• 지역사회간호학회지
• /
• 제16권2호
• /
• pp.127-136
• /
• 2005

Purpose: The purpose of this study was to present the outcomes of the district visiting nursing services. Method: We analyzed nursing records and inspected public health center data for evaluating nursing tasks. and conducted a telephone survey of 651 district inhabitants. Results: According to the result, the coverage of the district population, the rate of new registration and overall program activities increased. Meanwhile, accessibility of visiting health care, the level of health problem management, personal cognition and satisfaction concerning visiting nursing care increased, but there was little change in personal perception of health improvement. Furthermore, the status of client management was improved. In the analysis of participation in national cancer screening program, we found that there was twice higher participation in the district than others. Conclusion: We suggest that this district visiting nursing system takes responsibility for district inhabitant health management. Based on the study, we also suggest that the government and local autonomous entities should increase administrative and financial supports to execute the district-based visiting nursing system in wider areas.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.267-275
• /
• 2023

This paper presents the development of specialized software for annotating volume-of-interest on ¹⁸F-FDG PET/CT images with the goal of facilitating the studies and diagnosis of head and neck cancer (HNC). To achieve an efficient annotation process, we employed the SE-Norm-Residual Layer-based U-Net model. This model exhibited outstanding proficiency to segment cancerous regions within ¹⁸F-FDG PET/CT scans of HNC cases. Manual annotation function was also integrated, allowing researchers and clinicians to validate and refine annotations based on dataset characteristics. Workspace has a display with fusion of both PET and CT images, providing enhance user convenience through simultaneous visualization. The performance of deeplearning model was validated using a Hecktor 2021 dataset, and subsequently developed semi-automatic annotation functionalities. We began by performing image preprocessing including resampling, normalization, and co-registration, followed by an evaluation of the deep learning model performance. This model was integrated into the software, serving as an initial automatic segmentation step. Users can manually refine pre-segmented regions to correct false positives and false negatives. Annotation images are subsequently saved along with their corresponding ¹⁸F-FDG PET/CT fusion images, enabling their application across various domains. In this study, we developed a semi-automatic annotation software designed for efficiently generating annotated lesion images, with applications in HNC research and diagnosis. The findings indicated that this software surpasses conventional tools, particularly in the context of HNC-specific annotation with ¹⁸F-FDG PET/CT data. Consequently, developed software offers a robust solution for producing annotated datasets, driving advances in the studies and diagnosis of HNC.

• Journal of Hospice and Palliative Care
• /
• 제18권4호
• /
• pp.329-334
• /
• 2015

목적: 본 연구는 보건소에 등록된 재가 호스피스 완화돌봄 대상자의 특성과 증상을 분석하는 것이다. 방법: 부산광역시 소재 6개구 보건소에 등록된 호스피스 완화돌봄 대상자 144명의 초기 방문기록지(호스피스대상자 등록카드, 초기 통증평가지, 초기 통증 외 증상평가지)를 후향적으로 분석하였다. 결과: 대상자의 평균 연령은 67.7세이었으며, 혼자 사는 대상자가 46.2%, 교육정도는 중졸 이하가 65%였다. 종교는 불교가 36.3%로 가장 많았고, 47.5%가 의료급여 대상자였다. 진단명은 폐암, 위암, 간암의 순이었고, 기능 상태는 일상생활이 어려운 경우가 48.9%로 나타났다. 등록 당시 암 치료 중인 대상자는 39.6%이었고, 84.5%가 말기상태를 인지하고 있었다. 대상자들의 83.6%에서 통증을 호소하였으며, 그 중 36.5%에서 중간정도 이상의 통증을 호소하였다. 통증 외 증상에서 가장 많은 대상자가 호소하는 증상으로는 피로(84.7%)였으며, 피로를 호소하는 대상자의 49.3%가 중증의 증상을 호소하는 것으로 나타났다. 결론: 본 연구결과 재가 호스피스 완화돌봄 대상자들은 사회경제적 취약군으로, 중간정도 이상의 통증과 통증 외 증상을 호소하는 대상자가 많았다. 따라서 재가 호스피스 완화돌봄 대상자의 효율적인 관리를 위해서는 대상자 특성에 따른 차별화된 통합적 전략이 필요하다.

• 한국정보전자통신기술학회논문지
• /
• 제16권2호
• /
• pp.87-96
• /
• 2023

최근 의학계에서도 딥러닝 기술을 이용한 질병의 치료결과 예측 연구가 활발하다. 그러나, 소규모 환자 데이터와 특정한 딥러닝 알고리즘을 선택·활용, 연구를 진행하여 특정 조건 아래에서 의미 있는 결과를 보여주었다. 본 연구에서는 연구 결과의 일반화를 위하여 환자 대상을 좀 더 확대·세분화하여 80대·90대·100대 남녀 대상으로 폐암 진단 후 사망률 예측 연구 결과를 도출하였다. 건강보험심사평가원의 대규모 진료 정보와 다종의 딥러닝 알고리즘을 제공하는 AutoML을 이용, 80대·90대·100대 남녀의 폐암 진단 후 84개월간의 사망률 예측을 위해 Decision Tree, Random Forest, Gradient Boosting, XGBoost, Logistic Regression 등 5개 알고리즘별 모델을 생성하고 이를 통해 예측 성능을 비교하고 사망률에 영향을 미치는 요인에 대한 분석도 추진하였다. 연구 결과, 80대와 90대에서 남성이 여성보다 사망 예측률이 더 높았으며 100대에서는 여성의 사망 예측률이 남성보다 높게 나타났다. 그리고 사망률에 가장 큰 영향을 미치는 요인으로는 치료기간으로 분석되었다.

• 대한간호학회지
• /
• 제48권2호
• /
• pp.123-142
• /
• 2018

Purpose: This study was conducted to evaluate the effectiveness of non-pharmacologic interventions in chemotherapy-induced peripheral neuropathy (CIPN). Methods: PubMed, Cochrane Library CENTRAL, EMBASE, CINAHL, and several Korean databases (Until August 2017) were searched. The main search strategy combined terms for peripheral neuropathy and presence of neoplasms. The risk of bias was assessed using the Cochrane's Risk of Bias tool for randomized studies and the Risk of Bias Assessment tool for non-randomized studies. To estimate the effect size, a meta-analysis of the studies was performed using the Rev Man 5.3 program of the Cochrane Library random-effects models were used in the analyses. Results: Twenty-two studies with a total of 954 participants met the inclusion criteria. Of the 22 studies, 12 were used to estimate the effect size of the non-pharmacologic interventions. The non-pharmacologic interventions used in patients with CIPN were exercise, acupuncture, massage, and foot bath. The acupuncture significantly reduced CIPN symptoms and signs (d=-0.71) and CIPN pain (d=-0.73) (p<.001). Massage and foot bath were also effective in reducing CIPN symptoms (d=-0.68; 95% CI=-1.05, -0.30; p<.001; $I^2=19%$).Exercises were effective in improving muscle strength and endurance(d=-0.55) and quality of life (d=-2.96), but they were not significantly effective in improving CIPN. Conclusion: Although these results provide little evidence of the effectiveness of acupuncture, massage, and foot bath in the treatment of CIPN, they suggest that these interventions can reduce CIPN symptoms in patients with cancer. However, the findings of this study should be interpreted with caution as there is a relative lack of data in this field, and additional well-designed studies are needed. PROSPERO registration: CRD42017076278.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권8호
• /
• pp.3625-3628
• /
• 2014

Background: To evaluate the incidence, diagnosis and management of GTN among 28 centers in Turkey. Materials and Methods: A retrospective study was designed to include GTN patients attending 28 centers in the 10-year period between January 2003 and May 2013. Demographical characteristics of the patients, histopathological diagnosis, the International Federation of Gynecology and Obstetrics (FIGO) anatomical and prognostic scores, use of single-agent and multi-agent chemotherapy, surgical interventions and prognosis were evaluated. Results: From 2003-2013, there were 1,173,235 deliveries and 456 GTN cases at the 28 centers. The incidence was calculated to be 0.38 per 1,000 deliveries. According to the evaluated data of 364 patients, the median age at diagnosis was 31 years (range, 15-59 years). A histopathological diagnosis was present for 45.1% of the patients, and invasive mole, choriocarcinoma and PSTTs were diagnosed in 22.3% (n=81), 18.1% (n=66) and 4.7% (n=17) of the patients, respectively. Regarding final prognosis, 352 (96.7%) of the patients had remission, and 7 (1.9%) had persistence, whereas the disease was mortal for 5 (1.4%) of the patients. Conclusions: Because of the differences between countries, it is important to provide national registration systems and special clinics for the accurate diagnosis and treatment of GTN.