• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.14
• /
• pp.5601-5605
• /
• 2014

Background: Agrocybe aegerita Lectin (AAL) has been identified to have high affinity for sulfated and ${\alpha}2$-3-linked sialic acid glycoconjugates, especially the sulfated and sialyl TF (Thomsen-Friedenreich) disaccharide. This study was conducted to investigate the clinicopathological and prognostic value of AAL in identifying aberrant glycosylation in colorectal cancer (CRC). Materials and Methods: Glycoconjugate expression in 59 CRC tissues were detected using AAL-histochemistry. Clinicopathological associates of expression were analyzed with chisquare test or Fisher's exact test. Relationships between expression and the various clinicopathological parameters was estimated using Kaplan-Meier analysis and Cox regression models. Results: AAL specific glycoconjugate expression was significantly higher in tumor than corresponding normal tissues (66.1% and 46.1%, respectively, p=0.037), correlating with depth of invasion (p=0.015) and TNM stage (p=0.024). Patients with lower expression levels had a significantly higher survival rate than those with higher expression (p=0.046 by log rank test and p=0.047 by Breslow test for overall survival; p=0.054 by log rank test and P=0.038 by Breslow test for progress free survival). A marginally significant association was found between AAL specific glycoconjugate expression and overall survival by univariate Cox regression analysis (p=0.059). Conclusions: Lower AAL specific glycoconjugate expression is a significant favorable prognostic factor for overall and progress free survival in CRC. This is the first report about the employment of AAL for histochemical analysis of cancer tissues. The binding characteristics of AAL means it has potential to become a powerful tool for the glycan investigation and clinical application.

• Journal of Environmental Science International
• /
• v.19 no.1
• /
• pp.27-37
• /
• 2010

A system coupled the prognostic WRF mesoscale model and CALMET diagnostic model has been employed for predicting high-resolution wind field over complex coastal area. WRF has three nested grids down to from during two days from 24 August 2007 to 26 August 2007. CALMET simulation is performed using both initial meteorological field from WRF coarsest results and surface boundary condition that is Shuttle Radar Topography Mission (SRTM) 90m topography and Environmental Geographic Information System (EGIS) 30m landuse during same periods above. Four Automatic Weather System (AWS) and a Sonic Detection And Ranging (SODAR) are used to verify modeled wind fields. Horizontal wind fields in CM_100m is not only more complex but better simulated than WRF_1km results at Backwoon and Geumho in which there are shown stagnation, blocking effects and orographically driven winds. Being increased in horizontal grid spacing, CM_100m is well matched with vertically wind profile compared SODAR. This also mentions the importance of high-resolution surface boundary conditions when horizontal grid spacing is increased to produce detailed wind fields over complex terrain features.

• Korean Journal of Head & Neck Oncology
• /
• v.38 no.1
• /
• pp.17-24
• /
• 2022

Background/Objectives: This study analyzed the prognostic significance of clinico-pathologic factors including comprehensive nodal factors in parotid gland cancers (PGCs) patients and constructed a survival prediction model for PGCs patients using machine learning techniques. Materials & Methods: A total of 131 PGCs patients were enrolled in the study. Results: There were 19 cases (14.5%) of lymph nodes (LNs) at the lower neck level and 43 cases (32.8%) involved multiple level LNs metastases. There were 2 cases (1.5%) of metastases to the contralateral LNs. Intraparotid LNs metastasis was observed in 6 cases (4.6%) and extranodal extension (ENE) findings were observed in 35 cases (26.7%). Lymphovascular invasion (LVI) and perineural invasion findings were observed in 42 cases (32.1%) and 49 cases (37.4%), respectively. Machine learning prediction models were constructed using clinico-pathologic factors including comprehensive nodal factors and Decision Tree and Stacking model showed the highest accuracy at 74% and 70% for predicting patient's survival. Conclusion: Lower level LNs metastasis and LNR have important prognostic significance for predicting disease recurrence and survival in PGCs patients. These two factors were used as important features for constructing machine learning prediction model. Our machine learning model could predict PGCs patient's survival with a considerable level of accuracy.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.5
• /
• pp.1803-1811
• /
• 2015

Hepatoma-derived growth factor (HDGF) is a novel jack-of-all-trades in cancer. Here we quantify the prognostic impact of this biomarker and assess how consistent is its expression in solid tumors. A comprehensive search strategy was used to search relevant literature updated on October 3, 2014 in PubMed, EMBASE and WEB of Science. Correlations between HDGF expression and clinicopathological features or cancer prognosis was analyzed. All pooled HRs or ORs were derived from random-effects models. Twenty-six studies, primarily in Eastern Asia, covering 2,803 patients were included in the analysis, all of them published during the past decade. We found that HDGF overexpression was significantly associated with overall survival (OS) ($HR_{OS}=2.35$, 95%CI=2.04-2.71, p<0.001) and disease free survival (DFS) ($HR_{DFS}=2.25$, 95%CI =1.81-2.79, p<0.001) in solid tumors, especially in non-small cell lung cancer, hepatocellular carcinoma and cholangiocarcinoma (CCA). Moreover, multivariate survival analysis showed that HDGF overexpression was an independent predictor of poor prognosis ($HR_{OS}=2.41$, 95%CI: 2.02-2.81, p<0.001; $HR_{DFS}=2.39$, 95%CI: 1.77-3.24, p<0.001). In addition, HDGF overexpression was significantly associated with tumor category (T3-4 versus T1-2, OR=2.12, 95%CI: 1.17-3.83, p=0.013) and lymph node status (N+ versus N-, OR=2.37, 95%CI: 1.31-4.29, p=0.03) in CCA. This study provides a comprehensive examination of the literature available on the association of HDGF overexpression with OS, DFS and some clinicopathological features in solid tumors. Meta-analysis results provide evidence that HDGF may be a new indicator of poor cancer prognosis. Considering the limitations of the eligible studies, other large-scale prospective trials must be conducted to clarify the prognostic value of HDGF in predicting cancer survival.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.7
• /
• pp.3451-3454
• /
• 2012

Background: Esophageal cancer in Iran is the sixth most common cancer and is particularly important in east Azerbaijan. The aim of this study was to calculate survival rates and define prognostic factors in esophageal cancer patients. Methods: In this study, all patients with esophageal cancer registered in the Radiation Therapy Center, during March 2006 to March 2011, were analyzed and followed up for vital status. Data were analyzed using the Kaplan-Meier method and the Cox proportional hazard models. Results: Out of 532 patients, survival information was available for 460, including 205 (44/ 5%) females and 255 (55/4%) males. The mean age was $65.8{\pm}12.2$, ranging from 29 to 90 years at the time of diagnosis. 1-, 3- and 5-year survival rates after diagnosis were 55%, 18% and 12%, respectively, with a median survival time of $13.2{\pm}.7$ (CI 95% =11.8-14.6) months. In the univariate analysis, age (P=0/001), education (P=0/001), smoking status (P= 0/001), surgery (P= 0/001), tumor differentiation (P= 0/003) and tumor stage (P= 0/001) were significant prognostic factors. Tumor morphology, sex, place of residence, tumor histology and tumor location did not show any significant effects on the survival rate. In multivariate analysis, age (P = 0/003), smoking (P= 0/01) and tumor stage (P= 0/001) were significant independent predictors of survival. Conclusion: In summary, prognosis of esophageal cancer in North West of Iran is poor. Therefore, reduction in exposure to risk factors and early detection should be emphasized to improve survival.

• Journal of Gastric Cancer
• /
• v.19 no.1
• /
• pp.121-131
• /
• 2019

Purpose: The significance of neuroendocrine differentiation (NED) in gastric carcinoma (GC) is controversial, leading to ambiguous concepts in traditional classifications. This study aimed to determine the prognostic threshold of meaningful NED in GC and clarify its unclear features in existing classifications. Materials and Methods: Immunohistochemical staining for synaptophysin, chromogranin A, and neural cell adhesion molecule was performed for 945 GC specimens. Survival analysis was performed using the log-rank test and univariate/multivariate models with percentages of NED ($P_{NED}$) and demographic and clinicopathological parameters. Results: In total, 275 (29.1%) cases were immunoreactive to at least 1 neuroendocrine (NE) marker. GC-NED was more common in the upper third of the stomach. $P_{NED}$, and Borrmann's classification and tumor, lymph node, metastasis stages were independent prognostic factors. The cutoff $P_{NED}$ was 10%, beyond which patients had significantly worse outcomes, although the risk did not increase with higher $P_{NED}$. Tumors with ${\geq}10%$ NED tended to manifest as Borrmann type III lesion with mixed/diffuse morphology and poorer histological differentiation; the NE components in this population mainly grew in insulae/nests, which differed from the predominant growth pattern (glandular/acinar) in GC with <10% NED. Conclusions: GC with ${\geq}10%$ NED should be classified as a distinct subtype because of its worse prognosis, and more attention should be paid to the necessity of additional therapeutics for NE components.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.1-11
• /
• 2021

Recently, the importance of preventive maintenance has been emerging since failures in a complex system are automatically detected due to the development of artificial intelligence techniques and sensor technology. Therefore, prognostic and health management (PHM) is being actively studied, and prediction of the remaining useful life (RUL) of the system is being one of the most important tasks. A lot of researches has been conducted to predict the RUL. Deep learning models have been developed to improve prediction performance, but studies on identifying the importance of features are not carried out. It is very meaningful to extract and interpret features that affect failures while improving the predictive accuracy of RUL is important. In this paper, a total of six popular deep learning models were employed to predict the RUL, and identified important variables for each model through SHAP (Shapley Additive explanations) that one of the explainable artificial intelligence (XAI). Moreover, the fluctuations and trends of prediction performance according to the number of variables were identified. This paper can suggest the possibility of explainability of various deep learning models, and the application of XAI can be demonstrated. Also, through this proposed method, it is expected that the possibility of utilizing SHAP as a feature selection method.

• Korean Journal of Radiology
• /
• v.25 no.2
• /
• pp.189-198
• /
• 2024

Objective: To investigate the prognostic utility of radiomics features extracted from ¹⁸F-fluorodeoxyglucose (FDG) PET/CT combined with clinical factors and metabolic parameters in predicting progression-free survival (PFS) and overall survival (OS) in individuals diagnosed with extranodal nasal-type NK/T cell lymphoma (ENKTCL). Materials and Methods: A total of 126 adults with ENKTCL who underwent ¹⁸F-FDG PET/CT examination before treatment were retrospectively included and randomly divided into training (n = 88) and validation cohorts (n = 38) at a ratio of 7:3. Least absolute shrinkage and selection operation Cox regression analysis was used to select the best radiomics features and calculate each patient's radiomics scores (RadPFS and RadOS). Kaplan-Meier curve and Log-rank test were used to compare survival between patient groups risk-stratified by the radiomics scores. Various models to predict PFS and OS were constructed, including clinical, metabolic, clinical + metabolic, and clinical + metabolic + radiomics models. The discriminative ability of each model was evaluated using Harrell's C index. The performance of each model in predicting PFS and OS for 1-, 3-, and 5-years was evaluated using the time-dependent receiver operating characteristic (ROC) curve. Results: Kaplan-Meier curve analysis demonstrated that the radiomics scores effectively identified high- and low-risk patients (all P < 0.05). Multivariable Cox analysis showed that the Ann Arbor stage, maximum standardized uptake value (SUVmax), and RadPFS were independent risk factors associated with PFS. Further, β2-microglobulin, Eastern Cooperative Oncology Group performance status score, SUVmax, and RadOS were independent risk factors for OS. The clinical + metabolic + radiomics model exhibited the greatest discriminative ability for both PFS (Harrell's C-index: 0.805 in the validation cohort) and OS (Harrell's C-index: 0.833 in the validation cohort). The time-dependent ROC analysis indicated that the clinical + metabolic + radiomics model had the best predictive performance. Conclusion: The PET/CT-based clinical + metabolic + radiomics model can enhance prognostication among patients with ENKTCL and may be a non-invasive and efficient risk stratification tool for clinical practice.

• Tuberculosis and Respiratory Diseases
• /
• v.53 no.4
• /
• pp.379-388
• /
• 2002

Background : Although patients with stage IV non-small cell lung cancer are known to have a poor prognosis, the prognostic factors for survival have not been well evaluated. Such factors may be different from those for overall survival. This study was performed to analyze the prognostic factors for survuval and the variation of survival according to metastatic organ, in patients with stage IV non-small cell lung cancer. Materials and Methods : From January 1997 to December 2000, 151 patients with confirmed stage IV non-small cell lung cancer were enrolled into this study retrospectively. The clinical and laboratory data were analyzed using univareate Kaplan-Meied and Multivariate Cox regression models. Results : On univariate analysis, age, performance status, serum albumin level, weight loss, forced expiratory volume in one second (FEV1), systemic chemotherapy, the number of metastatic organs and serum lactate dehydrogenase (LDH) level were significant factors (p<0.05). In multivariate analysis, important factors for survival were ECOG performance (relative risk of death [RR]: 2.709), systemic chemotherapy (RR: 1.944), serum LDH level (RR: 1.819) and FEV1 (RR: 1.774) (p<0.05), Metastasis to the brain and liver was also a significant factor on univariate analysis). The presence of single lung metastasis was associated with better survival than that of other metastatic organs (p=0.000). Conclusion : We confirmed that performance status and systemic chemotherapy were independent prognostic factors, as has been recognized. The survival of stage IV non-small cell lung cancer patients was different according to the metastatic organs. Among the metastatic sites, only patients with metastasis to the lung showed bettrer survival than that of other sites, while metastasis of the brain or liver was associated with worse survival than that of other sites.

• Health Policy and Management
• /
• v.26 no.4
• /
• pp.359-372
• /
• 2016

Background: The purpose of this study was to develop risk-adjustment models for acute stroke mortality that were based on data from Health Insurance Review and Assessment Service (HIRA) dataset and to evaluate the validity of these models for comparing hospital performance. Methods: We identified prognostic factors of acute stroke mortality through literature review. On the basis of the avaliable data, the following factors was included in risk adjustment models: age, sex, stroke subtype, stroke severity, and comorbid conditions. Survey data in 2014 was used for development and 2012 dataset was analysed for validation. Prediction models of acute stroke mortality by stroke type were developed using logistic regression. Model performance was evaluated using C-statistics, $R^2$ values, and Hosmer-Lemeshow goodness-of-fit statistics. Results: We excluded some of the clinical factors such as mental status, vital sign, and lab finding from risk adjustment model because there is no avaliable data. The ischemic stroke model with age, sex, and stroke severity (categorical) showed good performance (C-statistic=0.881, Hosmer-Lemeshow test p=0.371). The hemorrhagic stroke model with age, sex, stroke subtype, and stroke severity (categorical) also showed good performance (C-statistic=0.867, Hosmer-Lemeshow test p=0.850). Conclusion: Among risk adjustment models we recommend the model including age, sex, stroke severity, and stroke subtype for HIRA assessment. However, this model may be inappropriate for comparing hospital performance due to several methodological weaknesses such as lack of clinical information, variations across hospitals in the coding of comorbidities, inability to discriminate between comorbidity and complication, missing of stroke severity, and small case number of hospitals. Therefore, further studies are needed to enhance the validity of the risk adjustment model of acute stroke mortality.