Background: The aim of this study is to validate a deep learning model for the classification of breast density according to American College of Radiology's breast density patterns.Methods: A convolutional neural network was developed with 10,229 digital screening mammogram images. Once the network was developed and tested, its performance was evaluated before a group of six professionals, the majority report and a commercial software application. We selected randomly 451 new mammographic images from different studies and patients. The categorization process by professionals was repeated in two stages.Results: The agreement between the convolutional neural network and the majority report was k=0.64 (95% CI: 0.58–0.69) in the first stage and k=0.57 (95% CI: 0.52–0.63) in the second stage. The agreement between the CNN and the commercial software application was k=0.54 (95% CI: 0.48–0.60). In both cases, we observed that the concordances of the CNN were within or above the range of professionals' concordances values.Conclusions: Considering the internal reference standard (majority report) and the external reference standard (commercial software application), we can affirm the CNN achieved professional level performance.

Objective: To determine the level of agreement within and between observers in the categorization of breast density on mammograms in a group of professionals using the fifth edition of the American College of Radiology's BI-RADS (R) Atlas and to analyze the concordance between experts' categorization and automatic categorization by commercial software on digital mammograms. Methods: Six radiologists categorized breast density on 451 mammograms on two occasions one month apart. We calculated the linear weighted kappa coefficients for inter- and intra-observer agreement for the group of radiologists and between the commercial software and the majority report. We analyzed the results for the four categories of breast density and for dichotomous classification as dense versus not dense. Results: The interobserver agreement among radiologists and the majority report was between moderate and nearly perfect for the analysis by category (kappa=0.64 to 0.84) and for the dichotomous classification (kappa=0.63 to 0.84). The intraobserver agreement was between substantial and nearly perfect (kappa=0.68 to 0.85 for 4 categories and k=0.70 to 0.87 for the dichotomous classification). The agreement between the majority report and the commercial software was moderate both for the four categories (kappa = 0.43) and for the dichotomous classification (kappa = 0.51). Conclusion: Agreement on breast density within and between radiologists using the criteria established in the fifth edition of the BI-RADS (R) Atlas was between moderate and nearly perfect. The level of agreement between the specialists and the commercial software was moderate. (C) 2020 SERAM. Published by Elsevier Espana, S.L.U. All rights reserved.

Determinar el acuerdo intra- e interobservador en la categorización de la densidad mamográfica entre un grupo de profesionales según la 5.a edición del Atlas BI-RADS® - ACR y analizar la concordancia entre la categorización de los expertos y un software comercial de un mamógrafo digital para categorización automática. 6 médicos categorizaron la densidad mamográfica de 451 mamografías en dos oportunidades con un intervalo de 1 mes. Calculamos los coeficientes kappa ponderados lineales de acuerdo inter- e intraobservador para el grupo médico y la concordancia entre el software comercial y el reporte de la mayoría. Analizamos los resultados para las cuatro categorías de densidad mamaria y para el resultado dicotómico de mama densa/no densa. El acuerdo interobservador entre especialistas y el reporte de la mayoría fue moderado y casi perfecto para el análisis por categoría (κ = 0,64 a 0,84) y de manera dicotómica (κ = 0,63 a 0,84). El acuerdo intraobservador fue sustancial y casi perfecto (κ = 0,68 a 0,85 para 4 categorías y k = 0,70 a 0,87 para el análisis dicotómico). El acuerdo entre el reporte de la mayoría y el software comercial fue moderado tanto por categoría (κ = 0,43) como en el análisis dicotómico (κ = 0,51). Hemos observado un acuerdo entre moderado y casi perfecto inter- e intraobservador entre los radiólogos, según los criterios establecidos en la 5.ª edición del Atlas BI-RADS®. El nivel de acuerdo entre el reporte de los especialistas y un software disponible comercialmente fue moderado. To determine the level of agreement within and between observers in the categorization of breast density on mammograms in a group of professionals using the fifth edition of the American College of Radiology's BI-RADS® Atlas and to analyze the concordance between experts’ categorization and automatic categorization by commercial software on digital mammograms. Six radiologists categorized breast density on 451 mammograms on two occasions one month apart. We calculated the linear weighted kappa coefficients for inter- and intra-observer agreement for the group of radiologists and between the commercial software and the majority report. We analyzed the results for the four categories of breast density and for dichotomous classification as dense versus not dense. The interobserver agreement among radiologists and the majority report was between moderate and nearly perfect for the analysis by category (κ = 0.64 to 0.84) and for the dichotomous classification (κ = 0.63 to 0.84). The intraobserver agreement was between substantial and nearly perfect (κ = 0.68 to 0.85 for 4 categories and k = 0.70 to 0.87 for the dichotomous classification). The agreement between the majority report and the commercial software was moderate both for the four categories (κ = 0.43) and for the dichotomous classification (κ = 0.51). Agreement on breast density within and between radiologists using the criteria established in the fifth edition of the BI-RADS® Atlas was between moderate and nearly perfect. The level of agreement between the specialists and the commercial software was moderate.

Transgender people experience their gender identity as different from the sex assigned to them at birth and/or those listed on their legal identification. A Master Patient Index (MPI) is a centralized index of all patients in a health care system. The objective of this work was to describe the designed strategies and adapting of a MPI that contemplates transgender patient registration needs as regards as health and legal context.

Under-reporting of adverse drug events (ADEs) is a common issue across healthcare systems, and lack of integration with clinical workflow and systems are among the leading causes of this problem. We sought to describe the development of an ADEs reporting system within an EHR that represents user needs and captures relevant data. We compared periods before and after the implementation, and describe the corresponding reporting rates.

The aim of this article was to know physician perceptions about a PHR for inpatients and to examine ways to take advantage of possible functionalities that could help physicians in their daily workflow. This qualitative research, was conducted through: two focus groups and nine personal interviews performed with internal medicine physicians. Collection and analysis of obtained data was carried out by two professionals. It was made by the codification and categorization of data based on a process of constant comparison. The authors agreed upon three main dimensional themes: information, physician-patient/relatives communication, impact of PHR in physician workload. Physicians suggested functionalities and expressed concerns related to the management of sensitive information. As a conclusion we understand that it is crucial to involve physicians along PHR's development. This will help to overcome barriers and will improve adoption chances. Physicians will be directly affected by the implementation of a PHR for inpatients.

In this communication we identify strategies for effectively documenting Sexual Orientation and Gender Identity in Electronic Health Records. For this review a multidisciplinary group composed by three physicians, a nurse, an engineer and a lawyer analyzed the evidence in bibliography related to the topic and summarized the results. After analyzing the information, we summarized and classified them into three major topics: To request, to store and to display and access to the information. How to standardize those data and where data specifically will be populated in EHRs have not been answered yet. The target of all of these efforts should be: to be sensitive with the needs of the patient and to ensure high quality of care.

On May 2016, our institution implemented a redesign of the personal health record (PHR) with the aim of enhancing its use. The objective of this research was to know and to understand end users' opinions as regards PH functionalities and the difficulties they have addressed while using the new PHR version. Research was based on a self administered survey, patient interviews and focus groups performed with out-patients. Topics examined: ways of access to the PHR log-in web page, frequency of use, type of device, most used functionalities, the different uses patients gave to PHR, perception as regards the redesign. This research allowed us to know the uses patients give to the PHR in this institution and to understand the difficulties they found in what refers to its re-design. This information constitutes the clue to motivate and accompany PHR users in the process of adoption of a patient portal.