Could machine learning improve the prediction of pelvic nodal status of prostate cancer patients? Preliminary results of a pilot study.

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

Neuroenergetic Response to Prolonged Cerebral Glucose Depletion after Severe Brain Injury and the Role of Lactate.

Lactate may represent a supplemental fuel for the brain. We examined cerebral lactate metabolism during prolonged brain glucose depletion (GD) in acute brain injury (ABI) patients monitored with cerebral microdialysis (CMD). Sixty episodes of GD (defined as spontaneous decreases of CMD glucose from normal to low [<1.0 mmol/L] for at least 2 h) were identified among 26 patients. During GD, we found a significant increase of CMD lactate (from 4±2.3 to 5.4±2.9 mmol/L), pyruvate (126.9±65.1 to 172.3±74.1 μmol/L), and lactate/pyruvate ratio (LPR; 27±6 to 35±9; all, p<0.005), while brain oxygen and blood lactate remained normal. Dynamics of lactate and glucose supply during GD were further studied by analyzing the relationships between blood and CMD samples. There was a strong correlation between blood and brain lactate when LPR was normal (r=0.56; p<0.0001), while an inverse correlation (r=-0.11; p=0.04) was observed at elevated LPR >25. The correlation between blood and brain glucose also decreased from r=0.62 to r=0.45. These findings in ABI patients suggest increased cerebral lactate delivery in the absence of brain hypoxia when glucose availability is limited and support the concept that lactate acts as alternative fuel.

Classification supervisée multi-étiquette en actes de dialogue: analyse discriminante et transformations de Schoenberg

Abstract This work studies the multi-label classification of turns in simple English Wikipedia talk pages into dialog acts. The treated dataset was created and multi-labeled by (Ferschke et al., 2012). The first part analyses dependences between labels, in order to examine the annotation coherence and to determine a classification method. Then, a multi-label classification is computed, after transforming the problem into binary relevance. Regarding features, whereas (Ferschke et al., 2012) use features such as uni-, bi-, and trigrams, time distance between turns or the indentation level of the turn, other features are considered here: lemmas, part-of-speech tags and the meaning of verbs (according to WordNet). The dataset authors applied approaches such as Naive Bayes or Support Vector Machines. The present paper proposes, as an alternative, to use Schoenberg transformations which, following the example of kernel methods, transform original Euclidean distances into other Euclidean distances, in a space of high dimensionality. Résumé Ce travail étudie la classification supervisée multi-étiquette en actes de dialogue des tours de parole des contributeurs aux pages de discussion de Simple English Wikipedia (Wikipédia en anglais simple). Le jeu de données considéré a été créé et multi-étiqueté par (Ferschke et al., 2012). Une première partie analyse les relations entre les étiquettes pour examiner la cohérence des annotations et pour déterminer une méthode de classification. Ensuite, une classification supervisée multi-étiquette est effectuée, après recodage binaire des étiquettes. Concernant les variables, alors que (Ferschke et al., 2012) utilisent des caractéristiques telles que les uni-, bi- et trigrammes, le temps entre les tours de parole ou l'indentation d'un tour de parole, d'autres descripteurs sont considérés ici : les lemmes, les catégories morphosyntaxiques et le sens des verbes (selon WordNet). Les auteurs du jeu de données ont employé des approches telles que le Naive Bayes ou les Séparateurs à Vastes Marges (SVM) pour la classification. Cet article propose, de façon alternative, d'utiliser et d'étendre l'analyse discriminante linéaire aux transformations de Schoenberg qui, à l'instar des méthodes à noyau, transforment les distances euclidiennes originales en d'autres distances euclidiennes, dans un espace de haute dimensionnalité.

The new final Clinical Skills examination in human medicine in Switzerland: Essential steps of exam development, implementation and evaluation, and central insights from the perspective of the national Working Group.

OBJECTIVE: Since 2011, the new national final examination in human medicine has been implemented in Switzerland, with a structured clinical-practical part in the OSCE format. From the perspective of the national Working Group, the current article describes the essential steps in the development, implementation and evaluation of the Federal Licensing Examination Clinical Skills (FLE CS) as well as the applied quality assurance measures. Finally, central insights gained from the last years are presented. METHODS: Based on the principles of action research, the FLE CS is in a constant state of further development. On the foundation of systematically documented experiences from previous years, in the Working Group, unresolved questions are discussed and resulting solution approaches are substantiated (planning), implemented in the examination (implementation) and subsequently evaluated (reflection). The presented results are the product of this iterative procedure. RESULTS: The FLE CS is created by experts from all faculties and subject areas in a multistage process. The examination is administered in German and French on a decentralised basis and consists of twelve interdisciplinary stations per candidate. As important quality assurance measures, the national Review Board (content validation) and the meetings of the standardised patient trainers (standardisation) have proven worthwhile. The statistical analyses show good measurement reliability and support the construct validity of the examination. Among the central insights of the past years, it has been established that the consistent implementation of the principles of action research contributes to the successful further development of the examination. CONCLUSION: The centrally coordinated, collaborative-iterative process, incorporating experts from all faculties, makes a fundamental contribution to the quality of the FLE CS. The processes and insights presented here can be useful for others planning a similar undertaking.

Cell type-specific expression and localization of cytochrome P450 isoforms in tridimensional aggregating rat brain cell cultures.

Within the Predict-IV FP7 project a strategy for measurement of in vitro biokinetics was developed, requiring the characterization of the cellular model used, especially regarding biotransformation, which frequently depends on cytochrome P450 (CYP) activity. The extrahepatic in situ CYP-mediated metabolism is especially relevant in target organ toxicity. In this study, the constitutive mRNA levels and protein localization of different CYP isoforms were investigated in 3D aggregating brain cell cultures. CYP1A1, CYP2B1/B2, CYP2D2/4, CYP2E1 and CYP3A were expressed; CYP1A1 and 2B1 represented almost 80% of the total mRNA content. Double-immunolabeling revealed their presence in astrocytes, in neurons, and to a minor extent in oligodendrocytes, confirming the cell-specific localization of CYPs in the brain. These results together with the recently reported formation of an amiodarone metabolite following repeated exposure suggest that this cell culture system possesses some metabolic potential, most likely contributing to its high performance in neurotoxicological studies and support the use of this model in studying brain neurotoxicity involving mechanisms of toxication/detoxication.