• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.8
• /
• pp.1021-1027
• /
• 2013

In this study, a prognostic technique for cavitation erosion that is applicable to centrifugal pumps is devised. To estimate the erosion states of pumps, damage rates are calculated based on cavitation noise measurements. The accumulated damage is predicted by using Miner's rule and the estimated damage undergone when coping with particular operating conditions. The remaining useful life (RUL) of the pump impellers is estimated according to the accumulated damage prediction and based on the assumption of future operating conditions. A Monte Carlo simulation is applied to obtain a prognostic uncertainty. The comparison of the prediction and the test results demonstrates that the developed method can be applied to predict cavitation erosion states and RUL estimates.

• Journal of the Korean Geotechnical Society
• /
• v.30 no.11
• /
• pp.17-23
• /
• 2014

In this study, the prognostic model for the prediction of the road surface temperature is developed using the surface energy balance theory. This model not only has a detailed micro meteorological physical attribute but also is able to accurately represent each surface energy budget. To verify the performance, the developed model output was compared with the German Weather Service (DWD)'s Energy Balance Model (EBM) output, which is based on the energy budget balance theory, and the observations. The simulated results by using both models are very similar to each other and are compatible with the observed data.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.8
• /
• pp.3869-3872
• /
• 2012

Background: The majority of patients with gastric cancer in developing countries present with advanced disease. Systemic chemotherapy therefore has limited impact on overall survival. Patients eligible for chemotherapy should be selected carefully. The aim of this study was to analyze prognostic factors for survival in advanced gastric cancer patients undergoing first-line palliative chemotherapy. Methods: We retrospectively reviewed 107 locally advanced or metastatic gastric cancer patients who were treated with docetaxel and cisplatin plus fluorouracil (DCF) as first-line treatment between June 2007 and August 2011. Twenty-eight potential prognostic variables were chosen for univariate and multivariate analyses. Results: Among the 28 variables of univariate analysis, nine variables were identified to have prognostic significance: performance status, histology, location of primary tumor, lung metastasis, peritoneum metastasis, ascites, hemoglobin, albumin, weight loss and bone metastasis. Multivariate analysis by Cox proportional hazard model, including nine prognostic significance factors evident in univariate analysis, revealed weight loss, histology, peritoneum metastasis, ascites and serum hemoglobin level to be independent variables. Conclusion: Performance status, weight loss, histology, peritoneum metastasis, ascites and serum hemoglobin level were identified as important prognostic factors in advanced gastric cancer patients. These findings may facilitate pretreatment prediction of survival and can be used for selecting patients for treatment.

• Journal of Breast Disease
• /
• v.6 no.2
• /
• pp.35-38
• /
• 2018

Purpose: The eighth American Joint Committee on Cancer staging system for breast cancer was recently published to more accurately predict the prognosis by adding biomarkers such as estrogen receptors, progesterone receptors, and human epidermal growth factor receptor 2. However, this system is very complicated and difficult to use by clinicians. The authors developed a program to aid in setting up the staging system and confirmed its usefulness by applying it to theoretical combinations and actual clinical data. Methods: The program was developed using the Microsoft Excel Macro. It was used for the anatomic, clinical and pathological prognostic staging of 588 theoretical combinations. The stages were also calculated the stages using 840 patients with breast cancer without carcinoma in situ or distant metastasis who did not undergo preoperative chemotherapy. Results: The anatomic, clinical and pathological prognostic stages were identical in 240 out of 588 theoretical combinations. In the actual patients' data, stages IB and IIIB were more frequent in clinical and pathological prognostic stages than in the anatomic stage. The anatomic stage was similar to the clinical prognostic stage in 58.2% and to the pathological prognostic stage in 61.9% of patients. Oncotype DX changed the pathological prognostic stage in 2.1% of patients. Conclusion: We developed a program for the new American Joint Committee on Cancer staging system that will be useful for clinical prognostic prediction and large survival data analysis.

• Journal of Hospice and Palliative Care
• /
• v.1 no.1
• /
• pp.30-38
• /
• 1998

Background : Hepatocellular carcinomoma is the 3rd most common malignancy and the 2nd most common cause of death in Korea. The prediction of life-expectancy in terminal cancer patients is a major problem for patients, families, and physicians. We would like to investigate the prognostic factors of hepatocellular carcinoma, and therefore contribute to the prediction of the survival time of patients with hepatocellular carcinoma. Methods : A total of 91 patients(male 73, female 18) with hepatocellular carcinoma who were admitted to the hospital between January and lune 1995 were entered into the study, and data were collected prospectively on 28 clinical parameters through medical obligation record. We surveyed an obligation and local district office records, and confirmed the surivival of patients till July, 1996. Using Cox-proportional hazard model, give the significant variables related to survival. These determined prognostic factors. Life regressional analysis was used, there were calculated predicted survival day based on combinations of the significant prognostic factors. Results : 1) Out of 91 patients, 73 were male, and 18 were female. The mean age was $56.7{\pm}10.6$ ears. During the study, except for 16 patients who could not follow up, out of 75 patients, the number of deaths was 57(76%) and the number of survivals was 18(24%). 2) Out of the 28 clinical parameters, the prognostic factors related to reduced survival rate were prothrombin time<40%(relative risk:10.8), weight loss(RR:4.4), past history of hypertension (RR:3.2), ascites(RR:2.8), hypocalcemia(RR:2.5)(P<0.001). 3) Out of five factors, the survival day is 1.7 in all of five, $4.2{\sim}10.0$ in four, $10.4{\sim}41.9$ in three, $29.5{\sim}118.1$ in two, $124.0{\sim}296.6$ in one, 724.0 in none. Conclusion : In hepatocellular carcinoma we found that the prognostic factors related to reduce survival rate were prolonged prothrombin time(<40%), weight loss, past history of hypertension, ascites, and hypocalcemia(<8.7mg/dl). The five prognostic factors enabled the prediction of life-expectancy in patients with hepatocellular carcinoma and may assist in managing patients with hepatocellular carcinomal.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.5
• /
• pp.1841-1844
• /
• 2012

Background: The majority of patients with pancreatic cancer present with advanced disease. Systemic chemotherapy has limited impact on overall survival (OS) so that eligible patients should be selected carefully. The aim of this study was to analyze prognostic factors for survival in Turkish advanced pancreatic cancer patients who survived more than one year from the diagnosis of recurrent and/or metastatic disease and receiving gemcitabine (Gem) alone or gemcitabine plus cisplatin (GemCis). Methods: This retrospective evaluation was performed for patients who survived more than one year from the diagnosis of recurrent and/or metastatic disease and who received gemcitabine between December 2005 and August 2011. Twenty-seven potential prognostic variables were chosen for univariate and multivariate analyses to identify prognostic factors associated with survival. Results: Among the 27 variables in univariate analysis, three were identified to have prognostic significance: sex (p = 0.04), peritoneal dissemination (p =0.02) and serum creatinine level (p=0.05). Multivariate analysis by Cox proportional hazard model showed only peritoneal dissemination to be an independent prognostic factor for survival. Conclusion: In conclusion, peritoneal metastasis was identified as an important prognostic factor in metastatic pancreatic cancer patients who survived more than one year from the diagnosis of recurrent and/or metastatic disease and receiving Gem or GemCis. The findings should facilitate pretreatment prediction of survival and can be used for selecting patients for treatment.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.6
• /
• pp.2805-2810
• /
• 2016

Background: Differentiated thyroid cancer is the most common endocrine malignancy with a generally good prognosis. Knowing long-term outcomes of each patient helps management planning. The study was conducted to develop and validate a clinical prognostic score for predicting disease remission in patients with differentiated thyroid cancer based on patient, tumor and treatment factors. Materials and Methods: A retrospective cohort study of 1,217 differentiated thyroid cancer patients from two tertiary-care hospitals in the Northeast of Thailand was performed. Associations between potential clinical prognostic factors and remission were tested by Cox proportional-hazards analysis in 852 patients (development cohort). The prediction score was created by summation of score points weighted from regression coefficients of independent prognostic factors. Risks of disease remission were estimated and the derived score was then validated in the remaining 365 patients (validation cohort). Results: During the median follow-up time of 58 months, 648 (76.1%) patients in the development cohort had disease remission. Five independent prognostic factors were identified with corresponding score points: duration from thyroid surgery to $^{131}I$ treatment (0.721), distant metastasis at initial diagnosis (0.801), postoperative serum thyroglobulin level (0.535), anti-thyroglobulin antibodies positivity (0.546), and adequacy of serum TSH suppression (0.293). The total risk score for each patient was calculated and three categories of remission probability were proposed: ${\leq}1.628$ points (low risk, 83% remission), 1.629-1.816 points (intermediate risk, 87% remission), and ${\geq}1.817$ points (high risk, 93% remission). The concordance (C-index) was 0.761 (95% CI 0.754-0.767). Conclusions: The clinical prognostic scoring model developed to quantify the probability of disease remission can serve as a useful tool in personalized decision making regarding treatment in differentiated thyroid cancer patients.

• 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.14 no.4
• /
• pp.2477-2481
• /
• 2013

Aims and Background: The purpose of the research was to study the prognostic value of tumor 18F-FDG PET-based parameters in neoadjuvant chemoradiation for patients with squamous esophageal carcinoma. Methods: Sixty patients received chemoradiation therapy followed by esophagectomy and two 18FDG-PET examinations at pre- and post-radiation therapy. PET-based metabolic-response parameters were calculated based on histopathologic response. Linear regression correlation and Cox proportional hazards models were used to determine prognostic value of all PET-based parameters with reference to overall survival. Results: Sensitivity (88.2%) and specificity (86.5%) of a percentage decrease of SUVmax were better than other PET-based parameters for prediction of histopathologic response. Only percentage decrease of SUVmax and tumor length correlated with overall survival time (linear regression coefficient ${\beta}$: 0.704 and 0.684, P<0.05). The Cox proportional hazards model indicated higher hazard ratio (HR=0.897, P=0.002) with decrease of SUVmax compared with decrease of tumor size (HR=0.813, P=0.009). Conclusion: Decrease of SUVmax and tumor size are significant prognostic factors in chemoradiation of esophageal carcinoma.