• Tuberculosis and Respiratory Diseases
• /
• v.54 no.3
• /
• pp.330-337
• /
• 2003

Background : Low spirometric forced vital capacity(FVC) in conjunction with a normal or high ratio of the forced expiratory volume at 1 second to the forced vital capacity($FEV_1$/FVC%) has traditionally been classified as a restrictive abnormality. However, the gold-standard diagnosis of a restrictive pulmonary impairment requires a measurement of the total lung capacity (TLC). This study was performed to determine the predictive value of spirometric measurements of the FVC for diagnosing a restrictive pulmonary abnormality. Methods : Test results from 1,371 adult patients who undertook both spirometry and lung volume measurements on the same visit from January 1999 to December 2000 were enrolled in this study. The test values for the FVC, the TLC that was below 80% of predicted value, and a $FEV_1$/FVC% that was below 70%, were classified as being abnormal. Results : Of the 1,371 patients, 353 patients had a reduced a FVC. Of these patients, 186 patients had a reduced TLC. Therefore, the positive predictive value was 52.7%. Of the 196 patients with a normal $FEV_1$/FVC% and a reduced FVC, 148(75.5%) patients had a lower TLC. Thirty eight (24.2%) patients out of 157 patients with a low $FEV_1$/FVC% and a low FVC showed a restrictive defect. Conclusion : Spirometry is useful to rule out a restrictive pulmonary abnormality, but a restrictive pattern on the spirometry dose not mean there is a true restrictive disease. For the patients with a low FVC, TLC measurements are essential for diagnosing a restrictive pulmonary impairment.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Tuberculosis and Respiratory Diseases
• /
• v.46 no.6
• /
• pp.786-794
• /
• 1999

Back ground : Arm span measurements provide a practical substitute for standing height to predict normal spirometric values in subjects unable to stand or those with a skeletal deformity such as kyphoscoliosis. The relationship between arm span and height has previously been reported as either a fixed ratio unaffected by age or as a regression equation in which the ratio varies as a function of age. The fixed ratio or regression equation is known to be specific for sex and race. Methods : We studied the relationship between standing height, arm span, and age in 381 Korean adult female subjects (ages 20 to 69 yrs) sampled in a general population. Results : The mean ratio for arm span to height is 1.004. Multiple linear analysis found arm span and age to be predictive of standing height (p=0.0001, $r^2$=0.76). We performed the analysis of the difference between the predicted height using either fixed ratio or regression equation and actual height. At the extremes of arm span and age, the ratio method either underestimated(at smaller arm span or younger age) or overestimated(at larger arm span or older age) as compared with actual height (p=0.0001). Conclusion : This results indicate that the estimated height using the fixed ratio method provides a less acceptable method of estimating height for the prediction of lung volumes in the Korean adult women when compared with the regression equations, especially at the extremes of stature or age.

• Tuberculosis and Respiratory Diseases
• /
• v.44 no.1
• /
• pp.93-103
• /
• 1997

Background : Malnutrition is a common finding in patients with chronic obstructive pulmonary disease, especially in the emphysema group. Although the mechanism of malnutrition is not confirmed, it is believed to be a relative deficiency caused by hypermetabolism due to increased energy requirements of the respiratory muscles, rather than a dietary deficiency. Malnutrition in chronic obstructive pulmonary disease is not a merely coincidental finding. It is known that the nutritional status correlates with physiologic parameters including pulmonary function, muscular power, and exercise performance, and is one of the important and independent prognostic factors of the disease. Methods : Patients with chronic obstructive pulmonary disease Yongdong Severance Hospital from May, 1995 to March, 1996 and age-matched healthy control group were studied. Survey of nutritional intake, anthropometric measurements and biochemical tests were done to assess nutritional status. Relationship between nutritional status and FEV1 (forced expiratory volume at one second), which was a significant functional parameter, was assessed. Results : 1) The patient group was consisted of 25 males with mean age of 66.1years and FEV1 of $42{\pm}14%$ of predicted values. The control group was consisted of 26 healthy males with normal pulmonary function, whose mean age was 65.0 years. 2) The ratio of calorie intake/calorie requirement per day was $107{\pm}28%$ in the patient group, and $94{\pm}14%$ in the control group, showing a tendency of more nutritional intake in patient group(B=0.06). 3) There were significant differences between the patient group and control group in percent ideal body weight(92.8% vs 101.6%, p=0.024), body mass index($20.0kg/m^2$ VS $21.9kg/m^2$, p=0.015), and handgrip strength(29.0kg vs 34.3kg, p=0.003). However, there were no significant differences in triceps skinfold thickness, mid-arm muscle circumference, albumin, and total lymphocyte count between two groups. Percentage of underweight population was 40%(10/25) in the patient group, and 15%(4/26) in the control group. 4) The percent ideal body weight, triceps skinfold thickness, and mid-arm muscle circumference had significant correlation with FEV1. Conclusion : The patients with chronic obstructive pulmonary disease showed significant depletion in nutritional parameters such as body weight and peripheral muscle strength, while absolute amount of dietary intake was not insufficient. Nutritional parameters were well correlated with FEV1.

• Tuberculosis and Respiratory Diseases
• /
• v.61 no.3
• /
• pp.218-226
• /
• 2006

Background: The lung volume and diffusing capacity are influenced by ethnicity. However, there are no equations for predicting the normal lung volume in the adult Korean population, and there is only one equation for diffusing capacity. The aim of this study is to select the most suitable reference equation for the Korean population. Method: 30 men and 33 women at Hanyang University Guri Hospital, and 27 men and 34 women at Asan Medical Center in healthy nonsmoking adults were enrolled in this study. The subject's age, gender, height, weight, lung volume by plethysmography, and diffusing capacity by a single breathing method were obtained. The most suitable equation with the lowest sum of residuals between the observed and predicted values for lung volume and diffusing capacity was selected. Result: At Hanyang University Guri Hospital, the equations with the lowest sum of residuals in the total lung capacity were ECSC's equation in males (sum of residual: 0.04 L) and Crapo/Morris's equation (-1.04) in women. At the Asan Medical Center, the equations with the lowest sum of residuals in the total lung capacity were Goldman/Becklake's equation in males (sum of residual: -2.35) and the ECSC's equation -4.49) in women. The equations with the lowest sum of residuals in the Diffusing capacity were Roca's equation in males (sum of residual: -13.66 ml/min/mmHg) and Park's in women (25.08) in Hanyang University Guri hospital and Park's equation in all cases in the Asan Medical Center (male: -1.65, female: -6.46). Conclusions: Until a reference equstion can be made for healthy Koreans by sampling, ECSC's equation can be used for estimating the lung volume and Park's can be used for estimating the diffusing capacity.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.4107-4107
• /
• 2001

Previous works have shown the viability of NIRS technology for the prediction of fatty acids in Iberian pig fat, but although the resulting equations showed high precision, in the predictions of new samples important fluctuations were detected, greater with the time passed from calibration development to NIRS analysis. This fact makes the use of NIRS calibrations in routine analysis difficult. Moreover, this problem only appears in products like fat, that show spectrums with very defined absorption peaks at some wavelengths. This circumstance causes a high sensibility to small changes of the instrument, which are not perceived with the normal checks. To avoid these inconveniences, the software WinISI 1.04 has a mathematic algorithm that consist of create a “Repeatability File”. This file is used during calibration development to minimize the variation sources that can affect the NIRS predictions. The objective of the current work is the evaluation of the use of a repeatability file in quantitative NIRS analysis of Iberian pig fat. A total of 188 samples of Iberian pig fat, produced by COVAP, were used. NIR data were recorded using a FOSS NIRSystems 6500 I spectrophotometer equipped with a spinning module. Samples were analysed by folded transmission, using two sample cells of 0.1mm pathlength and gold surface. High accuracy calibration equations were obtained, without and with repeatability file, to determine the content of six fatty acids: miristic (SECV$\sub$without/=0.07% r$^2$$\sub$without/=0.76 and SECV$\sub$with/=0.08% r$^2$$\sub$with/=0.65), Palmitic (SECV$\sub$without/=0.28 r$^2$$\sub$without/=0.97 and SECV$\sub$with/=0.24% r$^2$$\sub$with/=0.98), palmitoleic (SECV$\sub$without/=0.08 r$^2$$\sub$without/=0.94 and SECV$\sub$with/=0.09% r$^2$$\sub$with/=0.92), Stearic (SECV$\sub$without/=0.27 r$^2$$\sub$without/=0.97 and SECV$\sub$with/=0.29% r$^2$$\sub$with/=0.96), oleic (SECV$\sub$without/=0.20 r$^2$$\sub$without/=0.99 and SECV$\sub$with/=0.20% r$^2$$\sub$with/=0.99) and linoleic (SECV$\sub$without/=0.16 r$^2$$\sub$without/=0.98 and SECV$\sub$with/=0.16% r$^2$$\sub$with/=0.98). The use of a repeatability file like a tool to reduce the variation sources that can disturbed the prediction accuracy was very effective. Although in calibration results the differences are negligible, the effect caused by the repeatability file is appreciated mainly when are predicted new samples that are not in the calibration set and whose spectrum were recorded a long time after the equation development. In this case, bias values corresponding to fatty acids predictions were lower when the repeatability file was used: miristic (bias$\sub$without/=-0.05 and bias$\sub$with/=-0.04), Palmitic (bias$\sub$without/=-0.42 and bias$\sub$with/=-0.11), Palmitoleic (bias$\sub$without/=-0.03 and bias$\sub$with/=0.03), Stearic (bias$\sub$without/=0.47 and bias$\sub$with/=0.28), oleic (bias$\sub$without/=0.14 and bias$\sub$with/=-0.04) and linoleic (bias$\sub$without/=0.25 and bias$\sub$with/=-0.20).

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.4
• /
• pp.555-568
• /
• 1995

Background: It is most physiologic to measure the diffusing capacity of the lung by using oxygen, but it is so difficult to measure partial pressure of oxygen in the capillary blood of the lung that in clinical practice it is measured by using carbon monoxide, and single-breath diffusing capacity method is used most widely. However, since the process of withholding the breath for 10 seconds after inspiration to the total lung capacity is very hard to practice for patients who suffer from cough, dyspnea, etc, the intra-breath lung diffusing capacity method which requires a single exhalation of low-flow rate without such process was devised. In this study, we want to know whether or not there is any significant difference in the diffusing capacity of the lung measured by the single-breath and intra-breath methods, and if any, which factors have any influence. Methods: We chose randomly 73 persons without regarding specific disease, and after conducting 3 times the flow-volume curve test, we selected forced vital capacity(FVC), percent of predicted forced vital capacity, forced expiratory volume within 1 second($FEV_1$), percent of forced expiratory volume within 1 second, the ratio of forced expiratory volume within 1 second against forced vital capacity($FEV_1$/FVC) in test which the sum of FVC and $FEV_1$ is biggest. We measured the diffusing capacity of the lung 3 times in each of the single-breath and intra-breath methods at intervals of 5 minutes, and we evaluated which factors have any influence on the difference of the diffusing capacity of the lung between two methods[the mean values(ml/min/mmHg) of difference between two diffusing capacity measured by two methods] by means of the linear regression method, and obtained the following results: Results: 1) Intra-test reproducibility in the single-breath and intra-breath methods was excellent. 2) There was in general a good correlation between the diffusing capacity of the lung measured by a single-breath method and that measured by the intra-breath method, but there was a significant difference between values measured by both methods($1.01{\pm}0.35ml/min/mmHg$, p<0.01) 3) The difference between the diffusing capacity of the lung measured by both methods was not correlated to FVC, but was correlated to $FEV_1$, percent of $FEV_1$, $FEV_1$/FVC and the gradient of methane concentration which is an indicator of distribution of ventilation, and it was found as a result of the multiple regression test, that the effect of $FEV_1$/FVC was most strong(r=-0.4725, p<0.01) 4) In a graphic view of the difference of diffusing capacity measured by single-breath and intra-breath method and $FEV_1$/FVC, it was found that the former was divided into two groups in section where $FEV_1$/FVC is 50~60%, and that there was no significant difference between two methods in the section where $FEV_1$/FVC is equal or more than 60% ($0.05{\pm}0.24ml/min/mmHg$, p>0.1), but there was significant difference in the section, less than 60%($-4.5{\pm}0.34ml/min/mmHg$, p<0.01). 5. The diffusing capacity of the lung measured by the single-breath and intra-breath method was the same in value($24.3{\pm}0.68ml/min/mmHg$) within the normal range(2%/L) of the methane gas gradient, and there was no difference depending on the measuring method, but if the methane concentration gradients exceed 2%/L, the diffusing capacity of the lung measured by single-breath method became $15.0{\pm}0.44ml/min/mmHg$, and that measured by intra-breath method, $11.9{\pm}0.51ml/min/mmHg$, and there was a significant difference between them(p<0.01). Conclusion: Therefore, in case where $FEV_1$/FVC was less than 60%, the diffusing capacity of the lung measured by intra-breath method represented significantly lower value than that by single-breath method, and it was presumed to be caused largely by a defect of ventilation-distribution, but the possibility could not be excluded that the diffusing capacity of the lung might be overestimated in the single-breath method, or the actual reduction of the diffusing capacity of the lung appeared more sensitively in the intra-breath method.