• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2023

Research using AI and big data is also being actively conducted in the health and medical fields such as disease diagnosis and treatment. Most of the existing research data used cohort data from research institutes or some patient data. In this paper, the difference in the prediction rate of survival and the factors affecting survival between breast cancer patients in their 40~50s and other age groups was revealed using health insurance review claim data held by the HIRA. As a result, the accuracy of predicting patients' survival was 0.93 on average in their 40~50s, higher than 0.86 in their 60~80s. In terms of that factor, the number of treatments was high for those in their 40~50s, and age was high for those in their 60~80s. Performance comparison with previous studies, the average precision was 0.90, which was higher than 0.81 of the existing paper. As a result of performance comparison by applied algorithm, the overall average precision of Decision Tree, Random Forest, and Gradient Boosting was 0.90, and the recall was 1.0, and the precision of multi-layer perceptrons was 0.89, and the recall was 1.0. I hope that more research will be conducted using machine learning automation(Auto ML) tools for non-professionals to enhance the use of the value for health insurance review claim data held by the HIRA.

• Proceeding of EDISON Challenge
• /
• 2017.03a
• /
• pp.712-714
• /
• 2017

미병의 예방과 관리의 중요성이 거론되고 있으나, 미병에 대한 분류나 진단을 위한 확고한 근거가 미약한 상황으로서 미병 진단 인자 분류를 위한 생리시스템 모델 개발이 필요한 시점이다. 본 연구의 목적은 개발한 생리학적 모델이 미병 단계를 구별하는데 효과 및 유용성이 있는지를 임상 검증하기 위하여 생리학적 모델 인공지능 시뮬레이션을 개발하고자 함이다. 인공지능 계산은 3층으로 구성된 네트워크를 이용하였으며 각 층은 30개의 neuron들로 구성하였다. 인공지능망의 입력 값은 나이, 수축기 혈압, 이완기 혈압, 심박수 값 (입력 값 4개)이고 출력 값은 혈관 저항값인 Ra이다. 머신러닝 차수를 높이면서 인공지능을 사용하지 않은 생리적 모델로부터 도출된 결과와 인공지능을 통하여 계산된 결과를 비교하였다. 개발된 인공지능계산을 이용한 생리시스템 모델은 대량의 표본집단에서 임상 검증에 기여할 것이다.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.577-579
• /
• 2021

의료영상기반의 인공지능 연구는 질환의 조기진단 및 예측 분야에 눈부신 기술발전이 되어왔다. 근감소증 질환은 다양한 기저질환을 기반으로 발생하며, 특히 60대 이상은 30%의 유병율을 갖는다. 해당 질환은 임상적인 진단 방법의 발달과 임상 결과가 알려지면서 관심이 증가하고 있다. 최근 근감소증 진단방법 중의 하나로 CT 또는 MR 의료영상을 통한 진단방법이 제시되었다. 본 논문에서는 인공지능을 기반으로 하여, 근감소증을 진단하기 위해 척추부위 중 Lumbar 3 영역의 근육, 지방 영역의 영상분할 모델을 제시하고자 한다. 이를 위해 인공지능 영상분할 모델을 개발하는 과정과 그 근육과 지방의 영상분할 결과를 보인다. 본 논문에서 제시한 영상분할모델을 통해 근감소증을 빠르게 진단할 수 있을 것으로 기대한다.

• Journal of Nutrition and Health
• /
• v.42 no.2
• /
• pp.119-127
• /
• 2009

Malnutrition of hospitalized patients can adversely affect clinical outcomes and cost. Several nutritional screening tools have been developed to identify patients with malnutrition risk. However, many of those possess practical pitfalls of requiring much time and labor to administer and may not be highly applicable to a Korean population. This study sought to develop and evaluate a Nutrition Risk Screening Tool (NRST) which is simple and quick to administer and widely applicable to Korean hospitalized patients with various diseases. The study was also designed to generate a screening tool predictable of various clinical outcomes and to validate it against the Nutritional Risk Screening 2002 (NRS 2002). Electronic medical records of 424 patients hospitalized at a general hospital in Seoul during a 14-month period were abstracted for anthropometric, medical, biochemical, and clinical outcome variables. The study employed a 4-step process consisting of selecting NRST components, searching a scoring scheme, validating against a reference tool, and confirming clinical outcome predictability. NRST components were selected by stepwise multiple regression analysis of each clinical outcome (i.e., hospitalization period, complication, disease progress, and death) on several readily available patient characteristics. Age and serum levels of albumin, hematocrit (Hct), and total lymphocyte count (TLC) remained in the last model for any of 4 dependent variables were decided as NRST components. Odds ratios of malnutrition risk based on NRS 2002 according to levels of the selected components were utilized to frame a scoring scheme of NRST. A NRST score higher than 3.5 was set as a cut-off score for malnutrition risk based on sensitivity and specificity levels against NRS 2002. Lastly differences in clinical outcomes by patients' NRST results were examined. The results showed that the NRST can significantly predict the in-hospital clinical outcomes. It is concluded that the NRST can be useful to simply and quickly screen patients at high-nutritional risk in relation to prospective clinical outcomes.

• Radiation Oncology Journal
• /
• v.29 no.1
• /
• pp.11-19
• /
• 2011

Purpose: To evaluate the pathological and clinical effects of preoperative chemoradiation (CCRT) in cases of locally advanced rectal cancer and to determine the predictive factors for tumor downstaging. Materials and Methods: From March 2004 to August 2008, 33 patients with locally advanced rectal cancer were treated with preoperative CCRT. Twenty-eight patients (84.8%) were treated using a concomitant boost technique while five (15.2%) patients were treated using a cone down boost technique. All patients received 50.4 Gy of irradiation and concurrent chemotherapy with 5-fluorouracil. The median follow-up duration was 24.2 months (range, 9.8 to 64.7 months). Results: Thirty-one (93.9%) patients underwent surgery. Twenty-four patients (72.7%) underwent anal sphincter-preserving surgery. The 3-year disease free survival (DFS) and overall survival rates were 63.4% and 78.8%, respectively. Post-operative factors were more important for DFS. Pathologic N stage, margin status, and pathologic differentiation were significant prognostic factors (p=0.001, 0.029, 0.030). Tumor size and lymphovascular invasion were also associated with marginal significance (p=0.081, 0.073). However, only pre-treatment T stage was a significant pre-operative factor (p=0.018). The complete pathological response rate was 9.1 %. T-downstaging was observed in ten (30.3%) patients, whereas N-downstaging was found in 24 (72.7%) patients. Pre-treatment T stage and the interval between CCRT and operation were the predictive factors for downstaging in a univariate analysis (p=0.029, 0.027). Pre-treatment carcinoembryogenic antigen was also associated with marginal significance (p=0.068). Conclusion: The survival of rectal cancer patients can be better determined based on post-operative findings. Therefore, pre-operative CCRT for downstaging of the tumor seems to be important. Pre-treatment T stage and the interval between CCRT and operation can be used to predict downstaging.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.2
• /
• pp.290-298
• /
• 2016

This study was conducted to develop a model that explains the factors influencing the clinical nurses' willingness to perform Basic Life Support and to verify the appropriateness of the model. The participants were 550 clinical nurses working at a university hospital in Korea. The data were collected from self-reported questionnaires from October 2012 to February 2013. A total of 520 questionnaires were analyzed using the SPSS/WIN 20.0 and Amos version 18.0 software packages. The results indicated that the clinical nurses' knowledge of basic life support had a direct impact and their clinical experience had an indirect impact on their willingness to perform basic life support at the scene. These variables together explained 19.5% of the variance in the nurses' willingness to perform Basic Life Support. The clinical experience was correlated significantly with knowledge (r=.61, p<.001). To increase the clinical nurses' performance of Basic Life Support, knowledge and clinical experience should be reinforced by continuous in-service education on Basic Life Support, considering the disease status of hospitalized patients.

• Physical Therapy Korea
• /
• v.4 no.2
• /
• pp.89-99
• /
• 1997

임상 결과의 측정에서 새로운 관점을 갖는 것은 중요하다. 의료 재활은 심리적 측정의 질들(표준화, 신뢰도, 타당도)에서 충분한 노력에 수행되어지지 않아 왔기 때문에 환자와 프로그램 사이에 일반화된 기능적인 평가 범위가 부족하다. 장애의 적절한 측정을 위한 요구는 기능적인 상태에서 변화들을 알리고 치료의 필요성을 평가하고 치료를 계획하고 결과를 예측하고 보상 방법을 측정하기 위한 환자의 치료와 임상 연구에서 모두 나타난다. 세계적으로 사용되어지고 있는 기능 평가 도구인 FIM으로부터 이 연구는 신체적 측정의 기대되어진 것에 유사한 비율로 기능적 평가 측정들을 구성한다. 노인 재활에서 기능적인 결과의 측정은 중요한 몇 가지 점이 있다. 첫째는 접근에 기초한 기능적인 결과는 치료 목표 설정에 필요하다. 둘째는 도구는 기능적인 향상을 예상하는데 유용해야 한다. 셋째는 기능 평가는 적절한 타당도와 신뢰도와 함께 고려되어져야만 한다. 넷째는 다른 기능적 도구들이 함께 평가되어져야 할 필요가 있다는 것이다. FIM의 목록의 어려운 접들은 손상을 입은 집단에서는 다소 다양하다. 가장 중요한 부분이기 때문에 하나의 운동범위는 요통과 화상을 입은 환자를 제외한 모든 손상을 입은 집단들에게 적용되어 질 수 있다. 기능의 운동과 인지적인 면은 구분되어지는 것이 중요하였고 분리되어져서 치료되어 졌다. 어려운 목록들은 손상을 입은 집단에서 다양하였고, 다양한 손상의 종류의 독특한 영향을 반영하였다. FIM은 기능적인 장애를 측정하기 위해 고안되어진 또 다른 도구이다. 그리고 다른 것들은 의료 재활을 위한 국제적 자료 체계를 만들기 위한 것이다. FIM의 목적은 의료 재활의 결과를 확인하고 장애의 정도의 측정을 포함한다. FIM은 7가지 수준에서 사회적 인지, 의사 소통, 이동, 움직임 (mobility), 소변 관리, 자조 활동을 평가한다. 범위는 총체적 도움의 비율로부터 완전하게 독립적인 것까지의 범위이고 도움, 감독, 도구의 사용의 범위를 고려한다. 27,009의 환자를 조사한 최근 검사 기록들은 FIM이 움직임(motor)과 인지 기능을 평가하는 것이라는 것을 보여준다(Hinemann, 1993). FIM의 저자들은 자료가 프로그램 평가의 시도에서 즉각적으로 적용 할 수 있기를 기대한다. FSI은 어떤 과제의 수행에서 어려움에 관계된 정보를 제공하는 것을 나타내고 과제를 수행하기 위한 환자를 위한 변경된 전략들을 발달시키기 위해 노력하는 임상가들에게 유용할 수 있다. 두 도구 모두는 전통적인 범위들보다 고관절 골절을 동반한 장애의 좀더 정확한 정보를 모으도록 할 수 있다. 고찰된 모든 연구의 결과들은 골절 후에 남아 있는 잔여 장애의 중요한 수준을 강조한다. 골절 전의 보행으로 회복된 사람은 매우 드물었다. 대부분은 기본적인 움직임 혹은 옷입기, 개인 위생에 관계된 활동들에서 의존적이었다. 많은 사람들은 사회에서 활동을 할 수 없었다. 장애의 적절한 측정의 요구는 환자 치료와 기능적인 상태에서 변화를 알고 치료의 요구도를 측정하고 치료를 계획하고 결과를 예상하고 보상 수단을 결정하는 임상적 연구에서 모두 나타난다. 물리치료 분야는 분야의 다른 영역에서 기능적인 결과를 충족시키고 발달시키는 것이 필요하다.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.701-710
• /
• 2012

Retinitis Pigmentosa(RP) is a common hereditary disease. While they have been normally living, those who have this symptom feel frustration and pain by the damage of visual acuity. At the national level, the loss of the economic activity due to the reduction of economically active population will be also greater. There is an urgent need for the base study that can provide the clinical prognosis information of RP disease. In this study, we suggest that it is possible to predict prognosis through the pattern classification of RP data. Statistical processing results through statistical software like SPSS(Statistical Package for the Social Service) were mainly applied for the conventional study in data analysis. However, machine learning and automatic pattern classification was applied to this study. SVM(Support Vector Machine) and other various pattern classifiers were used for it. The proposed method confirmed the possibility of prognostic prediction based on the result of automatically classified RP data by SVM classifier.

• The korean journal of orthodontics
• /
• v.38 no.4
• /
• pp.252-264
• /
• 2008

Objective: To aid the development of a frontal image simulating program, we evaluated the soft tissue frontal changes in relationship to movement of hard tissue with orthognathic surgery of facial asymmetry patients. Methods: Preoperative and postoperative frontal cephalograms and frontal view photographs of 45 mandibular surgery patients with facial asymmetry were obtained in a standardized manner. Vertical and horizontal changes of hard tissue and soft tissue were measured from cephalograms and photographs, respectively. Soft tissue change in result to hard tissue change was then analyzed. Results: Both vertical and horizontal correlation analysis showed a weak relationship between the changes. Hard tissue points that were picked for 1 : 1 mean ratio with soft tissue points did not show any significant relevance. For each soft tissue change, regressive equation was formulated by stepwise multiple regression analysis, and the equation for soft tissue Menton was most reliable in predicting changes. Both vertical and horizontal hard tissue changes were used together in prediction of vertical or horizontal soft tissue change. Conclusions: The results suggest that computerized image simulation using regression analysis may be of help for prediction of soft tissue change, while 1:1 mean ratio method is not useful.

• Korean Journal of Clinical Laboratory Science
• /
• v.55 no.1
• /
• pp.29-36
• /
• 2023

This study proposes a spirometry reference equation suitable for Asian migrant workers undergoing special health examinations. The study participants were divided according to their region: Central Asia, Northeast Asia, and South Asia Pacific. We confirmed results of the spirometry analysis of migrant workers and the interpretation consistency between the prediction equations. Based on this data, we propose a reference equation suitable for domestic migrant workers and suggest a scaling factor applicable to the spirometer wherein the reference equation is not easily applicable. The kappa-values obtained for men and women, respectively, between the global lung function initiative 2012 (GLI2012)-Southeast Asian and the Southeast Asian equations were 0.819 and 0.770, between the GLI2012-Southeast Asian and the South Asian equations were 0.881 and 0.866, and between the GLI2012-Northeast Asian and the Central Asian equations were 0.831 and 0.833. We propose applying the GLI2012-Northeast Asian equation for Northeast Asian and Central Asian countries, whereas the GLI2012-Southeast Asian equation was found to be more suitable for predicting Southeast Asian and South Asian populations. For spirometry, we recommend applying a scaling factor of 0.87 to the Dr. Choi equation, wherein the GLI2012-Southeast Asian equation is not applicable.