• Clinical Endoscopy
• /
• v.57 no.4
• /
• pp.476-485
• /
• 2024

Background/Aims: Sedation has become a standard practice for patients undergoing gastrointestinal (GI) endoscopy. However, considering the serious cardiopulmonary adverse events associated with sedatives, it is important to identify patients at high risk. Machine learning can generate reasonable prediction for a wide range of medical conditions. This study aimed to evaluate the risk factors associated with sedation during GI endoscopy and develop a predictive model for hypoxia during endoscopy under sedation. Methods: This prospective observational study enrolled 446 patients who underwent sedative endoscopy at the Korea University Ansan Hospital. Clinical data were used as predictor variables to construct predictive models using the random forest method that is a machine learning algorithm. Results: Seventy-two of the 446 patients (16.1%) experienced life-threatening hypoxia requiring immediate medical intervention. Patients who developed hypoxia had higher body weight, body mass index (BMI), neck circumference, and Mallampati scores. Propofol alone and higher initial and total dose of propofol were significantly associated with hypoxia during sedative endoscopy. Among these variables, high BMI, neck circumference, and Mallampati score were independent risk factors for hypoxia. The area under the receiver operating characteristic curve for the random forest-based predictive model for hypoxia during sedative endoscopy was 0.82 (95% confidence interval, 0.79-0.86) and displayed a moderate discriminatory power. Conclusions: High BMI, neck circumference, and Mallampati score were independently associated with hypoxia during sedative endoscopy. We constructed a model with acceptable performance for predicting hypoxia during sedative endoscopy.

• The Korean Journal of Nuclear Medicine
• /
• v.34 no.1
• /
• pp.55-61
• /
• 2000

Purpose: We performed this study to evaluate the changes of gallbladder ejection fraction (GBEF) in diabetic patients with or without autonomic neuropathy. Materials and Methods: This study included 37 diabetic patients (25 women, 12 men, mean age 51 years) and 24 normal controls (10 women, 14 men, mean age 38 years). After intravenous injection of 185 MBq of $^{99m}Tc$-DISIDA, serial anterior abdominal images were acquired before and after fatty meal. Regions of interest were applied on gallbladder and right hepatic lobe on 60 and 90 minute images to calculate GBEF. Results: GBEF was significantly reduced in diabetes with autonomic neuropathy ($43{\pm}12.3%$) and without autonomic neuropathy ($57.5{\pm}13.2%$) compared with normal controls ($68{\pm}11.6%$, p<0.05). And also, GBEF was significantly reduced in diabetes with autonomic neuropathy compared with diabetes without autonomic neuropathy (p<0.05). Fasting blood glucose level, age, sex, hemoglobin Alc, body mass index, serum lipid level were not different in these two diabetic patient groups (p>0.05). When 50.2% of GBEF was used as the criteria for diabetic autonomic neuropathy, the sensitivity and specificity were 80%, 76.5%, respectively. The area under receiver operating characteristic curve was 0.846. Conclusion: GBEF of diabetic patients with autonomic neuropathy was significantly reduced than that of diabetic patients without autonomic neuropathy.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.3
• /
• pp.24-30
• /
• 2009

Purpose: Today, Prostate cancer has been gradually increasing, according to the change of internal incidence rate of cancer. Generally, prostate cancer has lead to dead over 90%, in case of metastasis of lymph node and bone. So, innovative development of new radiopharmaceutical and imaging modality is progressed for detection of that metastasis, in nuclear medicine, now. Therefore, this study shows the usefulness of $^{18}F$-Fluoride PET/CT improved diagnosability on bone metastasis of prostate cancer. Materials and Methods: In this study, 33 male patients with prostate cancer were examined (The mean age: $67.8{\pm}10.2$ years old). Every patient was done each whole body bone scan (WBBS) and $^{18}F$-Fluoride positron emission tomography/computed tomography ($^{18}F$-Fluoride PET/CT). And then, using Receiver Operating Characteristic Curve (ROC curve), each sensitivity and specificity of two modalities was measured and compared with. Results: In 22 patients (66.6%) of all, bone metastasis was detected. And, in WBBS, sensitivity was 63.6%, specificity, 81.8%; in $^{18}F$-Fluoride PET/CT, sensitivity was 100% and specificity was 90.9%. As a result of ROC curve, AUROC (The Area under an ROC) of WBBS was 0.778, and that of $^{18}F$-Fluoride PET/CT, 0.942. Conclusions: $^{18}F$-Fluoride PET/CT was higher both sensitivity and specificity than WBBS, and it was valuable to detect bone metastasis of prostate cancer more definitely, with 3D imaging realization. Also, in $^{18}F$-Fluoride PET/CT, physiological images were acquired in more short time than WBBS, so, it was possible to reduce patient's waiting time and complaint. Therefore, it is considered that $^{18}F$-Fluoride PET/CT is able to improve diagnosability by offering more accurate images, as cuts in a share of high cost.

• Tuberculosis and Respiratory Diseases
• /
• v.64 no.4
• /
• pp.266-271
• /
• 2008

Background: Estimation of the probability of a patient having an acute pulmonary embolism (PE) for patients with a suspected PE are well established in North America and Europe. However, an assessment of the prediction rules for a PE has not been clearly defined in Korea. The aim of this study is to assess the prediction rules for patients with a suspected PE in Korea. Methods: We performed a retrospective study of 210 inpatients or patients that visited the emergency ward with a suspected PE where computed tomography pulmonary angiography was performed at a single institution between January 2005 and March 2007. Simplified Wells rules and revised Geneva rules were used to estimate the clinical probability of a PE based on information from medical records. Results: Of the 210 patients with a suspected PE, 49 (19.5%) patients had an actual diagnosis of a PE. The proportion of patients classified by Wells rules and the Geneva rules had a low probability of 1% and 21%, an intermediate probability of 62.5% and 76.2%, and a high probability of 33.8% and 2.8%, respectively. The prevalence of PE patients with a low, intermediate and high probability categorized by the Wells rules and Geneva rules was 100% and 4.5% in the low range, 18.2% and 22.5% in the intermediate range, and 19.7% and 50% in the high range, respectively. Receiver operating characteristic curve analysis showed that the revised Geneva rules had a higher accuracy than the Wells rules in terms of detecting PE. Concordance between the two prediction rules was poor ($\kappa$ coefficient=0.06). Conclusion: In the present study, the two prediction rules had a different predictive accuracy for pulmonary embolisms. Applying the revised Geneva rules to inpatients and emergency ward patients suspected of having PE may allow a more effective diagnostic process than the use of the Wells rules.

• Journal of Yeungnam Medical Science
• /
• v.23 no.2
• /
• pp.205-212
• /
• 2006

Background: Malignant pulmonary nodules account for about 30 to 40 percent of solitary pulmonary nodules (SPN). Therefore, tissue characterization of SPNs is very important. Recently, PET/CT has been widely used for tissue characterization, and has become of importance. The purpose of this study was to compare and to assess multiple factors in PET/CT comparing benign and malignant nodules. Materials and Method: Nineteen patients with SPN underwent PET/CT and biopsy. The difference of standardized uptake value 1 (SUV1), standardized uptake value 2 (SUV2) and retention index in PET/CT between malignancy and benignancy were compared by Levene's test. Result: There were twelve malignant and seven benign nodules. SUV1 and SUV2 were significantly different between malignant nodule and benign nodule (p=0.006 and 0.022), but retention index was not significantly different between malignant nodule and benign nodule (p=0.526). By receiver-operating-characteristic (ROC) analysis, the sensitivity was 66.7% and the specificity was 71.4% at a cut off value of 5.40 in SUV1. The sensitivity was 75% and the specificity was 71.4% at cut off value of 7.45 in SUV2. Conclusion: There was a statistically significant difference in SUV1 and SUV2 between benign and malignant nodules. However, the cut off value of SUV1 and SUV2 by receiver-operating-characteristic (ROC) analysis was 5.40 and 7.45 which is different from previous studies. Therefore, studies on a larger sample of patients are required for confirmation.

• Journal of Veterinary Clinics
• /
• v.23 no.2
• /
• pp.105-110
• /
• 2006

A three-layer, feed-forward artificial neural network (ANN) with sixteen input neurons, three hidden neurons, and one output neuron was developed to identify the presence of infectious bronchitis (IB) infection as early as possible in laying hen flocks. Retrospective data from flocks that enrolled IB surveillance program between May 2003 and November 2005 were used to build the ANN. Data set of 86 flocks was divided randomly into two sets: 77 cases for training set and 9 cases for testing set. Input factors were 16 epidemiological findings including characteristics of the layer house, management practice, flock size, and the output was either presence or absence of IB. ANN was trained using training set with a back-propagation algorithm and test set was used to determine the network's capability to predict outcomes that it has never seen. Diagnostic performance of the trained network was evaluated by constructing receiver operating characteristic (ROC) curve with the area under the curve (AUC), which were also used to determine the best positivity criterion for the model. Several different ANNs with different structures were created. The best-fitted trained network, IBV_D1, was able to predict IB in 73 cases out of 77 (diagnostic accuracy 94.8%) in the training set. Sensitivity and specificity of the trained neural network was 95.5% (42/44, 95% CI, 84.5-99.4) and 93.9% (31/33, 95% CI, 79.8-99.3), respectively. For testing set, AVC of the ROC curve for the IBV_D1 network was 0.948 (SE=0.086, 95% CI 0.592-0.961) in recognizing IB infection status accurately. At a criterion of 0.7149, the diagnostic accuracy was the highest with a 88.9% with the highest sensitivity of 100%. With this value of sensitivity and specificity together with assumed 44% of IB prevalence, IBV_D1 network showed a PPV of 80% and an NPV of 100%. Based on these findings, the authors conclude that neural network can be successfully applied to the development of a screening model for identifying IB infection in laying hen flocks.

• The Korean Journal of Nuclear Medicine
• /
• v.33 no.2
• /
• pp.131-142
• /
• 1999

Purpose: Either gated myocardial perfusion SPECT or attenuation corrected SPECT can be used to improve specificity in the diagnosis of coronary artery disease. We investigated in this study whether gating or attenuation correction improved diagnostic performance of rest/stress perfusion SPECT in patients having intermediate pre-test likelihood of coronary artery disease. Materials and Methods: Sixty-eight patients underwent rest attenuation-corrected T1-20l/dipyridamole stress gated attenuation-corrected Tc-99m -MIBI SPECT using an ADAC vertex camera (M:F=29:39, aged $59{\pm}12$ years, coronary artery stenosis ${\geq}70%$, one vessel: 13, two vessel: 18, three vessel: 8, normal: 29). Using a five-point scale, three physicians graded the post-test likelihood of coronary artery disease for each arterial territory (1:normal, 2: possibly normal, 3:equivocal, 4. possibly abnormal, 5: abnormal). Sensitivity, specificity and area under receiver-operating-characteristic curves were compared for each operator between three methods : (A) non-attenuation-corrected SPECT; (B) gated SPECT added to (A): and (C) attenuation-corrected SPECT added to (B). Results: When grade 3 was used as the criteria for coronary artery disease, no differences in sensitivity and specificity were found between the three methods for each operator. Areas under receiver-operating-characteristic curves for diagnosis of coronary artery disease revealed no differences between each modality (p>0.05). Conclusion: In patients at intermediate risk of coronary artery disease, gated SPECT and attenuation- corrected SPECT did not improve diagnostic performance.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.23 no.2
• /
• pp.38-42
• /
• 2019

Purpose Although computed tomography (CT) is used for coronary artery calcification, it is difficult to differentiate between high risk microcalcifications. Studies have shown that $^{18}F$-sodium fluoride ($^{18}F-NaF$) is very useful for the diagnosis of microcalcifications. In this study, we aimed to evaluate the usefulness of $^{18}F-NaF$ PET imaging in quantitative evaluation of calcification. Materials and Methods A total of 45 patients ($67.1{\pm}6.9years\;old$) were injected with 250 MBq of $^{18}F-NaF$ for 1 hour and images were acquired for 30 minutes. All patients underwent CT angiography (CTAngiography, CTA) before the PET scan. The SUVmax of calcification was measured and the background radioactivity of the left atrium was measured to determine Target to Background (TBR) and quantitatively analyzed. High risk group was classified through ROC curve (Receiver Operating Characteristic Curve). Results There were 226 coronary artery calcifications in the cohort and SUVmax was $1.15{\pm}0.39$. Of the 28 patients (62%), 58 were classified as high risk (TBR > 1.25). The remaining 168 were $TBR{\leq}1.25$. Conclusion $^{18}F-NaF$ PET images were available for quantitative assessment of microcalcifications and could be classified into high-risk groups. The combination of angiographic CT and $^{18}F-NaF$ PET may be a new method for early diagnosis of high-risk microcalcifications.

• Journal of the Korean Society of Radiology
• /
• v.82 no.2
• /
• pp.406-416
• /
• 2021

Purpose To evaluate the association between magnetic resonance imaging (MRI)-based texture parameters and Kirsten rat sarcoma viral oncogene homolog (KRAS) mutation in patients with non-mucinous rectal cancer. Materials and Methods Seventy-nine patients who had pathologically confirmed rectal non-mucinous adenocarcinoma with or without KRAS-mutation and had undergone rectal MRI were divided into a training (n = 46) and validation dataset (n = 33). A texture analysis was performed on the axial T2-weighted images. The association was statistically analyzed using the Mann-Whitney U test. To extract an optimal cut-off value for the prediction of KRAS mutation, a receiver operating characteristic curve analysis was performed. The cut-off value was verified using the validation dataset. Results In the training dataset, skewness in the mutant group (n = 22) was significantly higher than in the wild-type group (n = 24) (0.221 ± 0.283; -0.006 ± 0.178, respectively, p = 0.003). The area under the curve of the skewness was 0.757 (95% confidence interval, 0.606 to 0.872) with a maximum accuracy of 71%, a sensitivity of 64%, and a specificity of 78%. None of the other texture parameters were associated with KRAS mutation (p > 0.05). When a cut-off value of 0.078 was applied to the validation dataset, this had an accuracy of 76%, a sensitivity of 86%, and a specificity of 68%. Conclusion Skewness was associated with KRAS mutation in patients with non-mucinous rectal cancer.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1231-1245
• /
• 2021

Purpose To investigate the usefulness of imaging features for differentiating between small lobular carcinoma in situ (LCIS) and invasive lobular carcinoma (ILC). Materials and Methods It included 52 female with LCISs (median 45 years, range 32-67 years) and 180 female with ILCs (median 49 years, range 36-75 years), with the longest diameter of ≤ 2 cm, who were evaluated between January 2012 and December 2016. All the female underwent mammography and ultrasonography. Twenty female with LCIS and 150 female with ILC underwent MRI. The clinical and imaging features were compared, and multivariate analysis was performed to identify the independent predictors of LCIS. Female with LCIS were also sub-grouped by lesion size and compared with the female with ILC. Results Multivariate analysis showed that younger age (odds ratio [OR] = 1.100), smaller lesion size (OR = 1.103), oval or round shape (OR = 4.098), parallel orientation (OR = 5.464), and isoechotexture (OR = 3.360) were significant independent factors predictive of LCIS. The area under the receiver operating characteristic curve for distinguishing LCIS from ILC was 0.904 (95% confidence interval, 0.857-0.951). Subgroup analysis showed that benign features were more prevalent in female with smaller LCISs (≤ 1 cm) than in those with ILC. Conclusion Small LCISs tend to demonstrate more benign features than small ILCs. Several imaging features are independently predictive of LCIS.