Search

• medBERT.de : German BERT model tailored for medical domain expertise. • Trained using 4.7 million diverse medical documents for optimal results. • Achieved new state-of-the-art on eight medical NLP benchmarks. • Efficient tokenization has minor role, focus on domain-specific training. • Public release of pre-trained model weights and new benchmarks for research. This paper presents medBERT.de , a pre-trained German BERT model specifically designed for the German medical domain. The model has been trained on a large corpus of 4.7 Million German medical documents and has been shown to achieve new state-of-the-art performance on eight different medical benchmarks covering a wide range of disciplines and medical document types. In addition to evaluating the overall performance of the model, this paper also conducts a more in-depth analysis of its capabilities. We investigate the impact of data deduplication on the model's performance, as well as the potential benefits of using more efficient tokenization methods. Our results indicate that domain-specific models such as medBERT.de are particularly useful for longer texts, and that deduplication of training data does not necessarily lead to improved performance. Furthermore, we found that efficient tokenization plays only a minor role in improving model performance, and attribute most of the improved performance to the large amount of training data. To encourage further research, the pre-trained model weights and new benchmarks based on radiological data are made publicly available for use by the scientific community. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) offers opportunities but also challenges for biomedical research and healthcare. This position paper shares the results of the international conference "Fair medicine and AI" (online 3–5 March 2021). Scholars from science and technology studies (STS), gender studies, and ethics of science and technology formulated opportunities, challenges, and research and development desiderata for AI in healthcare. AI systems and solutions, which are being rapidly developed and applied, may have undesirable and unintended consequences including the risk of perpetuating health inequalities for marginalized groups. Socially robust development and implications of AI in healthcare require urgent investigation. There is a particular dearth of studies in human-AI interaction and how this may best be configured to dependably deliver safe, effective and equitable healthcare. To address these challenges, we need to establish diverse and interdisciplinary teams equipped to develop and apply medical AI in a fair, accountable and transparent manner. We formulate the importance of including social science perspectives in the development of intersectionally beneficent and equitable AI for biomedical research and healthcare, in part by strengthening AI health evaluation. • Bias, discrimination and structural injustice for medical AI are an overlooked issue. • AI for biomedical research and healthcare should be beneficent and equitable. • Social science perspectives within AI for medicine development are essential. • Challenges are multifold and an agenda for future research is needed. • Qualitative, ethnographic and participatory approaches could help provide fairer AI. [ABSTRACT FROM AUTHOR]

Medical use cases for machine learning (ML) are growing exponentially. The first hospitals are already using ML systems as decision support systems in their daily routine. At the same time, most ML systems are still opaque and it is not clear how these systems arrive at their predictions. In this paper, we provide a brief overview of the taxonomy of explainability methods and review popular methods. In addition, we conduct a systematic literature search on PubMed to investigate which explainable artificial intelligence (XAI) methods are used in 450 specific medical supervised ML use cases, how the use of XAI methods has emerged recently, and how the precision of describing ML pipelines has evolved over the past 20 years. A large fraction of publications with ML use cases do not use XAI methods at all to explain ML predictions. However, when XAI methods are used, open-source and model-agnostic explanation methods are more commonly used, with SHapley Additive exPlanations (SHAP) and Gradient Class Activation Mapping (Grad-CAM) for tabular and image data leading the way. ML pipelines have been described in increasing detail and uniformity in recent years. However, the willingness to share data and code has stagnated at about one-quarter. XAI methods are mainly used when their application requires little effort. The homogenization of reports in ML use cases facilitates the comparability of work and should be advanced in the coming years. Experts who can mediate between the worlds of informatics and medicine will become more and more in demand when using ML systems due to the high complexity of the domain. [Display omitted] • We estimate that only 16 % of the reported explainability methods could be understood by patients. • The distribution of data types for explainable ML applications for tabular | image | text | audio data is 51 % | 32 % | 3 % | 0 %. • The quality of the description of machine learning pipelines increased in recent years with more homogeneity. • The data and code sharing ratio stagnated in about one quarter. • Most popular explainability methods are SHAP, LIME, and Grad-CAM. [ABSTRACT FROM AUTHOR]

• Daily or circadian rhythms are physiological and behavioural rhythms that occur over a roughly 24-hour period. • These bodily rhythms have been largely overlooked by historians of health and medicine. • How circadian rhythms are understood to affect health and disease varies across cultural and temporal contexts. • Henri Lefebvre's concept of rhythmanalysis offers a methodology for new research in 'rhythmic history'. Rhythm characterizes life on Earth. Daily physiological rhythms of eating and fasting, sleeping and waking, moving and resting, are common to almost all life forms which evolved under the solar light–dark cycle. Despite their ubiquity, historians of health and medicine have yet to grapple with the lived experiences of these daily rhythms in the past. This paper presents a potential new research agenda in 'rhythmic history' that understands rhythmicity as something which lies between biology and culture. Thinking with rhythms offers exciting opportunities to unite previously disparate historical studies of daily rhythms like eating and sleeping and opens up a new way to view the enmeshed connections between body and environment. In this paper, I take inspiration from the scientific concept of the 'zeitgeber' ('time giver'), coined by the German chronobiologist Jürgen Aschoff, to frame a review of current literature relating to rhythms and explore Henry Lefebvre's notion of 'rhythmanalysis' as a methodological tool for historians undertaking 'rhythmic histories'. [ABSTRACT FROM AUTHOR]

Over the last two decades, augmented reality (AR) has led to the rapid development of new interfaces in various fields of social and technological application domains. One such domain is medicine, and to a higher extent surgery, where these visualization techniques help to improve the effectiveness of preoperative and intraoperative procedures. Following this trend, this paper presents SLIMBRAIN, a real-time acquisition and processing AR system suitable to classify and display brain tumor tissue from hyperspectral (HS) information. This system captures and processes HS images at 14 frames per second (FPS) during the course of a tumor resection operation to detect and delimit cancer tissue at the same time the neurosurgeon operates. The result is represented in an AR visualization where the classification results are overlapped with the RGB point cloud captured by a LiDAR camera. This representation allows natural navigation of the scene at the same time it is captured and processed, improving the visualization and hence effectiveness of the HS technology to delimit tumors. The whole system has been verified in real brain tumor resection operations. [ABSTRACT FROM AUTHOR]

Background: Despite the growing interest in health data science education, it is not embedded in undergraduate medical curricula and little is known about best teaching practices. This paper presents a highly innovative course in a UK university that introduces undergraduate medical students to data science. It also discusses a study on student perspectives on the learning and teaching of health data science.Methods: The pedagogical design elements of the Data Science in Medicine course are discussed, along with its syllabus, assessment methodology and flipped classroom delivery. The course has been offered to approximately 630 students over three years. Student perspectives were investigated through three focus groups with the participation of 19 students across different study years in medicine. An experiment was conducted regarding instructor-led vs. video-based modalities of online programming labs, with the participation of 8 students.Results: The course has led to improved data competency among medical students and to a positive change in their opinions about data science. Motivating the course and showing relevance to clinical practice was one of the biggest challenges. Statistics was perceived by focus group participants as an essential data skill. Including data science in the medical curriculum was perceived as important by Year 1 students, while opinions varied between Year 4/5 participants. Video-based online labs were preferred over instructor-led online labs, and they were found to be more useful and enjoyable, without leading to any significant difference in academic performance.Conclusions: Teaching data science to undergraduate medicine students is highly desirable and feasible. We recommend including statistics in the curriculum and practical skill development through simple and clinically-relevant data science tasks, supported through video-based online labs. Further reporting on similar courses is needed, as well as larger-scale studies on student perspectives. [ABSTRACT FROM AUTHOR]