Personalized modeling for drug concentration prediction using Support Vector Machine

Building a personalized model to describe the drug concentration inside the human body for each patient is highly important to the clinical practice and demanding to the modeling tools. Instead of using traditional explicit methods, in this paper we propose a machine learning approach to describe the relation between the drug concentration and patients' features. Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. We focus mainly on the prediction of the drug concentrations as well as the analysis of different features' influence. Models are built based on Support Vector Machine and the prediction results are compared with the traditional analytical models.

Towards a user-friendly webservice architecture for statistical machine translation in the PANACEA project

This paper presents a webservice architecture for Statistical Machine Translation aimed at non-technical users. A workfloweditor allows a user to combine different webservices using a graphical user interface. In the current state of this project,the webservices have been implemented for a range of sentential and sub-sententialaligners. The advantage of a common interface and a common data format allows the user to build workflows exchanging different aligners.

Interobserver and intraobserver variability of the apparent diffusion coefficient in treated malignant hepatic lesions on a 3.0T machine: measurements in the whole lesion versus in the area with the most restricted diffusion.

PURPOSE: To assess the inter/intraobserver variability of apparent diffusion coefficient (ADC) measurements in treated hepatic lesions and to compare ADC measurements in the whole lesion and in the area with the most restricted diffusion (MRDA). MATERIALS AND METHODS: Twenty-five patients with treated malignant liver lesions were examined on a 3.0T machine. After agreeing on the best ADC image, two readers independently measured the ADC values in the whole lesion and in the MRDA. These measurements were repeated 1 month later. The Bland-Altman method, Spearman correlation coefficients, and the Wilcoxon signed-rank test were used to evaluate the measurements. RESULTS: Interobserver variability for ADC measurements in the whole lesion and in the MRDA was 0.17 x 10(-3) mm(2)/s [-0.17, +0.17] and 0.43 x 10(-3) mm(2)/s [-0.45, +0.41], respectively. Intraobserver limits of agreement could be as low as [-0.10, +0.12] 10(-3) mm(2)/s and [-0.20, +0.33] 10(-3) mm(2)/s for measurements in the whole lesion and in the MRDA, respectively. CONCLUSION: A limited variability in ADC measurements does exist, and it should be considered when interpreting ADC values of hepatic malignancies. This is especially true for the measurements of the minimal ADC.

Development, optimization, and validation of novel anti-TEM1/CD248 affinity agent for optical imaging in cancer.

Tumor Endothelial Marker-1 (TEM1/CD248) is a tumor vascular marker with high therapeutic and diagnostic potentials. Immuno-imaging with TEM1-specific antibodies can help to detect cancerous lesions, monitor tumor responses, and select patients that are most likely to benefit from TEM1-targeted therapies. In particular, near infrared(NIR) optical imaging with biomarker-specific antibodies can provide real-time, tomographic information without exposing the subjects to radioactivity. To maximize the theranostic potential of TEM1, we developed a panel of all human, multivalent Fc-fusion proteins based on a previously identified single chain antibody (scFv78) that recognizes both human and mouse TEM1. By characterizing avidity, stability, and pharmacokinectics, we identified one fusion protein, 78Fc, with desirable characteristics for immuno-imaging applications. The biodistribution of radiolabeled 78Fc showed that this antibody had minimal binding to normal organs, which have low expression of TEM1. Next, we developed a 78Fc-based tracer and tested its performance in different TEM1-expressing mouse models. The NIR imaging and tomography results suggest that the 78Fc-NIR tracer performs well in distinguishing mouse- or human-TEM1 expressing tumor grafts from normal organs and control grafts in vivo. From these results we conclude that further development and optimization of 78Fc as a TEM1-targeted imaging agent for use in clinical settings is warranted.

Análise de Reantabilidade através da Margem de Contribuição

Este trabalho versa sobre a análise de rentabilidade através da margem de contribuição e tem por objectivo evidenciar como a margem de contribuição pode ser utilizada pelos gestores, na rentabilidade dos clientes, dos produtos, dos canais de distribuição e dos segmentos de mercado em que as empresas operam. O estudo está assente num referencial teórico que faz incursões nos principais conceitos conexos ao tema principal nomeadamente: análise custo – volume – resultado, métodos apuramento dos resultados na óptica da absorção e da contribuição, e a curva ABC. Na aplicação prática, procurámos utilizar alguns instrumentos de gestão nomeadamente o ponto de equilíbrio, apuramento dos resultados por segmentos de clientes, negócios e territórios de comercialização e a aplicação da curva de experiência ABC. O caso de estudo incide sobre a empresa nacional de moagem (Moave S.A) e restringe-se ao plano de produção e embalagem através do pequeno ensaque. O processo de colecta de dados foi obtido directamente das informações fornecidas pela Direcção da empresa, nomeadamente os produtos a serem embalados, a estrutura de custos, o plano de produção, a capacidade máxima da máquina e o calendário de trabalho diário e mensal. Os resultados evidenciaram que a utilização da margem de contribuição como ferramenta de gestão, constitui um importante instrumento de análise e avaliação da rentabilidade dos produtos, dos clientes, dos canais de distribuição bem como dos territórios de comercialização. This work focuses on the analysis of profitability through contribution margin and aims to highlight the contribution margin can be used by managers, in the profitability of customers, products, distribution channels and market segments in which companies operate. The study is based on the referential theoretical that makes inroads in key concepts related to the main topic, namely: cost analysis – volume – result, methods of clearance results in optical absorption and contribution, and ABC. In practice, we try to use some management tools in the balance, such as breakeven point, clearance of results by segments of customers, business and marketing territories and the application of experience curve ABC. The case study focuses on the national milling company (Moave s.a), and restricts itself to plan production and packaging through small bagging. The process of collecting data was obtained directly from the information provided by the management of the undertaking, in particular the products to be packed, the cost structure, the production plan, the maximum capacity of the machine and the daily work schedule and monthly. The results showed that the use of the contribution margin as a management tool constitutes an important instrument of analysis and assessment of the profitability of products, customers, distribution channels and marketing territories.