Long-term effects of supervised exercise training on walking capacity and quality of life in patients with intermittent claudication

Supervised exercise training has been shown to improve walking capacity in several studies of patients with intermittent claudication. However, data on long-term outcome are quite limited. The aim of this prospective study was to evaluate long-term effects of supervised exercise training on walking capacity and quality of life in patients with intermittent claudication. Patients and methods: Sixty-seven consecutive patients with intermittent claudication who completed a supervised 12-week exercise training program were asked for follow up evaluation 39 +/- 20 months after program completion. Pain-free walking distance (PWD) and maximum walking distances (MWD) were assessed by treadmill test and several questionnaires. Results: Forty (60%) patients agreed to participate, 22 (33%) refused participation, and 5 (7%) died during follow-up. PWD and MWD significantly improved at completion of 12-weeks supervised exercise training as compared to baseline (PWD 114 +/- 100 vs. 235 +/- 248, p = 0.002; MWD 297 +/- 273 vs. 474 +/- 359, p = 0.001). Improvement of PWD and MWD could be maintained at follow up (197 +/- 254, p = 0.014; 390 +/- 324, p = 0.035, respectively) with non-smokers showing significantly better sustained PWD and MWD improvement as compared to baseline. Overall, walking capacity correlated with functional status of quality of life. Conclusions: Major findings of this investigation were that improvement in walking capacity is sustained after completion of supervised exercise training program with best results in patients who quitted or never smoked. Improved walking capacity is associated with increased functional status of quality of life.

Effect of 6-month supervised exercise on low-density lipoprotein apolipoprotein B kinetics in patients with type 2 diabetes mellitus

Although low-density lipoprotein (LDL) cholesterol is often normal in patients with type 2 diabetes mellitus, there is evidence for a reduced fractional catabolic rate and consequently an increased mean residence time (MRT), which can increase atherogenic risk. The dyslipidemia and insulin resistance of type 2 diabetes mellitus can be improved by aerobic exercise, but effects on LDL kinetics are unknown. The effect of 6-month supervised exercise on LDL apolipoprotein B kinetics was studied in a group of 17 patients with type 2 diabetes mellitus (mean age, 56.8 years; range, 38-68 years). Patients were randomized into a supervised group, who had a weekly training session, and an unsupervised group. LDL kinetics were measured with an infusion of 1-(13)C leucine at baseline in all groups and after 6 months of exercise in the patients. Eight body mass index-matched nondiabetic controls (mean age, 50.3 years; range, 40-67 years) were also studied at baseline only. At baseline, LDL MRT was significantly longer in the diabetic patients, whereas LDL production rate and fractional clearance rates were significantly lower than in controls. Percentage of glycated hemoglobin A(1c), body mass index, insulin sensitivity measured by the homeostasis model assessment, and very low-density lipoprotein triglyceride decreased (P < .02) in the supervised group, with no change in the unsupervised group. After 6 months, LDL cholesterol did not change in either the supervised or unsupervised group; but there was a significant change in LDL MRT between groups (P < .05) that correlated positively with very low-density lipoprotein triglyceride (r = 0.51, P < .04) and negatively with maximal oxygen uptake, a measure of fitness (r = -0.51, P = .035), in all patients. The LDL production and clearance rates did not change in either group. This study suggests that a supervised exercise program can reduce deleterious changes in LDL MRT.

Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Patient-Specific Semi-Supervised Learning for Postoperative Brain Tumor Segmentation

In contrast to preoperative brain tumor segmentation, the problem of postoperative brain tumor segmentation has been rarely approached so far. We present a fully-automatic segmentation method using multimodal magnetic resonance image data and patient-specific semi-supervised learning. The idea behind our semi-supervised approach is to effectively fuse information from both pre- and postoperative image data of the same patient to improve segmentation of the postoperative image. We pose image segmentation as a classification problem and solve it by adopting a semi-supervised decision forest. The method is evaluated on a cohort of 10 high-grade glioma patients, with segmentation performance and computation time comparable or superior to a state-of-the-art brain tumor segmentation method. Moreover, our results confirm that the inclusion of preoperative MR images lead to a better performance regarding postoperative brain tumor segmentation.

Comparison of three different brushing techniques to isolate and culture primary nasal epithelial cells from human subjects.

PURPOSE Primary nasal epithelial cells are used for diagnostic purposes in clinical routine and have been shown to be good surrogate models for bronchial epithelial cells in studies of airway inflammation and remodeling. We aimed at comparing different instruments allowing isolation of nasal epithelial cells. METHODS Primary airway epithelial cell cultures were established using cells acquired from the inferior surface of the middle turbinate of both nostrils. Three different instruments to isolate nasal cells were used: homemade cytology brush, nasal swab, and curette. Cell count, viability, time until a confluent cell layer was reached, and success rate in establishing cell cultures were evaluated. A standard numeric pain intensity scale was used to assess the acceptability of each instrument. RESULTS Sixty healthy adults (median with interquartile range [IQR] age of 31 [26-37] years) participated in the study. Higher number of cells (×10(5) cells/ml) was obtained using brushes (9.8 [5.9-33.5]) compared to swabs (2.4 [1.5-3.9], p < 0.0001) and curettes (5.5 [4.4-6.9], p < 0.01). Cell viability was similar between groups. Cells obtained by brushes had the fastest growth rate, and the success rate in establishing primary cell cultures was highest with brushes (90% vs. 65% for swabs and 70% for curettes). Pain was highest with curettes (VAS score 4.0 [3.0-5.0] out of 10). The epithelial phenotype of the cultures was confirmed through cytokeratin and E-cadherin staining. CONCLUSIONS All three types of instruments allow collection and growth of human nasal epithelial cells with good acceptability to study participants. The most efficient instrument is the nasal brush.

Facial Nerve Image Enhancement from CBCT using Supervised Learning Technique

Facial nerve segmentation plays an important role in surgical planning of cochlear implantation. Clinically available CBCT images are used for surgical planning. However, its relatively low resolution renders the identification of the facial nerve difficult. In this work, we present a supervised learning approach to enhance facial nerve image information from CBCT. A supervised learning approach based on multi-output random forest was employed to learn the mapping between CBCT and micro-CT images. Evaluation was performed qualitatively and quantitatively by using the predicted image as input for a previously published dedicated facial nerve segmentation, and cochlear implantation surgical planning software, OtoPlan. Results show the potential of the proposed approach to improve facial nerve image quality as imaged by CBCT and to leverage its segmentation using OtoPlan.

Prediction of Trabecular Bone Anisotropy from Quantitative Computed Tomography using Supervised Learning and a Novel Morphometric Feature Descriptor

Patient-specific biomechanical models including local bone mineral density and anisotropy have gained importance for assessing musculoskeletal disorders. However the trabecular bone anisotropy captured by high-resolution imaging is only available at the peripheral skeleton in clinical practice. In this work, we propose a supervised learning approach to predict trabecular bone anisotropy that builds on a novel set of pose invariant feature descriptors. The statistical relationship between trabecular bone anisotropy and feature descriptors were learned from a database of pairs of high resolution QCT and clinical QCT reconstructions. On a set of leave-one-out experiments, we compared the accuracy of the proposed approach to previous ones, and report a mean prediction error of 6% for the tensor norm, 6% for the degree of anisotropy and 19◦ for the principal tensor direction. These findings show the potential of the proposed approach to predict trabecular bone anisotropy from clinically available QCT images.

Fast Prediction of Femoral Biomechanics Using Supervised Machine Learning and Statistical Shape Modeling

Finite element (FE) analysis is an important computational tool in biomechanics. However, its adoption into clinical practice has been hampered by its computational complexity and required high technical competences for clinicians. In this paper we propose a supervised learning approach to predict the outcome of the FE analysis. We demonstrate our approach on clinical CT and X-ray femur images for FE predictions ( FEP), with features extracted, respectively, from a statistical shape model and from 2D-based morphometric and density information. Using leave-one-out experiments and sensitivity analysis, comprising a database of 89 clinical cases, our method is capable of predicting the distribution of stress values for a walking loading condition with an average correlation coefficient of 0.984 and 0.976, for CT and X-ray images, respectively. These findings suggest that supervised learning approaches have the potential to leverage the clinical integration of mechanical simulations for the treatment of musculoskeletal conditions.

Grapevine Yield and Leaf Area Estimation Using Supervised Classification Methodology on RGB Images Taken under Field Conditions

The aim of this research was to implement a methodology through the generation of a supervised classifier based on the Mahalanobis distance to characterize the grapevine canopy and assess leaf area and yield using RGB images. The method automatically processes sets of images, and calculates the areas (number of pixels) corresponding to seven different classes (Grapes, Wood, Background, and four classes of Leaf, of increasing leaf age). Each one is initialized by the user, who selects a set of representative pixels for every class in order to induce the clustering around them. The proposed methodology was evaluated with 70 grapevine (V. vinifera L. cv. Tempranillo) images, acquired in a commercial vineyard located in La Rioja (Spain), after several defoliation and de-fruiting events on 10 vines, with a conventional RGB camera and no artificial illumination. The segmentation results showed a performance of 92% for leaves and 98% for clusters, and allowed to assess the grapevine’s leaf area and yield with R2 values of 0.81 (p < 0.001) and 0.73 (p = 0.002), respectively. This methodology, which operates with a simple image acquisition setup and guarantees the right number and kind of pixel classes, has shown to be suitable and robust enough to provide valuable information for vineyard management.

Semi-supervised subspace clustering and applications to neuroscience

Machine learning techniques are used for extracting valuable knowledge from data. Nowa¬days, these techniques are becoming even more important due to the evolution in data ac¬quisition and storage, which is leading to data with different characteristics that must be exploited. Therefore, advances in data collection must be accompanied with advances in machine learning techniques to solve new challenges that might arise, on both academic and real applications. There are several machine learning techniques depending on both data characteristics and purpose. Unsupervised classification or clustering is one of the most known techniques when data lack of supervision (unlabeled data) and the aim is to discover data groups (clusters) according to their similarity. On the other hand, supervised classification needs data with supervision (labeled data) and its aim is to make predictions about labels of new data. The presence of data labels is a very important characteristic that guides not only the learning task but also other related tasks such as validation. When only some of the available data are labeled whereas the others remain unlabeled (partially labeled data), neither clustering nor supervised classification can be used. This scenario, which is becoming common nowadays because of labeling process ignorance or cost, is tackled with semi-supervised learning techniques. This thesis focuses on the branch of semi-supervised learning closest to clustering, i.e., to discover clusters using available labels as support to guide and improve the clustering process. Another important data characteristic, different from the presence of data labels, is the relevance or not of data features. Data are characterized by features, but it is possible that not all of them are relevant, or equally relevant, for the learning process. A recent clustering tendency, related to data relevance and called subspace clustering, claims that different clusters might be described by different feature subsets. This differs from traditional solutions to data relevance problem, where a single feature subset (usually the complete set of original features) is found and used to perform the clustering process. The proximity of this work to clustering leads to the first goal of this thesis. As commented above, clustering validation is a difficult task due to the absence of data labels. Although there are many indices that can be used to assess the quality of clustering solutions, these validations depend on clustering algorithms and data characteristics. Hence, in the first goal three known clustering algorithms are used to cluster data with outliers and noise, to critically study how some of the most known validation indices behave. The main goal of this work is however to combine semi-supervised clustering with subspace clustering to obtain clustering solutions that can be correctly validated by using either known indices or expert opinions. Two different algorithms are proposed from different points of view to discover clusters characterized by different subspaces. For the first algorithm, available data labels are used for searching for subspaces firstly, before searching for clusters. This algorithm assigns each instance to only one cluster (hard clustering) and is based on mapping known labels to subspaces using supervised classification techniques. Subspaces are then used to find clusters using traditional clustering techniques. The second algorithm uses available data labels to search for subspaces and clusters at the same time in an iterative process. This algorithm assigns each instance to each cluster based on a membership probability (soft clustering) and is based on integrating known labels and the search for subspaces into a model-based clustering approach. The different proposals are tested using different real and synthetic databases, and comparisons to other methods are also included when appropriate. Finally, as an example of real and current application, different machine learning tech¬niques, including one of the proposals of this work (the most sophisticated one) are applied to a task of one of the most challenging biological problems nowadays, the human brain model¬ing. Specifically, expert neuroscientists do not agree with a neuron classification for the brain cortex, which makes impossible not only any modeling attempt but also the day-to-day work without a common way to name neurons. Therefore, machine learning techniques may help to get an accepted solution to this problem, which can be an important milestone for future research in neuroscience. Resumen Las técnicas de aprendizaje automático se usan para extraer información valiosa de datos. Hoy en día, la importancia de estas técnicas está siendo incluso mayor, debido a que la evolución en la adquisición y almacenamiento de datos está llevando a datos con diferentes características que deben ser explotadas. Por lo tanto, los avances en la recolección de datos deben ir ligados a avances en las técnicas de aprendizaje automático para resolver nuevos retos que pueden aparecer, tanto en aplicaciones académicas como reales. Existen varias técnicas de aprendizaje automático dependiendo de las características de los datos y del propósito. La clasificación no supervisada o clustering es una de las técnicas más conocidas cuando los datos carecen de supervisión (datos sin etiqueta), siendo el objetivo descubrir nuevos grupos (agrupaciones) dependiendo de la similitud de los datos. Por otra parte, la clasificación supervisada necesita datos con supervisión (datos etiquetados) y su objetivo es realizar predicciones sobre las etiquetas de nuevos datos. La presencia de las etiquetas es una característica muy importante que guía no solo el aprendizaje sino también otras tareas relacionadas como la validación. Cuando solo algunos de los datos disponibles están etiquetados, mientras que el resto permanece sin etiqueta (datos parcialmente etiquetados), ni el clustering ni la clasificación supervisada se pueden utilizar. Este escenario, que está llegando a ser común hoy en día debido a la ignorancia o el coste del proceso de etiquetado, es abordado utilizando técnicas de aprendizaje semi-supervisadas. Esta tesis trata la rama del aprendizaje semi-supervisado más cercana al clustering, es decir, descubrir agrupaciones utilizando las etiquetas disponibles como apoyo para guiar y mejorar el proceso de clustering. Otra característica importante de los datos, distinta de la presencia de etiquetas, es la relevancia o no de los atributos de los datos. Los datos se caracterizan por atributos, pero es posible que no todos ellos sean relevantes, o igualmente relevantes, para el proceso de aprendizaje. Una tendencia reciente en clustering, relacionada con la relevancia de los datos y llamada clustering en subespacios, afirma que agrupaciones diferentes pueden estar descritas por subconjuntos de atributos diferentes. Esto difiere de las soluciones tradicionales para el problema de la relevancia de los datos, en las que se busca un único subconjunto de atributos (normalmente el conjunto original de atributos) y se utiliza para realizar el proceso de clustering. La cercanía de este trabajo con el clustering lleva al primer objetivo de la tesis. Como se ha comentado previamente, la validación en clustering es una tarea difícil debido a la ausencia de etiquetas. Aunque existen muchos índices que pueden usarse para evaluar la calidad de las soluciones de clustering, estas validaciones dependen de los algoritmos de clustering utilizados y de las características de los datos. Por lo tanto, en el primer objetivo tres conocidos algoritmos se usan para agrupar datos con valores atípicos y ruido para estudiar de forma crítica cómo se comportan algunos de los índices de validación más conocidos. El objetivo principal de este trabajo sin embargo es combinar clustering semi-supervisado con clustering en subespacios para obtener soluciones de clustering que puedan ser validadas de forma correcta utilizando índices conocidos u opiniones expertas. Se proponen dos algoritmos desde dos puntos de vista diferentes para descubrir agrupaciones caracterizadas por diferentes subespacios. Para el primer algoritmo, las etiquetas disponibles se usan para bus¬car en primer lugar los subespacios antes de buscar las agrupaciones. Este algoritmo asigna cada instancia a un único cluster (hard clustering) y se basa en mapear las etiquetas cono-cidas a subespacios utilizando técnicas de clasificación supervisada. El segundo algoritmo utiliza las etiquetas disponibles para buscar de forma simultánea los subespacios y las agru¬paciones en un proceso iterativo. Este algoritmo asigna cada instancia a cada cluster con una probabilidad de pertenencia (soft clustering) y se basa en integrar las etiquetas conocidas y la búsqueda en subespacios dentro de clustering basado en modelos. Las propuestas son probadas utilizando diferentes bases de datos reales y sintéticas, incluyendo comparaciones con otros métodos cuando resulten apropiadas. Finalmente, a modo de ejemplo de una aplicación real y actual, se aplican diferentes técnicas de aprendizaje automático, incluyendo una de las propuestas de este trabajo (la más sofisticada) a una tarea de uno de los problemas biológicos más desafiantes hoy en día, el modelado del cerebro humano. Específicamente, expertos neurocientíficos no se ponen de acuerdo en una clasificación de neuronas para la corteza cerebral, lo que imposibilita no sólo cualquier intento de modelado sino también el trabajo del día a día al no tener una forma estándar de llamar a las neuronas. Por lo tanto, las técnicas de aprendizaje automático pueden ayudar a conseguir una solución aceptada para este problema, lo cual puede ser un importante hito para investigaciones futuras en neurociencia.

Adaptive neuro-fuzzy inference systems (ANFIS) for supervised classification of competence in MIS based on psychomotor skills

INTRODUCTION: Objective assessment of motor skills has become an important challenge in minimally invasive surgery (MIS) training.Currently, there is no gold standard defining and determining the residents' surgical competence.To aid in the decision process, we analyze the validity of a supervised classifier to determine the degree of MIS competence based on assessment of psychomotor skills METHODOLOGY: The ANFIS is trained to classify performance in a box trainer peg transfer task performed by two groups (expert/non expert). There were 42 participants included in the study: the non-expert group consisted of 16 medical students and 8 residents (< 10 MIS procedures performed), whereas the expert group consisted of 14 residents (> 10 MIS procedures performed) and 4 experienced surgeons. Instrument movements were captured by means of the Endoscopic Video Analysis (EVA) tracking system. Nine motion analysis parameters (MAPs) were analyzed, including time, path length, depth, average speed, average acceleration, economy of area, economy of volume, idle time and motion smoothness. Data reduction was performed by means of principal component analysis, and then used to train the ANFIS net. Performance was measured by leave one out cross validation. RESULTS: The ANFIS presented an accuracy of 80.95%, where 13 experts and 21 non-experts were correctly classified. Total root mean square error was 0.88, while the area under the classifiers' ROC curve (AUC) was measured at 0.81. DISCUSSION: We have shown the usefulness of ANFIS for classification of MIS competence in a simple box trainer exercise. The main advantage of using ANFIS resides in its continuous output, which allows fine discrimination of surgical competence. There are, however, challenges that must be taken into account when considering use of ANFIS (e.g. training time, architecture modeling). Despite this, we have shown discriminative power of ANFIS for a low-difficulty box trainer task, regardless of the individual significances between MAPs. Future studies are required to confirm the findings, inclusion of new tasks, conditions and sample population.

Supervised classification of minimally invasive surgery psychomotor competence based on instruments motion analysis

Background Objective assessment of psychomotor skills has become an important challenge in the training of minimally invasive surgical (MIS) techniques. Currently, no gold standard defining surgical competence exists for classifying residents according to their surgical skills. Supervised classification has been proposed as a means for objectively establishing competence thresholds in psychomotor skills evaluation. This report presents a study comparing three classification methods for establishing their validity in a set of tasks for basic skills’ assessment. Methods Linear discriminant analysis (LDA), support vector machines (SVM), and adaptive neuro-fuzzy inference systems (ANFIS) were used. A total of 42 participants, divided into an experienced group (4 expert surgeons and 14 residents with >10 laparoscopic surgeries performed) and a nonexperienced group (16 students and 8 residents with <10 laparoscopic surgeries performed), performed three box trainer tasks validated for assessment of MIS psychomotor skills. Instrument movements were captured using the TrEndo tracking system, and nine motion analysis parameters (MAPs) were analyzed. The performance of the classifiers was measured by leave-one-out cross-validation using the scores obtained by the participants. Results The mean accuracy performances of the classifiers were 71 % (LDA), 78.2 % (SVM), and 71.7 % (ANFIS). No statistically significant differences in the performance were identified between the classifiers. Conclusions The three proposed classifiers showed good performance in the discrimination of skills, especially when information from all MAPs and tasks combined were considered. A correlation between the surgeons’ previous experience and their execution of the tasks could be ascertained from results. However, misclassifications across all the classifiers could imply the existence of other factors influencing psychomotor competence.

Adaptaciones cardiacas hemodinámicas, estructurales y funcionales a un programa de ejercicio físico supervisado durante el embarazo: ensayo clínico aleatorizado = Hemodynamic, structural and functional cardiac adaptations in a supervised physical exercise program during pregnancy: a randomized controlled trial

Introducción: Diversos cambios ocurren en el sistema cardiovascular materno durante el embarazo, lo que genera un gran estrés sobre este sistema especialmente durante el tercer trimestre, pudiendo acentuarse en presencia de determinados factores de riesgo. Los objetivos de este estudio fueron, valorar las adaptaciones cardiovasculares producidas por un programa específico de ejercicio físico; su seguridad sobre el sistema cardiovascular materno y los resultados del embarazo; y su eficacia en el control de los factores de riesgo cardiovascular. Material y métodos: El diseño del estudio fue un ensayo clínico aleatorizado. 151 gestantes sanas fueron evaluadas mediante un ecocardiograma y un electrocardiograma en la semana 20 y 34 de gestación. Un total de 89 gestantes participaron en un programa de ejercicio físico (GE) desde el primer hasta el tercer trimestre de embarazo, constituido principalmente por 25-30 minutos de trabajo aeróbico (55-60% de la frecuencia cardiaca de reserva), trabajo de fortalecimiento general y específico, y un trabajo de tonificación del suelo pélvico; desarrollado 3 días a la semana con una duración de 55-60 minutos cada sesión. Las gestantes aleatoriamente asignadas al grupo de control (GC; n=62) permanecieron sedentarias durante el embarazo. El estudio fue aprobado por el Comité Ético de investigación clínica del Hospital Universitario de Fuenlabrada. Resultados: Las características basales fueron similares entre ambos grupos. A diferencia del GC, las gestantes del GE evitaron el descenso significativo del gasto cardiaco indexado, entre el 2º y 3ºT de embarazo, y conservaron el patrón geométrico normal del ventrículo izquierdo; mientras que en el GC cambió hacia un patrón de remodelado concéntrico. En la semana 20, las gestantes del GE presentaron valores significativamente menores de frecuencia cardiaca (GC: 79,56±10,76 vs. GE: 76,05±9,34; p=0,04), tensión arterial sistólica (GC: 110,19±10,23 vs. GE: 106,04±12,06; p=0,03); tensión arterial diastólica (GC: 64,56±7,88 vs. GE: 61,81±7,15; p=0,03); tiempo de relajación isovolumétrica (GC: 72,94±14,71 vs. GE: 67,05±16,48; p=0,04); y un mayor tiempo de deceleración de la onda E (GC: 142,09±39,11 vs. GE: 162,10±48,59; p=0,01). En la semana 34, el GE presentó valores significativamente superiores de volumen sistólico (GC: 51,13±11,85 vs. GE: 56,21±12,79 p=0,04), de llenado temprano del ventrículo izquierdo (E) (GC: 78,38±14,07 vs. GE: 85,30±16,62; p=0,02) y de tiempo de deceleración de la onda E (GC: 130,35±37,11 vs. GE: 146,61±43,40; p=0,04). Conclusión: La práctica regular de ejercicio físico durante el embarazo puede producir adaptaciones positivas sobre el sistema cardiovascular materno durante el tercer trimestre de embarazo, además de ayudar en el control de sus factores de riesgo, sin alterar la salud materno-fetal. ABSTRACT Background: Several changes occur in the maternal cardiovascular system during pregnancy. These changes produce a considerable stress in this system, especially during the third trimester, which can be increased in presence of some risk factors. The aims of this study were, to assess the maternal cardiac adaptations in a specific exercise program; its safety on the maternal cardiovascular system and pregnancy outcomes; and its effectiveness in the control of cardiovascular risk factors. Material and methods: A randomized controlled trial was designed. 151 healthy pregnant women were assessed by an echocardiography and electrocardiography at 20 and 34 weeks of gestation. A total of 89 pregnant women participated in a physical exercise program (EG) from the first to the third trimester of pregnancy. It consisted of 25-30 minutes of aerobic conditioning (55-60% of their heart rate reserve), general and specific strength exercises, and a pelvic floor muscles training; 3 times per weeks during 55-60 minutes per session. Pregnant women randomized allocated to the control group (CG) remained sedentary during pregnancy. The study was approved by the Research Ethics Committee of Hospital Universitario de Fuenlabrada. Results: Baseline characteristics were similar between groups. Difference from the CG, pregnant women from the EG prevented the significant decrease of the cardiac output index, between the 2nd and 3rd trimester of pregnancy, and preserved the normal left ventricular pattern; whereas in the CG shifted to concentric remodeling pattern. At 20 weeks, women in the EG had significant lower heart rate (CG: 79,56±10,76 vs. EG: 76,05±9,34; p=0,04), systolic blood pressure (CG: 110,19±10,23 vs. EG: 106,04±12,06; p=0,03); diastolic blood pressure (CG: 64,56±7,88 vs. EG: 61,81±7,15; p=0,03); isovolumetric relaxation time (GC: 72,94±14,71 vs. GE: 67,05±16,48; p=0,04); and a higher deceleration time of E Wave (GC: 142,09±39,11 vs. GE: 162,10±48,59; p=0,01). At 34 weeks, the EG had a significant higher stroke volume (CG: 51,13±11,85 vs. EG: 56,21±12,79 p=0,04), early filling of left ventricular (E) (CG: 78,38±14,07 vs. EG: 85,30±16,62; p=0,02) and deceleration time of E wave (CG: 130,35±37,11 vs. EG:146,61±43,40; p=0,04). Conclusion: Physical regular exercise program during pregnancy may produce positive maternal cardiovascular adaptations during the third trimester of pregnancy. In addition, it helps to control the cardiovascular risk factors without altering maternal and fetus health.