• Journal of Medicine and Life Science
• /
• 제20권4호
• /
• pp.141-157
• /
• 2023

Stroke is a leading cause of disability and death. The condition requires prompt diagnosis and treatment. The quality of care provided to patients with stroke can vary depending on the availability of medical resources, which in turn, can affect prognosis. Recently, there has been growing interest in using machine learning (ML) to support stroke diagnosis and treatment decisions based on large medical data sets. Current ML applications in stroke care can be divided into two categories: analysis of neuroimaging data and clinical information-based predictive models. Using ML to analyze neuroimaging data can increase the efficiency and accuracy of diagnoses. Commercial software that uses ML algorithms is already being used in the medical field. Additionally, the accuracy of predictive ML models is improving with the integration of radiomics and clinical data. is expected to be important for improving the quality of care for patients with stroke.

• Journal of Korea Artificial Intelligence Association
• /
• 제2권1호
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• 열처리공학회지
• /
• 제15권1호
• /
• pp.21-24
• /
• 2002

The electrode materials for welding machine in automobile industry such as Cu-Cr, Cu-Zr and Cu-$Al_2O_3$ require the high electrical conductivity and the proper hardness. Therefore the effects of solution heat treatment and aging treatment on the electrical conductivity and hardness of Cu-0.8wt%Cr and Cu-1.2wt%Cr alloys have been investigated. Cu-0.8wt%Cr alloy showed the higher electrical conductivity and hardness than Cu-1.2wt%Cr alloy and both alloys showed the better electrical conductivity at $930^{\circ}C$ among 930, 980 and $1030^{\circ}C$ solution heat treatment temperatures. The electrical conductivity and hardness in both alloys were not affected by aging treatment but remarkably affected by solution heat treatment temperature. The final drawing process reduced electrical conductivity and increased hardness more in Cu-1.2wt%Cr alloy.

• Tuberculosis and Respiratory Diseases
• /
• 제86권3호
• /
• pp.203-215
• /
• 2023

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R² and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R² value was 0.27 and in set II, LightGBM was the best model with the highest R² value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R² value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 추계학술대회(한국공작기계학회)
• /
• pp.336-340
• /
• 2001

Theoretical efforts were taken to investigate an optimum heat treatment process in martensitic stainlesssteel. The approach is based on the combination of the interpolation and extrapolation method of a standard heat treatment technology with the principle of quenching and tempering temperature difference. The relationship of macroscopic structure and fracture toughness and ductility as well as the Hardness and strength has been focused to induce a simple rule to apply with feasibility. As a result it was found that the grain size influences to the fracture toughness and ductility significantly.

• 한국방사선학회논문지
• /
• 제11권2호
• /
• pp.123-130
• /
• 2017

암(caner)라는 중증의 질환을 가지고 있는 환자의 경우, 방사선 치료시 받을 수 있는 불안감, 폐쇄적 공포심을 알아보려 하였다. 연구의 대상은 각각 선형가속기의 치료, 토모테라피 치료를 받는 환자를 대상으로 하였으며 연구의 방법은 설문조사의 방법으로 시행을 하였다. 설문의 내용은 치료시간별로 조사 하였고, (5분 이내의 치료시, 10분이내, 20분 이상, 30분 이상), 장비의 고장으로 인한 치료실 및 치료기기 변경의 경험에 대한 설문조사를 시행하였다. 설문에 성실히 응답한 200개의 설문지를 연구한 결과 방사선치료의 경험이 없을수록 불안감이 많았으며 그 이유로는 치료시 고틍이 있을 것 같다는 의견이 지배적이었다. 치료기로는 선형가속기가 가장 불안감이 높았으며 이유는 환자의 테이블의 개방감 때문인 것으로 나타났다. 가장 안정적인 상태는 토모테라피 치료를 20분 이상 30분 미만 시행한 경우였으며 치료시 토모테라피 치료장비의 아늑함이 원인이었다. 30분이 초과된 경우는 외부와 분리에 대한 불안감으로 불안한 심리상태를 보였다. 본 논문을 통하여 임상에서는 환자의 만족도를 높이는 양질의 의료서비스를 제공하기 위한 제반 자료로 활용되길 기대해 본다.

• 한국기계가공학회지
• /
• 제9권4호
• /
• pp.44-52
• /
• 2010

Recently, with the high performance and efficiency of machine, there have been required the multi-functions in various machine parts, such as the heat resistance, the abrasion resistance and the stress resistance as well as the strength. Fatigue crack growth tests were carried out to investigate the fatigue characteristics of high carbon steel (SM53C) experienced by high-frequency induction treatment. The influence of high-frequency induction treatment on fatigue limit was experimentally examined with the specialfocus on the variation of surface microstructure and the fatigue crack initiation and propagation through fractography. Also, the shape of hardening depth, hardened structure, hardness, and fatigue-fracture characteristics of SM53C composed by carbon steel are also investigated.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 추계학술대회 논문집
• /
• pp.315-320
• /
• 2004

Cutting fluid usually has been used in order to improve machinability, tool life, surface quality. However, problems such as pollution, costs of chip and fluid treatment caused. In this paper, compressed chilly air was used to machine aircraft parts and investigate possibility and advantage of that. The experiments were carried out in various cutting environments, such as wet and compressed chilly air. With respect to the cutting environment, compressed chilly air gave advantages such as decrease of pollution and easy chip treatment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 B
• /
• pp.952-954
• /
• 2000

In the cleaning-water treatment process, the flocculation machine is operated by the V.S motor when the coagulation-facility of the coagulation-process is operated. But after the flocculation machine is stopped by an instantaneous power failure, the transient takes place when the coagulation facility is re-started. To improve the transient state, we developed the reinforcement-circuit which had the function of soft-start and adapted to the field. As a result of this study, we reduced the damage of facilities and had the safety in maintaining the quality of water and improved the efficiency in the maintenance and the management.

• 융합보안논문지
• /
• 제23권1호
• /
• pp.89-95
• /
• 2023

자동차보험 사고 환자의 진료비 감소를 위한 대책 마련에 도움을 주기 위해 본 연구에서는 자동차보험 사고 40대~50대 경상 환자들의 진료비에 가장 핵심 요소인 진료 기간을 예측하고 진료 기간에 영향을 미치는 요인을 분석하였다. 이를 위해 Decision Tree 등 5개 알고리즘을 활용한 머신러닝 모델을 생성하고 모델간에 그 성능을 비교·분석하였다. 진료 기간 예측에 정밀도, 재현율, FI 점수 등 3가지 평가 지표에서 좋은 성능을 나타낸 알고리즘은 Decision Tree, Gradient Boosting 및 XGBoost 등 3가지였다. 그리고 진료 기간 예측에 영향을 미치는 요인 분석 결과, 병원의 종류, 진료 지역, 나이, 성별 등으로 나타났다. 본 연구를 통해 AutoML을 활용한 손쉬운 연구 방법을 제시하였으며, 본 연구 결과가 자동차보험 사고 진료비 경감을 위한 정책에 도움이 되기를 기대한다.