• 치위생과학회지
• /
• 제20권4호
• /
• pp.206-212
• /
• 2020

Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google's Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle's web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google's Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue's diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li's experimental results calculated with convolution neural network. Google's Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.

• Clinical and Experimental Reproductive Medicine
• /
• 제48권1호
• /
• pp.61-68
• /
• 2021

Objective: This study was conducted to investigate the relationship of semen parameters in samples used for intracytoplasmic sperm injection (ICSI) with fertilization and pregnancy rates in infertile couples. Methods: In this prospective study of Infertile couples with male factor infertility that had undergone ICSI, fractions of the same semen samples obtained for microinjection (to ensure the best predictability) were evaluated to determine the semen parameters and sperm DNA fragmentation index (DFI) on the day of oocyte recovery. Results: In total, 120 couples completed the study and were subdivided into fertilized (n=87) and non-fertilized couples (n=33). The fertilized couples were further classified into pregnant (n=48) and non-pregnant (n=39) couples. Compared to non-fertilized and non-pregnant couples, fertilized and pregnant couples showed statistically significantly higher sperm viability and percentage of normal sperm morphology, as well as significantly lower sperm DFI values. A receiver operating characteristic curve analysis of data from the 120 ICSI cycles showed that sperm viability, normal sperm morphology percentages, and sperm DFI were significant prognostic indicators of fertilization at cutoff values of 40%, 7%, and 46%, respectively. A sperm DFI of 46% showed sensitivity and specificity of 95% and 90%, respectively, for predicting fertilization, and no clinical pregnancies occurred in couples with a sperm DFI above 46%. Conclusion: Semen parameters from the ICSI day sample, especially sperm viability, normal morphology, and DFI, had an impact on fertilization and pregnancy outcomes in ICSI cycles.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• 제2권1호
• /
• pp.1-14
• /
• 2021

The study has been carried out with an objective to prepare Siberian roe deer habitat potential maps in South Korea based on three geographic information system-based models including frequency ratio (FR) as a bivariate statistical approach as well as convolutional neural network (CNN) and long short-term memory (LSTM) as machine learning algorithms. According to field observations, 741 locations were reported as roe deer's habitat preferences. The dataset were divided with a proportion of 70:30 for constructing models and validation purposes. Through FR model, a total of 10 influential factors were opted for the modelling process, namely altitude, valley depth, slope height, topographic position index (TPI), topographic wetness index (TWI), normalized difference water index, drainage density, road density, radar intensity, and morphological feature. The results of variable importance analysis determined that TPI, TWI, altitude and valley depth have higher impact on predicting. Furthermore, the area under the receiver operating characteristic (ROC) curve was applied to assess the prediction accuracies of three models. The results showed that all the models almost have similar performances, but LSTM model had relatively higher prediction ability in comparison to FR and CNN models with the accuracy of 76% and 73% during the training and validation process. The obtained map of LSTM model was categorized into five classes of potentiality including very low, low, moderate, high and very high with proportions of 19.70%, 19.81%, 19.31%, 19.86%, and 21.31%, respectively. The resultant potential maps may be valuable to monitor and preserve the Siberian roe deer habitats.

• 한국환경보건학회지
• /
• 제47권4호
• /
• pp.320-329
• /
• 2021

Background: Smoking exposure may be objectively assessed through specific biomarkers. The most common biomarker for smoking is cotinine concentration in urine, and setting an optimal cut-off point can accurately classify smoking status. Such a cut-off point for Korean adolescents has never been studied. Objectives: The aim of this study was to determine a cut-off point for urinary cotinine concentration for the discrimination of smoking in adolescents. Methods: Participants were adolescents aged 13~18 years who participated in the third cycle of the Korean National Environmental Health Survey. We used urine samples to confirm the level of cotinine concentrations. Smoking status was determined by self-reported questionnaire. We identified the optimal cotinine cut-off point for discriminating smoking status using receiver operating characteristic curve analysis. Results: Of the 904 participants, 28 (3.1%) were smokers, among whom 20 (71.4%) were male. The median urinary cotinine concentrations in smokers was 218 ㎍/L (male: 215 ㎍/L, female: 303 ㎍/L), and that in non-smokers was 1.31 ㎍/L (male: 1.46 ㎍/L, female: 1.18 ㎍/L). We found significant differences in urinary cotinine concentration according to smoking status and sex (p<0.001). Urinary cotinine concentrations performed well for identifying smoking adolescents [area under the curve: 0.954 (male: 0.963, female: 0.908)]. The cut-off that optimally distinguished smokers from non-smokers was 39.85 ㎍/L (sensitivity: 89.3%, specificity: 97.4%). Male [39.85 ㎍/L (sensitivity: 90.0%, specificity: 94.9%)] had a different optimal cut-off point than female [26.26 ㎍/L (sensitivity: 87.5%, specificity: 99.6%)]. Conclusions: This study determined a cut-off point for urinary cotinine of 39.85 ㎍/L (male: 39.85 ㎍/L, female: 26.26 ㎍/L) to distinguish smokers from non-smokers in adolescents.

• Journal of Gastric Cancer
• /
• 제22권1호
• /
• pp.24-34
• /
• 2022

Purpose: Total gastrectomy (TG) with lymph node (LN) dissection is recommended for early gastric cancer (EGC) but is not indicated for endoscopic resection (ER). We aimed to identify patients who could avoid TG by establishing a scoring system for predicting lymph node metastasis (LNM) in proximal EGCs. Materials and Methods: Between January 2003 and December 2017, a total of 1,025 proximal EGC patients who underwent TG with LN dissection were enrolled. Patients who met the absolute ER criteria based on pathological examination were excluded. The pathological risk factors for LNM were determined using univariate and multivariate logistic regression analyses. A scoring system for predicting LNM was developed and applied to the validation group. Results: Of the 1,025 cases, 100 (9.8%) showed positive LNM. Multivariate analysis confirmed the following independent risk factors for LNM: tumor size >2 cm, submucosal invasion, lymphovascular invasion (LVI), and perineural invasion (PNI). A scoring system was created using the four aforementioned variables, and the areas under the receiver operating characteristic curves in both the training (0.85) and validation (0.84) groups indicated excellent discrimination. The probability of LNM in mucosal cancers without LVI or PNI, regardless of size, was <2.9%. Conclusions: Our scoring system involving four variables can predict the probability of LNM in proximal EGC and might be helpful in determining additional treatment plans after ER, functioning as a good indicator of the adequacy of treatments other than TG in high surgical risk patients.

• Clinical and Experimental Reproductive Medicine
• /
• 제49권3호
• /
• pp.202-209
• /
• 2022

Objective: The aim of this study was to assess the correlation of oocyte number with serum anti-Müllerian hormone (AMH) levels measured by two automated methods (Access or Elecsys) in fresh stimulated in vitro fertilization (IVF) cycles. Methods: In this retrospective study at a university hospital, data were collected from 243 fresh stimulated IVF cycles performed from August 2016 to December 2020. The serum AMH level was measured by Access in 120 cycles and by Elecsys in 123 cycles. The cut-off of serum AMH for prediction of poor responders (three or fewer oocytes) or high responders (15 or more oocytes) was calculated by the receiver operating characteristic curve analysis. Results: For the two automated methods, the following equations were derived: total oocyte number=2.378+1.418×(Access-AMH) (r=0.645, p<0.001) and total oocyte number=2.417+2.163×(Elecsys-AMH) (r=0.686, p<0.001). The following combined equation could be derived: (Access-AMH)=0.028+1.525×(Elecsys-AMH). To predict poor responders, the cut-off of Access-AMH was 1.215 ng/mL (area under the curve [AUC], 0.807; 95% confidence interval [CI], 0.730-0.884; p<0.001), and the cut-off of Elecsys-AMH was 1.095 ng/mL (AUC, 0.848; 95% CI, 0.773-0.923; p<0.001). To predict high responders, the cut-off of Access-AMH was 3.450 ng/mL (AUC, 0.922; 95% CI, 0.862-0.981; p<0.001), and the cut-off of Elecsys-AMH was 2.500 ng/mL (AUC, 0.884; 95% CI, 0.778-0.991; p<0.001). Conclusion: Both automated methods for serum AMH measurement showed a good correlation with oocyte number and good performance for predicting poor and high responders in fresh stimulated IVF cycles. The Access method usually yielded higher measured serum AMH levels than the Elecsys method.

• Journal of Chest Surgery
• /
• 제55권3호
• /
• pp.214-224
• /
• 2022

Background: Studies of the prognostic role of circulating tumor cells (CTCs) in early-stage non-small cell lung cancer (NSCLC) are still limited. This study investigated the prognostic power of CTCs from the pulmonary vein (PV), peripheral blood (PB), and bone marrow (BM) for postoperative recurrence in patients who underwent curative resection for NSCLC. Methods: Forty patients who underwent curative resection for NSCLC were enrolled. Before resection, 10-mL samples were obtained of PB from the radial artery, blood from the PV of the lobe containing the tumor, and BM aspirates from the rib. A microfabricated filter was used for CTC enrichment, and immunofluorescence staining was used to identify CTCs. Results: The pathologic stage was stage I in 8 patients (20%), II in 15 (38%), III in 14 (35%), and IV in 3 (8%). The median number of PB-, PV-, and BM-CTCs was 4, 4, and 5, respectively. A time-dependent receiver operating characteristic curve analysis showed that PB-CTCs had excellent predictive value for recurrence-free survival (RFS), with the highest area under the curve at each time point (first, second, and third quartiles of RFS). In a multivariate Cox proportional hazard regression model, PB-CTCs were an independent risk factor for recurrence (hazard ratio, 10.580; 95% confidence interval, 1.637-68.388; p<0.013). Conclusion: The presence of ≥4 PB-CTCs was an independent poor prognostic factor for RFS, and PV-CTCs and PB-CTCs had a positive linear correlation in patients with recurrence.

• Journal of Korean Biological Nursing Science
• /
• 제24권1호
• /
• pp.17-25
• /
• 2022

Purpose: To determine the prognostic role of muscle area and muscle radiation attenuation in the erector spinae (ES) and multifidus (MF) muscles in patients undergoing gastrectomy. Methods: Patients with stage I-III gastric cancer undergoing gastrectomy were retrospectively enrolled in this study. Clinicopathologic characteristics were collected and analyzed. Both paraspinal muscle index of ES/MF muscles (PMI_EM) and paraspinal muscle radiation attenuation in the same muscles (PMRA_EM) were analyzed at the 3rd lumbar level using axial computed tomographic images. Cox regression analysis was applied to estimate overall survival (OS) and disease-free survival (DFS). Results: There was only a weak correlation between PMI_EM and PMRA_EM (r= 0.28). Multivariate Cox regression revealed that PMRA_EM, but not PMI_EM, was an important determinant of survival. PMRA_EM along with age, tumor-node-metastasis (TNM) stage, perineural invasion, and serum albumin level were significant determinants of both OS and DFS that constituted Model 1. Harrell's concordance index and integrated area under receiver operating characteristic curve were greater for Model 1 than for Model 2 (consisting of the same covariates as Model 1 except PMRA_EM) or Model 3 (consisting of only TNM stage). Conclusion: PMRA_EM, but not PMIEM, was an important determinant of survival. Because there was only a weak correlation between PMI_EM and PMRA_EM in this study, it was presumed that they were mutually exclusive. Model 1 consisting of age, TNM stage, perineural invasion, serum albumin level, and PMRA_EM was greater than nested models (i.e., Model 2 or Model 3) in predicting survival outcomes.

• ETRI Journal
• /
• 제44권4호
• /
• pp.573-587
• /
• 2022

The agricultural sector is completely different from other sectors since it completely relies on various natural and climatic factors. Climate changes have many effects, including lack of annual rainfall and pests, heat waves, changes in sea level, and global ozone/atmospheric CO₂ fluctuation, on land and agriculture in similar ways. Climate change also affects the environment. Based on these factors, farmers chose their crops to increase productivity in their fields. Many existing agricultural ontologies are either domain-specific or have been created with minimal vocabulary and no proper evaluation framework has been implemented. A new agricultural ontology focused on subdomains is designed to assist farmers using Jaccard relative extractor (JRE) and Naïve Bayes algorithm. The JRE is used to find the similarity between two sentences and words in the agricultural documents and the relationship between two terms is identified via the Naïve Bayes algorithm. In the proposed method, the preprocessing of data is carried out through natural language processing techniques and the tags whose dimensions are reduced are subjected to rule-based formal concept analysis and mapping. The subdomain ontologies of weather, pest, and soil are built separately, and the overall agricultural ontology are built around them. The gold standard for the lexical layer is used to evaluate the proposed technique, and its performance is analyzed by comparing it with different state-of-the-art systems. Precision, recall, F-measure, Matthews correlation coefficient, receiver operating characteristic curve area, and precision-recall curve area are the performance metrics used to analyze the performance. The proposed methodology gives a precision score of 94.40% when compared with the decision tree(83.94%) and K-nearest neighbor algorithm(86.89%) for agricultural ontology construction.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.53-53
• /
• 2023

본 연구에서는 토양의 동결-융해 상태 구분을 위해 영상레이더(Synthetic Aperture Radar) 자료를 활용해 지표상태인자(Surface State Factor, SSF)를 산정하고, 관측 토양수분 자료 및 지표면 온도(Land Surface Temperature, LST) 자료와의 비교를 통해 SSF의 정확도를 분석하였다. SSF 산정은 용담댐 유역을 포함한 인근 40×50 km²의 영역(N35°35'~36°00', E127°20'~127°45')에 대한 9개의 토양수분 관측지점(계북, 천천, 상전, 안천, 부귀, 주천, 장수읍, 진안읍, 무주읍)을 대상으로 연구를 수행하였으며, 이를 위해 2015년부터 2019년까지의 해당 지점의 토양수분 관측자료와 Sentinel-1A Interferometric Wide swath (IW) 모드의 Ground Range Detected (GRD) product를 구축하여 활용하였다. SSF 자료의 정확도 분석을 위한 토양수분 관측지점에 대한 LST 자료는 인근 7개 기상관측소 지점(전주, 금산, 임실, 남원, 장수, 함양군, 거창)의 관측자료로부터 역거리가중법을 통해 산정하였다. Receiver Operating Characteristic (ROC) 분석을 통한 겨울철(12-2월)의 SSF 산정 정확도를 평가한 결과, 지표면 온도 자료와의 평균 정확도는 0.75(0.48-0.87)로 나타났다. 그러나, 지표면 온도가 0℃ 이상일 때 SSF가 동결 상태로 나타나는 오차가 관측되었으며, 이는 여름철 후방산란계수의 평균값과 겨울철 후방산란계수의 평균값을 통해 산정하는 SSF 산정 수식의 특성 때문으로 이 값의 조정을 통해 오차를 개선할 수 있음을 보였다.