No abstract

No abstract

Background Systemic inflammation plays a critical role in cancer progression and oncologic outcomes in cancer patients. We investigated whether preoperative inflammatory biomarkers, including C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), and neutrophil to lymphocyte ratio (NLR), could be surrogate biomarkers for predicting overall survival (OS) in soft tissue sarcoma (STS) patients treated with surgery and postoperative radiotherapy. Methods A series of 99 patients who presented with localized extremity STS were retrospectively reviewed. The preoperative CRP levels, ESR, and NLR were evaluated for associations with OS, disease-free survival (DFS), local recurrence-free survival (LRFS), and distant metastasis-free survival (DMFS). Cutoff values for CRP, ESR, and NLR were derived from receiver-operating characteristic curve analysis. Results Elevated CRP (> 0.14 mg/dL), ESR (> 15 mm/h), and NLR (> 1.95) levels were seen in 33, 44, and 45 patients, respectively. Of these three inflammatory biomarkers, elevated CRP and ESR were associated with a poorer OS (CRP: P = 0.050; ESR: P = 0.001), DFS (CRP: P = 0.023; ESR: P = 0.003), and DMFS (CRP: P = 0.015; ESR: P = 0.001). By multivariate analysis, an elevated ESR was found to be an independent prognostic factor for OS (HR 3.580, P = 0.025) and DMFS (HR 3.850, P = 0.036) after adjustment for other established prognostic factors. Conclusions The preoperative ESR level is a simple and useful surrogate biomarker for predicting survival outcomes in STS patients and might improve the identification of high-risk patients of tumor relapse in clinical practice.

No abstract

The naive Bayesian classification method has received significant attention in the field of supervised learning. This method has an unrealistic assumption in that it views all attributes as equally important. Attribute weighting is one of the methods used to alleviate this assumption and consequently improve the performance of the naive Bayes classification. This study, with a focus on nonlinear optimization problems, proposes four attribute weighting methods by minimizing four different loss functions. The proposed loss functions belong to a family of exponential functions that makes the optimization problems more straightforward to solve, provides analytical properties of the trained classifier, and allows for the simple modification of the loss function such that the naive Bayes classifier becomes robust to noisy instances. This research begins with a typical exponential loss which is sensitive to noise and provides a series of its modifications to make naive Bayes classifiers more robust to noisy instances. Based on numerical experiments conducted using 28 datasets from the UCI machine learning repository, we confirmed that the proposed scheme successfully determines optimal attribute weights and improves the classification performance.

No abstract

No abstract

No abstract