Search

Due to advances in Artificial Intelligence (AI), computer science education has rapidly started to include topics related to AI along K-12 education. Although this development is timely and important, it is also concerning because the elaboration of the AI field for K-12 is still ongoing. Current efforts may significantly underestimate the role of data, the fundamental component of an AI system. If the goal is to enable students to understand how AI systems work, knowledge of key concepts related to data processing is a prerequisite, as data collection, preparation, and engineering are closely linked to the functionality of AI systems. To advance the field, the following research provides a comprehensive collection of key data-related concepts relevant to K-12 computer science education. These concepts were identified through a theoretical review of the AI field, aligned through a review of AI curricula for school education, evaluated through interviews with domain experts and teachers, and structured hierarchically according to the data lifecycle. Computer science educators can use the elaborated structure as a conceptual guide for designing learning arrangements that aim to enable students to understand how AI systems are created and function.

Summary: Background: Surviving sepsis can lead to chronic physical, psychological and cognitive impairments, which affect millions of patients worldwide, including survivors after COVID-19 viral sepsis. We aimed to characterize the magnitude and trajectory of functional dependence and new impairments post-sepsis. Methods: We conducted a prospective cohort study including sepsis survivors who had been discharged from five German intensive care units (ICUs), until 36 months post-discharge. Primary outcome was functional dependence, defined as ≥1 impaired activity of daily living (ADL; 10-item ADL score

Abstract BackgroundDigital health has been taught at medical faculties for a few years. However, in general, the teaching of digital competencies in medical education and training is still underrepresented. ObjectiveThis study aims to analyze the objective acquisition of digital competencies through the implementation of a transdisciplinary digital health curriculum as a compulsory elective subject at a German university. The main subject areas of digital leadership and management, digital learning and didactics, digital communication, robotics, and generative artificial intelligence were developed and taught in a transdisciplinary manner over a period of 1 semester. MethodsThe participants evaluated the relevant content of the curriculum regarding the competencies already taught in advance during the study, using a Likert scale. The participants’ increase in digital competencies were examined with a pre-post test consisting of 12 questions. Statistical analysis was performed using an unpaired 2-tailed Student tP ResultsIn the first year after the introduction of the compulsory elective subject, students of human medicine (n=15), dentistry (n=3), and medical biotechnology (n=2) participated in the curriculum. In total, 13 participants were women (7 men), and 61.1% (n=11) of the participants in human medicine and dentistry were in the preclinical study stage (clinical: n=7, 38.9%). All the aforementioned learning objectives were largely absent in all study sections (preclinical: mean 4.2; clinical: mean 4.4; PP ConclusionsThe transdisciplinary teaching of a digital health curriculum, including digital teaching methods, considers perspectives and skills from different disciplines. Our new curriculum facilitates an objective increase in knowledge regarding the complex challenges of the digital transformation of our health care system. Of the 16 student term papers arising from the course, robotics and artificial intelligence attracted the most interest, accounting for 9 of the submissions.

Medical education is experiencing a paradigm shift towards more interactive and collaborative pedagogical approaches. Barcamps, also known as unconferences, offer an interactive, participant-driven learning approach. This study aims to evaluate the feasibility of using barcamps as an educational model in medical education. Furthermore, the possibility of establishing barcamps in medical education as a pedagogical tool is discussed. The study integrates two evaluations to achieve a multifaceted understanding: a pilot study conducted in 2022 and a subsequent feasibility study in 2023. Participation in the barcamps and their evaluations was voluntary. We combined quantitative data, primarily from post-event evaluations, and qualitative data from open-ended survey questions. These methods were designed to capture a broad range of participant experiences and perceptions. The pilot study in 2022 included 11 participants and produced a response rate for the evaluations. The feasibility study in 2023 had 34 participants but a lower evaluation response rate of 53%. Both barcamps were generally positively evaluated by the participants, indicating a high level of satisfaction and perceived value. Regarding the active participation of participants, the wide range of presented topics highlights the adaptability and flexibility of the barcamp model. Attendees at the pilot mentioned a significantly higher previous experience with barcamps. The study suggests that barcamps are generally well received as an interactive and collaborative educational tool in medical education, reflected by high participant evaluation scores. The wide range of topics presented and discussed indicates that barcamps can accommodate diverse educational needs and interests. However, the study also identified areas for improvement, most notably in the structure of topic plans and the overall learning environment. Finally, the principals for barcamps might adapt to other educational methods by adding more interaction, choice, collaboration, communication, critical thinking, creativity, and caring to the learning process.

The interest in sports performance analysis is rising and tracking data holds high potential for game analysis in team sports due to its accuracy and informative content. Together with machine learning approaches one can obtain deeper and more objective insights into the performance structure. In soccer, the analysis of the defense was neglected in comparison to the offense. Therefore, the aim of this study is to predict ball gains in defense using tracking data to identify tactical variables that drive defensive success. We evaluated tracking data of 153 games of German Bundesliga season 2020/21. With it, we derived player (defensive pressure, distance to the ball, & velocity) and team metrics (inter-line distances, numerical superiority, surface area, & spread) each containing a tactical idea. Afterwards, we trained supervised machine learning classifiers (logistic regression, XGBoost, & Random Forest Classifier) to predict successful (ball gain) vs. unsuccessful defensive plays (no ball gain). The expert-reduction-model (Random Forest Classifier with 16 features) showed the best and satisfying prediction performance (F1-Score (test) = 0.57). Analyzing the most important input features of this model, we are able to identify tactical principles of defensive play that appear to be related to gaining the ball: press the ball leading player, create numerical superiority in areas close to the ball (press short pass options), compact organization of defending team. Those principles are highly interesting for practitioners to gain valuable insights in the tactical behavior of soccer players that may be related to the success of defensive play. [ABSTRACT FROM AUTHOR]

Medical education is experiencing a paradigm shift towards more interactive and collaborative pedagogical approaches. Barcamps, also known as unconferences, offer an interactive, participant-driven learning approach. This study aims to evaluate the feasibility of using barcamps as an educational model in medical education. Furthermore, the possibility of establishing barcamps in medical education as a pedagogical tool is discussed. The study integrates two evaluations to achieve a multifaceted understanding: a pilot study conducted in 2022 and a subsequent feasibility study in 2023. Participation in the barcamps and their evaluations was voluntary. We combined quantitative data, primarily from post-event evaluations, and qualitative data from open-ended survey questions. These methods were designed to capture a broad range of participant experiences and perceptions. The pilot study in 2022 included 11 participants and produced a response rate for the evaluations. The feasibility study in 2023 had 34 participants but a lower evaluation response rate of 53%. Both barcamps were generally positively evaluated by the participants, indicating a high level of satisfaction and perceived value. Regarding the active participation of participants, the wide range of presented topics highlights the adaptability and flexibility of the barcamp model. Attendees at the pilot mentioned a significantly higher previous experience with barcamps. The study suggests that barcamps are generally well received as an interactive and collaborative educational tool in medical education, reflected by high participant evaluation scores. The wide range of topics presented and discussed indicates that barcamps can accommodate diverse educational needs and interests. However, the study also identified areas for improvement, most notably in the structure of topic plans and the overall learning environment. Finally, the principals for barcamps might adapt to other educational methods by adding more interaction, choice, collaboration, communication, critical thinking, creativity, and caring to the learning process. [ABSTRACT FROM AUTHOR]