Comparative analysis of targeted metabolomics: dominance-based rough set approach versus orthogonal partial least square-discriminant analysis.

BACKGROUND: Metabolomics is an emerging field that includes ascertaining a metabolic profile from a combination of small molecules, and which has health applications. Metabolomic methods are currently applied to discover diagnostic biomarkers and to identify pathophysiological pathways involved in pathology. However, metabolomic data are complex and are usually analyzed by statistical methods. Although the methods have been widely described, most have not been either standardized or validated. Data analysis is the foundation of a robust methodology, so new mathematical methods need to be developed to assess and complement current methods. We therefore applied, for the first time, the dominance-based rough set approach (DRSA) to metabolomics data; we also assessed the complementarity of this method with standard statistical methods. Some attributes were transformed in a way allowing us to discover global and local monotonic relationships between condition and decision attributes. We used previously published metabolomics data (18 variables) for amyotrophic lateral sclerosis (ALS) and non-ALS patients. RESULTS: Principal Component Analysis (PCA) and Orthogonal Partial Least Square-Discriminant Analysis (OPLS-DA) allowed satisfactory discrimination (72.7%) between ALS and non-ALS patients. Some discriminant metabolites were identified: acetate, acetone, pyruvate and glutamine. The concentrations of acetate and pyruvate were also identified by univariate analysis as significantly different between ALS and non-ALS patients. DRSA correctly classified 68.7% of the cases and established rules involving some of the metabolites highlighted by OPLS-DA (acetate and acetone). Some rules identified potential biomarkers not revealed by OPLS-DA (beta-hydroxybutyrate). We also found a large number of common discriminating metabolites after Bayesian confirmation measures, particularly acetate, pyruvate, acetone and ascorbate, consistent with the pathophysiological pathways involved in ALS. CONCLUSION: DRSA provides a complementary method for improving the predictive performance of the multivariate data analysis usually used in metabolomics. This method could help in the identification of metabolites involved in disease pathogenesis. Interestingly, these different strategies mostly identified the same metabolites as being discriminant. The selection of strong decision rules with high value of Bayesian confirmation provides useful information about relevant condition-decision relationships not otherwise revealed in metabolomics data.

Planning and tracking chemotherapy production for cancer treatment: a performing and integrated solution.

PURPOSE: Chemotherapy drugs are intended for the treatment of cancer. The production of such drugs and their administration to the patient is a delicate and expensive operation. The study deals with the acquisition and processing of data regarding the production of intravenous chemotherapy, from the production request (the medical prescription), the production itself (pharmaceutical process), to the delivery in the health care unit, for the administration of the chemotherapy. The goal of this study is to develop a system that can schedule, control and track the chemotherapy preparations and satisfy a certification process of quality management ("ISO 9001 version 2000" standard). METHODS: The solution proposed in this paper was developed within the framework of a common certification process at the Biopharmaceutical Unit of the Oncology Clinic (UBCO) of the Bretonneau hospital in Tours (France). The system consists of two software programs: a software to insure traceability and a decision making software to plan the production. To simplify the data entry process, some mobile entry points with bar code reader have been deployed. These tools enable an accurate tracking of the production, a security and control for the schedule production phases, and a full traceability of each operation leading to the administration of the chemotherapy drug. RESULTS: The first result is a software that creates the production schedule, allows a real time control of the production process and a full traceability of each step. Computational experiments are based on real data sets, with a comparison of a time period before and after the implementation of this solution. The results show the positive impacts of this software, like the reduction of delayed deliveries, real time generation of production indicators, optimization of the production and a saving of staff time. CONCLUSIONS: This intuitive system guarantees a traceability in connection with a high quality system certified ISO 9001-v2000 (with a rapid data entry), an assistant to schedule the production of preparations in a better way, a permanent follow-up and analysis of operations. This project proves the benefits of implementing computer solutions for the traceability and assistance in decision making in the hospital systems.