Computer-Assisted Cohort Identification in Practice

The standard approach to expert-in-the-loop machine learning is active learning, where, repeatedly, an expert is asked to annotate one or more records and the machine finds a classifier that respects all annotations made until that point. We propose an alternative approach, IQRef , in which the expert iteratively designs a classifier and the machine helps him or her to determine how well it is performing and, importantly, when to stop, by reporting statistics on a fixed, hold-out sample of annotated records. We justify our approach based on prior work giving a theoretical model of how to re-use hold-out data. We compare the two approaches in the context of identifying a cohort of EHRs and examine their strengths and weaknesses through a case study arising from an optometric research problem. We conclude that both approaches are complementary, and we recommend that they both be employed in conjunction to address the problem of cohort identification in health research.

Innovation Attributes of F2F Computer Assisted Cooperative Learning in Teaching Reading Skills

This study aimed at investigating the innovation attributes of face-to-face Computer Assisted Cooperative Learning (CACL). It employed a mixed method design as the data were collected through a survey and semi-structured interviews. The findings showed that face to face CACL has a high degree of adoption in higher education institutes to teach EFL/ESL learners. Also, the regression analysis showed that the five factors are strong predictors of innovation adoption with complexity has the highest significance, followed by compatibility, relative advantage, observability and trialability respectively. The study found that accessibility is an emerging innovation attribute which increases the adoption of any innovation practice. The paper concluded that the human element of face-to-face cooperative learning increases the adoption of CACL, and that relative advantage has influence on the other innovation attributes. The study recommends using face-to-face CACL in teaching EFL/ESL learners, and using accessibility as an innovation attribute.

Effect of quercetin or butylated hydroxytoluene on cooled or frozen-thawed ram sperm quality

Cooling and freezing processes cause physical and chemical damage to sperm by cold shock and oxidative stress. This study aimed to evaluate the effect of two antioxidants on sperm parameters of cooled and frozen-thawed ram semen diluted in an egg yolk-based extender. Semen was collected from 30 rams and processed in two consecutive experiments to test the inclusion of different concentrations of quercetin and butylated hydroxytoluene (BHT) in an egg yolk-based semen extender. Dimethyl sulfoxide (DMSO) was added as a solvent to the semen extender in a ratio of 1 mL DMSO for 90 mg of quercetin and 1 mL DMSO for 880 mg of BHT. After collection, semen was diluted at 200 × 106 motile sperm/mL (control) and split into different groups in each experiment. In experiment 1, semen was diluted with the extender containing quercetin (Q5, 5 μg/mL; Q10, 10 μg/mL; Q15, 15 μg/mL) or DMSO alone (DMSO1, 0.055 μL DMSO per mL; DMSO2, 0.165 μL DMSO per mL). In experiment 2, semen was diluted with the extender with BHT (BHT1, 0.5 μg/mL; BHT2, 1 μg/mL; BHT3, 1.5 μg/mL) or DMSO alone (DMSO3, 0.375 μL DMSO per mL; DMSO4, 1.125 μL DMSO per mL). After dilution, the semen was divided into two aliquots. Treated ram sperm samples were also subjected to different storage methods. The first set of samples was cooled at 5 °C for 24 h, whereas the second set of samples was frozen-thawed. Sperm motility parameters and plasma membrane integrity (PMI) were evaluated immediately after dilution (0h) and 24 h after cooling and in the frozen-thawed samples via computer-assisted sperm analysis and epifluorescence microscopy, respectively. The inclusion of quercetin or BHT did not affect sperm motility parameters or PMI of fresh, cooled, or frozen-thawed sperm in this study (P < 0.05). However, further studies are needed to test the effects of these antioxidants on the fertility of cryopreserved ram semen.

Innovation Attributes of F2F Computer-Assisted Cooperative Learning in Teaching Reading Skills

This study aimed at investigating the innovation attributes of face-to-face Computer Assisted Cooperative Learning (CACL). It employed a mixed method design as the data were collected through a survey and semi-structured interviews. The findings showed that face to face CACL has a high degree of adoption in higher education institutes to teach EFL/ESL learners. Also, the regression analysis showed that the five factors are strong predictors of innovation adoption with complexity has the highest significance, followed by compatibility, relative advantage, observability and trialability respectively. The study found that accessibility is an emerging innovation attribute which increases the adoption of any innovation practice. The paper concluded that the human element of face-to-face cooperative learning increases the adoption of CACL, and that relative advantage has influence on the other innovation attributes. The study recommends using face-to-face CACL in teaching EFL/ESL learners, and using accessibility as an innovation attribute.

Intelligent recognition of colorectal cancer combining application of computer-assisted diagnosis with deep learning approaches

<span>The malignancy of the colorectal testing methods has been exposed triumph to decrease the occurrence and death rate; this cancer is the relatively sluggish rising and has an extremely peculiar to develop the premalignant lesions. Now, many patients are not going to colorectal cancer screening, and people who do, are able to diagnose existing tests and screening methods. The most important concept of this motivation for this research idea is to evaluate the recognized data from the immediately available colorectal cancer screening methods. The data provided to laboratory technologists is important in the formulation of appropriate recommendations that will reduce colorectal cancer. With all standard colon cancer tests can be recognized agitatedly, the treatment of colorectal cancer is more efficient. The intelligent computer assisted diagnosis (CAD) is the most powerful technique for recognition of colorectal cancer in recent advances. It is a lot to reduce the level of interference nature has contributed considerably to the advancement of the quality of cancer treatment. To enhance diagnostic accuracy intelligent CAD has a research always active, ongoing with the deep learning and machine learning approaches with the associated convolutional neural network (CNN) scheme.</span>

Toward People’s Community Control of Technology: Race, Access, and Education

This field review explores how the benefits of access to computing for racialized and minoritized communities has become an accepted fact in policy and research, despite decades of evidence that technical fixes do not solve the kinds of complex social problems that disproportionately affect these communities. I use the digital divide framework—a 1990s policy diagnosis that argues that the growth and success of the internet would bifurcate the public into digital “haves” and “have-nots”—as a lens to look at why access to computing frequently appears as a means to achieve economic, political, and social equality for racialized and minoritized communities. First, I present a brief cultural history of computer-assisted instruction to show that widely-held assumptions about the educational utility of computing emerged from utopian narratives about scientific progress and innovation—narratives that also traded on raced and gendered assumptions about users of computers. Next, I use the advent of the digital divide framework and its eventual transformation into digital inequality research to show how those raced and gendered norms about computing and computer users continue to inform research on information and communication technologies (ICTs) used in educational contexts. This is important because the norms implicated in digital divide research are also present in other sites where technology and civic life intersect, including democratic participation, public health, and immigration, among others. I conclude by arguing that naïve or cynical deployments of computing technology can actually harm or exploit the very same racialized and minoritized communities that access is supposed to benefit. In short, access to computing in education—or in any other domain—can only meaningfully contribute to equality when minoritized and racialized communities are allowed to pursue their own collective goals.

A Mask-guided Attention Deep Learning Model for COVID-19 Diagnosis based on an Integrated CT Scan Images Database

<p>The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images.</p><p>The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task baseline and state-of-the-art models, as measured by various popular metrics. In our experiment with different percentages of data from our curated dataset, the classification performance gain from this multi-task learning approach is more significant for the smaller training sizes. Furthermore, experimental results demonstrate that our method enhances the focus on the lesions, as witnessed by both</p><p>attention and attribution maps, resulting in a more interpretable model.</p>

A Mask-guided Attention Deep Learning Model for COVID-19 Diagnosis based on an Integrated CT Scan Images Database

<p>The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images.</p><p>The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task baseline and state-of-the-art models, as measured by various popular metrics. In our experiment with different percentages of data from our curated dataset, the classification performance gain from this multi-task learning approach is more significant for the smaller training sizes. Furthermore, experimental results demonstrate that our method enhances the focus on the lesions, as witnessed by both</p><p>attention and attribution maps, resulting in a more interpretable model.</p>