Search

Reviewing learned knowledge is critical in the learning process. Testing the learning content instead of restudying, which is known as the testing effect, has been demonstrated to be an effective review strategy. However, education research recommends that instructors generate practice tests, but this burdens teachers and may also hinder teaching quality. To resolve this issue, the current study applied a modern artificial intelligence technique (BERT) to automate the generation of tests and evaluate the testing effect through e-books in a university lecture (N = 74). The last 5 minutes of each course session were utilized to review the taught content by having students either answer cloze item questions or restudy the summary of the core concepts covered in the lecture. A reading comprehension pretest was conducted before the experiment to ensure that the differences in prior knowledge were nonsignificant between groups, and a posttest was performed to examine the effectiveness of testing. In addition, we evaluated students' reading skills and reading engagement through their ability to identify key concepts and their interaction with e-books, respectively. A positive effect was observed for students who engaged in cloze item practice before the end of each class. The results indicated that the repeated testing group exhibited significantly better reading skills and engaged more with e-books than the restudying group did. More importantly, compared with only restudying the key concepts, answering the cloze items questions significantly improved students' reading comprehension. Our results suggest that machine-generated cloze testing may benefit learning in higher education.

Research has revealed the positive effects of flipped classroom approaches on students' learning engagement and performance compared with conventional lecture-based classrooms. However, because of a lack of out-of-class learning support, many students fail to comprehensively prepare the provided lecture materials before class. One promising solution to this problem is recommendation systems in the educational area, which have been instrumental in helping learners identify useful and relevant lecture materials that satisfy their learning needs. Thus, in this study, we propose a summarized lecture material recommendation system, which is integrated into an e-book reading system as an enhancement of the flipped classroom approach. This system helps students identify pages that contain essential knowledge that must be thoroughly studied before class. The proposed system was constructed on the basis of our previous work. In this study, a quasi-experiment was conducted in a graduate course that implemented the flipped classroom model: experimental group students learned with the proposed system, whereas the control group students had no access to the additional features. The findings of this study suggest that students who learn with the proposed recommendation system significantly outperform those who learn without the system in a flipped classroom in terms of their learning outcomes and engagement in preclass preparation.

Precision education is now recognized as a new challenge of applying artificial intelligence, machine learning, and learning analytics to improve both learning performance and teaching quality. To promote precision education, digital learning platforms have been widely used to collect educational records of students' behavior, performance, and other types of interaction. On the other hand, the increasing volume of students' learning behavioral data in virtual learning environments provides opportunities for mining data on these students' learning patterns. Accordingly, identifying students' online learning patterns on various digital learning platforms has drawn the interest of the learning analytics and educational data mining research communities. In this study, the authors applied data analytics methods to examine the learning patterns of students using an ebook system for one semester in an undergraduate course. The authors used a clustering approach to identify subgroups of students with different learning patterns. Several subgroups were identified, and the students' learning patterns in each subgroup were determined accordingly. In addition, the association between these students' learning patterns and their learning outcomes from the course was investigated. The findings of this study provide educators opportunities to predict students' learning outcomes by analyzing their online learning behaviors and providing timely intervention for improving their learning experience, which achieves one of the goals of learning analytics as part of precision education.

Precision education is a new challenge in leveraging artificial intelligence, machine learning, and learning analytics to enhance teaching quality and learning performance. To facilitate precision education, text marking skills can be used to determine students' learning process. Text marking is an essential learning skill in reading. In this study, we proposed a model that leverages the state-of-the-art text summarization technique, Bidirectional Encoder Representations from Transformers (BERT), to calculate the marking score for 130 graduate students enrolled in an accounting course. Then, we applied learning analytics to analyze the correlation between their marking scores and learning performance. We measured students' self-regulated learning (SRL) and clustered them into four groups based on their marking scores and marking frequencies to examine whether differences in reading skills and text marking influence students' learning performance and awareness of self-regulation. Consistent with past research, our results did not indicate a strong relationship between marking scores and learning performance. However, high-skill readers who use more marking strategies perform better in learning performance, task strategies, and time management than high-skill readers who use fewer marking strategies. Furthermore, high-skill readers who actively employ marking strategies also achieve superior scores of environment structure, and task strategies in SRL than low-skill readers who are inactive in marking. The findings of this research provide evidence supporting the importance of monitoring and training students' text marking skill and facilitating precision education.

This article explores the application of generative artificial intelligence (GAI) and large language models (LLMs) in the field of gastroenterology and hepatology. It introduces the concept of prompt engineering, which involves optimizing user inputs to guide LLMs in generating desired outputs. The article discusses the goals of prompt engineering, such as task completion and in-context learning, and explains the core elements of a prompt. It also examines different approaches to prompting and the roles of system, user, and assistant in the interaction with LLMs. The article concludes by emphasizing the importance of prompt engineering in improving the performance of LLMs in extracting data from research articles, while acknowledging the limitations of this approach. [Extracted from the article]

Artificial intelligence (AI) systems have increasingly achieved expert-level performance in medical imaging applications. However, there is growing concern that such AI systems may reflect and amplify human bias, and reduce the quality of their performance in historically under-served populations such as female patients, Black patients, or patients of low socioeconomic status. Such biases are especially troubling in the context of underdiagnosis, whereby the AI algorithm would inaccurately label an individual with a disease as healthy, potentially delaying access to care. Here, we examine algorithmic underdiagnosis in chest X-ray pathology classification across three large chest X-ray datasets, as well as one multi-source dataset. We find that classifiers produced using state-of-the-art computer vision techniques consistently and selectively underdiagnosed under-served patient populations and that the underdiagnosis rate was higher for intersectional under-served subpopulations, for example, Hispanic female patients. Deployment of AI systems using medical imaging for disease diagnosis with such biases risks exacerbation of existing care biases and can potentially lead to unequal access to medical treatment, thereby raising ethical concerns for the use of these models in the clinic. Artificial intelligence algorithms trained using chest X-rays consistently underdiagnose pulmonary abnormalities or diseases in historically under-served patient populations, raising ethical concerns about the clinical use of such algorithms., Author(s): Laleh Seyyed-Kalantari [sup.1] [sup.2] , Haoran Zhang [sup.3] , Matthew B. A. McDermott [sup.3] , Irene Y. Chen [sup.3] , Marzyeh Ghassemi [sup.2] [sup.3] Author Affiliations: (1) University of [...]

Classical biological control aims to actively manage threats that cause immense losses in biological diversity. The introduction of a biological control agent Colletotrichum gloeosporioides f. sp. miconiae (Cgm) in April 2000 to Tahiti, French Polynesia was intended to control the massive spread of an invasive weed Miconia calvescens. However, while Cgm has subsequently spread to Mo’orea, its impact on reducing M. calvescens remains uncertain. The main objectives of this study are: (1) to quantify the amount of the fungal pathogen infecting the M. calvescens plants at three elevation ranges on Mo’orea, (2) to understand the impact of moisture on the proliferation of disease development, and (3) to test the influence of endophytic fungal communities on the competitive ability of Cgm. Results from quantifying leaf damage showed that at higher elevations, Cgm disease development is more rampant. In laboratory experiments, varying moisture did not significantly affect the health of the seedling. While Cgm growth rate correlates with competitive ability, endophytic fungal growth rate does not, leading to speculation that other modes such as chemical interactions allow for endophytic competitive ability. Lastly, data supports the hypothesis that Cgm becomes a better competitor against the endophytic fungal species at higher elevations. Results of this study suggest that other microclimatic factors such as temperature and humidity may play a role in disease development. While Cgm may decelerate the growth of M. calvescens, Cgm alone is not likely to obliterate the massive damage M. calvescens has done on the native flora of Mo’orea and its surrounding islands. Conservation biologists must urgently attack this pest, or the fragile ecosystem of the islands will lead to massive losses in biological diversity.

Pleomorphic dermal sarcoma (PDS) is a rare dermal-based mesenchymal tumor that shares histologic characteristics with atypical fibroxanthoma (AFX), but demonstrates aggressive features increasing the risk of local recurrence or metastases. We report a unique case of a 62-year-old man with a recent history of left-groin PDS, now with a 2-cm pedunculated left tonsillar mass and two hypermetabolic nodules in the left thyroid. Microscopically, the tonsillar biopsy demonstrated infiltrating spindle cell neoplasm composed of highly pleomorphic tumor cells with abundant mitoses. The left hemithyroidectomy specimen also demonstrated similar pleomorphic spindled tumor cells infiltrating thyroid parenchyma with perineural invasion and focal osseous and chondroid components. Immunohistochemically, both tumors were diffusely positive for smooth muscle actin. Focal nonspecific positive staining with p53, SATB2, and S100 was observed in the thyroid tumor. Additional markers, including p40, CK5, p63, pancytokeratin, CAM5.2, S100, SOX10, Melan-A, HMB45, CD45, CD68, CD163, caldesmon, p16, TTF1, PAX8, and calcitonin, were all negative. INI-1 expression was retained. Molecular analysis showed that the tumor harbored PDGFRA deletion of exon 9 and amplification, PTCH1 A300fs*24, MDM2 amplification, CDKN2A/B loss, and FRS2 amplification. Compared with the patient's groin tumor, the current tumors showed similar morphology. Overall, the histologic and immunohistochemical findings are consistent with metastatic PDS to the tonsil and thyroid. Although PDS is commonly found on the sun-exposed skin in the elderly, this case highlights an unusual primary site as well as peculiar locations for the metastasis of PDS. Treatment and management of the patient are also considered. [ABSTRACT FROM AUTHOR]

Ameloblastic carcinoma is a rare malignant neoplasm arising from the odontogenic epithelium. Ameloblastic carcinoma commonly occurs de novo affecting the posterior segments of the mandible. Presently, only less than 100 cases have been reported arising from the maxilla. We report a unique case of maxillary ameloblastic carcinoma in a 68-year-old male with a 5.6 cm positron emission tomography (PET) avid left maxillary sinus mass. The patient underwent a left maxillectomy which revealed hyperchromatic and pleomorphic tumor cells arranged in a nested and trabecular architecture. The tumor cells showed distinct peripheral palisading with reverse polarization. Areas of bone destruction, necrosis, lymphovascular and perineural invasions, as well as atypical mitoses, were identified. Immunohistochemically, the tumor cells were positive for keratin cocktail (AE1/AE3 and CAM 5.2), keratin 19, p40, and weakly positive for MDM2, while negative for calretinin. Molecular analysis revealed wild-type BRAF ; however, alterations in CDKN2A / B, MTAP, RB1, SMARCA4, STK11, FGF12, SETD2, and TP53 were present. This histopathologic and molecular profile supported the diagnosis of ameloblastic carcinoma. There has been no evidence of disease recurrence or metastasis eleven months after the initial diagnosis. [ABSTRACT FROM AUTHOR]

Increasing organizations and educational institutions have implemented virtual learning communities to encourage knowledge sharing. However, this task can not be accomplished simply by grouping people together and telling them "sharing your knowledge will make you learn better". This research attempts to examine the factors influencing knowledge sharing from the perspective of human behavior. Theory of Planned Behavior is integrated with social network ties and empirical findings from virtual learning community literature to develop the research model. The current research model comprises eight hypotheses to explore questions of whether social network ties, learners' attitude toward knowledge sharing, learners' beliefs of their capabilities in performing online knowledge sharing, and subjective norms relate to knowledge sharing intention, which leads to actual behavior in a virtual learning environment. This study empirically validates the hypothesized relationships using a field survey of college students and MBA students enrolling courses conducted in a virtual learning community. Attitude, subjective norm, Web-specific self-efficacy and social network ties are shown to be good predictors of knowledge sharing intention which, in turn, is significantly associated with knowledge sharing behavior. Knowledge creation self-efficacy does not significantly impact knowledge sharing intention. (Contains 3 tables and 2 figures.)

Virtual learning communities encourage members to learn and contribute knowledge. However, knowledge sharing requires mutual-trust collaboration between learners and the contribution of quality knowledge. This task cannot be accomplished by simply storing learning content in repositories. It requires a mechanism to help learners find relevant learning content as well as knowledgeable collaborators to work with. In this paper, we present a peer-to-peer based social network to enhance the quality of e-learning regarding knowledge sharing in virtual learning communities. From a technical viewpoint, we will present advanced semantic search mechanisms for finding quality content and trustworthy collaborators. From the social viewpoint, we will address how to support a trustworthy social network that encourages learners to share. Results of this research demonstrate that applying such mechanisms to knowledge sharing can improve the quality of e-learning in virtual learning communities. (Contains 5 figures and 2 tables.)