• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.442-449
• /
• 2019

Objective : Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT. Methods : We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation. Results : The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900). Conclusion : This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.

• Journal of Yeungnam Medical Science
• /
• v.35 no.2
• /
• pp.171-178
• /
• 2018

Background: To evaluate mid-term oncological and functional outcomes in patients with prostate cancer treated by robot-assisted laparoscopic radical prostatectomy (RALP) at our institution. Methods: We retrospectively reviewed the medical records of 128 patients with prostate cancer who underwent RALP at our institution between February 2008 and April 2010. All patients enrolled in this study were followed up for at least 5 years. We analyzed biochemical recurrence (BCR)-free survival using a Kaplan-Meier survival curve analysis and predictive factors for BCR using multivariate Cox regression analysis. Continence recovery rate, defined as no use of urinary pads, was also evaluated. Results: Based on the D'Amico risk classification, there were 30 low-risk patients (23.4%), 47 intermediaterisk patients (38.8%), and 51 high-risk patients (39.8%), preoperatively. Based on pathological findings, 50.0% of patients (64/128) showed non-organ confined disease (${\geq}T3a$) and 26.6% (34/128) had high grade disease (Gleason score ${\geq}8$). During a median follow-up period of 71 months (range, 66-78 months), the frequency of BCR was 33.6% (43/128) and the median BCR-free survival was 65.9 (0.4-88.0) months. Multivariate Cox regression analysis revealed that high grade disease (Gleason score ${\geq}8$) was an independent predictor for BCR (hazard ratio=4.180, 95% confidence interval=1.02-17.12, p=0.047). In addition, a majority of patients remained continent following the RALP procedure, without the need for additional intervention for post-prostatectomy incontinence. Conclusion: Our study demonstrated acceptable outcomes following an initial RALP procedure, despite 50% of the patients investigated demonstrating high-risk features associated with non-organ confined disease.

• Journal of Chest Surgery
• /
• v.55 no.5
• /
• pp.378-387
• /
• 2022

Background: Atrial fibrillation (Afib) is a marker of increased cardiovascular morbidity and mortality. Owing to the increased prevalence of Afib in patients undergoing cardiac surgery, assessing the effect of Afib on postsurgical outcomes is important. We aimed to analyze the effect of preoperative Afib on clinical outcomes in patients undergoing cardiac surgery using a large surgical database. Methods: This retrospective cohort study was based on the national health claims database established by the National Health Insurance Service of the Republic of Korea from 2009 to 2015. Diagnosis and procedure codes were used to identify diseases according to the International Statistical Classification of Diseases, 10th revision. Results: We included 1,037 patients (0.1%) who had undergone cardiac surgery from a randomized 1,000,000-patient cohort, and 15 patients (1.5%) treated with isolated surgical Afib ablation were excluded. Of these 1,022 patients, 412 (39.7%), 303 (29.2%), and 92 (9.0%) underwent coronary artery bypass, heart valve surgery, and Cox-maze surgery, respectively. Preoperative Afib was associated with higher patient mortality (p=0.028), regardless of the surgical procedure. Patients with preoperative Afib (n=190, 18.6%) experienced a higher cumulative risk of overall mortality (hazard ratio [HR], 1.435; 95% confidence interval [CI], 1.263-2.107; p=0.034). Subgroup analysis revealed a reduced risk of overall mortality with Cox-maze surgery in Afib patients (HR, 0.500; 95% CI, 0.266-0.938; p=0.031). Postoperative cerebral ischemia or hemorrhage events were not related to Afib. Conclusion: Preoperative Afib was independently associated with worse long-term postoperative outcomes after cardiac surgery. Concomitant Cox-maze surgery may improve the survival rate.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.1C
• /
• pp.65-76
• /
• 2010

Recent earthquake events revealed that severe seismic damages were concentrated mostly at sites composed of soil sediments rather than firm rock. This indicates that the site effects inducing the amplification of earthquake ground motion are associated mainly with the spatial distribution and dynamic properties of the soils overlying bedrock. In this study, an integrated GIS-based information system for geotechnical data was constructed to establish a regional counterplan against ground motions at a representative metropolitan area, Seoul, in Korea. To implement the GIS-based geotechnical information system for the Seoul area, existing geotechnical investigation data were collected in and around the study area and additionally a walkover site survey was carried out to acquire surface geo-knowledge data. For practical application of the geotechnical information system used to estimate the site effects at the area of interest, seismic zoning maps of geotechnical earthquake engineering parameters, such as the depth to bedrock and the site period, were created and presented as regional synthetic strategy for earthquake-induced hazards prediction. In addition, seismic zonation of site classification was also performed to determine the site amplification coefficients for seismic design at any site and administrative sub-unit in the Seoul area. Based on the case study on seismic zonations for Seoul, it was verified that the GIS-based geotechnical information system was very useful for the regional prediction of seismic hazards and also the decision support for seismic hazard mitigation particularly at the metropolitan area.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.273-275
• /
• 2022

The use of drugs by pregnant women poses a potential risk to the fetus. Therefore, it is essential to classify drugs that pregnant women should prohibit. However, the fetal toxicity of most drugs has not been identified. This takes a lot of time and cost. In silico approaches, such as virtual screening, can identify compounds that may present a high risk to the fetus for a wide range of compounds at the low cost and time. We collected class information of each drug from the hazard classification lists for prescribing drugs in pregnancy by the government of Korea and Australia. Using the structural and chemical features of each drug, various machine learning models were constructed to predict fetal toxicity of drugs. For all models, the quantitative performance evaluation was performed. Based on the attention algorithm, important molecular substructures of compounds were identified in the process of predicting the fetal toxicity of the drug by the proposed model. From the results, we confirmed that drugs with a high risk of fetal toxicity can be predicted for a wide range of compounds by machine learning. This study can be used as a pre-screening tool for fetal toxicity predictions, as it provides key molecular substructures associated with the fetal toxicity of compounds.

• Journal of the Korean GEO-environmental Society
• /
• v.16 no.4
• /
• pp.5-12
• /
• 2015

Civil engineers have taken the numerous slope monitoring data for an engineering project subjected to hazard potential of slide. However, the topics on how to deal with and draw out proper information from the data related to the slope behavior have not been widely discussed. Recently, several researchers had installed the real-time monitoring system to cope with slope failure; however they are mainly focused on the hardware system installation. Therefore, this study tries to show how the measured data could be grouped and connected each other. The basic idea of analyzing method studied in this paper came from the clustering, which is the part of data mining analysis. Therefore, at the base of classification of time series data, the authors suggest three mathematical data analyzing methods; Average Index of different displacement ($AD_{i,j}$), Difference of average relative displacement ($\overline{RD}_{i,j}$) and Coordinate system of average and relative displacement ($\overline{RD}$, AD). These analyzing methods are based on the statistical method and failure mechanism of slope. Therefore they showed clustering relationships of the similar parts of the slope which makes the same sliding mechanism.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1786-1796
• /
• 2021

Objective: To evaluate the prognostic implications of preoperative magnetic resonance imaging (MRI) features of hepatocellular carcinoma (HCC) with a focus on those with targetoid appearance based on the Liver Imaging Reporting and Data System (LI-RADS), as well as known microvascular invasion (MVI) features. Materials and Methods: This retrospective study included 242 patients (190 male; mean age, 57.1 years) who underwent surgical resection of a single HCC (≤ 5 cm) as well as preoperative gadoxetic acid-enhanced MRI between January 2012 and March 2015. LI-RADS category was assigned, and the LR-M category was further classified into two groups according to rim arterial-phase hyperenhancement (APHE). The imaging features associated with MVI were also assessed. The overall survival (OS), recurrence-free survival (RFS), and their associated factors were evaluated. Results: Among the 242 HCCs, 190 (78.5%), 25 (10.3%), and 27 (11.2%) were classified as LR-4/5, LR-M with rim APHE, and LR-M without rim APHE, respectively. LR-M with rim APHE (vs. LR-4/5; hazard ratio [HR] for OS, 5.48 [p = 0.002]; HR for RFS, 2.09 [p = 0.042]) and tumor size (per cm increase; HR for OS, 6.04 [p = 0.009]; HR for RFS, 1.77 [p = 0.014]) but not MVI imaging features (p > 0.05) were independent factors associated with OS and RFS. Compared to the 5-year OS and RFS rates in the LR-4/5 group (93.9% and 66.8%, respectively), the LR-M with rim APHE group had significantly lower rates (68.0% and 45.8%, respectively, both p < 0.05), while the LR-M without rim APHE group did not significantly differ in the survival rates (91.3% and 80.2%, respectively, both p > 0.05). Conclusion: Further classification of LR-M according to the presence of rim APHE may help predict the postoperative prognosis of patients with a single HCC.

• Industry Promotion Research
• /
• v.9 no.1
• /
• pp.39-45
• /
• 2024

Dangerous tasks that occur every day at industrial site manufacturing plants, which have recently been making rapid changes, were classified by type, and the effect of mobile circuit television (CCTV) on safety accidents among daily safety management methods was analyzed. The subject of the study is about 3,000 workers who manage the infrastructure facility sector to supply utilities such as gas, water, and electricity to the display manufacturing process located in Asan City, and the study was conducted based on the daily dangerous work from 2019 to 2022, and during this study period, many construction works such as new investment and expansion of construction and manufacturing processes were occurring at the site. As a result, the rate of safety accidents and exposure to risks are expanding, and most of the safety accidents occurred because the sectors that did not follow the basics and the safety measures on the site were not implemented. In this paper, it was confirmed that there is an accident reduction effect according to the relationship between the dangerous work classified according to the work importance and the mobile CCTV shooting rate. Considering the characteristics of the manufacturing plant site, it can be used to play the role of basic data for preventing safety accidents based on the expansion of the introduction of a new safety management culture in the future.

• Tuberculosis and Respiratory Diseases
• /
• v.87 no.2
• /
• pp.176-184
• /
• 2024

Background: Results of studies investigating the association between body mass index (BMI) and mortality in patients with coronavirus disease-2019 (COVID-19) have been conflicting. Methods: This multicenter, retrospective observational study, conducted between January 2020 and August 2021, evaluated the impact of obesity on outcomes in patients with severe COVID-19 in a Korean national cohort. A total of 1,114 patients were enrolled from 22 tertiary referral hospitals or university-affiliated hospitals, of whom 1,099 were included in the analysis, excluding 15 with unavailable height and weight information. The effect(s) of BMI on patients with severe COVID-19 were analyzed. Results: According to the World Health Organization BMI classification, 59 patients were underweight, 541 were normal, 389 were overweight, and 110 were obese. The overall 28-day mortality rate was 15.3%, and there was no significant difference according to BMI. Univariate Cox analysis revealed that BMI was associated with 28-day mortality (hazard ratio, 0.96; p=0.045), but not in the multivariate analysis. Additionally, patients were divided into two groups based on BMI ≥25 kg/m² and underwent propensity score matching analysis, in which the two groups exhibited no significant difference in mortality at 28 days. The median (interquartile range) clinical frailty scale score at discharge was higher in nonobese patients (3 [3 to 5] vs. 4 [3 to 6], p<0.001). The proportion of frail patients at discharge was significantly higher in the nonobese group (28.1% vs. 46.8%, p<0.001). Conclusion: The obesity paradox was not evident in this cohort of patients with severe COVID-19. However, functional outcomes at discharge were better in the obese group.

• The Journal of Bigdata
• /
• v.9 no.1
• /
• pp.75-88
• /
• 2024

Recently, there have been cases reported in the news of individuals experiencing symptoms of food poisoning after consuming raw beef purchased from online platforms, or reviews claiming that cherry tomatoes tasted bitter. This suggests the potential for analyzing food reviews on online platforms to detect food hazards, enabling government agencies, food manufacturers, and distributors to manage consumer food safety risks. This study proposes a classification model that uses sentiment analysis and large language models to analyze food reviews and detect negative ones, multi-labeling key food safety hazards (food poisoning, spoilage, chemical odors, foreign objects). The sentiment analysis model effectively minimized the misclassification of negative reviews with a low False Positive rate using a 'funnel' model. The multi-labeling model for food safety hazards showed high performance with both recall and accuracy over 96% when using GPT-4 Turbo compared to GPT-3.5. Government agencies, food manufacturers, and distributors can use the proposed model to monitor consumer reviews in real-time, detect potential food safety issues early, and manage risks. Such a system can protect corporate brand reputation, enhance consumer protection, and ultimately improve consumer health and safety.