• Asian Oncology Nursing
• /
• v.5 no.1
• /
• pp.3-10
• /
• 2005

Back ground: Nurses now occupy one third of all hospital human resources. Therefore, efficient management of nursing manpower is getting more important. While it is very clear that nursing workload requirement analysis and patient severity classification should be done first for the efficient allocation of nursing workforce, these processes have been conducted manually with ad hoc rule. Purposes: This study was tried to make a predict model for patient classification according to nursing need. We tried to find the easier and faster method to classify nursing patients that can help efficient management of nursing manpower. Methods: The nursing patient classifications data of the hospitalized cancer patients in one of the biggest cancer center in Korea during 2003.1.1-2003.12.31 were assessed by trained nurses. This study developed a prediction model and analyzing nursing needs by data mining techniques. Patients were classified by three different data mining techniques, (Logistic regression, Decision tree and Neural network) and the results were assessed. Results: The data set was created using 165,073 records of 2,228 patients classification database. Main explaining variables were as follows in 3 different data mining techniques. 1) Logistic regression : age, month and section. 2) Decision tree : section, month, age and tumor. 3) Neural network : section, diagnosis, age, sex, metastasis, hospital days and month. Among these three techniques, neural network showed the best prediction power in ROC curve verification. As the result of the patient classification prediction model developed by neural network based on nurse needs, the prediction accuracy was 84.06%. Conclusion: The patient classification prediction model was developed and tested in this study using real patients data. The result can be employed for more accurate calculation of required nursing staff and effective use of labor force.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.2
• /
• pp.835-838
• /
• 2016

Background: Lung cancer remains one of the most common cancers in the world, both in terms of new cases (about 13% of total per year) and deaths (nearly one cancer death in five), because of the high case fatality. Errors in lung cancer type or malignant growth determination lead to degraded treatment efficacy, because anticancer strategy depends on tumor morphology. Materials and Methods: We have made an attempt to evaluate effectiveness of machine learning algorithms in the task of lung cancer classification based on gene expression levels. We processed four publicly available data sets. The Dana-Farber Cancer Institute data set contains 203 samples and the task was to classify four cancer types and sound tissue samples. With the University of Michigan data set of 96 samples, the task was to execute a binary classification of adenocarcinoma and non-neoplastic tissues. The University of Toronto data set contains 39 samples and the task was to detect recurrence, while with the Brigham and Women's Hospital data set of 181 samples it was to make a binary classification of malignant pleural mesothelioma and adenocarcinoma. We used the k-nearest neighbor algorithm (k=1, k=5, k=10), naive Bayes classifier with assumption of both a normal distribution of attributes and a distribution through histograms, support vector machine and C4.5 decision tree. Effectiveness of machine learning algorithms was evaluated with the Matthews correlation coefficient. Results: The support vector machine method showed best results among data sets from the Dana-Farber Cancer Institute and Brigham and Women's Hospital. All algorithms with the exception of the C4.5 decision tree showed maximum potential effectiveness in the University of Michigan data set. However, the C4.5 decision tree showed best results for the University of Toronto data set. Conclusions: Machine learning algorithms can be used for lung cancer morphology classification and similar tasks based on gene expression level evaluation.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.6
• /
• pp.2245-2250
• /
• 2015

Background: The interaction between tumor cells and inflammatory cells has not been systematically investigated in esophageal squamous cell carcinoma (ESCC). The aim of the present study was to evaluate whether preoperative the lymphocyte-monocyte ratio (LMR), the neutrophil-lymphocyte ratio (NLR), and the platelet-lymphocyte ratio (PLR) could predict the prognosis of ESCC patients undergoing esophagectomy. Materials and Methods: Records from 218 patients with histologically diagnosed ESCC who underwent attempted curative surgery from January 2007 to December 2008 were retrospectively reviewed. Besides clinicopathological prognostic factors, we evaluated the prognostic value of the LMR, the NLR, and the PLR using Kaplan-Meier curves and Cox regression models. Results: The median follow-up was 38.6 months (range 3-71 months). The cut-off values of 2.57 for the LMR, 2.60 for the NLR and 244 for the PLR were chosen as optimal to discriminate between survival and death by applying receiver operating curve (ROC) analysis. Kaplan-Meier survival analysis of patients with low preoperative LMR demonstrated a significant worse prognosis for DFS (p=0.004) and OS (p=0.002) than those with high preoperative LMR. The high NLR cohort had lower DFS (p=0.004) and OS (p=0.011). Marginally reduced DFS (p=0.068) and lower OS (p=0.039) were found in the high PLR cohort. On multivariate analysis, only preoperative LMR was an independent prognostic factor for both DFS (p=0.009, HR=1.639, 95% CI 1.129-2.381) and OS (p=0.004, HR=1.759, 95% CI 1.201-2.576) in ESCC patients. Conclusions: Preoperative LMR better predicts cancer survival compared with the cellular components of systemic inflammation in patients with ESCC undergoing esophagectomy.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.6
• /
• pp.2441-2445
• /
• 2015

Background: Several risk factors leading to malignant transformation of hydatidiform moles have been described previously. Many studies showed that prophylactic chemotherapy for high risk hydatidiform moles could significantly decrease the incidence of malignancy. Thus, it is essential to discover a breakthrough to determine patients with high risk malignancy so that prophylactic chemotherapy can be started as soon as possible. Objectives: Development of a scoring system of risk factors as a predictor of hydatidiform mole malignant transformation. Materials and Methods: This research is a case control study with hydatidiform mole and choriocarcinoma patients as subjects. Multiple logistic regression was used to analyze the data. Odds ratios (OR), attributable at risk (AR : OR-1) and risk index ($ARx{\beta}$) were calculated for develoipment of a scoring system of malignancy risk. The optimal cut-off point was determined using receiver operating characteristic (ROC) curve. Results: This study analyzed 34 choriocarcinoma cases and 68 benign hydatidiform mole cases. Four factors significantly increased the risk of malignancy, namely age ${\geq}35$ years old (OR:4.41, 95%CI:1.07-16.09, risk index 5); gestational age ${\geq}$ 12weeks (OR:11.7, 95%CI:1.8-72.4, risk index 26); uterine size greater than the gestational age (OR:10.2, 95%CI:2.8-36.6, risk index 21); and histopathological grade II-III (OR:3.4, 95%CI:1.1-10.6, risk index 3). The lowest and the highest scores for the risk factors were zero and 55, respectively. The best cut-off point to decide high risk malignancy patients was ${\geq}31$. Conclusions: Malignant transformation of hydatidiform moles can be predicted using the risk scoring by analyzing the above four parameters. Score ${\geq}31$ implies high risk patients so that prophylactic chemotherapy can be promptly administered for prevention.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.23
• /
• pp.10171-10174
• /
• 2015

Background: The purpose of this study was to determine the prognostic significance of the maximum standardized uptake value (SUVmax) on F-18-fluorodeoxyglucose (FDG)-positron emission tomography (PET) in patients undergoing surgical treatment for non-small cell lung cancer. Materials and Methods: Seventy-eight consecutive patients (58 with adenocarcinomas, 20 with squamous cell carcinomas) treated with potentially curative surgery were retrospectively reviewed. Results: The SUVmax was significantly higher in the patients with recurrent than with non-recurrent adenocarcinoma (p<0.01). However, among the patients with squamous cell carcinoma, there were no differences with or without recurrence (p=0.69). Multivariate analysis indicated that the SUVmax of adenocarcinoma lesions was a significant predictor of disease-free survival (p=0.04). In addition, an SUVmax of 6.19, the cut-off point based on ROC curve analysis of the patients with pathological IB or more advanced stage adenocarcinomas, was found to be a significant predictor of disease-free survival (p<0.01). Conclusions: SUVmax is a useful predictor of disease-free survival in patients with resected adenocarcinoma, but not squamous cell carcinoma. Patients with adenocarcinoma exhibiting an SUVmax above 6.19 are candidates for more intensive adjuvant therapy.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.6
• /
• pp.2689-2692
• /
• 2014

Purpose: To investigate the risk factors for appendiceal metastasis of epithelial ovarian cancer and compare findings with the previous studies. Materials and Methods: One hundred and thirty-four patients with epithelial ovarian cancer were assessed in this study. All of them had undergone a surgical procedure including appendectomy. Of these, 21 (15.7%) patients who had appendiceal metastasis were analyzed as the case group and the patients with no metastasis were the controls, compared according to stage, grade, histology of tumor, preoperative Ca125 levels, presence of ascites, peritoneal cytology, diameter and site of tumor considered as risk factors. Results: We found statistically significant differences between the groups in terms of stage, grade, right-sided tumor location, presence of ascites, diameter of tumor${\geq}10cm$ and positive peritoneal cytology (p<0.05). In the logistic regression model, stage, grade, presence of ascites, right-sided location and diameter of tumor were independent risk factors. ROC curve analysis showed that stage, grade and diameter of the tumor were discriminative factors for appendiceal metastasis. Conclusions: In epithelial ovarian cancer, stage, grade, presence of ascites, right-sided location and large tumor size have importance for estimation of risk of appendiceal metastasis. As we compare our findings with previous studies, there is no definite recommendation for the risk factors of appendiceal metastasis in epithelial ovarian cancer and more studies are needed.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.6
• /
• pp.2647-2650
• /
• 2014

Background: Colorectal cancers(CRC) are the third most common cancer in the western world, with surgery preferred for management of non-metastatic disease and post surgical treatment usually arranged according to the TNM staging system. However, there is still prognostic variation between patients who have the same stage. It is increasingly recognized that variations within disease course and clinical outcome in colorectal cancer patients are influenced by not only oncological characteristics of the tumor itself but also host response factors. Recent studies have shown correlation between the inflammatory response and clinical outcomes in various cancers. The neutrophil/lymphocyte ratio (NLR) has been described as a marker for immune response to various stimuli including cancer. Material-Methods: Two hundred eighty-one CRC patients were included in our retrospective analysis, separated into two groups according to a cut-off value for the NLR. Patient data including age, gender, vertical penetration, anatomic location, and differentiation of the tumor, TNM stage, survival rate, and disease-free survival were analyzed for correlations with the NLR. Results: Using ROC curve analysis, we determined a cut-off value of 2.2 for NLR to be best to discriminate between patient survival in the whole group. In univariate analysis, high pretreatment NLR (p=0.001, 95%CI 1.483-4.846), pathologic nodal stage (p<0.001, 95%CI 1.082-3.289) and advanced pathologic TNM stage (p<0.001, 95%CI 1.462-4.213) were predictive of shorter survival. In multivariate analysis, advanced pathologic TNM stage (p=0.001, 95%CI 1.303-26.542) and high pretreatment NLR (p=0.005, 95%CI 1.713-6.378) remained independently associated with poor survival. Conclusions: High pre-treatment NLR is a significant independent predictor of shorter survival in patients with colorectal cancer. This parameter is a simple, easily accessible laboratory value for identifying patients with poorer prognosis.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.22
• /
• pp.9611-9614
• /
• 2014

Purpose: To investigate the clinical value in lung cancer of a combination of four serum tumor markers, haptoglobin (Hp), carcinoembryonic antigen (CEA), neuron specific enolase (NSE) as well as the cytokeratin 19 fragment (CYFRA21-1). Materials and Methods: Serum Hp (with immune-turbidimetric method), CEA, NSE, CYFRA21-1 (with chemiluminescence method) level were assessed in 193 patients with lung cancer, 87 patients with benign lung disease and 150 healthy controls. Differences of expression were compared among groups, and joint effects of these tumor markers for the diagnosis of lung cancer were analyzed. Results: Serum tumor marker levels in patients with lung cancer were obviously higher than those with benign lung disease and normal controls (p<0.01). The sensitivities of Hp, CEA, NSE and CYFRA21-1 were 43.5%, 40.9%, 23.3% and 41.5%, with specificities of 90.7%, 99.2%, 97.9% and 97.9%. Four tumor markers combined together could produce a positive detection rate of 85.0%, significantly higher than that of any single test. With squamous carcinomas, the positive detection rates with Hp and CYFRA21-1 were higher than that of other markers. In the adenocarcinoma case, the positive detection rate of CEA was higher than that of other markers. For small cell carcinomas, the positive detection rate of NSE was highest. The area under receiver operating characteristic curve ($AUC^{ROC}$) of Hp in squamous carcinoma (0.805) was higher than in adenocarcinoma (0.664) and small cell carcinoma (0.665). Conclusions: Hp can be used as a new serum tumor marker for lung cancer. Combination detection of Hp, CEA, NSE and CYFRA21-1 could significantly improve the sensitivity and specificity in diagnosis of lung cancer, and could be useful for pathological typing.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.12
• /
• pp.7421-7426
• /
• 2013

Background: Colorectal cancer is the fourth most common cancer worldwide and the second leading cause of cancer-related death. FOLFOX is the most common regimen used in the first-line chemotherapy in advanced colorectal cancer, but only half of the patients respond to this regimen and we have almost no clue in predicting resistance in such first-line application. Methods: To explore the potential molecular biomarkers predicting the resistance of FOLFOX regimen as the first-line treatment in advanced colorectal cancer, we screened microRNAs in serum samples from drug-responsive and drug-resistant patients by microarrays. Then differential microRNA expression was further validated in an independent population by reverse transcription and quantitative real-time PCR. Results: 62 microRNAs expressing differentially with fold-change >2 were screened out by microarray analysis. Among them, 5 (miR-221, miR-222, miR-122, miR-19a, miR-144) were chosen for further validation in an independent population (N=72). Our results indicated serum miR-19a to be significantly up-regulated in resistance-phase serum (p=0.009). The ROC curve analysis showed that the sensitivity of serum miR-19a to discriminate the resistant patients from the response ones was 66.7%, and the specificity was 63.9% when the AUC was 0.679. We additionally observed serum miR-19a had a complementary value for cancer embryonic antigen (CEA). Stratified analysis further revealed that serum miR-19a predicted both intrinsic and acquired drug resistance. Conclusions: Our findings confirmed aberrant expression of serum miR-19a in FOLFOX chemotherapy resistance patients, suggesting serum miR-19a could be a potential molecular biomarker for predicting and monitoring resistance to first-line FOLFOX chemotherapy regimens in advanced colorectal cancer patients.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.12
• /
• pp.7315-7319
• /
• 2013

Background: The metastasis gene osteopontin (OPN) is subject to alternative splicing, which yields three messages, osteopontin-a, osteopontin-b and osteopontin-c. Osteopontin-c is selectively expressed in invasive, but not in noninvasive tumors. In the present study, we examined the expression of OPN-c in esophageal squamous cell carcinomas (ESCCs) and assessed its value as a diagnostic biomarker. Methods: OPN-c expression was assessed by immunohistochemistry in 63 ESCC samples and correlated with clinicopathologic factors. Expression was also examined in peripheral blood mononuclear cells (PBMCs) from 120 ESCC patients and 30 healthy subjects. The role of OPN-c mRNA as a tumor marker was investigated by receiver operating characteristic curve (ROC) analysis. Results: Immunohistochemistry showed that OPN-c was expressed in 30 of 63 cancer lesions (48%)and significantly associated with pathological T stage (P=0.038) and overall stage (P=0.023). Real time PCR showed that OPN-c mRNA was expressed at higher levels in the PBMCs of ESCC patients than in those of healthy subjects (P<0.0001) with a sensitivity as an ESCC biomarker of 86.7%. Conclusion: Our findings suggest that expression of OPN-c is significantly elevated in ESCCs and this upregulation could be a potential diagnostic marker.