study was more negative compared to those of Korea1 nursing professorss, nurses and nursing students. B. Variables which influence families' attitude about mental illness: 1. There is no significant between general characteristics and authoritarianism. (p＞ 0.05) 2. Benevolence (Factor B) was found to be significantly related to such variables as religion, eucation levels, existence of mental patient in their an intimate friends. (P < 0.01) Families' attitude about benevolence was mere positive in families who have not relegion or having christion beliefs: haying the higher education levels; not having a mental patient in their an intimate friends. 3. Mental health ideology (Factor C) was found to be significantly related to variable experience of mental illness. (P < 0.01). families' attitude about mental health ideology was more positive in families who had experience of mental illness. 4. Social Restrictiveness (Factor D) was found to be significantly related to variable relationship between families and patients(P<0.01). An intimate friend's attitude about mental health Ideology was mon positive than that of parent and couple. 5. Interpersonal Etiology (Factor E) was found to be significantly related to variable religion (P < 0.05). Families' attitude about interpersonal etiology was more positive in families who have relegion.