• Imaging Science in Dentistry
• /
• v.52 no.2
• /
• pp.187-195
• /
• 2022

Purpose: This study developed a convolutional neural network (CNN) model to diagnose maxillary sinusitis on panoramic radiographs(PRs) and cone-beam computed tomographic (CBCT) images and evaluated its performance. Materials and Methods: A CNN model, which is an artificial intelligence method, was utilized. The model was trained and tested by applying 5-fold cross-validation to a dataset of 148 healthy and 148 inflamed sinus images. The CNN model was implemented using the PyTorch library of the Python programming language. A receiver operating characteristic curve was plotted, and the area under the curve, accuracy, sensitivity, specificity, positive predictive value, and negative predictive values for both imaging techniques were calculated to evaluate the model. Results: The average accuracy, sensitivity, and specificity of the model in diagnosing sinusitis from PRs were 75.7%, 75.7%, and 75.7%, respectively. The accuracy, sensitivity, and specificity of the deep-learning system in diagnosing sinusitis from CBCT images were 99.7%, 100%, and 99.3%, respectively. Conclusion: The diagnostic performance of the CNN for maxillary sinusitis from PRs was moderately high, whereas it was clearly higher with CBCT images. Three-dimensional images are accepted as the "gold standard" for diagnosis; therefore, this was not an unexpected result. Based on these results, deep-learning systems could be used as an effective guide in assisting with diagnoses, especially for less experienced practitioners.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1448-1456
• /
• 2022

This paper studies a model to diagnose efficiency reduction of inverter using Multilayer Perceptron(MLP). In this study, two inverter data which started operation at different day was used. A Multilayer Perceptron model was made to predict photovoltaic power data of the latest inverter. As a result of the model's performance test, the Mean Absolute Percentage Error(MAPE) was 4.1034. The verified model was applied to one-year-old and two-year-old data after old inverter starting operation. The predictive power of one-year-old inverter was larger than the observed power by 724.9243 on average. And two-year-old inverter's predictive value was larger than the observed power by 836.4616 on average. The prediction error of two-year-old inverter rose 111.5572 on a year. This error is 0.4% of the total capacity. It was proved that the error is meaningful difference by t-test. The error is predicted value minus actual value. Which means that PV system actually generated less than prediction. Therefore, increasing error is decreasing conversion efficiency of inverter. Finally, conversion efficiency of the inverter decreased by 0.4% over a year using this model.

• Tuberculosis and Respiratory Diseases
• /
• v.75 no.6
• /
• pp.238-243
• /
• 2013

Background: The aim of our study was to evaluate the "diagnosis changed" rate in patients notified as tuberculosis (TB) on the Korean TB surveillance system (KTBS). Methods: A total of 1,273 patients notified as TB cases on the KTBS in one private tertiary hospital in 2011 were enrolled in the present study. Patients were classified into three groups: "diagnosis maintained", "diagnosis changed" (initially notified as TB, but ultimately diagnosed as non-TB), and "administrative error" (notified as TB due to administrative errors). Results: Excluding 17 patients in the "administrative error" group, the "diagnosis maintained" and "diagnosis changed" groups included 1,097 (87.3%) and 159 patients (12.7%), respectively. Common causes of "diagnosis changed" were nontuberculous mycobacterial (NTM) disease (51.7%, 61/118), and pneumonia (17.8%) in cases notified as pulmonary TB, and meningitis (19.5%, 8/41) and Crohn's disease (12.2%) in cases notified as extrapulmonary TB. Being older than 35 years of age (odds ratio [OR], 2.18) and a positive acid-fast bacilli stain (OR, 1.58) were positive predictors and a TB-related radiological finding (OR, 0.42) was a negative predictor for a "diagnosis changed" result via multivariate logistic regression analysis in pulmonary TB cases. Conclusion: Because of a high "diagnosis changed" rate in TB notifications to the KTBS, the TB incidence rate measured by the KTBS may be overestimated. Considering the worldwide trend toward increased NTM disease, the "diagnosis changed" rate may increase over time. Thus, when reporting the annual TB notification rate in Korea, the exclusion of "diagnosis changed" cases is desirable.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.6
• /
• pp.2705-2709
• /
• 2012

Objective: To evaluate the predictive value of glutathione S-transferase (GST) gene polymorphisms for the prognosis of osteosarcoma patients receiving chemotherapy. Methods: A total of 159 patients were included in our study between January 2005 and December 2007., with follow-up until January 2012. Genotyping was based upon the duplex polymerase-chain-reaction with the PCR-CTPP method. Results: At the time of diagnosis, 15.4% of the patients presented with metastasis, while 22.3% developed metastasis during follow-up. At the time of final analysis on January 2012, the median follow-up was 45.5 months. Patients with null GSTM1 and GSTT1 had a higher event free survival rate than non-null genotype, but no significant association was found between the two genotypes and prognosis of osteosarcoma. Individuals with GSTP1 Val/Val genotype tended to live shorter than with the IIe/IIe genotype, and we found a significantly higher risk of death from osteosarcoma (adjusted HR=2.35, 95% CI=1.13-4.85). Conclusion: The GSTP1 gene polymorphism may have an important role in the prognosis of osteosarcoma patients with chemotherapy. Further analyses with larger samples and more genes encoding metabolizing and DNA repair enzymes are warranted.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.4
• /
• pp.1961-1966
• /
• 2016

Background: To investigate the prevalence of premature ejaculation (PE) and erectile dysfunction (ED) in a sample of patients with prostate cancer and to determine the utility of the previously suggested cutoffs of the Premature Ejaculation Diagnostic Tool (PEDT) for the diagnosis of PE and that of International Index of Erectile Function (IIEF-5) for ED. Materials and Methods: A total of 1,202 men with prostate cancer were invited from urology clinics at the universities of Iran, Tehran, Qazvin, Ahvaz, Guilan and Tabriz. Clinical characteristics were collected through medical records. PE and ED diagnoses were made by trained urologists. In addition to the clinical diagnoses, PE and ED were measured through self-report using the PEDT and the IIEF-5. Questionnaire cutoff scores were determined using receiver operating characteristic (ROC) curves and confirmed by predictive ability using logistic regression. Results: The prevalence of PE was 63.7% and that of ED was 66.2%. Prevalences of PE decreased and that of ED increased with advanced TNM stages. According to ROC, the suggested cutoff for the PEDT to diagnose a PE was ${\geq}11$ (sensitivity=0.988, 1-specificity=0.084, and predictive ability=0.914) and ${\leq}17$ for the IIEF-5 (sensitivity=0.966, 1-specificity=0.031, and predictive ability=0.967). Conclusions: Prevalence of sexual problems was high in prostate cancer patients in Iran, therefore oncologists should take into account these potential problems when deciding on treatment modalities.

• Clinical and Experimental Pediatrics
• /
• v.63 no.8
• /
• pp.329-334
• /
• 2020

Background: Birth asphyxia is a leading cause of neonatal mortality. Ischemia-modified albumin (IMA) levels may have a predictive role in the identification and prevention of hypoxic disorders, as they increase in cases of ischemia of the liver, heart, brain, bowel, and kidney. Purpose: This study aimed to assess the value of IMA levels as a diagnostic marker for neonatal hypoxic-ischemic encephalopathy (HIE). Methods: Sixty newborns who fulfilled 3 or more of the clinical and biochemical criteria and developed HIE as defined by Levene staging were included in our study as the asphyxia group. Neonates with congenital malformation, systemic infection, intrauterine growth retardation, low-birth weight, cardiac or hemolytic disease, family history of neurological diseases, congenital or perinatal infections, preeclampsia, diabetes, and renal diseases were excluded from the study. Sixty healthy neonates matched for gestational age and with no maternal history of illness, established respiration at birth, and an Apgar score ≥7 at 1 and 5 minutes were included as the control group. IMA was determined by double-antibody enzyme-linked immunosorbent assay of a cord blood sample collected within 30 minutes after birth. Results: Cord blood IMA levels were higher in asphyxiated newborns than in controls (250.83±36.07 pmol/mL vs. 120.24±38.9 pmol/mL). Comparison of IMA levels by HIE stage revealed a highly significant difference among them (207.3±26.65, 259.28±11.68, 294.99±4.41 pmol/mL for mild, moderate, and severe, respectively). At a cutoff of 197.6 pmol/mL, the sensitivity was 84.5%, specificity was 86%, positive predictive value was 82.8%, negative predictive value was 88.3%, and area under the curve was 0.963 (P<0.001). Conclusion: IMA levels can be a reliable marker for the early diagnosis of neonatal HIE and can be a predictor of injury severity.

• Tuberculosis and Respiratory Diseases
• /
• v.83 no.4
• /
• pp.312-320
• /
• 2020

Background: Systemic sclerosis (SSc) involves multiple organ systems and has the highest mortality among connective tissue diseases. Interstitial lung disease is the most common cause of death among SSc patients and requires closer studies and follow-ups. This study aimed to identify lung function changes and predictors of progressive disease in systemic sclerosis-related interstitial lung disease (SSc-ILD). Methods: A retrospective study extracted SSc patients from an electronic database January 2002-July 2019. Eligible cases were SSc patients >age 15 diagnosed with SSc-ILD. Factors associated with progressive disease were analyzed by univariate and multivariate logistic regression analyses. Results: Seventy-eight SSc-ILD cases were enrolled. Sixty-five patients (83.3%) were female, with mean age of 44.7±14.4, and 50 (64.1%) were diffuse type SSc-ILD. Most SSc-ILD patients had crackles (75.6%) and dyspnea on exertion (71.8%), and 19.2% of the SSc-ILD patients had no abnormal respiratory symptoms but had abnormal chest radiographic findings. The most common diagnosis of SSc-ILD patients was non-specific interstitial pneumonia (43.6%). The lung function values of diffusing capacity of the lung for carbon monoxide (DLCO) and DLCO per unit alveolar volume declined in progressive SSc-ILD during a 12-month follow-up. Male and no previous aspirin treatment were the two significant predictive factors of progressive SSc-ILD with adjusted odds ratios of 5.72 and 4.99, respectively. Conclusion: This present study showed that short-term lung function had declined during the 12-month follow-up in progressive SSc-ILD. The predictive factors in progressive SSc-ILD were male sex and no previous aspirin treatment. Close follow-up of the pulmonary function tests is necessary for early detection of progressive disease.

• Sleep Medicine and Psychophysiology
• /
• v.9 no.1
• /
• pp.34-40
• /
• 2002

Objectives: The gold standard for diagnosing obstructive sleep apnea syndrome (OSAS) is nocturnal polysomnography (NPSG). This is rather expensive and somewhat inconvenient, however, and consequently simpler and cheaper alternatives to NPSG have been proposed. Oximetry is appealing because of its widespread availability and ease of application. In this study, we have evaluated whether oximetry alone can be used to diagnose or screen OSAS. The diagnostic performance of an analysis algorithm using arterial oxygen saturation ($SaO_2$) base on 'dip index', mean of $SaO_2$, and CT90 (the percentage of time spent at $SaO_2$<90%) was compared with that of NPSG. Methods: Fifty-six patients referred for NPSG to the Division of Sleep Studies at Seoul National University Hospital, were randomly selected. For each patient, NPSG with oximetry was carried out. We obtained three variables from the oximetry data such as the dip index most linearly correlated with respiratory disturbance index (RDI) from NPSG, mean $SaO_2$, and CT90 with diagnosis from NPSG. In each case, sensitivity, specificity and positive and negative predictive values of oximetry data were calculated. Results: Thirty-nine patients out of fifty-six patients were diagnosed as OSAS with NPSG. Mean RDI was 17.5, mean $SaO_2$ was 94.9%, and mean CT90 was 5.1%. The dip index [4%-4sec] was most linearly correlated with RDI (r=0.861). With dip index [4%-4sec]${\geq}2$ as diagnostic criteria, we obtained sensitivity of 0.95, specificity of 0.71, positive predictive value of 0.88, and negative predictive value of 0.86. Using mean $SaO_2{\leq}97%$, we obtained sensitivity of 0.95, specificity of 0.41, positive predictive value of 0.79, and negative predictive value of 0.78. Using $CT90{\geq}5%$, we obtained sensitivity of 0.28, specificity of 1.00, positive predictive value of 1.00, and negative predictive value of 0.38. Conclusions: The dip index [4%-4sec] and mean $SaO_2{\leq}97%$ obtained from nocturnal oximetry data are helpful in diagnosis of OSAS. CT90${\leq}$5% can be also used in excluding OSAS.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.245-257
• /
• 2015

This study was to develop the predictive model for severity-adjusted mortality of inpatients with multiple chronic conditions and analyse the factors on the variation of hospital standardized mortality ratio(HSMR) to propose the plan to reduce the variation. We collect the data "Korean National Hospital Discharge In-depth Injury Survey" from 2008 to 2010 and select the final 110,700 objects of study who have chronic diseases for principal diagnosis and who are over the age of 30 with more than 2 chronic diseases including principal diagnosis. We designed a severity-adjusted mortality predictive model with using data-mining methods (logistic regression analysis, decision tree and neural network method). In this study, we used the predictive model for severity-adjusted mortality ratio by the decision tree using Elixhauser comorbidity index. As the result of the hospital standardized mortality ratio(HSMR) of inpatients with multiple chronic conditions, there were statistically significant differences in HSMR by the insurance type, bed number of hospital, and the location of hospital. We should find the method based on the result of this study to manage mortality ratio of inpatients with multiple chronic conditions efficiently as the national level. So we should make an effort to increase the quality of medical treatment for inpatients with multiple chronic diseases and to reduce growing medical expenses.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.8
• /
• pp.4143-4147
• /
• 2016

Purpose: We evaluated all PET/CTs acquired for patients without a primary diagnosis of colorectal cancer, and compared results for those who had subsequent colonoscopy within 6 months, to assess the accuracy of FDG PET/CT for detection of incidental pre-malignant polyps and malignant colon cancers. Materials and Methods: Medical records of 9,545 patients who underwent F-18 FDG PET/CT studies over 3.5 years were retrospectively reviewed. Due to pre-existing diagnosis of colorectal cancer, 818 patients were excluded. Of the remainder, 157 patients had colonoscopy within 6 months (79 males; mean age 61). We divided the colon into 4 regions and compared PET/CT results for each region with colonoscopy and histopathologic findings. True positive lesions included colorectal cancer, villous adenoma, tubulovillous adenoma, tubular adenoma and serrated hyperplastic polyp/hyperplastic polyposis. Results: Of 157 patients, 44 had incidental colonic uptake on PET/CT (28%). Of those, 25 had true positive (TP) uptake, yielding a 48% positive predictive value (PPV); 9% (4/44) were adenocarcinoma. There were 23 false positive (FP) lesions of which 4 were hyperplastic polyp, one was juvenile polyp and 7 were explained by diverticulitis. Fifty eight patients had false negative PET scans but colonoscopy revealed true pre-malignant and malignant pathology, yielding 23% sensitivity. The specificity, negiative predictive value (NPV) and accuracy were 96%, 90% and 87%, respectively. The average SUVmax values of TP, FP and FN lesions were 7.25, 6.11 and 2.76, respectively. There were no significant difference between SUVmax of TP lesions and FP lesions (p>0.95) but significantly higher than in FN lesions (p<0.001). The average size (by histopathology and colonoscopy) of TP lesions was 18.1 mm, statistically different from that of FN lesions which was 5.9 mm (p<0.001). Fifty-one percent of FN lesions were smaller than 5 mm (29/57) and 88% smaller than 10 mm (50/57). Conclusions: The high positive predictive value of incidental focal colonic FDG uptake of 48% for colonic neoplasia suggests that colonoscopy follow-up is warranted with this finding. We observed a low sensitivity of standardly acquired FDG-PET/CT for detecting small polyps, especially those less than 5 mm. Clinician and radiologists should be aware of the high PPV of focal colonic uptake reflecting pre-malignant and malignant lesions, and the need for appropriate follow up.