• 응용통계연구
• /
• 제31권4호
• /
• pp.529-538
• /
• 2018

결핵은 높은 이환과 사망을 일으키는 질병으로 현대의학의 발달에 따라 발생률과 사망률은 감소하고 있다. 그러나 한국은 아직까지 OECD 국가 중 결핵 발생률과 사망률이 가장 높다. 이에 따라 한국은 결핵의 예방 및 통제를 위해 여러 정책 사업을 실시하고 있다. 본 연구에서는 공공민간협력(public-private mix) 결핵관리사업이 치료결과에 미치는 영향을 분석하고 결핵환자의 치료 성공에 영향을 미치는 요인을 확인하고자 한다. 질병관리본부에서 관리하는 결핵환자 신고 자료를 이용하여 2012-2015년 전국 결핵 신환자 코호트 약 13만명을 대상으로 분석하였다. 누적 발생 함수(cumulative incidence function)를 이용하여 요인별로 누적 치료 성공률을 비교하였으며. 주 관심사건(치료성공) 및 경쟁사건(사망)을 고려한 두 가지 경쟁위험모형(cause-specific Cox's proportional hazards model and subdistribution hazard model)을 사용하여 분석 결과를 비교하였다.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.302-310
• /
• 2022

Efficient use of limited blood products is becoming very important in terms of socioeconomic status and patient recovery. To predict the appropriateness of patient-specific transfusions for the intensive care unit (ICU) patients who require real-time monitoring, we evaluated a model to predict the possibility of transfusion dynamically by using the Medical Information Mart for Intensive Care III (MIMIC-III), an ICU admission record at Harvard Medical School. In this study, we developed an explainable machine learning to predict the possibility of red blood cell transfusion for major medical diseases in the ICU. Target disease groups that received packed red blood cell transfusions at high frequency were selected and 16,222 patients were finally extracted. The prediction model achieved an area under the ROC curve of 0.9070 and an F1-score of 0.8166 (LightGBM). To explain the performance of the machine learning model, feature importance analysis and a partial dependence plot were used. The results of our study can be used as basic data for recommendations related to the adequacy of blood transfusions and are expected to ultimately contribute to the recovery of patients and prevention of excessive consumption of blood products.

• 디지털융복합연구
• /
• 제18권7호
• /
• pp.299-306
• /
• 2020

본 연구는 환자중심성 의료문화 변화에 따라, 데이터마이닝 기법을 이용한 융복합 외래 의료서비스 환자경험조사 연구를 시행하여 환자중심성 의료기관 경영전략에 도움이 될 수 구체적 방안을 모색하고자 하였다. '2018 의료서비스경험조사' 원시자료를 이용하여 외래 의료서비스 환자경험이 있는 만 15세 이상 8,843명을 분석하였다. 의사결정나무분석을 수행하였다. 외래 의료서비스 환자경험에 대한 전반적 만족도 결정요인은 의사와 환자 권리보호였으며 추천의사 결정요인은 의사와 시설의 안락함과 편안함이었다. 여성이 남성에 비해 전반적 만족도에서 경험을 긍정적으로 평가했으며 60세 이상이 전반적 만족도와 추천의사에 대한 경험을 긍정적으로 평가했다. 외래 의료서비스 환자경험 의사결정예측 모형을 제시하고 의사 영역과 환자권리보호 영역, 시설의 안락함과 편안함이 중요한 요인임을 확인한 점이 의의가 있다. '의료서비스경험조사'에 대한 종단적 연구가 필요하며 입원 의료서비스경험에 대한 연구가 필요하다.

• 전기학회논문지
• /
• 제64권3호
• /
• pp.429-432
• /
• 2015

Radio Frequency (RF) coils in Magnetic Resonance Imaging (MRI) systems interact with a patient's tissues, resulting in the absorption of RF energy by the tissues. The presence of an electrically conducting medical implant may concentrate the RF energy and causes tissue heating near the implant devices. Here we present a novel design for a medical lead to reduce this undesired heating. Specific Absorption Rate (SAR), an indicator of heating, was calculated. Remcom XFdtd software was used to calculate the peak SAR distribution (1g and 10 g) in a realistic model of the human body. The model contained a medical lead that was exposed to RF magnetic fields at 64 MHz (1.5 T MRI), 128 MHz (3 T MRI) and 300 MHz (7 T MRI) using a model of an MR birdcage body coil. Our results demonstrate that, our proposed design of adding nails to the medical lead can significantly reduce the SAR for different MRI systems.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권2호
• /
• pp.867-870
• /
• 2014

Purpose: This study used receiver operating characteristic curve to analyze Surveillance, Epidemiology and End Results (SEER) ependymoma data to identify predictive models and potential disparity in outcome. Materials and Methods: This study analyzed socio-economic, staging and treatment factors available in the SEER database for ependymoma. For the risk modeling, each factor was fitted by a Generalized Linear Model to predict the outcome ('brain and other nervous systems' specific death in yes/no). The area under the receiver operating characteristic curve (ROC) was computed. Similar strata were combined to construct the most parsimonious models. A random sampling algorithm was used to estimate the modeling errors. Risk of ependymoma death was computed for the predictors for comparison. Results: A total of 3,500 patients diagnosed from 1973 to 2009 were included in this study. The mean follow up time (S.D.) was 79.8 (82.3) months. Some 46% of the patients were female. The mean (S.D.) age was 34.4 (22.8) years. Age was the most predictive factor of outcome. Unknown grade demonstrated a 15% risk of cause specific death compared to 9% for grades I and II, and 36% for grades III and IV. A 5-tiered grade model (with a ROC area 0.48) was optimized to a 3-tiered model (with ROC area of 0.53). This ROC area tied for the second with that for surgery. African-American patients had 21.5% risk of death compared with 16.6% for the others. Some 72.7% of patient who did not get RT had cerebellar or spinal ependymoma. Patients undergoing surgery had 16.3% risk of death, as compared to 23.7% among those who did not have surgery. Conclusion: Grading ependymoma may dramatically improve modeling of data. RT is under used for cerebellum and spinal cord ependymoma and it may be a potential way to improve outcome.

• 보건행정학회지
• /
• 제31권4호
• /
• pp.518-530
• /
• 2021

Background: This study examined the effect of having a usual source of care on the degree of patient-centered communication among persons with disability. The role of the usual source of care has been emphasized to improve patient experience, especially for patients with complex health conditions. Methods: This study used the 2017-2018 Korean Health Panel data, and the final study observations were 22,475 (20,806 people without disability and 1,669 people with disability). We applied generalized estimating equation model to show the effect of having a usual source of care on patient-centered communication, and subgroup analysis considering the types and severity of disabilities. Results: Persons who have disabilities, compared with ones without it, significantly had more usual sources of care (32.4% vs. 24.6%). By type of disability, persons with mental (51.4%), internal organ (43.8%), visual (37%), and physical disabilities (31.6%) had more usual sources of care than hearing/speech (26.6%), and developmental disabilities (18.6%). The average score of patient-centered communication was higher among who had a usual sources of care (3.2 vs. 2.7), and the regression analysis showed that having a usual sources of care was positively associated with higher patient-centered communication score (𝛽=0.476, p<0.05). However, the positive effects of usual sources of care was not observed among persons with severe hearing/speech, developmental, and mental disabilities. Conclusion: This study showed that role of patient-centered communication was limited in persons with severe hearing/speech disabilities, developmental, and mental disabilities. The education programs and supports are needed to improve communication skills between medical staff and persons with specific types of disabilities.

• Journal of Radiation Protection and Research
• /
• 제34권3호
• /
• pp.95-101
• /
• 2009

Protective behavior of radiological technologists against radiation exposure is important to achieve reduction of the patient doses without compromising medical achievements. This study attempts to provide a basic model for the sophisticated intervention strategy that increases the level of the protective behavior of the technologists. The model was applied to real situations in Korea to demonstrate its utility. The results of this study are summarized as follows: First, the protective environment showed the highest relationship in the factors considered, r=0.637 (p<0.01). Secondly, the important factors were protective environment in environment characteristics, expectation for the protective behavior 0.228 (p<0.001), self-efficacy 0.142 (p<0.001), and attitude for the protective behavior 0.178 (p<0.001) in personal characteristics, and daily patient -0.112 (p<0.001) and number of the participation in the education session for the protective behavior 0.074 (p<0.05). Thirdly, the final protective behavior model by a path analysis method had direct influence on the attitude 0.171 (p<0.01) and environment 0.405 (p<0.01) for the protective behavior, self efficacy 0.122 (p<0.01), expectation for the protective behavior 0.16 (p<0.01), and self-efficacy in the specialty of projects 0.154 (p<0.01). The acceptance of the model determined by the absolute fit index (GFI), 0.969, and by the incremental fit index (CFI), 0.943, showed very significant levels. Value of $x^2$/df that is a factor applied to verify the acceptance of the model was 37, which implies that the result can be accepted in the desirable range. In addition, the parsimonious fit index configured by AGFI (0.890) and TLI (0.852) was also considered as a scale that accepts the model in practical applications. In case of the establishment of some specific intervention strategies based on the protective behavior model against harmful radiation effects proposed in this study, the strategy will provide an effective way to prevent medical harmful radiation effects that could cause severe injuries to people.

• Journal of Hospice and Palliative Care
• /
• 제20권1호
• /
• pp.1-7
• /
• 2017

이 논문은 개인적으로 경험되는 독특한 희망경험을 찾도록 도와주기 위하여 저자들이 개발한 "희망 찾기 내러티브 커뮤니케이션 모델"에 대하여 서술한다. 모델은 희망과 희망경험의 본질에 대한 문헌 및 저자들의 연구결과들과 주관적인 의미들과 경험들로서 희망 개념, 개인 특수한 희망경험에 접촉하기 위한 방법으로서 이야기하기 과정 및 내러티브 구성의 개념, 그리고 개인중심커뮤니케이션의 통합에 근거 개발되었다. 모델을 적용한 한 연구의 희망 찾기 경험은 모델을 한층 명확하게 하였다. 개인중심커뮤니케이션을 통하여 이야기하기와 내러티브 구성을 통합하는 모델은 세 요소들-이야기하기 요소, 내러티브 중재 요소, 커뮤니케이션 요소-로 구성된다. 이러한 요소들은 화자로서의 대상자가 희망경험의 근본인 개인 특수 주제적 플롯을 가진 희망 내러티브를 생산하는데 필수적으로 요구되는 커뮤니케이션 촉진자로서의 중재자의 적극적인 참여 속에서 개인-특수 희망경험을 찾는 것을 목적으로 하는 하나의 중재로서 과정화된다. 대상자에서 이 모델을 적용하여 성공적인 개인 희망경험 찾기의 긍정적인 결과가 나타났다. 이 모델의 성공은 중재자의 모델에 대한 이해와 개인중심-커뮤니케이션 전략 적용능력에 기인된 것으로 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권4호
• /
• pp.826-842
• /
• 2024

As 5G and AI continue to develop, there has been a significant surge in the healthcare industry. The COVID-19 pandemic has posed immense challenges to the global health system. This study proposes an FL-supported edge computing model based on federated learning (FL) for predicting clinical outcomes of COVID-19 patients during hospitalization. The model aims to address the challenges posed by the pandemic, such as the need for sophisticated predictive models, privacy concerns, and the non-IID nature of COVID-19 data. The model utilizes the FATE framework, known for its privacy-preserving technologies, to enhance predictive precision while ensuring data privacy and effectively managing data heterogeneity. The model's ability to generalize across diverse datasets and its adaptability in real-world clinical settings are highlighted by the use of SHAP values, which streamline the training process by identifying influential features, thus reducing computational overhead without compromising predictive precision. The study demonstrates that the proposed model achieves comparable precision to specific machine learning models when dataset sizes are identical and surpasses traditional models when larger training data volumes are employed. The model's performance is further improved when trained on datasets from diverse nodes, leading to superior generalization and overall performance, especially in scenarios with insufficient node features. The integration of FL with edge computing contributes significantly to the reliable prediction of COVID-19 patient outcomes with greater privacy. The research contributes to healthcare technology by providing a practical solution for early intervention and personalized treatment plans, leading to improved patient outcomes and efficient resource allocation during public health crises.

• BMB Reports
• /
• 제52권6호
• /
• pp.349-359
• /
• 2019

After the first research declaring the generation of human induced pluripotent stem cells (hiPSCs) in 2007, several attempts have been made to model neurodegenerative disease in vitro during the past decade. Parkinson's disease (PD) is the second most common neurodegenerative disorder, which is mainly characterized by motor dysfunction. The formation of unique and filamentous inclusion bodies called Lewy bodies (LBs) is the hallmark of both PD and dementia with LBs. The key pathology in PD is generally considered to be the alpha-synuclein (${\alpha}$-syn) accumulation, although it is still controversial whether this protein aggregation is a cause or consequence of neurodegeneration. In the present work, the recently published researches which recapitulated the ${\alpha}$-syn aggregation phenomena in sporadic and familial PD hiPSC models were reviewed. Furthermore, the advantages and potentials of using patient-derived PD hiPSC with focus on ${\alpha}$-syn aggregation have been discussed.