• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.33-41
• /
• 2022

In this article, we proposed to predict natural gas (NG) leakage levels through feature selection based on a factor analysis (FA) of the integrating the Korean Meteorological Agency data and natural gas leakage data for considering complex factors. The paper has been divided into three modules. First, we filled missing data based on the linear interpolation method on the integrated data set, and selected essential features using FA with OrdinalEncoder (OE)-based normalization. The dataset is labeled by K-means clustering. The final module uses four algorithms, K-nearest neighbors (KNN), decision tree (DT), random forest (RF), Naive Bayes (NB), to predict gas leakage levels. The proposed method is evaluated by the accuracy, area under the ROC curve (AUC), and mean standard error (MSE). The test results indicate that the OrdinalEncoder-Factor analysis (OE-F)-based classification method has improved successfully. Moreover, OE-F-based KNN (OE-F-KNN) showed the best performance by giving 95.20% accuracy, an AUC of 96.13%, and an MSE of 0.031.

• Journal of Veterinary Clinics
• /
• v.32 no.1
• /
• pp.69-72
• /
• 2015

This study was performed to differentiate calcium oxalate and struvite canine urinary stones using computed tomography. A total of 38 urinary stones (8 calcium oxalate and 30 struvite) were scanned using a computed tomography scanner. These urinary stones (10-15 mm diameter) extracted surgically without fragmentation were obtained from the different individual patients. The stone's Hounsfield units(HU) values, heterogenicity, and roughness of surface were evaluated to differentiate calcium oxalate and struvite. The HU values of calcium oxalate were significantly higher than those of struvite. A receiver operator characteristic (ROC) curve revealed 1272 as the best threshold value to distinguish calcium oxalate from struvite (ROC curve AUC 0.87, p < 0.0014). The heterogenicity of calcium oxalate and struvite significantly differed on bone and dental window setting (p < 0.0001). There was no significant difference between calcium oxalate and struvite in roughness of surface. On computed tomographic images, bone and dental windows setting were useful for evaluation of heterogenicity between calcium oxalate and struvite. The HU value and heterogenicity are highly promising factor that can distinguish calcium oxalate and struvite with reasonable accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.6
• /
• pp.597-607
• /
• 2016

The goal of this study was to analyze landslide susceptibility using two different models and compare the results. For this purpose, a landslide inventory map was produced from a field survey, and the inventory was divided into two groups for training and validation, respectively. Sixteen landslide conditioning factors were considered. The relationships between landslide occurrence and landslide conditioning factors were analyzed using the FR (Frequency Ratio) and EBF (Evidential Belief Function) models. The LSI (Landslide Susceptibility Index) maps that were produced were validated using the ROC (Relative Operating Characteristics) curve and the SCAI (Seed Cell Area Index). The AUC (Area under the ROC Curve) values of the FR and EBF LSI maps were 80.6% and 79.5%, with prediction accuracies of 72.7% and 71.8%, respectively. Additionally, in the low and very low susceptibility zones, the FR LSI map had higher SCAI values compared to the EBF LSI map, as high as 0.47%p. These results indicate that both models were reasonably accurate, however that the FR LSI map had a slightly higher accuracy for landslide susceptibility mapping in the study area.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.4
• /
• pp.1133-1138
• /
• 2014

Ultrahigh performance liquid chromatography-electrospray ionization-tandem mass spectrometry (UPLC-ESI- MS/MS) provides a high-speed method to screen a large number of samples for small molecules with specific properties. In this study, UPLC-ESI-MS/MS with multiple reaction monitoring (MRM) was employed to screen urinary phospholipid (PL) content for biomarkers of prostate cancer. From lists of urinary PLs structurally identified using nanoflow LC-ESI-MS/MS, 52 PL species were selected for quantitative analysis in urine samples between 22 cancer-free urologic patients as controls and 45 prostate cancer patients. Statistical treatment of data by receiver operating characteristic (ROC) analysis yielded 14 PL species that differed significantly in relative concentrations (area under curve (AUC) > 0.8) between the two groups. Among PLs present at higher levels in prostate cancer urine, phosphatidylcholines (PCs) and phosphatidylinositols (PIs) constituted the major head group PLs (3 PCs and 7 PIs). For technical reasons, PL species of low abundance may be underrepresented in data from UPLC-ESI-MS/MS performed in MRM mode. However, the proposed method enables the rapid screening of large numbers of plasma or urine samples in the search for biomarkers of human disease.

• Psychiatry investigation
• /
• v.15 no.11
• /
• pp.1037-1045
• /
• 2018

Objective The present study aimed to identify risk factors for future SI and to predict individual-level risk for future or persistent SI among college students. Methods Mental health check-up data collected over 3 years were retrospectively analyzed. Students were categorized as suicidal ideators and non-ideators at baseline. Logistic regression analyses were performed separately for each group, and the predicted probability for each student was calculated. Results Students likely to exhibit future SI had higher levels of mental health problems, including depression and anxiety, and significant risk factors for future SI included depression, current SI, social phobia, alcohol problems, being female, low self-esteem, and number of close relationships and concerns. Logistic regression models that included current suicide ideators revealed acceptable area under the curve (AUC) values (0.7-0.8) in both the receiver operating characteristic (ROC) and precision recall (PR) curves for predicting future SI. Predictive models with current suicide non-ideators revealed an acceptable level of AUCs only for ROC curves. Conclusion Several factors such as low self-esteem and a focus on short-term rather than long-term outcomes may enhance the prediction of future SI. Because a certain range of SI clearly necessitates clinical attention, further studies differentiating significant from other types of SI are necessary.

• Journal of muscle and joint health
• /
• v.31 no.2
• /
• pp.65-74
• /
• 2024

Purpose: This study was conducted to verify fall predictive power and reasonable fall risk assessment tool by a comparative analysis of the sensitivity, specificity, positive forecast and negative forecast of each tool by applying Morse Fall Scale (MFS), Johns Hopkins Fall Risk Assessment Tool (JHFRAT), and Fall Assessment Scale-Korean version (FAS-K) through electronic medical records to adult patients hospitalized in a general hospital in Korea. Methods: We performed a retrospective evaluation study from January to December 2018, 123 fall groups experiencing falls during hospitalization and 123 non-falls groups were selected. Data presented a reasonable assessment tool that predicts and distinguishes fall high-risk patients through area comparison based on the ROC curve for each tool. Results: In the ROC curve analysis by fall risk assessment group, the AUC of MFS is shown to be .706 (good), JHFRAT is shown to be .649 (sufficient) and FAS-K is shown to be .804 (very good). FAS-K at a cut-off score of 4, sensitivity, specificity, and positive and negative prediction values were 83.7%, 60.2%, 67.8%, and 78.7%, respectively. Conclusion: Based on the above findings, it is believed that the FAS-K was presented as a suitable and reasonable tool for predicting falls for adult patients in general hospitals.

• Journal of Trauma and Injury
• /
• v.30 no.4
• /
• pp.140-144
• /
• 2017

Purpose: The optic nerve sheath diameter (ONSD) measured by ultrasonography is among the indicators of intracranial pressure (ICP) elevation. However, whether ONSD measurement is useful for initial treatment remains controversial. Thus, this study aimed to investigate the relationship between ONSD measured by computed tomography (CT) and ICP in patients with traumatic brain injury (TBI). Methods: A total of 246 patients with severe trauma from January 1, 2015 until December 31, 2015 were included in the study. A total of 179 patients with brain damage with potential for ICP elevation were included in the TBI group. The remaining 67 patients comprised the non-TBI group. A comparison was made between the two groups. Receiver operating characteristic (ROC) curve analysis was performed to determine the accuracy of ONSD when used as a screening test for the TBI group including those with TBI with midline shift (with elevated ICP). Results: The mean injury severity score (ISS) and glasgow coma scale (GCS) of all patients were $24.2{\pm}6.1$ and $5.4{\pm}0.8$, respectively. The mean ONSD of the TBI group ($5.5{\pm}1.0mm$) was higher than that of the non-TBI group ($4.7{\pm}0.6mm$). Some significant differences in age ($55.3{\pm}18.1$ vs. $49.0{\pm}14.8$, p<0.001), GCS ($11.7{\pm}4.1$ versus $13.3{\pm}3.0$, p<0.001), and ONSD ($5.5{\pm}1.0$ vs. $4.7{\pm}0.6$, p<0.001) were observed between the TBI and the non-TBI group. An ROC analysis was used to assess the correlation between TBI and ONSD. Results showed an area under the ROC curve (AUC) value of 0.752. The same analysis was used in the TBI with midline shift group, which showed an AUC of 0.912. Conclusions: An ONSD of >5.5 mm, measured on CT, is a good indicator of ICP elevation. However, since an ONSD is not sensitive enough to detect an increased ICP, it should only be used as one of the parameters in detecting ICP along with other screening tests.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.11
• /
• pp.4467-4474
• /
• 2014

Background: We aimed to comprehensively review the evidence for using sputum DNA to detect non-small cell lung cancer (NSCLC). Materials and Methods: We searched PubMed, Science Direct, Web of Science, Chinese Biological Medicine (CBM), Chinese National Knowledge Infrastructure (CNKI), Wanfang, Vip Databases and Google Scholar from 2003 to 2013. The meta-analysis was carried out using a random-effect model with sensitivity, specificity, diagnostic odd ratios (DOR), summary receiver operating characteristic curves (ROC curves), area under the curve (AUC), and 95% confidence intervals (CI) as effect measurements. Results: There were twenty-two studies meeting the inclusion criteria for the meta-analysis. Combined sensitivity and specificity were 0.62 (95%CI: 0.59-0.65) and 0.73 (95%CI: 0.70-0.75), respectively. The DOR was 10.3 (95%CI: 5.88-18.1) and the AUC was 0.78. Conclusions: The overall accuracy of the test was currently not strong enough for the detection of NSCLC for clinical application. Dscovery and evaluation of additional biomarkers with improved sensitivity and specificity from studies rated high quality deserve further attention.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.11-23
• /
• 2024

Triage is a practice of accurately prioritizing patients in emergency department (ED) based on their medical condition to provide them with proper treatment service. The variation in triage assessment among medical staff can cause mis-triage which affect the patients negatively. Developing ED triage system based on machine learning (ML) techniques can lead to accurate and efficient triage outcomes. This study aspires to develop a triage system using machine learning techniques to predict ED triage levels using patients' information. We conducted a retrospective study using Security Forces Hospital ED data, from 2021 through 2023 during Hajj period in Saudia Arabi. Using demographics, vital signs, and chief complaints as predictors, two machine learning models were investigated, naming gradient boosted decision tree (XGB) and deep neural network (DNN). The models were trained to predict ED triage levels and their predictive performance was evaluated using area under the receiver operating characteristic curve (AUC) and confusion matrix. A total of 11,584 ED visits were collected and used in this study. XGB and DNN models exhibit high abilities in the predicting performance with AUC-ROC scores 0.85 and 0.82, respectively. Compared to the traditional approach, our proposed system demonstrated better performance and can be implemented in real-world clinical settings. Utilizing ML applications can power the triage decision-making, clinical care, and resource utilization.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.11
• /
• pp.5529-5533
• /
• 2012

Aim: To investigate the utility of prostate-specific antigen velocity (PSAV) and PSAV per initial volume (PSAVD) for early detection of prostate cancer (PCa) in Chinese men. Methods: Between January 2009 and June 2012, a total of 193 men (aged 49-84 years, median 67 years) with at least 2 transrectal ultrasonography (TRUS) procedures and concurrent serum PSA measurements underwent prostate biopsy because of suspicion of PCa. The total group were classified into PCa and non-PCa groups, and the variables of the two groups were compared. Univariate and multivariate analyses were used to investigate which variables were predictove. The diagnostic values of PSAV, PSAVD and prostate-specific antigen density (PSAD) were compared using receiver operating characteristic (ROC) analysis. Results: Prostate cancer was diagnosed in 44 (22.8%) of the 193 men. There were significant differences between the groups in last and initial prostate volumes determined by TRUS, initial age, last serum PSA levels, PSAV, PSAD and PSAVD. After adjusting for confounding factors, the odds ratios of PCa across the quartile of PSAVD were 1, 4.06, 10.6, and 18.9 (P for trend <0.001).The area under the ROC curves (AUCs) of PSAD (0.779) and PSAVD (0.776) were similar and both significantly greater than that of PSA (AUC 0.667). PSAVD was a significantly better indicator of PCa than PSAV (AUC 0.736). There was no statistical significant difference between the AUC of PSAV and that of last serum PSA level. The sensitivity and specificity of PSAVD at a cutoff of 0.023ng in participants with last serum PSA levels of 4.0ng/mL-10.0ng was 73.7% and 70.7%, respectively. Conclusions: The results of this study demonstrated PSAVD may be a useful tool in PCa detection, especially in those undergoing previous TRUS examination.