Development and external validation of a mixed-effects deep learning model to diagnose COVID-19 from CT imaging.

Background: The automatic analysis of medical images has the potential improve diagnostic accuracy while reducing the strain on clinicians. Current methods analyzing 3D-like imaging data, such as computerized tomography imaging, often treat each image slice as individual slices. This may not be able to appropriately model the relationship between slices. Methods: Our proposed method utilizes a mixed-effects model within the deep learning framework to model the relationship between slices. We externally validated this method on a data set taken from a different country and compared our results against other proposed methods. We evaluated the discrimination, calibration, and clinical usefulness of our model using a range of measures. Finally, we carried out a sensitivity analysis to demonstrate our methods robustness to noise and missing data. Results: In the external geographic validation set our model showed excellent performance with an AUROC of 0.930 (95%CI: 0.914, 0.947), with a sensitivity and specificity, PPV, and NPV of 0.778 (0.720, 0.828), 0.882 (0.853, 0.908), 0.744 (0.686, 0.797), and 0.900 (0.872, 0.924) at the 0.5 probability cut-off point. Our model also maintained good calibration in the external validation dataset, while other methods showed poor calibration. Conclusion: Deep learning can reduce stress on healthcare systems by automatically screening CT imaging for COVID-19. Our method showed improved generalizability in external validation compared to previous published methods. However, deep learning models must be robustly assessed using various performance measures and externally validated in each setting. In addition, best practice guidelines for developing and reporting predictive models are vital for the safe adoption of such models.

Bilateral adaptive graph convolutional network on CT based Covid-19 diagnosis with uncertainty-aware consensus-assisted multiple instance learning.

Coronavirus disease (COVID-19) has caused a worldwide pandemic, putting millions of people's health and lives in jeopardy. Detecting infected patients early on chest computed tomography (CT) is critical in combating COVID-19. Harnessing uncertainty-aware consensus-assisted multiple instance learning (UC-MIL), we propose to diagnose COVID-19 using a new bilateral adaptive graph-based (BA-GCN) model that can use both 2D and 3D discriminative information in 3D CT volumes with arbitrary number of slices. Given the importance of lung segmentation for this task, we have created the largest manual annotation dataset so far with 7,768 slices from COVID-19 patients, and have used it to train a 2D segmentation model to segment the lungs from individual slices and mask the lungs as the regions of interest for the subsequent analyses. We then used the UC-MIL model to estimate the uncertainty of each prediction and the consensus between multiple predictions on each CT slice to automatically select a fixed number of CT slices with reliable predictions for the subsequent model reasoning. Finally, we adaptively constructed a BA-GCN with vertices from different granularity levels (2D and 3D) to aggregate multi-level features for the final diagnosis with the benefits of the graph convolution network's superiority to tackle cross-granularity relationships. Experimental results on three largest COVID-19 CT datasets demonstrated that our model can produce reliable and accurate COVID-19 predictions using CT volumes with any number of slices, which outperforms existing approaches in terms of learning and generalisation ability. To promote reproducible research, we have made the datasets, including the manual annotations and cleaned CT dataset, as well as the implementation code, available at https://doi.org/10.5281/zenodo.6361963.

Validación del índice de fertilidad en endometriosis (EFI) para predecir el embarazo en una población infértil / Validation of fertility index in endometriosis (EFI) to predict pregnancy in an infertile population

Objetivo: Determinar si el Índice de Fertilidad en Endometriosis (EFI) es útil para estimar el pronóstico reproductivo en pacientes infértiles con diagnóstico y tratamiento quirúrgico de endometriosis. Diseño: Estudio de cohorte retrospectivo. Material y Métodos: Se analizaron las historias clínicas de 65 pacientes que consultaron por infertilidad entre Abril de 2011 a Septiembre de 2014 a las cuales se les realizó una videolaparoscopía diagnóstica con los mismos operadores quirúrgicos y con hallazgo de endometriosis. Se excluyeron del análisis todas aquellas pacientes que presentaban factor masculino severo, factor uterino y que realizaron tratamientos de alta complejidad. Los datos de los factores quirúrgicos para la categorización de las pacientes según el EFI fueron obtenidos a través de la visualización de videos de las laparoscopías y los factores históricos se recolectaron de las historias clínicas. Se evaluó la tasa de embarazo luego de 18 meses de seguimiento. Se subdividieron a las pacientes según los valores de EFI obtenidos en 3 grupos y se compararon las tasas acumulativas de embarazos entre dichos grupos. Resultados: La edad promedio de las pacientes fue de 33,5 años (SD=2,7). El tiempo de infertilidad promedio fue de 2,8 años (SD=1,5), y el tipo de infertilidad primaria representó el 80 % de las pacientes. La tasa total de embarazo fue de 47,7%, y según la clasificación del EFI fue 12,5% en el grupo 1, 35,7% en el grupo 2 y 69% en el grupo 3, presentando una tendencia lineal estadísticamente significativa (p=0,002). Conclusiones: Se observó que la probabilidad de embarazo espontáneo o con tratamiento de baja complejidad dentro de los 12 meses posteriores a la laparoscopía fue aumentando significativamente a medida que aumentaba la categorización del EFI. Esto nos permite considerar al EFI como una herramienta útil para estimar el pronóstico reproductivo de las pacientes infértiles con diagnóstico de endometriosis.

Objective: To determine if Endometriosis Fertility Index (EFI) is useful to estimate the reproductive outcome in infertile patients with diagnosis and surgical treatment of endometriosis. Design: Retrospective cohort study. Material and Methods: The medical records of 65 patients who consulted for infertility from April 2011 to September 2014 which underwent a diagnostic videolaparoscopy with the same surgical operators and findings of endometriosis were analyzed. All those patients with severe male factor, cervical factor and those who underwent high complexity treatments were excluded from the analysis. Data from surgical factors for categorization of patients according to EFI was obtained from videos of laparoscopy, and historical factors were collected from medical records. The pregnancy rate was evaluated after an 18- month follow-up. Patients were divided according to EFI values obtained in 3 groups, and cumulative pregnancy rates among these groups were compared. Results: The mean age of the patients was 33.5 years (SD = 2.7). The mean infertility time was 2.8 years (SD = 1.5), and primary infertility accounted for 80% of the patients. The total pregnancy rate was 47.7%, being 12.5% in group 1, 35.7% in group 2 and 69% in group 3. Conclusions: It was observed that in patients with higher EFI category, the probability of spontaneous pregnancy or low complexity treatment was increased within 12 months after laparoscopy, in a statistically significant way (p = 0.002). This allows us to validate the EFI as a useful tool to estimate the reproductive prognosis of infertile patients diagnosed with endometriosis.

Impacto del cambio de malla curricular en la percepción del ambiente educacional en alumnos de enfermería / Impacto da mudança de malha curricular na percepção do ambiente educacional em alunos de enfermagem / Impact of curricular change on the perception of the educational environment by nursing students

Objetivo. Evaluar el impacto del cambio curricular en la percepción del Ambiente Educacional (AE) en alumnos de enfermería. Metodología. Estudio transversal. Se evaluaron dos cohortes consecutivas en segundo año, ingreso 2010 (N: 58) y 2011 (N: 57) para currículo antiguo y nuevo respectivamente. Se aplicó una encuesta sociodemográfica y de percepción del AE mediante el cuestionario Dundee Ready Educational Environment Measure (DREEM). Resultados. No hubo diferencias en las variables sociodemográficas entre las cohortes. Ambos grupos evaluaron el AE más positivo que negativo. El puntaje total promedio de la percepción del AE de la cohorte 2010 fue de 132 puntos y el de la cohorte 2011 de 126 puntos, diferencia que fue estadísticamente significativa. Al analizar los ítemes de la encuesta se observó que existe una peor percepción de la atmósfera de aprendizaje y ambiente social, como también una peor evaluación de las habilidades académicas en la cohorte 2011 comparada con la de 2010. La buena preparación que están recibiendo para la profesión y la relevancia de las materias que están aprendiendo son considerados como fortalezas por los alumnos de los dos grupos. Conclusión. A pesar de lo positivo que pudieran parecer los cambios en el currículo, la percepción del AE en ambas cohortes no alcanza la categoría “excelente”. Es indispensable que se estudie la carga académica que significará para los estudiantes cualquier modificación que se haga en la malla curricular...

Objective. This study sought to evaluate the impact of curricular change on the perception of the Educational Environment (EE) in nursing students. Methodology. This was a cross-sectional study. Two consecutive cohorts were evaluated during the second year, entering 2010 (N: 58) and 2011 (N: 57) for former and new curriculum, respectively. A sociodemographic survey and perception of the EE was applied through the Dundee Ready Educational Environment Measure (DREEM) questionnaire. Results. No differences were detected in the sociodemographic variables between the cohorts. Both groups evaluated EE more positively than negatively. The total average score of the perception of the EE by the 2010 cohort was of 132 points and by the 2011 cohort of 126 points, a statistically significant difference. Upon analyzing the survey items, it was observed that poorer perception exists of the learning atmosphere and of the social environment, as well as poorer assessment of the academic skills in the 2011 cohort compared to the 2010 cohort. The good preparation the students are receiving for the profession and the relevance of the assignments they are learning are considered strengths by the students from both groups. Conclusions. In spite of how positive the curricular changes could seem, perception of the EE in both cohorts does not reach the excellent category. Before any changes are made to the curriculum, it is indispensable to take into account how the academic load might affect the students...

Objetivo. Avaliar o impacto da mudança curricular na percepção do Ambiente Educacional (AE) em alunos de enfermagem. Metodologia. Estudo transversal. Avaliaram-se dois coortes consecutivas em segundo ano, rendimento 2010 (N: 58) e 2011 (N: 57) para currículo antigo e novo respectivamente. Aplicou-se uma enquete sócio-demográfica e de percepção do AE mediante o questionário Dundee Ready Educational Environment Measure (DREEM). Resultados. Não teve diferenças nas variáveis sócio-demográficas entre os coortes. Ambas grupos avaliaram o AE mais positivo que negativo. A pontuação total média da percepção do AE do coorte 2010 foi de 132 pontos e do coorte 2011 de 126 pontos, diferença que foi estatisticamente significativa. Ao analisar os itens da enquete se observou que existe uma pior percepção da atmosfera de aprendizagem e ambiente social, como também uma pior avaliação das habilidades acadêmicas no coorte 2011 comparada com a de 2010. A boa preparação que estão recebendo para a profissão e a relevância das matérias que estão aprendendo são considerados como fortalezas pelos alunos dos dois grupos. Conclusão. Apesar do positivo que pudessem parecer as mudanças no currículo, a percepção do AE em ambos coortes não atinge a categoria “excelente”. É indispensável que para qualquer modificação que se faça na malha curricular, estude-se o ônus acadêmico que significará para os estudantes...

The tools and techniques of evidence-based medicine.

Evidence-based medicine is the conscientious, explicit and judicious use of the current best evidence in making decisions about the care of individual patients. Along with individual clinical expertise, it is a required core skill for clinical problem solving and it is considered to be a comprehensive component of the medical curricula. This chapter is a general overview of the steps to be followed by clinicians to search, identify and appraise the best-available evidence that could help them to resolve a particular clinical problem. It includes the principles for the identification of a clinical problem and its translation into a question, and the main sources for searching and locating the best-available evidence. References for guidelines designed for appraisal of the methods used in the original papers and for the interpretation of its results are also provided.