Novel deep learning method for coronary artery tortuosity detection through coronary angiography.

Coronary artery tortuosity is usually an undetected condition in patients undergoing coronary angiography. This condition requires a longer examination by the specialist to be detected. Yet, detailed knowledge of the morphology of coronary arteries is essential for planning any interventional treatment, such as stenting. We aimed to analyze coronary artery tortuosity in coronary angiography with artificial intelligence techniques to develop an algorithm capable of automatically detecting this condition in patients. This work uses deep learning techniques, in particular, convolutional neural networks, to classify patients into tortuous or non-tortuous based on their coronary angiography. The developed model was trained both on left (Spider) and right (45°/0°) coronary angiographies following a fivefold cross-validation procedure. A total of 658 coronary angiographies were included. Experimental results demonstrated satisfactory performance of our image-based tortuosity detection system, with a test accuracy of (87 ± 6)%. The deep learning model had a mean area under the curve of 0.96 ± 0.03 over the test sets. The sensitivity, specificity, positive predictive values, and negative predictive values of the model for detecting coronary artery tortuosity were (87 ± 10)%, (88 ± 10)%, (89 ± 8)%, and (88 ± 9)%, respectively. Deep learning convolutional neural networks were found to have comparable sensitivity and specificity with independent experts' radiological visual examination for detecting coronary artery tortuosity for a conservative threshold of 0.5. These findings have promising applications in the field of cardiology and medical imaging.

Biometric analysis of healthy coronary arteries in a Chilean population: an angiographic study / Análisis biométrico de arterias coronarias sanas en población chilena: un estudio angiográfico

SUMMARY: Thorough knowledge and understanding of coronary arteries and their anatomy is essential when performing cardiac surgery such as a coronary bypass. Coronary angiography is a minimally invasive method used to evaluate the anatomy and obtain different measurements of the coronary arteries. This study was designed to evaluate the endoluminal diameter, trunk length and anatomical distribution of coronary arteries in Chilean subjects without apparent angiographic lesions. Measurements were carried out by 3 trained examiners using Leonardo® software program in 238 Chilean subjects of both sexes with an age-range of 45 to 78 years. Ostium and the distal luminal segments diameters were measured, as well as trunk length of both right and left coronary arteries. Ostium of the anterior interventricular artery, dominance and tortuosity were also registered. In the right coronary artery, the diameters (3.8 ± 1.2 mm and 3.6 ± 1.0 mm) differed according to sex and dominance, and the length (35.2 ± 12.5 mm) differed according to age. In the left coronary artery, the diameters (4.9 ± 1.1 mm and 4.7 ± 1.0 mm) were greater in males than in females. The left coronary artery showed greater diameters and length than the right coronary artery. The prevalence of right arterial dominance was 88.0 %. Patients with right arterial dominance presented greater distal caliber in the right coronary artery than those with left arterial dominance (p<0.05), especially in older patients. Significant arterial tortuosity was observed in seven subjects.

RESUMEN: Un factor clave durante los procedimientos quirúrgicos cardiacos tal como el bypass coronario, es el conocimiento exhaustivo de las arterias coronarias y su anatomía. La angiografía coronaria es un método mínimamente invasivo que se utiliza para evaluar la anatomía y obtener diferentes medidas. El presente estudio fue diseñado para evaluar el diámetro endoluminal, la longitud del tronco y la distribución anatómica de las arterias coronarias en sujetos chilenos sin lesiones angiográficas significativas. Las mediciones fueron realizadas en 238 sujetos chilenos de ambos sexos con un rango etario entre 45 a 78 años. Tres examinadores preparados llevaron a cabo las mediciones utilizando el software Leonardo®. Se midieron los ostios y los diámetros luminales distales de los troncos coronarios derecho e izquierdo, como también las longitudes del tronco de las arterias coronarias derecha e izquierda. Además, se identificaron los ostios de la arteria interventricular anterior, dominancia y tortuosidad. En la arteria coronaria derecha, los diámetros (3,8 ± 1,2 mm y 3,6 ± 1,0 mm) se observaron variaciones según el sexo y la dominancia, y la longitud (35,2 ± 12,5 mm) difirió según la edad. En la arteria coronaria izquierda, los diámetros (4,9 ± 1,1 mm y 4,7 ± 1,0 mm) fueron mayores en los hombres que en las mujeres. La arteria coronaria izquierda mostró mayor diámetro y longitud que la arteria coronaria derecha. La prevalencia de dominancia arterial derecha fue del 88,0 %. Los pacientes con dominancia arterial derecha presentaron mayor calibre distal en la arteria coronaria derecha que aquellos con dominancia arterial izquierda (p <0,05), especialmente en pacientes mayores. En siete sujetos se observó una tortuosidad arterial significativa.

[Collaborative clinical simulation to train medical students]. / Simulación clínica colaborativa para el desarrollo de competencias de trabajo en equipo en estudiantes de medicina.

In health sciences and medicine, collaborative learning has an important role in the development of competences to solve clinical situations. Adequate cooperation, coordination and communication skills have a direct effect on patient safety. Computer Supported Collaborative Learning (CSCL) and Clinical Simulation (CS), separately, are effective and efficient educational methods to develop competences in undergraduate medical students. To our knowledge, educational models that combine both teaching methods, including a personalized attention of the student, educational infrastructure, materials, teaching techniques and assessment competencies, have not been proposed previously. This article describes the application of a combined model of CSCL and CS for teaching clinical competences to medical students. Since 2015, the collaborative clinical simulation model is part of the training agenda of the Universidad de Talca Medical School in Chile. During 2016 and 2017 it was also applied on students of the Universidad de Barcelona Faculty of Medicine in Spain. According to the experience acquired, implementation of this method is feasible with commonly used resources, although its real efficacy remains to be evaluated.

Simulación clínica colaborativa para el desarrollo de competencias de trabajo en equipo en estudiantes de medicina / Collaborative clinical simulation to train medical students

In health sciences and medicine, collaborative learning has an important role in the development of competences to solve clinical situations. Adequate cooperation, coordination and communication skills have a direct effect on patient safety. Computer Supported Collaborative Learning (CSCL) and Clinical Simulation (CS), separately, are effective and efficient educational methods to develop competences in undergraduate medical students. To our knowledge, educational models that combine both teaching methods, including a personalized attention of the student, educational infrastructure, materials, teaching techniques and assessment competencies, have not been proposed previously. This article describes the application of a combined model of CSCL and CS for teaching clinical competences to medical students. Since 2015, the collaborative clinical simulation model is part of the training agenda of the Universidad de Talca Medical School in Chile. During 2016 and 2017 it was also applied on students of the Universidad de Barcelona Faculty of Medicine in Spain. According to the experience acquired, implementation of this method is feasible with commonly used resources, although its real efficacy remains to be evaluated.

A collaborative clinical simulation model for the development of competencies by medical students.

Herein, we present a new collaborative clinical simulation (CCS) model for the development of medical competencies by medical students. The model is a comprehensive compendium of published considerations and recommendations on clinical simulation (CS) and computer-supported collaborative learning (CSCL). Currently, there are no educational models combining CS and CSCL. The CCS model was designed for the acquisition and assessment of clinical competencies; working collaboratively and supported by technology, small groups of medical students independently design and perform simulated cases. The model includes four phases in which the learning objectives, short case scenarios, materials, indices, and the clinical simulation are designed, monitored, rated and debriefed.

Remodelación ventricular post infarto agudo al miocardio: caso clínico / Ventricular remodeling post acute infarct to myocardium: clinical case

Se presenta el caso de una paciente de 64 años que tras sufrir un IAM, sufre un proceso de remodelación ventricular en un período menor 7 meses que la conduce a una insuficiencia cardíaca severa.