Fernando Sánchez-Lasheras

Bankruptcy forecasting: A hybrid approach using Fuzzy c-means clustering and Multivariate Adaptive Regression Splines (MARS)

During the last years, hybrid models have proven to be a promising approach for the design of classification systems for the forecasting of bankruptcy. In the present research we propose a hybrid system which combines fuzzy clustering and MARS. Both models are especially suitable for the bankruptcy prediction problem, due to their theoretical advantages when the information used for the forecasting is drawn from company financial statements. We test the accuracy of our approach in a real setting consisting of a database made up of 59,336 non-bankrupt Spanish companies and 138 distressed firms which went bankrupt during 2007. As benchmarking techniques we used discriminant analysis, MARS and a feed-forward neural network. Our results show that the hybrid model outperforms the other systems, both in terms of the percentage of correct classifications and in terms of the profit generated by the lending decisions.

La reestenosis en el stent depende del daño vascular inducido. ¿Son válidos los modelos experimentales actuales de análisis de los stents farmacoactivos?

INTRODUCTION AND OBJECTIVES Drug-eluting stents are useful for preventing restenosis, but the patho-physiological processes involved in the proliferative response after implantation are still not known in detail. The aim of this study is to compare the coronary vascular histomorphometry after implanting drug-eluting stents and bare metal stents in a swine model. METHODS Sixty stents were randomly implanted in 20 Large White female pigs with a ratio of baremetal/drug-eluting stents of 1:2. After 28 days, euthanasia and histomorphometry were performed. We defined the vessel injury score in accordance to whether the internal elastic lamina was intact or ruptured. RESULTS There were no differences between drug-eluting stents and bare metal stents in the intact internal elastic lamina group regarding neointimal area or % restenosis (1.3 [1.1-2.2]) vs 2.0 [1.3-2.5] mm²; P=.6; and 14.0 [12.1-20.8] vs 22.2 [14.1-23.3] %; P=.5). We assessed statistically significant differences for the ruptured internal elastic lamina group, (neointimal area 1.2 [0.8-2.0] vs 2.9 [2.3-3.7] mm²; P=.001 and % restenosis 16.63 [11.2-23.5] vs 30.4 [26.4-45.7] %; P=.001). CONCLUSIONS In our swine model, we did not find any differences between proliferative response of drug-eluting stents and bare metal stents when the internal elastic lamina is intact; differences are only found when vascular injury is deeper.

Suicidio, desempleo y recesión económica en España

INTRODUCTION The aim of the present work is to determine the association between unemployment and suicide, and to investigate whether this association is affected by changes in the economic cycle or other variables such as age and sex. METHODS A time-trend analysis was conducted to study changes in the number of suicides between 1999 and 2013 in Spain. Pearsons correlation coefficients and regression models were used to find the association between unemployment and suicide. RESULTS A significant positive association was found between unemployment and suicide in the pre-crisis period in men. In that period (1999-2007), each 1% annual increase in unemployment was associated with a 6.90% increase in the annual variation of suicide in the total population, and with a 9.04% increase in the annual variation of suicide in working age men. CONCLUSIONS The correlation between unemployment and suicide is significant in periods of economic stability, but has weakened during the recent financial crisis. Unemployment and suicide have a complex relationship modulated by age, sex and economic cycle.

Power Cell SOC Modelling for Intelligent Virtual Sensor Implementation

Batteries are one of the principal components in electric vehicles and mobile electronic devices. They operate based on electrochemical reactions, which are exhaustively tested to check their behavior and to determine their characteristics at each working point. One remarkable issue of batteries is their complex behavior. The power cell type under analysis in this research is a LFP (Lithium Iron Phosphate LiFePO4). The purpose of this research is to predict the power cell State of Charge (SOC) by creating a hybrid intelligent model. All the operating points measured from a real system during a capacity confirmation test make up the dataset used to obtain the model. This dataset is clustered to obtain different behavior groups, which are used to develop the final model. Different regression techniques such as polynomial regression, support vector regression (SVR), and artificial neural networks (ANN) have been implemented for each cluster. A combination of these methods is performed to achieve an intelligent model. The SOC of the power cell can be predicted by this hybrid intelligent model, and good results are achieved.

Biomechanical Consequences of the Elastic Properties of Dental Implant Alloys on the Supporting Bone: Finite Element Analysis.

The objective of the present study is to evaluate how the elastic properties of the fabrication material of dental implants influence peri-implant bone load transfer in terms of the magnitude and distribution of stress and deformation. A three-dimensional (3D) finite element analysis was performed; the model used was a section of mandibular bone with a single implant containing a cemented ceramic-metal crown on a titanium abutment. The following three alloys were compared: rigid (Y-TZP), conventional (Ti-6Al-4V), and hyperelastic (Ti-Nb-Zr). A 150-N static load was tested on the central fossa at 6° relative to the axial axis of the implant. The results showed no differences in the distribution of stress and deformation of the bone for any of the three types of alloys studied, mainly being concentrated at the peri-implant cortical layer. However, there were differences found in the magnitude of the stress transferred to the supporting bone, with the most rigid alloy (Y-TZP) transferring the least stress and deformation to cortical bone. We conclude that there is an effect of the fabrication material of dental implants on the magnitude of the stress and deformation transferred to peri-implant bone.

Survival model in oral squamous cell carcinoma based on clinicopathological parameters, molecular markers and support vector machines

The aim of the present study is to find an intelligent and efficient model, based on Support Vector Machines (SVM), able to predict prognosis in patients with oral squamous cell carcinoma (OSCC). A total of 34 clinical and molecular variables were studied in 69 patients suffering from an OSCC. Variables were selected by means of two methods applied in parallel (Non-concave penalty and Newtons methods). The implementation of a predictive model was performed using the SVM as a classifier algorithm. Finally, its classification ability was evaluated by discriminant analysis. Recurrence, number of recurrences, and TNM stage have been identified as the most relevant prognosis factors with both used methods. Classification rates reached 97.56% and 100% for alive and dead patients, respectively (overall classification rate of 98.55%). SVM techniques build tools able to predict with high accuracy the survival of a patient with OSCC.

La elección de la especialidad medicina intensiva: análisis de los últimos 10 años

In Spain, practicing the medical profession requires a Degree in Medicine. Furthermore, access to specialized training requires passing a State examination called on an annual basis by the Spanish Ministry of Health, Social Services and Equality (Ministerio de Sanidad, Servicios Sociales e Igualdad [MSSSI]), and known as the Internal Resident in Training (Médico Interno Residente [MIR]) exam. Those candidates that reach an examination grade above the minimum cutoff point are listed from higher to lower total score and are assigned an order number with which they become potential choosers of one of the offered specialized training posts. The higher the total score, the lower the order number: number one corresponds to the candidate with the maximum note, and this individual is the first to choose a specialized training post. The choice and designation of posts is called by the MSSSI, and the data are public. The present communication analyzes the offer and demand referred to the specialty of Intensive Care Medicine in recent years, and presents the map of Spanish Autonomous Communities and chosen centers with the best order numbers. The analysis has been based on the official MIR posts designated by the MSSSI covering the annual examinations from 2006 to 2015--the latter corresponding to the post designation act of 2016. The data obtained from the different analyses are reported as the mean, maximum and minimum, median and percentiles 25 and 75 of the order number of the candidates that chose such training posts. We studied the association between the number of posts in Intensive Care Medicine and the total posts offered annually, based on the Pearson correlation coefficient.

Prognostic value of computed tomography pulmonary angiography indices in patients with cancer-related pulmonary embolism: Data from a multicenter cohort study

OBJECTIVE To analyze the prognostic value of pulmonary artery obstruction versus right-ventricle (RV) dysfunction radiologic indices in cancer-related pulmonary embolism (PE). METHODS We enrolled 303 consecutive patients with paraneoplastic PE, evaluated by computed tomography pulmonary angiography (CTPA) between 2013 and 2014. The primary outcome measure was serious complications at 15days. Multivariate analyses were conducted by using binary logistic and robust regressions. Radiological features such as the Qanadli index (QI) and RV dysfunction signs were analyzed with Spearmans partial rank correlations. RESULTS RV diameter was the only radiological variable associated with an adverse outcome. Subjects with enlarged RV (diameter>45mm) had more 15-day complications (58% versus 40%, p=0.001). The QI correlated with the RV diameter (r=0.28, p<0.001), left ventricle diameter (r=-0.19, p<0.001), right ventricular-to-left ventricular diameter ratio (r=0.39, p<0.001), pulmonary artery diameter (r=0.22, p<0.001), and pulmonary artery/ascending aorta ratio (r=0.27, p<0.001). A QI≥50% was only associated with 15-day complications in subjects with enlarged RV, inverted intraventricular septum, or chronic cardiopulmonary diseases. The central or peripheral PE location did not affect the correlations among radiological variables and was not associated with clinical outcomes. CONCLUSIONS Right ventricular dysfunction signs in CTPA are more useful than QI in predicting cancer-related PE outcome.

Aparato Digestivo: evolución de la elección de la especialidad en los últimos años

INTRODUCTION Gastroenterology is one of the medical specialties offered to residency training candidates each year. This project analyzes the data associated with the choice of a Gastroenterology residency program in recent years. MATERIAL AND METHODS Data related to specialty selection were obtained from official reports with regard to the allocation of residency places by the Spanish Ministry of Health, Social Services and Equality. Information was collected from various teaching centers via their training guides, the Spanish National Catalogue of Hospitals and the National Transplant Organization. RESULTS The median consecutive number involved in the choice of Gastroenterology training has decreased year after year, and this specialty is now positioned among the five most commonly selected residency programs in 2015. The median number of hospitals with a higher number of beds, adult liver transplantation activities and dedicated GI bleeding units is significantly lower. This is also true when centers are analyzed according to the presence of specific Gastroenterology on-call shifts for residents or their association with medical schools. Data from the past five years highlight Madrid, Aragón and the Basque Country as the autonomous communities where Gastroenterology is the most popular. Centers selected by candidates with the lowest median consecutive numbers from 2011-2015 included the university hospitals Ramón y Cajal, Santiago de Compostela and Gregorio Marañón. CONCLUSIONS Gastroenterology has gradually escalated in the ranking of residency choices and is now one of the five most popular options. Potential residents prefer larger centers with complex-care patients and more research activity.

PoDA Algorithm: Predictive Pathways in Colorectal Cancer

Colorectal cancer (CRC) has the third highest incidence in men, and the second highest in women worldwide. As it is known, both genetic and environmental factors play a role in colorectal cancer. So far, the most common way of studying genetic factors affecting CRC has been the SNP-SNP analysis. However, since these rarely act in an individualized way, it would be interesting to study them together. For that reasons, it is important to detect pathways or SNPs with a known relation which plays a role in this disease. In this study, we use Pathway of Distinction Analysis methodology (PoDA) in order to do it. PoDA is a novel bioinformatics tool that identifies significant pathways that could play an essential role in a specific disease based on genetics distance. Based on this method, we state that mitochondrial biogenesis pathway could be a good predictor pathway on colorectal cancer.