Biomedical subjects

Juan J Rodríguez

Publications and source records attributed to Juan J Rodríguez.

5 recordsLinked to original sources

PubMed2007

Diagnosing scrapie in sheep: a classification experiment.

Scrapie is a neuro-degenerative disease in small ruminants. A data set of 3113 records of sheep reported to the Scrapie Notifications Database in Great Britain has been studied. Clinical signs were recorded as present/absent in each animal by veterinary officials (VO) and a post-mortem diagnosis was made. In an attempt to detect healthy animals within the set of suspects using only the clinical signs, 18 classification methods were applied ranging from simple linear classifiers to classifier ensembles such as Bagging, AdaBoost and Random Forests. The results suggest that the clinical classification by the VO was adequate as no further differentiation within the set of suspects was feasible.

Animals↗

PubMed2006

Rotation forest: A new classifier ensemble method.

We propose a method for generating classifier ensembles based on feature extraction. To create the training data for a base classifier, the feature set is randomly split into K subsets (K is a parameter of the algorithm) and Principal Component Analysis (PCA) is applied to each subset. All principal components are retained in order to preserve the variability information in the data. Thus, K axis rotations take place to form the new features for a base classifier. The idea of the rotation approach is to encourage simultaneously individual accuracy and diversity within the ensemble. Diversity is promoted through the feature extraction for each base classifier. Decision trees were chosen here because they are sensitive to rotation of the feature axes, hence the name "forest." Accuracy is sought by keeping all principal components and also using the whole data set to train each base classifier. Using WEKA, we examined the Rotation Forest ensemble on a random selection of 33 benchmark data sets from the UCI repository and compared it with Bagging, AdaBoost, and Random Forest. The results were favorable to Rotation Forest and prompted an investigation into diversity-accuracy landscape of the ensemble models. Diversity-error diagrams revealed that Rotation Forest ensembles construct individual classifiers which are more accurate than these in AdaBoost and Random Forest, and more diverse than these in Bagging, sometimes more accurate as well.

Algorithms↗

PubMed2006

[Reduction in acute myocardial infarction mortality over a five-year period].

INTRODUCTION AND OBJECTIVES: To assess recent changes in the management of patients with acute myocardial infarction (AMI) and their impact on mortality using data from the PRIAMHO I and II registries (1995 and 2000). PATIENTS AND METHOD: Of the 168 public hospitals in Spain, 24 and 58 contributed to the 1995 and 2000 PRIAMHO registries, respectively. RESULTS: Patients in the PRIAMHO II registry (n=6221) were significantly older, more often female, and proportionally more likely to have coronary risk factors or a previous myocardial infarction, or to have undergone revascularization than those in PRIAMHO I (n=5242). Reperfusion therapy was administered more often (46.9% vs 41.9%, P<.001) and earlier (48 min vs 60 min, P<.001). Antiplatelet drugs were given to 96.1% vs 89.1% of patients, beta-blockers to 51.1% vs 30.1%, and ACE inhibitors to 41.6% vs 24.9% (P<.001 for all comparisons). In addition, 28-day mortality was 11.3% and 14.2% (P<.001), respectively, and one-year mortality, 16.4% and 18.5% (P<.001), respectively. The adjusted hazard ratio for mortality at one year in PRIAMHO II compared with PRIAMHO I was 0.78 (95% CI, 0.70-0.86, P<.001; adjusted for age, sex, diabetes, smoking, dyslipemia, hypertension, previous MI and CABG, ST-elevation status and Killip class at admission, and hospital characteristics). CONCLUSIONS: Even though patients registered in 2000 formed a higher risk group than those registered in 1995, one-year mortality after AMI decreased by 22% over the five-year period. This improvement was due to more frequent and earlier reperfusion therapy and better use of antithrombotics, beta-blockers and ACE inhibitors.

Adrenergic beta-Antagonists↗

PubMed2003

[Management of myocardial infarction in Spain in the year 2000. The PRIAMHO II study].

INTRODUCTION AND OBJECTIVES: Hospital registries are useful tools to measure the degree of implementation of new treatments and clinical practice guidelines. PATIENTS AND METHOD: The hospital registry described here was developed in the prospective PRIAMHO II study, which involved a random selection of Spanish hospitals with a coronary intensive care unit and external quality control. This study investigated patients admitted to the coronary care unit with acute myocardial infarction. Demographic and clinical characteristics were recorded, as well as the management, clinical course and survival after 28 days and one year. RESULTS: From May 15 to December 15 2000 we included in the registry 6,221 patients from the 58 hospitals that complied with the quality control requirements (71.6% of all participating hospitals). Acute mortality was 9.6%; 28-day and one-year mortality were 11.4% and 16.5%, respectively. Of the patients with ST elevation-myocardial infarction of less than 12 hours' duration, 71.6% were reperfused and 89.3% received fibrinolysis with a median door-to-needle time of 48 minutes. Ejection fraction was measured in 81% of the patients, and 43% were tested for inducible ischemia. About nine-tenths (91%) of the patients were discharged on least one antiplatelet drug, 56% on a beta blocker, 45% on an ACE inhibitor, and 45% on a lipid-lowering agent, with a coefficient of variation between hospitals greater than 25% for the last three drugs. CONCLUSIONS: The percentage of patients with ST elevation treated with reperfusion should increase, as it probably will thanks to the increasing use of primary angioplasty. The door-to-needle time was longer than the recommended interval. In-hospital risk stratification was good but nonsystematic for the evaluation of ejection fraction, and unsatisfactory for inducible ischemia testing. At discharge the percentages of patients receiving beta blockers, ACE inhibitors and statins were not optimal, and there were wide variations in prescribing practices between hospitals.

Aged↗

PubMedDate not supplied

[Obtention and characterization of a diploid cell line of human kidney].

A new diploid cell line of human embrionary kidney was obtained by serial subcultures (Mag) starting from a primary culture. It was prepared by applying the explant technique instead of the classical enzymatic digestion with trypsin. The stabilization process of the diploid line after the "secondary culture" was attained between the passes 6 and 7. 3 culture media were tested during the process. Only the MEM was completely satisfactory. The biological characteristics of the new line were as follows: fibroblastic morphology, Eagle MEM culture mean with 10% of SBF, split from 1:2 to 1:3, normal human carotype, postfreezing viability of 60%, pollutant-free and non-tumorigenic. The cryopreserved Mag subcultures 11-13 were studied from the point of view of their usefulness for the diagnosis of different viral groups.

Cell Line↗