Abstract-Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (SVM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVMbased approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.

Abstract-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.

Nowadays medical software is tightly coupled with medical devices that perform patient state monitoring and lately even some basic treatment procedures. Medical guidelines (GLs) can be seen as specification of a medical system which requires their computerinterpretable representation of medical GLs. Until now most of the medical GLs are often represented in a textual format and therefore often suffer from such structural problems as incompleteness, inconsistencies, ambiguity and redundancy, which makes the translation process to the machine-interpretable language more complicated. Computer-based interpretation of GLs can improve the quality of protocols as well as the quality of medical service. Several GLs formal representation methods have been presented recently. Only some of them enable automatic formal verification by introducing an additional translation path to the existing model checking environments. However, if a verified property fails it is difficult to trace back the result needed to change the model. Moreover, these formalisms provide the notion of time mostly in terms of actions order. In this paper we preset the application of a well-know formal behaviour representation approach of embedded systems design domain to medical GLs interpretation. We use Timed Automata extended with Tasks (TAT) and TIMES toolbox to represent medical GLs as a system behaviour in a computer interpretable form. We discuss the verification issues with the help of the anticancer drug imatinib case study.

IntroductionBRCA tumour testing is a crucial tool for personalised therapy of patients with ovarian cancer. Since different next-generation sequencing (NGS) platforms and BRCA panels are available, the NGS Italian Network proposed to assess the robustness of different technologies.MethodsSix centres, using four different technologies, provided raw data of 284 cases, including 75 cases with pathogenic/likely pathogenic variants, for a revision blindly performed by an external bioinformatic platform.ResultsThe third-party revision assessed that all the 284 raw data reached good quality parameters. The variant calling analysis confirmed all the 75 pathogenic/likely pathogenic variants, including challenging variants, achieving a concordance rate of 100% regardless of the panel, instrument and bioinformatic pipeline adopted. No additional variants were identified in the reanalysis of a subset of 41 cases.ConclusionsBRCA tumour testing performed with different technologies in different centres, may achieve the realibility and reproducibility required for clinical diagnostic procedures.

Abstract-Drug delivery is one of the most common clinical routines in hospitals, and is critical to patients' health and recovery. It includes a decision making process in which a medical doctor decides the amount (dose) and frequency (dose interval) on the basis of a set of available patients' feature data and the doctor's clinical experience (a priori adaptation). This process can be computerized in order to make the prescription procedure in a fast, objective, inexpensive, non-invasive and accurate way. This paper proposes a Drug Administration Decision Support System (DADSS) to help clinicians/patients with the initial dose computing. The system is based on a Support Vector Machine (SVM) algorithm for estimation of the potential drug concentration in the blood of a patient, from which a best combination of dose and dose interval is selected at the level of a DSS. The addition of the RANdom SAmple Consensus (RANSAC) technique enhances the prediction accuracy by selecting inliers for SVM modeling. Experiments are performed for the drug imatinib case study which shows more than 40% improvement in the prediction accuracy compared with previous works. An important extension to the patient features' data is also proposed in this paper.