• Asian Pacific Journal of Cancer Prevention
• /
• 제16권4호
• /
• pp.1627-1631
• /
• 2015

Background: Stage at diagnosis is one of the most important prognostic factors of breast cancer survival. Because in the breast cancer case this may vary with socioeconomic characteristics, this study was performed to recognize the relationship between demographic and socioeconomic factors with stage at diagnosis in Iran. Materials and Methods: This cross-sectional, descriptive study conducted on 526 patients suffering from breast cancer and registered in Cancer Research Center of Shahid Beheshti University of Medical Sciences from 2008 to 2013. A reliable and valid questionnaire about family levels of socioeconomic status filled in by interviewing the patients via phone. For analyzing the data, Multinomial logistic regression, Kendal tau-b correlation coefficient and Contingency Coefficient tests were executed by SPSS22. Economic status, educational attainment of patient and household head and/or a combination of these were considered as parameters for socioeconomic status. First, the relationship between stage at diagnosis and demographic and socioeconomic status was assessed in univariate analysis then these relationships assessed in two different models of multinomial logistic regression. Results: The mean age of the patients was 48.3 (SD=11.4). According to the results of this study, there were significant relationships between stage at diagnosis of breast cancer with patient education (p=0.011), living place (p=0.044) and combined socioeconomic status (p=0.024). These relationships persisted in multiple multinomial logistic regressions. Other variables, however, had no significant correlation. Conclusions: Patient education, combined socioeconomic status and living place are important variables in stage at diagnosis of breast cancer in Iranian women. Interventions have to be applied with the aim of raising women's accessibility to diagnostic and medical facilities and also awareness in order to reducing delay in referring. In addition, covering breast cancer screening services by insurance is recommended.

• 대한임상독성학회지
• /
• 제16권2호
• /
• pp.149-156
• /
• 2018

Purpose: The purpose of this study was to determine whether hepatotoxicity could be predicted early using biochemical markers in patients with acetaminophen (AAP) poisoning and to assess the usefulness of predictive factors for acute liver injury or hepatotoxicity. Methods: This study was a retrospective observational study involving a medical records review. The participants were patients who were admitted to the emergency department (ED) with AAP overdose at two hospitals over a 10-year period. Demographic data, age, time from ingestion to visit, initial AAP level, initial hepatic aminotransferases, and initial prothrombin time were recorded. Acute liver injury was defined as a peak serum ALT >50 U/L or double the admission value, and hepatotoxicity was defined as a peak ALT >1,000 U/L. Receiver operating characteristic curve analyses were performed to compare the prognostic performance among variables. Results: A total of 97 patients were admitted to the ED with AAP overdose, of whom 26 had acute liver injury and 6 had hepatotoxicity. Acute liver injury was associated with the time interval after taking the drug, and hepatotoxicity was associated with the initial PT and the ALT level. The scoring system proposed by the authors has a significant ability to predict both acute liver injury and hepatotoxicity. Conclusion: To predict the prognosis of AAP poisoning patients, the time interval after taking AAP was important, and initial prothrombin time and ALT level were useful tests. Also a scoring system combining variables may be useful.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• 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.

• 응용통계연구
• /
• 제24권1호
• /
• pp.161-167
• /
• 2011

소수의 피험자로 이루어지는 생물학적 동등성 시험에서 제제의 특성으로 인해 측정된 생체이용률이 크게 영향을 받는 경우 교차설계법을 사용하더라도 적절한 통제가 어려워지는 경우가 많다. 이 때 적절한 공변량을 통해 이러한 영향력을 통제할 수 있다면 공변량을 고려한 교차설계법 모형이 고려될 필요가 있다. 본 연구논문에서는 공변량을 갖는 $2{\times}2$ 교차설계법을 고려하고 제제간의 생물학적 동등성 평가를 위한 통계적 추론을 제안한다. 제안된 방법은 실제 사례를 통해 논의한다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권12호
• /
• pp.7133-7136
• /
• 2013

Background: We studied Surveillance, Epidemiology and End Results (SEER) breast cancer data of Georgia USA to analyze the impact of socio-economic factors on the disparity of breast cancer treatment outcome. Materials and Methods: This study explored socio-economic, staging and treatment factors that were available in the SEER database for breast cancer from Georgia registry diagnosed in 2004-2009. An area under the receiver operating characteristic curve (ROC) was computed for each predictor to measure its discriminatory power. The best biological predictors were selected to be analyzed with socio-economic factors. Survival analysis, Kolmogorov-Smirnov 2-sample tests and Cox proportional hazard modeling were used for univariate and multivariate analyses of time to breast cancer specific survival data. Results: There were 34,671 patients included in this study, 99.3% being females with breast cancer. This study identified race and education attainment of county of residence as predictors of poor outcome. On multivariate analysis, these socio-economic factors remained independently prognostic. Overall, race and education status of the place of residence predicted up to 10% decrease in cause specific survival at 5 years. Conclusions: Socio-economic factors are important determinants of breast cancer outcome and ensuring access to breast cancer treatment may eliminate disparities.

• 지역사회간호학회지
• /
• 제17권1호
• /
• pp.17-25
• /
• 2006

Purpose: The goals of this research are to find out factors influencing the duration of work-related disability and to present implications for policies to prevent delayed recovery. Method: The subjects of this study were 238 workers who had been proved to be industrial disaster victims for occupational low back pain between January 1 2000 and December 31 2003. Kaplan-Meier method was used to estimate the proportion of duration of disability associated with low back pain, and Cox proportional hazards analysis was used to identify factors predicting it. The model distinguished main symptom variables affecting acute(${\leq}90\;days$) and chronic phase of disability (>90 days). Result: Fifty percent of the workers had not recovered in 408 days. The results of Cox regression show that delayed duration of disability was predicted by diagnosis, pain radiation (in chronic phase), sex, the size and labor union of the workplace, scheduled rest, compensation from the company, and operation. Conclusion: Duration of disability associated with compensated low back pain is influenced not only by factors related to the company and compensation system but also by individual factors. Thus, future efforts to reduce duration of disability may need to take into account all these factors.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권7호
• /
• pp.3619-3622
• /
• 2016

Background: Triple negative breast cancers (TNBCs) are high grade aggressive tumors generally with a poor prognosis, not responding to hormonal and anti Her2 Neu therapy. Expression of the antiapoptotic B cell lymphoma 2 gene (Bcl-2) is associated with low grade, slowly proliferating hormone receptor positive tumors with improved survival. Anti Bcl2 agents can be used as alternative targeted therapy in triple negative cancers. Materials and Methods: The objective of this study was to determine the immunohistochemical expression of Bcl2 in triple negative breast cancers and any correlation with clinicopathological variables in Northern Pakistan. Results: All 52 patients were females, aged between 28 and 80 years(average $48.0{\pm}12.1$). 28 cases (53.8%) were positive for Bcl2, this being associated with low grade invasive ductal carcinomas, lymph node metastasis and lymphovascular invasion. Conclusions: Bcl-2 may be an important prognostic factor and its expression might be used for targeted therapy using Anti Bcl2 drugs.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권14호
• /
• pp.5593-5596
• /
• 2014

Background: The objective of this study was to determine a diagnostic classification scheme using a decision tree based model. Materials and Methods: The study was conducted as a retrospective case-control study in Imam Khomeini hospital in Tehran during 2001 to 2009. Data, including demographic and clinical-pathological characteristics, were uniformly collected from 624 females, 312 of them were referred with positive diagnosis of breast cancer (cases) and 312 healthy women (controls). The decision tree was implemented to develop a diagnostic classification scheme using CART 6.0 Software. The AUC (area under curve), was measured as the overall performance of diagnostic classification of the decision tree. Results: Five variables as main risk factors of breast cancer and six subgroups as high risk were identified. The results indicated that increasing age, low age at menarche, single and divorced statues, irregular menarche pattern and family history of breast cancer are the important diagnostic factors in Iranian breast cancer patients. The sensitivity and specificity of the analysis were 66% and 86.9% respectively. The high AUC (0.82) also showed an excellent classification and diagnostic performance of the model. Conclusions: Decision tree based model appears to be suitable for identifying risk factors and high or low risk subgroups. It can also assists clinicians in making a decision, since it can identify underlying prognostic relationships and understanding the model is very explicit.

• 대한기관식도과학회지
• /
• 제1권1호
• /
• pp.151-158
• /
• 1995

Anaplastic carcinoma of thyroid gland account for no more than 10% of thyroid cancer, but it shows extremely poor prognosis. The purpose of this study is to review the outcome of patients with anaplastic carcinoma over the span of 5 years and to determine the patterns of clinical presentation, age, sex and other possible prognostic variables. We analyzed 30 cases of anaplastic carcinoma retrospectively from 1991 to 1995. There were 14 men and 16 women. There age ranged 33 to 75 years with a mean of 61.0 years. Sixteen patients presented with transformationqr of well differentiated carcinoma to anaplastic carcinoma, 1 with rapid in-crease in the size of long standing goiter, 8 with rapidly growing neck mass and 4 with meta static disease. Twenty-eight patients(93.3%) showed cervical lymphnode metastasis at presentation and twenty three patients(76.6%) showed laryngotracheal invasion. Nine patients (30.3%) showed distant metastasis. Treatment modalities included surgical resection, external irradiation, radioactive iodine and systemic chemotherapy. At decision making of treatment plan, we considered completeness of initial surgery, uptake rate of whole body radioactive io-dine scan, locoregional progression and distant metastasis. The median survival was 6.8 months and three cases survived beyond 12 months.

• Journal of Gastric Cancer
• /
• 제19권3호
• /
• pp.254-277
• /
• 2019

Inflammation can be a causative factor for carcinogenesis or can result from a consequence of cancer progression. Moreover, cancer therapeutic interventions can also induce an inflammatory response. Various inflammatory parameters are used to assess the inflammatory status during cancer treatment. It is important to select the most optimal biomarker among these parameters. Additionally, suitable biomarkers must be examined if there are no known parameters. We briefly reviewed the published literature for the use of inflammatory parameters in the treatment of patients with cancer. Most studies on inflammation evaluated the correlation between host characteristics, effect of interventions, and clinical outcomes. Additionally, the levels of C-reactive protein, albumin, lymphocytes, and platelets were the most commonly used laboratory parameters, either independently or in combination with other laboratory parameters and clinical characteristics. Furthermore, the immune parameters are classically examined using flow cytometry, immunohistochemical staining, and enzyme-linked immunosorbent assay techniques. However, gene expression profiling can aid in assessing the overall peri-interventional immune status. The checklists of guidelines, such as STAndards for Reporting of Diagnostic accuracy and REporting recommendations for tumor MARKer prognostic studies should be considered when designing studies to investigate the inflammatory parameters. Finally, the data should be interpreted after adjusting for clinically important variables, such as age and cancer stage.