Background: Microarray technology can acquire information about thousands of genes simultaneously. We analyzed published breast cancer microarray databases to predict five-year recurrence and compared the performance of three data mining algorithms of artificial neural networks (ANN), decision trees (DT) and logistic regression (LR) and two composite models of DT-ANN and DT-LR. The collection of microarray datasets from the Gene Expression Omnibus, four breast cancer datasets were pooled for predicting five-year breast cancer relapse. After data compilation, 757 subjects, 5 clinical variables and 13,452 genetic variables were aggregated. The bootstrap method, Mann-Whitney U test and 20-fold cross-validation were performed to investigate candidate genes with 100 most-significant p-values. The predictive powers of DT, LR and ANN models were assessed using accuracy and the area under ROC curve. The associated genes were evaluated using Cox regression. Results: The DT models exhibited the lowest predictive power and the poorest extrapolation when applied to the test samples. The ANN models displayed the best predictive power and showed the best extrapolation. The 21 most-associated genes, as determined by integration of each model, were analyzed using Cox regression with a 3.53-fold (95% CI: 2.24-5.58) increased risk of breast cancer five-year recurrence… Conclusions: The 21 selected genes can predict breast cancer recurrence. Among these genes, CCNB1, PLK1 and TOP2A are in the cell cycle G2/M DNA damage checkpoint pathway. Oncologists can offer the genetic information for patients when understanding the gene expression profiles on breast cancer recurrence.

Background: Symptom distress often occurs in lung cancer patients undergoing chemotherapy. However, a biomarker has not been identified to reflect the severity of their symptom distress.Objective: The aim of this study was to investigate the relationship between symptom distress and serum inflammatory biomarkers in lung cancer patients undergoing chemotherapy.Methods: A longitudinal, repeated-measures design was used to assess subjective symptoms (fatigue, sleep disturbance, pain, depression, and confusion), serum biomarkers (tartrate-resistant acid phosphatase 5a [TRACP5a], interleukin 6 [IL-6], IL-8, and C-reactive protein), and white blood cells in 62 lung cancer patients recruited from a single medical center at 3 time points: T1 was the baseline, T2 was the eighth day after the first chemotherapy cycle, and T3 was prior to the second cycle. Symptom distress was measured individually by 5 questionnaires (General Fatigue Scale, Pittsburgh Sleep Quality Index, Brief Pain Inventory, Profile of Mood States–Depressive, and Confusion).Results: The trend of TRACP5a was positively correlated to the trend of the patients’ symptom distress. However, the trends of IL-6 and IL-8 did not correlate.Conclusions: Serum TRACP5a was associated with symptom distress in lung cancer patients. Therefore, TRACP5a might be a potential biomarker to assess symptom distress of lung cancer patients undergoing chemotherapy.Implications for Practice: Oncology nurses may be able to apply TRACP5a expression to predict or monitor multiple distress symptoms in lung cancer patients undergoing chemotherapy. Furthermore, nurses can use these study findings to better understand the patients who need more attention to improve their quality of life.

This study aims to investigate the variations in fatigue and sleep disturbances among female patients with advanced lung cancer (ALC) and advanced breast cancer (ABC) during chemotherapy. A total of 36 female patients with ALC and 36 with ABC, all of whom had completed their first cycle of chemotherapy, were included. Fatigue was assessed using the General Fatigue Scale (GFS), and sleep disturbances were evaluated using the Pittsburgh Sleep Quality Index (PSQI) at designated time points throughout the chemotherapy process. Linear regression analysis indicated that variables such as age, education level, employment status, cancer type, clinical stage, and symptom distress had no significant correlation with either fatigue or sleep disturbances. The GFS significantly discriminated fatigue among the ALC, ABC, and combined groups, while the PSQI demonstrated a significant distinction in sleep disturbance only within the ALC and combined groups. In summary, when considering the findings of both assessments in this study, the GFS score exhibited greater sensitivity in detecting fatigue than the PSQI score did for identifying sleep disturbances in advanced cancer patients undergoing chemotherapy.