Validation procedures in radiological diagnostic models. Neural network and logistic regression

The objective of this paper is to compare the performance of twopredictive radiological models, logistic regression (LR) and neural network (NN), with five different resampling methods. One hundred and sixty-seven patients with proven calvarial lesions as the only known disease were enrolled. Clinical and CT data were used for LR and NN models. Both models were developed with cross validation, leave-one-out and three different bootstrap algorithms. The final results of each model were compared with error rate and the area under receiver operating characteristic curves (Az). The neural network obtained statistically higher Az than LR with cross validation. The remaining resampling validation methods did not reveal statistically significant differences between LR and NN rules. The neural network classifier performs better than the one based on logistic regression. This advantage is well detected by three-fold cross-validation, but remains unnoticed when leave-one-out or bootstrap algorithms are used.

The role of fibroblast growth factor (FGF) and type beta transforming growth factot beta (TGF beta1, beta2 and beta3) during rat craniofacial development

Growth factors seem to be part of a complex cellular signalling language, in which individual growth factors are the equivalents of the letters that compose words. According to this analogy, informational content lies, not in an individual growth factor, but in the entire set of growth factors and others signals to which a cell is exposed. The ways in which growth factors exert their combinatorial effects are becoming clearer as the molecular mechanisms of growth factors actions are being investigated. A number of related extracellular signalling molecules that play widespread roles in regulating development in both invertebrates and vertebrates constitute the Fibroblast Growth Factor (FGF) and type beta Transforming Growth Factor ((TGF beta). The latest research literature about the role and fate of these Growth factors and their influence in the craniofacial bone growth ad development is reviewed

The role of fibroblast growth factor (FGF) and type beta transforming growth factot beta (TGF beta1, beta2 and beta3) during rat craniofacial development

Growth factors seem to be part of a complex cellular signalling language, in which individual growth factors are the equivalents of the letters that compose words. According to this analogy, informational content lies, not in an individual growth factor, but in the entire set of growth factors and others signals to which a cell is exposed. The ways in which growth factors exert their combinatorial effects are becoming clearer as the molecular mechanisms of growth factors actions are being investigated. A number of related extracellular signalling molecules that play widespread roles in regulating development in both invertebrates and vertebrates constitute the Fibroblast Growth Factor (FGF) and type beta Transforming Growth Factor ((TGF beta). The latest research literature about the role and fate of these Growth factors and their influence in the craniofacial bone growth ad development is reviewed

Circulating progenitor cells during exercise, muscle electro-stimulation and intermittent hypobaric hypoxia in patients with traumatic brain injury. A pilot study

BACKGROUND: Circulating progenitor cells (CPC) treatments may have great potential for the recovery of neurons and brain function. OBJECTIVE: To increase and maintain CPC with a program of exercise, muscle electro-stimulation (ME) and/or intermittent-hypobaric-hypoxia (IHH), and also to study the possible improvement in physical or psychological functioning of participants with Traumatic Brain Injury (TBI). METHODS: Twenty-one participants. Four groups: exercise and ME group (EEG), cycling group (CyG), IHH and ME group (HEG) and control group (CG). Psychological and physical stress tests were carried out. CPC were measured in blood several times during the protocol. RESULTS: Psychological tests did not change. In the physical stress tests the VO2 uptake increased in the EEG and the CyG, and the maximal tolerated workload increased in the HEG. CPC levels increased in the last three weeks in EEG, but not in CyG, CG and HEG. CONCLUSIONS: CPC levels increased in the last three weeks of the EEG program, but not in the other groups and we did not detect performed psychological test changes in any group. The detected aerobic capacity or workload improvement must be beneficial for the patients who have suffered TBI, but exercise type and the mechanisms involved are not clear.