Search

This study focuses on the monitoring, transmission, recognition and detection of snoring signals and their relationship with obstructive sleep apnea. To achieve this purpose, the ESP32 microcontroller and a MEMS technology microphone were used to capture and measure characteristic parameters of snoring signals, such as their intensity, frequency and duration. In addition, the WiFi radio interface was used to send the signals to a server where the information was processed, the snoring was detected, linked to a chatbot in Nodred to show the user in a graphical interface his diagnosis of the snoring level. This comprehensive approach allows real-time, wireless monitoring of snoring, leading to a less invasive diagnosis of obstructive sleep apnea.

Opacities of non-interstitial origin in a pediatric patient's chest radiograph may indicate either consolidations and/or atelectasis, based on the appropriate clinical context. However, the overlapping and complex symptomatology of respiratory tract diseases in pediatric patients can make it difficult for physicians to interpret opacities. Artificial intelligence models are frequently employed by physicians for diagnostic support in healthcare, especially to evaluate aspects of radiographs that are not visible with the naked eye. In this study, a prediction model based on deep learning was used to differentiate between atelectasis and consolidations in pediatric chest radiographs from a clinical perspective. The radiologist can assist pediatricians in diagnosing respiratory pathologies based on the type of opacities using the machine learning model. We used 1297 chest X-ray images of pediatric patients with opacities including consolidations (n=500), atelectasis (n=499); and images without opacities (n=298). The images were preprocessed, and various deep learning models were applied to determine the model with the best metrics. The InceptionV3 model demonstrated a significant improvement over its initial results.

The mobilization of academic research via online platforms presents a troubling paradox. Digital-first publications offer the opportunity for scholars to reach a wider audience, yet this same online vehicle for knowledge mobilization opens scholars to the risk of online abuse. Furthermore, the concept of online abuse is often misunderstood or dismissed by post-secondary institution administrators. The aim of this research is to understand why faculty members who experience online abuse do not report the such abuse to their administration, even though there is indication that support from administration is needed to manage the problem. Drawing from a series of semi-structured interviews and focus groups, this research examines the reasons why faculty members decide not to report their experiences of online abuse to their various academic administrators. A total of 11 faculty members in academic positions located North America agreed to participate in the research. We used a combination of semi-structured and narrative interview questions to understand participants’ experiences of online abuse. The data was coded using the constant comparative approach to identify emergent themes (Glaser & strauss, 1967), a nd guided by the research questions. The Theory of Planned Behavior was used to schematize the attitudes, social norms, and perceived behavioral controls that dissuade reporting of online abuse, and provide institutional recommendations that may encourage reporting and improve support for targeted faculty members. This study contributes to theory and practice by offering that when academic administrators foster a culture of care, faculty would be encouraged to report incidences of online abuse.

Purpose: To evaluate and compare the effectiveness of nearest neighbor (NN)- and variational autoencoder (VAE)-smoothing algorithms to reduce variability and enhance the performance of glaucoma visual field (VF) progression models. Design: Longitudinal cohort study. Subjects: 7150 eyes (4232 patients), with ≥ 5 years of follow-up and ≥ 6 visits. Methods: Vsual field thresholds were smoothed with the NN and VAE algorithms. The mean total deviation (mTD) and VF index rates, pointwise linear regression (PLR), permutation of PLR (PoPLR), and the glaucoma rate index were applied to the unsmoothed and smoothed data. Main Outcome Measures: The proportion of progressing eyes and the conversion to progression were compared between the smoothed and unsmoothed data. A simulation series of noiseless VFs with various patterns of glaucoma damage was used to evaluate the specificity of the smoothing models. Results: The mean values of age and follow-up time were 62.8 (standard deviation: 12.6) years and 10.4 (standard deviation: 4.7) years, respectively. The proportion of progression was significantly higher for the NN and VAE smoothed data compared with the unsmoothed data. VF progression occurred significantly earlier with both smoothed data compared with unsmoothed data based on mTD rates, PLR, and PoPLR methods. The ability to detect the progressing eyes was similar for the unsmoothed and smoothed data in the simulation data. Conclusions: Smoothing VF data with NN and VAE algorithms improves the signal-to-noise ratio for detection of change, results in earlier detection of VF progression, and could help monitor glaucoma progression more effectively in the clinical setting. Financial Disclosure(s): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

IntroductionBipolar disorder (BD) is a chronically progressive mental condition, associated with a reduced quality of life and greater disability. Patient admissions are preventable events with a considerable impact on global functioning and social adjustment. While machine learning (ML) approaches have proven prediction ability in other diseases, little is known about their utility to predict patient admissions in this pathology.AimTo develop prediction models for hospital admission/readmission within 5 years of diagnosis in patients with BD using ML techniques.MethodsThe study utilized data from patients diagnosed with BD in a major healthcare organization in Colombia. Candidate predictors were selected from Electronic Health Records (EHRs) and included sociodemographic and clinical variables. ML algorithms, including Decision Trees, Random Forests, Logistic Regressions, and Support Vector Machines, were used to predict patient admission or readmission. Survival models, including a penalized Cox Model and Random Survival Forest, were used to predict time to admission and first readmission. Model performance was evaluated using accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC) and concordance index.ResultsThe admission dataset included 2,726 BD patients, with 354 admissions, while the readmission dataset included 352 patients, with almost half being readmitted. The best-performing model for predicting admission was the Random Forest, with an accuracy score of 0.951 and an AUC of 0.98. The variables with the greatest predictive power in the Recursive Feature Elimination (RFE) importance analysis were the number of psychiatric emergency visits, the number of outpatient follow-up appointments and age. Survival models showed similar results, with the Random Survival Forest performing best, achieving an AUC of 0.95. However, the prediction models for patient readmission had poorer performance, with the Random Forest model being again the best performer but with an AUC below 0.70.ConclusionML models, particularly the Random Forest model, outperformed traditional statistical techniques for admission prediction. However, readmission prediction models had poorer performance. This study demonstrates the potential of ML techniques in improving prediction accuracy for BD patient admissions.

This paper is born out of conceptual work stimulated in the construction of a literary search engine for the PhoneMe project (www.phonemeproject.com), social media for spoken-word poetry. Drawing on Hiroki Azuma, we explore the ways in which desires are located and consummated through acts of searching and propose a pedagogy of search literacy which embraces spontaneity and accidents to break out of the algorithmic guidance. Azuma sees the postmodern as an historical period characterized by a shift away from grand narratives to database culture, whereby information is consumed not as a cohesive unit stabilized by collectivized narratives, but as a protean association of data fragments made available through searching databases. Such a cultural shift not only transforms the media, but also subjectivity. We propose a theory based on the idea of inadvertent semiosis we call anti-signs. In the database environment, these anti-signs are aggregated to produce the consumers’ Antibody. This Antibody, or one’s algorithmic guide, begins to direct the user’s desires and attentions. We present a way to bring contingency back into the act of searching through prompting glitches to occur–what Azuma calls misdelivery–and through the aesthetic (as opposed to efferent) textual representation of literary search results.

Violence is an almost ubiquitous phenomenon in contemporary digital environments. In this context, there is a growing need to understand how violence is enacted and represented on social media. Drawing from a case study where Colombian young adults discussed the violence they interacted with on their everyday uses of digital platforms, this article explores how violence on social media is experienced and understood by users. Findings emphasize the need to look at violence on digital platforms as a multifaceted, fluid, overlapping, and interconnected phenomenon. In light of these results, I suggest framing current harmful practices as ecologies of violence. To better explore these ecologies, I outline three specific areas that highlight how violence is transformed on social media: practices, contexts, and grammars. Overall, this study emphasizes the need to recognize and address the complexity of violence in social media—a necessary step toward building cultures of peace in and outside of our digital environments.

This article explores the role of literary user preference and experience of contextualizing information in the interpretive responses to poems on PhoneMe, a social media web-platform and mobile app for place-based spoken word poetry. 137 education students in three Canadian universities participated by completing a survey that asked them to choose one of three stylistically distinct poems and subsequently introduced multimodal contextual information about the poet and location inspiring the poem. Findings indicate a productive tension between the reader/user’s interpretive agency with typographic text and the increasing relationality imposed by indexical, transmodal information, thus helping to update Reader Response theory.

Purpose: To report an image analysis pipeline, DDLSNet, consisting of a rim segmentation (RimNet) branch and a disc size classification (DiscNet) branch to automate estimation of the disc damage likelihood scale (DDLS). Design: Retrospective observational. Participants: RimNet and DiscNet were developed with 1208 and 11 536 optic disc photographs (ODPs), respectively. DDLSNet performance was evaluated on 120 ODPs from the RimNet test set, for which the DDLS scores were graded by clinicians. Reproducibility was evaluated on a group of 781 eyes, each with 2 ODPs taken within 4 years apart. Methods: Disc damage likelihood scale calculation requires estimation of optic disc size, provided by DiscNet (VGG19 network), and the minimum rim-to-disc ratio (mRDR) or absent rim width (ARW), provided by RimNet (InceptionV3/LinkNet segmentation model). To build RimNet’s dataset, glaucoma specialists marked optic disc rim and cup boundaries on ODPs. The ''ground truth'' mRDR or ARW was calculated. For DiscNet’s dataset, corresponding OCT images provided ''ground truth'' disc size. Optic disc photographs were split into 80/10/10 for training, validation, and testing, respectively, for RimNet and DiscNet. DDLSNet estimation was tested against manual grading of DDLS by clinicians with the average score used as ''ground truth.'' Reproducibility of DDLSNet grading was evaluated by repeating DDLS estimation on a dataset of nonprogressing paired ODPs taken at separate times. Main Outcome Measures: The main outcome measure was a weighted kappa score between clinicians and the DDLSNet pipeline with agreement defined as ± 1 DDLS score difference. Results: RimNet achieved an mRDR mean absolute error (MAE) of 0.04 (± 0.03) and an ARW MAE of 48.9 (± 35.9) degrees when compared to clinician segmentations. DiscNet achieved 73% (95% confidence interval [CI]: 70%, 75%) classification accuracy. DDLSNet achieved an average weighted kappa agreement of 0.54 (95% CI: 0.40, 0.68) compared to clinicians. Average interclinician agreement was 0.52 (95% CI: 0.49, 0.56). Reproducibility testing demonstrated that 96% of ODP pairs had a difference of ≤ 1 DDLS score. Conclusions: DDLSNet achieved moderate agreement with clinicians for DDLS grading. This novel approach illustrates the feasibility of automated ODP grading for assessing glaucoma severity. Further improvements may be achieved by increasing the number of incomplete rims sample size, expanding the hyperparameter search, and increasing the agreement of clinicians grading ODPs. Financial Disclosure(s): Proprietary or commercial disclosure may be found after the references.

Purpose: Accurate neural rim measurement based on optic disc imaging is important to glaucoma severity grading and often performed by trained glaucoma specialists. We aim to improve upon existing automated tools by building a fully automated system (RimNet) for direct rim identification in glaucomatous eyes and measurement of the minimum rim-to-disc ratio (mRDR) in intact rims, the angle of absent rim width (ARW) in incomplete rims, and the rim-to-disc-area ratio (RDAR) with the goal of optic disc damage grading. Design: Retrospective cross sectional study. Participants: One thousand and twenty-eight optic disc photographs with evidence of glaucomatous optic nerve damage from 1021 eyes of 903 patients with any form of primary glaucoma were included. The mean age was 63.7 (± 14.9) yrs. The average mean deviation of visual fields was −8.03 (± 8.59). Methods: The images were required to be of adequate quality, have signs of glaucomatous damage, and be free of significant concurrent pathology as independently determined by glaucoma specialists. Rim and optic cup masks for each image were manually delineated by glaucoma specialists. The database was randomly split into 80/10/10 for training, validation, and testing, respectively. RimNet consists of a deep learning rim and cup segmentation model, a computer vision mRDR measurement tool for intact rims, and an ARW measurement tool for incomplete rims. The mRDR is calculated at the thinnest rim section while ARW is calculated in regions of total rim loss. The RDAR was also calculated. Evaluation on the Drishti-GS dataset provided external validation (Sivaswamy 2015). Main Outcome Measures: Median Absolute Error (MAE) between glaucoma specialists and RimNet for mRDR and ARW. Results: On the test set, RimNet achieved a mRDR MAE of 0.03 (0.05), ARW MAE of 31 (89)°, and an RDAR MAE of 0.09 (0.10). On the Drishti-GS dataset, an mRDR MAE of 0.03 (0.04) and an mRDAR MAE of 0.09 (0.10) was observed. Conclusions: RimNet demonstrated acceptably accurate rim segmentation and mRDR and ARW measurements. The fully automated algorithm presented here would be a valuable component in an automated mRDR-based glaucoma grading system. Further improvements could be made by improving identification and segmentation performance on incomplete rims and expanding the number and variety of glaucomatous training images.

La evolución en el diseño de aeronaves de combate se ha visto modificada por la inclusión de nuevos parámetros de alta exigencia, dentro de los cuales se incluyen las áreas de investigación relacionadas con la aerodinámica, la furtividad y la optimización en los procesos de operación. El presente artículo contempla el diseño de un Vehículo de Combate Aéreo no Tripulado (UCAV) para la ejecución de misiones de Apoyo Aéreo Cercano (CAS por sus siglas en inglés) en las próximas décadas. Los resultados obtenidos demuestran las habilidades de los UCAV como aeronaves de quinta generación para el reemplazo de flotas reconocidas a nivel mundial (A-10 Thunderbolt II y Sukhoi Su-25) y, además, garantiza su utilidad y viabilidad en los futuros entornos de combate. Así mismo, la investigación se enfoca en una de las variables de mayor discusión respecto a la supervivencia en el combate aéreo, se trata de la furtividad por fenómenos electromagnéticos, con la cual se obtuvieron valores de Sección Equivalente de Radar (RCS) iguales a -24,18 dBsm o representables en un área de detectabilidad de 0,0038 m2 en configuración limpia, de modo que este valor es inferior al de aeronaves furtivas como lo es el Northrop Grumman B-2 Spirit. Finalmente, el diseño permite la operación con un máximo peso de despegue de 61,900 lb y una carga paga de 11,240 lb que se acondicionan a una configuración alar y de estabilizadores para rangos transónicos.

Background: Social annotation (SA) is a genre of learning technology that enables the addition of digital notes to shared texts and affords contextualized peer-to-peer online discussion. A small body of literature examines how SA, as asynchronous online discussion, can contribute to students’ knowledge construction (KC)—or a process whereby learners collaborate through shared socio-cognitive practices. This case study analyzed how SA enabled student participation in seven KC activities, such as interpretation and elaboration. Methods: We analyzed 2,121 annotations written by 59 students in three undergraduate courses at a Canadian University in the first months of 2019. Using a method of open coding and constant comparison, we coded each annotation for evidence of KC activities. Results: Results showed a range of KC activities in students’ SA. Across courses, interpretation was the most common KC activity (40%), followed by elaboration (20%). Annotations that were part of peer-to-peer discussion included all seven types of KC activities, but some activities, such as consensus building, support, and conflict, were almost exclusively found in replies to others. Conclusions: This study suggests that SA is a productive form of online learning through which undergraduate students in multiple disciplinary contexts can interact with peers, make sense of academic content, and construct knowledge by reading and writing together.

Background: Social annotation (SA) is a genre of learning technology that enables the addition of digital notes to shared texts and affords contextualized peer-to-peer online discussion. A small body of literature examines how SA, as asynchronous online discussion, can contribute to students’ knowledge construction (KC)—or a process whereby learners collaborate through shared socio-cognitive practices. This case study analyzed how SA enabled student participation in seven KC activities, such as interpretation and elaboration. Methods: We analyzed 2,121 annotations written by 59 students in three undergraduate courses at a Canadian University in the Winter 2019 semester. Using a method of open coding and constant comparison, we coded each annotation for evidence of KC activities. Results: Results showed a range of KC activities in students’ SA. Across courses, interpretation was the most common KC activity (40%), followed by elaboration (20%). Annotations that were part of peer-to-peer discussion included all seven types of KC activities, but some activities, such as consensus building, support, and conflict, were almost exclusively found in replies to others. Conclusions: This study suggests that SA is a productive form of online learning through which undergraduate students in multiple disciplinary contexts can interact with peers, make sense of academic content, and construct knowledge by reading and writing together.

Review, promotion, and tenure (RPT) processes at universities typically assess candidates along three dimensions: research, teaching, and service. In recent years, some have argued for the inclusion of a controversial fourth criterion: collegiality. While collegiality plays a role in the morale and effectiveness of academic departments, it is amorphic and difficult to assess, and could be misused to stifle dissent or enforce homogeneity. Despite this, some institutions have opted to include this additional element in their RPT documents and processes, but it is unknown the extent of this practice and how it varies across institution type and disciplinary units. This study is based on two sets of data: survey data collected as part of a project that explored the publishing decisions of faculty and how these related to perceived importance in RPT processes, and 864 RPT documents collected from 129 universities from the United States and Canada. We analysed these RPT documents to determine the degree to which collegiality and related terms are mentioned, if they are defined, and if and how they may be assessed during the RPT process. Results show that when collegiality and related terms appear in these documents they are most often just briefly mentioned. It is less common for collegiality and related terms to be defined or assessed in RPT documents. Although the terms are mentioned across all types of institutions, there is a statistically significant difference in how prevalent they are at each. Collegiality is more commonly mentioned in the documents of doctoral research-focused universities (60%), than of master's universities and colleges (31%) or baccalaureate colleges (15%). Results from the accompanying survey of faculty also support this finding: individuals from R-Types were more likely to perceive collegiality to be a factor in their RPT processes. We conclude that collegiality likely plays an important role in RPT processes, whether it is explicitly acknowledged in policies and guidelines or not, and point to several strategies in how it might be best incorporated in the assessment of academic careers.

BackgroundPrevious studies have suggested associations between trends of web searches and COVID-19 traditional metrics. It remains unclear whether models incorporating trends of digital searches lead to better predictions. ObjectiveThe aim of this study is to investigate the relationship between Google Trends searches of symptoms associated with COVID-19 and confirmed COVID-19 cases and deaths. We aim to develop predictive models to forecast the COVID-19 epidemic based on a combination of Google Trends searches of symptoms and conventional COVID-19 metrics. MethodsAn open-access web application was developed to evaluate Google Trends and traditional COVID-19 metrics via an interactive framework based on principal component analysis (PCA) and time series modeling. The application facilitates the analysis of symptom search behavior associated with COVID-19 disease in 188 countries. In this study, we selected the data of nine countries as case studies to represent all continents. PCA was used to perform data dimensionality reduction, and three different time series models (error, trend, seasonality; autoregressive integrated moving average; and feed-forward neural network autoregression) were used to predict COVID-19 metrics in the upcoming 14 days. The models were compared in terms of prediction ability using the root mean square error (RMSE) of the first principal component (PC1). The predictive abilities of models generated with both Google Trends data and conventional COVID-19 metrics were compared with those fitted with conventional COVID-19 metrics only. ResultsThe degree of correlation and the best time lag varied as a function of the selected country and topic searched; in general, the optimal time lag was within 15 days. Overall, predictions of PC1 based on both search terms and COVID-19 traditional metrics performed better than those not including Google searches (median 1.56, IQR 0.90-2.49 versus median 1.87, IQR 1.09-2.95, respectively), but the improvement in prediction varied as a function of the selected country and time frame. The best model varied as a function of country, time range, and period of time selected. Models based on a 7-day moving average led to considerably smaller RMSE values as opposed to those calculated with raw data (median 0.90, IQR 0.50-1.53 versus median 2.27, IQR 1.62-3.74, respectively). ConclusionsThe inclusion of digital online searches in statistical models may improve the nowcasting and forecasting of the COVID-19 epidemic and could be used as one of the surveillance systems of COVID-19 disease. We provide a free web application operating with nearly real-time data that anyone can use to make predictions of outbreaks, improve estimates of the dynamics of ongoing epidemics, and predict future or rebound waves.

As long as there has been violence in organized societies, achieving peace has been a goal through different means, including education. In Colombia –a country where the national government and the guerrilla FARC reached a peace agreement–, education was set to be essential to promote a culture of peace. Accordingly, this article presents a literature review of Cátedra de la Paz, a peace education course that seeks to encourage and strengthen a culture of peace in every educational institution in Colombia. The literature review suggests that, whereas this course reveals a positive impact in the communities, a lack of institutional support –which could stem from larger-scale political and societal conflicts over what peace means and how to achieve it– trumps its implementation. Furthermore, this paper argues that –if Cátedra de la Paz or other future peace education courses aim to promote a culture of peace grounded in contextualized needs and opportunities– critical lenses towards the topics and pedagogy are necessary.

Despite the calls for change, there is significant consensus that when it comes to evaluating publications, review, promotion, and tenure processes should aim to reward research that is of high "quality," is published in "prestigious" journals, and has an "impact." Nevertheless, such terms are highly subjective and present challenges to ascertain precisely what such research looks like. Accordingly, this article responds to the question: how do faculty from universities in the United States and Canada define the terms quality, prestige, and impact of academic journals? We address this question by surveying 338 faculty members from 55 different institutions in the U.S. and Canada. While relying on self-reported definitions that are not linked to their behavior, this study’s findings highlight that faculty often describe these distinct terms in overlapping ways. Additionally, results show that marked variance in definitions across faculty does not correspond to demographic characteristics. This study’s results highlight the subjectivity of common research terms and the importance of implementing evaluation regimes that do not rely on ill-defined concepts and may be context specific.

Reseña de María Mercedes Gómez Gómez y Eulalia Hernández Ciro, Palabras de amor: vida erótica en fragmentos de papel. De la escritura y los relatos populares en el Archivo Histórico Judicial de Medellín, 1900-1950 (Medellín: Sílaba Editores, 2015), 137 pp.

New sources for ancillary services are needed, yet the requirements for service provision in most countries are explicitly formulated for traditional generators. This leads to waste of the potential for new technologies to deliver ancillary services. In order to harness this potential, we propose to parameterize the requirements of ancillary services so that reserves can be built by combining the advantageous properties of different technologies. The proposal is exemplified through a laboratory test where it shown that the system needs can be covered through cheaper and smaller reserves.