• Korean Journal of Biological Psychiatry
• /
• v.6 no.1
• /
• pp.30-33
• /
• 1999

While depression is certainly a prevalent disorder, it is often severe and debilitating and does not always have the good prognosis we have been led to expect. Social approaches to affective disorders have not been subjected to the same level of scrutiny as the interventions used in the management of schizophrenia. Psychosocial Rehabilitation is now at a critical stage. Psychoeducation, social skill training, cognitive remediation, family education, vocational rehabilitation and case management programs are essential for the rehabilitation of chronic depression.

• Journal of Korean Institute of Industrial Engineers
• /
• v.14 no.2
• /
• pp.63-70
• /
• 1988

Recently a new regime, called "back school" is advocated for the purpose of rapidly and economically returning a patient to full functional fitness and normal occupational activities. Assuming that this functional and vocational restoration is a goal of a regabilitation program, it is apparent that early recovery and higher success rate are major concern. In this study, a mixture model is developed and used to evaluate the recovery process of low back pain (LBP) patients in a rehabilitation program. The model provides (1) the probability of being recovered, and (2) the rate of recovery. Patients with gradual onset, with higher education, or of young age tend to show better prognosis.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.4
• /
• pp.1563-1566
• /
• 2014

Background: Esophageal squamous cell carcinoma (ESCC) accounts for most esophageal cancer in Asia, and is the sixth common cause of cancer-related deaths worldwide. Previous studies indicated HOXB7 is overexpressed in ESCC tissues, but data on prognostic value are limited. Methods: A total of 76 advanced ESCC cases were investigated. Immunohistochemistry (IHC) was used to detect the expression levels of HOXB7 and Kaplan-Meier curves and Cox regression models to determine prognostic significance. Stratified analysis was also performed according to lymph node (LN) status. Results: Kaplan-Meier curve analysis indicated that HOXB7 positive patients had significantly shorter overall survival (OS) than HOXB7 negative patients. Multivariate analysis using the Cox proportional hazards model indicated only TNM stage and HOXB7 expression to be independent predictors of overall survival of advanced ESCC patients. HOXB7 indicated poor OS in both lymph node negative (LN-) and lymph node positive (LN+) patients. Conclusion: HOXB7 predicts poor prognosis of advanced ESCC patients and can be applied as an independent prognostic predictor.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.sup3
• /
• pp.305-309
• /
• 2016

PTEN protein is an important tumour suppressor factor detectable by immunohistochemistry. The goal of the present study was to investigate the prognostic role of PTEN gene expression focusing on length of survival in breast cancer patients. This descriptive-analytical study was conducted on 100 breast cancer cases referred to Sabzevar hospitals in the north east of Iran between 2010 and 2011, followed up to 2015. The PTEN gene expression of tumour tissue samples was determined using specific monoclonal antibodies. The data were analyzed using Chi-square test and Fisher's exact test. Patient length of survival was analyzed after 4 years of follow-up using the Cox regression model. The PTEN gene was expressed in 70 of 100 samples, while being found at a high level in all noncancerous samples. There was an inverse significant relationship between expression of PTEN and tumour stage and grade (p<0.001). In addition, expression of PTEN in invasive ductal tumours was less than in non-invasive tumours. There was also an inverse significant relationship between the likelihood of death and PTEN gene expression (p<0.01). These findings indicate that lack of PTEN gene expression can be sign for a worse prognosis and poor survival in breast cancer.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.23 no.6
• /
• pp.641-649
• /
• 2010

Estimation of uncertain parameters is required in many engineering problems which involve probabilistic structural analysis as well as prognosis of existing structures. In this case, Bayesian framework is often employed, which is to represent the uncertainty of parameters in terms of probability distributions conditional on the provided data. The resulting form of distribution, however, is not amenable to the practical application due to its complex nature making the standard probability functions useless. In this study, Markov chain Monte Carlo (MCMC) method is proposed to overcome this difficulty, which is a modern computational technique for the efficient and straightforward estimation of parameters. Three case studies that implement the estimation are presented to illustrate the concept. The first one is an inverse estimation, in which the unknown input parameters are inversely estimated based on a finite number of measured response data. The next one is a metamodel uncertainty problem that arises when the original response function is approximated by a metamodel using a finite set of response values. The last one is a prognostics problem, in which the unknown parameters of the degradation model are estimated based on the monitored data.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

• Proceedings of the Korea Association of Crystal Growth Conference
• /
• 1996.06a
• /
• pp.139-156
• /
• 1996

The phase field model is becoming the model of choice for the theoretical study of the morphologies of crystals growth from the melt. This model provides an alternative approach to the solution of the classical (sharp interface) model of solidification by introducing a new variable, the phase field, Ø, to identify the phase. The variable Ø takes on constant values in the bulk phases and makes a continuous transition between these values over a thin transition layer that plays the role of the classically sharp interface. This results in Ø being governed by a new partial differential equation(in addition to the PDE's that govern the classical fields, such as temperature and composition) that guarantees (in the asymptotic limit of a suitably thin transition layer) that the appropriate boundary conditions at the crystal-melt interface are satisfied. Thus, one can proceed to solve coupled PDE's without the necessity of explicitly tracking the interface (free boundary) that would be necessary to solve the classical (sharp interface) model. Recent advances in supercomputing and algorithms now enable generation of interesting and valuable results that display most of the fundamental solidification phenomena and processes that are observed experimentally. These include morphological instability, solute trapping, cellular growth, dendritic growth (with anisotropic sidebranching, tip splitting, and coupling to periodic forcing), coarsening, recalescence, eutectic growth, faceting, and texture development. This talk will focus on the fundamental basis of the phase field model in terms of irreversible thermodynamics as well as it computational limitations and prognosis for future improvement. This work is supported by the National Science Foundation under grant DMR 9211276

• Journal of Gastric Cancer
• /
• v.17 no.2
• /
• pp.162-172
• /
• 2017

Purpose: Previous studies indicated conflicting results regarding the prognosis of gastric cancer with a family history (FHX). This study aimed to determine the clinicopathological features and survival of patients with gastric cancer with a FHX. Materials and Methods: We reviewed 2,736 patients with gastric cancer who underwent surgery between 2003 and 2009. The prognostic value of a FHX was determined in the multivariate model after adjusting for variables in the Asian and internationally validated prognostic models. Results: Of the patients, 413 (15.1%) had a FHX of gastric cancer. The patients with a FHX were younger (58.1 vs. 60.4 years; P<0.001) than the patients without a FHX. There were no significant differences in the histopathological characteristics between the 2 groups. A FHX was associated with a better overall survival (OS) rate only in the stage I group (5-year survival rate, 95% vs. 92%; P=0.006). However, the disease-specific survival (DSS) rate was not significantly different between the 2 groups in all stages. The multivariate model adjusted for the variables in the Asian and internationally validated prognostic models revealed that FHX has no significant prognostic value for OS and DSS. Conclusions: The clinicopathological features and survival of the patients with gastric cancer with a FHX did not significantly differ from those of the patients without a FHX.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.11
• /
• pp.6715-6719
• /
• 2013

Objective: To explore the incidence, clinical characteristics, diagnosis and treatment strategies, prognosis of patients with malignancy-associated hypercalcemia (MAH). Methods: The data of 115 patients with MAH who were treated at the Medical Oncology Department of Chinese PLA General Hospital from Jan., 2001 to Dec., 2010 was retrospectively reviewed. Survival analysis was performed using the Kaplan-Meier method and the Cox proportional hazard model with statistic software SPSS 18.0. Results: The patients had blood calcium levels ranging from 2.77 to 4.87 mmol/L. Except for 9 cases who died or were discharged within 5 days after admission, all other patients recovered to normal blood calcium level after treatment with bisphosphonates or intravenous hydration and diuretics; their survival after occurrence of MAH was from 1 day to 4,051 days, and the median survival time was only 50 days. In the log-rank test, the male, renal metastasis, central nervous system symptoms and hypercalcemia occurring over 140 days after cancer diagnosis were predictors of poor survival (P=0.002, P=0.046, P=0.000, P=0.009). In the COX analysis, being male, central nervous system symptoms and hypercalcemia lasting over 140 days after cancer diagnosis were independent prognostic factors for survival time (RR=2.131, P=0.027; RR=3.054, P=0.002; RR=2.403, P=0.001). According to these factors, a score system was established to predict the patient prognosis and adjust the treatment. Conclusion: Cancer patients with MAH have an extremely poor median survival. Some independent factors indicate poor prognosis, including male gender, central nervous system symptoms and hypercalcemia lasting over 140 days after cancer diagnosis. The prognostic score can serve as a reference for MAH prognosis and treatment, worthy of further investigation.