• Tuberculosis and Respiratory Diseases
• /
• v.86 no.3
• /
• pp.203-215
• /
• 2023

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R² and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R² value was 0.27 and in set II, LightGBM was the best model with the highest R² value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R² value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

• Korean Journal of Organic Agriculture
• /
• v.25 no.2
• /
• pp.329-344
• /
• 2017

This study was carried out to investigate the hot pepper yield, chemical properties of soil and distribution of animalcule with split irrigation and input of organic matter under no-tillage hot pepper green house condition. After experiment, soil pH maintained range of 5.6~6.2 in whole treatments. Organic matter content of soil was range of $32{\sim}42g{\cdot}kg^{-1}$. Soil salinity (EC) content of soil was range of $1.0{\sim}2.7dS{\cdot}m^{-1}$. Exchangeable cations in soil were range of $0.08{\sim}0.24cmol^+{\cdot}kg^{-1}$ in K, $9.5{\sim}12.8cmol^+{\cdot}kg^{-1}$ in Ca, and $2.7{\sim}3.2cmol^+{\cdot}kg^{-1}$ in Mg. Avaliable phosphorus ($P_2O_4$) content in soil was range of $1,011{\sim}1,137mg{\cdot}kg^{-1}$. Yield of pepper was more decreased in treatment of soybean cake fertilizer than no-treatment of soybean cake fertilizer. Yield of pepper in treatment of soybean cake fertilizer was increased at 33% of standard fertilizer application. Yield of pepper in no-treatment of soybean cake fertilizer was increased at 33% and 66% of standard fertilizer application. Number of fruits was increased range of 12.5~34.9% at half division irrigation compared with whole quantity irrigation. Yield of pepper was increased range of 13.5~34.4% at half division irrigation compared with whole quantity irrigation. Nine index of nature status and 271 Individual were captured in treatment of soybean cake fertilizer. Five index of nature status and 54 Individual were captured in treatment of soybean cake fertilizer. Nature status for environmental change as index organism was 11 points and 5 points, at treatment of soybean cake fertilizer and no-treatment of soybean cake fertilizer, respectively.

• Korean Journal of Organic Agriculture
• /
• v.25 no.2
• /
• pp.311-328
• /
• 2017

This study was carried out to investigate the changes in soil microorganisms and soil enzymes by split irrigation and organic matter application under no-tillage green house conditions. Soil bacteria and fungi abundances were higher in soybean cake fertilizer than in the soil without the soybean cake fertilizer under whole quantity irrigation. Bacteria and fungi abundances in soil increased with increasing organic fertilizer application rate. Bacteria and fungi amount in the soil increased at half division irrigation in no-treatment of soybean cake fertilizer compared with whole quantity irrigation. Actinomycete amount in the soil decreased with increasing soybean cake fertilizer with whole quantity irrigation while clearly increased in no-treatment of soybean cake fertilizer. Actinomycete amount in soil clearly increased with increasing organic fertilizer input at half division irrigation. Chitinase activity in the soil decreased in soybean cake fertilizer with increasing organic fertilizer input, while increased in no-treatment of soybean cake fertilizer. Chitinase activity in the soil increased at half division irrigation compared with whole quantity irrigation regardless of soybean cake fertilizer input. ${\beta}$-Glucosidase activity in the soil was higher in soybean cake fertilizer than in no-treatment of soybean cake fertilizer with whole quantity irrigation. ${\beta}$-Glucosidase activity in the soil increased with increasing organic fertilizer input, but decreased in above the standard level 66%. ${\beta}$-Glucosidase activity in the soil clearly increased in no-treatment of soybean cake fertilizer at half division irrigation compared with whole quantity irrigation. N-acetyl-${\beta}$-D-glucosaminidase activity was higher in soybean cake fertilizer than in no-treatment of soybean cake fertilizer with whole quantity irrigation. N-acetyl-${\beta}$-D-glucosaminidase activity in the soil increased with increasing organic fertilizer input, but decreased in above the standard level 66%. N-acetyl-${\beta}$-D-glucosaminidase activity in the soil was not significantly different at half division irrigation and whole quantity irrigation in organic fertilizer input, while increased at half division irrigation in no-treatment of soybean cake fertilizer. Acid phosphatase activity increased at standard level 66% in soybean cake fertilizer, while was not significantly different in no-treatment of soybean cake fertilizer. Spore density of Arbuscular Mycorrhizal Fungi (AMF) in the soil increased with increasing organic fertilizer input at whole quantity irrigation in no-treatment of soybean cake fertilizer, while decreased above the standard level 66% in organic fertilizer input. However, spore density of AMF in the soil was not significantly different in soybean cake fertilizer regardless of input amount of organic fertilizer. Root colonization rate of AMF in red pepper roots was not significant difference at two irrigations regardless of soybean cake input.