Building a house without foundations? A 24-country qualitative interview study on artificial intelligence in intensive care medicine.

OBJECTIVES: To explore the views of intensive care professionals in high-income countries (HICs) and lower-to-middle-income countries (LMICs) regarding the use and implementation of artificial intelligence (AI) technologies in intensive care units (ICUs). METHODS: Individual semi-structured qualitative interviews were conducted between December 2021 and August 2022 with 59 intensive care professionals from 24 countries. Transcripts were analysed using conventional content analysis. RESULTS: Participants had generally positive views about the potential use of AI in ICUs but also reported some well-known concerns about the use of AI in clinical practice and important technical and non-technical barriers to the implementation of AI. Important differences existed between ICUs regarding their current readiness to implement AI. However, these differences were not primarily between HICs and LMICs, but between a small number of ICUs in large tertiary hospitals in HICs, which were reported to have the necessary digital infrastructure for AI, and nearly all other ICUs in both HICs and LMICs, which were reported to neither have the technical capability to capture the necessary data or use AI, nor the staff with the right knowledge and skills to use the technology. CONCLUSION: Pouring massive amounts of resources into developing AI without first building the necessary digital infrastructure foundation needed for AI is unethical. Real-world implementation and routine use of AI in the vast majority of ICUs in both HICs and LMICs included in our study is unlikely to occur any time soon. ICUs should not be using AI until certain preconditions are met.

[Artificial intelligence in intensive care medicine]. / Künstliche Intelligenz in der Intensivmedizin.

The integration of artificial intelligence (AI) into intensive care medicine has made considerable progress in recent studies, particularly in the areas of predictive analytics, early detection of complications, and the development of decision support systems. The main challenges remain availability and quality of data, reduction of bias and the need for explainable results from algorithms and models. Methods to explain these systems are essential to increase trust, understanding, and ethical considerations among healthcare professionals and patients. Proper training of healthcare professionals in AI principles, terminology, ethical considerations, and practical application is crucial for the successful use of AI. Careful assessment of the impact of AI on patient autonomy and data protection is essential for its responsible use in intensive care medicine. A balance between ethical and practical considerations must be maintained to ensure patient-centered care while complying with data protection regulations. Synergistic collaboration between clinicians, AI engineers, and regulators is critical to realizing the full potential of AI in intensive care medicine and maximizing its positive impact on patient care. Future research and development efforts should focus on improving AI models for real-time predictions, increasing the accuracy and utility of AI-based closed-loop systems, and overcoming ethical, technical, and regulatory challenges, especially in generative AI systems.

YouTube as a Source of Information on Public Health Ethics.

BACKGROUND: Public health ethics (PHE) is a dynamic area within bioethics that addresses the complex moral implications of public health measures in the face of growing health threats. YouTube is a powerful and widely used platform for disseminating health-related information. The primary objective of this study is to assess videos related to PHE on YouTube. The aim is to gauge the extent of misinformation in collecting PHE videos on the platform. METHODS: On October 25, 2023, a thorough investigation on YouTube was undertaken, employing pre-determined search phrases involving 'public health,' 'healthcare,' 'health services administration,' and 'health policy and ethics.' The research encompassed a total of 137 videos that were selected according to strict inclusion and exclusion criteria. The videos were evaluated using the Global Quality Scale to measure quality and the modified DISCERN tool to evaluate reliability. The researchers identified video sources and compared several video attributes across different quality groups. RESULTS: A total of 137 videos were analyzed, and 65 (47.45%) were classified as high quality, 52 (37.23%) as moderate quality, and 21 (15.32%) as low quality. In high-quality videos, academic, government, physician, and university-hospital sources predominated, whereas Internet users and news sources were connected with low-quality videos. Significant differences in DISCERN score, per day views, likes, and comments were seen across the quality groups (P = 0.001 for views per day and P = 0.001 for other characteristics). According to the findings, low-quality videos had higher median values for daily views, likes, and comments. CONCLUSION: Although nearly half of the videos were high-quality, low-quality videos attracted greater attention. Critical contributors to high-quality videos included academic, government, physician, and university-hospital sources. The findings highlight the importance of quality control methods on social media platforms and strategies to direct users to trustworthy health information. Authors should prioritize appropriate citations and evaluate YouTube and other comparable platforms for potential promotional low-quality information.

Sub-Diffraction Correlation of Quantum Emitters and Local Strain Fields in Strain-Engineered WSe2 Monolayers.

Strain-engineering in atomically thin metal dichalcogenides is a useful method for realizing single-photon emitters (SPEs) for quantum technologies. Correlating SPE position with local strain topography is challenging due to localization inaccuracies from the diffraction limit. Currently, SPEs are assumed to be positioned at the highest strained location and are typically identified by randomly screening narrow-linewidth emitters, of which only a few are spectrally pure. In this work, hyperspectral quantum emitter localization microscopy is used to locate 33 SPEs in nanoparticle-strained WSe2 monolayers with sub-diffraction-limit resolution (≈30 nm) and correlate their positions with the underlying strain field via image registration. In this system, spectrally pure emitters are not concentrated at the highest strain location due to spectral contamination; instead, isolable SPEs are distributed away from points of peak strain with an average displacement of 240 nm. These observations point toward a need for a change in the design rules for strain-engineered SPEs and constitute a key step toward realizing next-generation quantum optical architectures.

"When somebody says this is a program for adults, it kind of smacks of pornography": Older adults' opinions on age labels in the public library.

Chronological age is invariably used as a categorizing tool for spaces, collections, and programs in public libraries. Stemming from a larger project that seeks to bring attention to the ways in which public libraries engage with community-dwelling older adults, this paper explores older patrons' perspectives on the language (e.g. older adult, seniors, adult) assigned to older adults in library programs and which label best (or least) suits their sense of identity and, in turn, what language encourages or deters their engagement with library programs. Findings illustrate that age-based language describing older adult library programs is often at odds with patrons' perceptions of how library programming relevant to them ought to be labelled. Common to all participants was a clear dislike for the term "elderly". While most participants preferred "older adult" to "senior", others voiced no preference, as long as they felt heard and valued. Many participants linked the use of language used to describe library programs to being excluded from and treated differently from other library patrons. As such, the language used to group and describe different library populations directly shapes feelings of belonging (or exclusion) in library programs. Insights from this research contribute to our evolving understandings of the ways in which language connected to age can shape one's sense of identity. Results also serve to cultivate a more sensitive and critical approach to the question of age within library science, and, by extension, the experiences of older adults who frequent the library.

Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review.

BACKGROUND: Breast cancer is the most common disease in women. Recently, explainable artificial intelligence (XAI) approaches have been dedicated to investigate breast cancer. An overwhelming study has been done on XAI for breast cancer. Therefore, this study aims to review an XAI for breast cancer diagnosis from mammography and ultrasound (US) images. We investigated how XAI methods for breast cancer diagnosis have been evaluated, the existing ethical challenges, research gaps, the XAI used and the relation between the accuracy and explainability of algorithms. METHODS: In this work, Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist and diagram were used. Peer-reviewed articles and conference proceedings from PubMed, IEEE Explore, ScienceDirect, Scopus and Google Scholar databases were searched. There is no stated date limit to filter the papers. The papers were searched on 19 September 2023, using various combinations of the search terms 'breast cancer', 'explainable', 'interpretable', 'machine learning', 'artificial intelligence' and 'XAI'. Rayyan online platform detected duplicates, inclusion and exclusion of papers. RESULTS: This study identified 14 primary studies employing XAI for breast cancer diagnosis from mammography and US images. Out of the selected 14 studies, only 1 research evaluated humans' confidence in using the XAI system-additionally, 92.86% of identified papers identified dataset and dataset-related issues as research gaps and future direction. The result showed that further research and evaluation are needed to determine the most effective XAI method for breast cancer. CONCLUSION: XAI is not conceded to increase users' and doctors' trust in the system. For the real-world application, effective and systematic evaluation of its trustworthiness in this scenario is lacking. PROSPERO REGISTRATION NUMBER: CRD42023458665.

Defining the Boundaries of Psychiatric and Medical Knowledge: Applying Cartographic Principles to Self-Organising Maps.

Biases in selection, training, and continuing professional development of medical specialists arise in part from reliance upon expert judgement for the design, implementation, and management of medical education. Reducing bias in curriculum development has primarily relied upon consensus processes modelled on the Delphi technique. The application of machine learning algorithms to databases indexing peer-reviewed medical literature can extract objective evidence about the novelty, relevance, and relative importance of different areas of medical knowledge. This study reports the construction of a map of medical knowledge based on the entire corpus of the MEDLINE database indexing more than 30 million articles published in medical journals since the 19th century. Techniques used in cartography to maximise the visually intelligible differentiation between regions are applied to knowledge clusters identified by a self-organising map to show the structure of published psychiatric evidence and its relationship to non-psychiatric medical domains.

Does spatial resolution matter in the estimation of average annual soil loss by using RUSLE?-a study of the Urmodi River Watershed (Maharashtra), India.

The study investigates the influence of multispectral satellite data's spatial resolution on land degradation in the Urmodi River Watershed in which Kaas Plateau, a UNESCO World Heritage site, is located. Specifically, the research focuses on soil erosion and its risk zonation. The study employs Landsat 8 (30-m resolution) and Sentinel-2 (10-m resolution) data to assess soil erosion risk. The Revised Universal Soil Loss Equation (RUSLE) is used to quantify the average annual soil erosion output denoted by (A), by using its factors such as rainfall (R), soil erodibility (K), slope-length (LS), cover management (C), and support practices (P). R-factor was computed from MERRA-2 rainfall data, K-factor was derived from field soil sample-based analysis, LS factor was from Cartosat Digital Elevation Model-based data. The C factor was derived from NDVI of Landsat 8 and Sentinel-2, and the P factor was prepared from LULC derived from Landsat 8, and Sentinel-2 was incorporated in the final integration. The soil erosion hazard map ranged from slight to extremely severe. Remote sensing (RS)-based parameters like Land Use Land Cover (LULC) are derived from the Landsat 8 and Sentine-2 satellite data and used to compute the difference in the final outcome of the integration. The study found similarities in average annual soil loss (A) in plain areas, but differences in final soil erosion risk zone (A) were influenced by LULC map variations due to different cell sizes, P factor, and slope gradient. Notable differences were observed in soil erosion risk categories, particularly in high to very severe zones, with a cumulative difference of 73.85 km2. In addition to this, a scatterplot between the final outputs was computed and found the moderate (R2 = 42.08%) correlation between Landsat 8 and Sentinel-2 imagery-based final average annual soil erosion (A) of RUSLE. The study area encompasses various landforms ranging from the plateau to pediplain, and in such situation, the water-led soil erosion categories vary depending on terrain condition along with its biophysical factors and, hence, need to analyze the need of such factors on the average annual soil erosion quantification. Different spatial resolution has an effect on the final output, and hence, there is a need to track this change at various spatial resolutions. This analysis highlights the significant impact of spatial resolution on land degradation assessment, providing precise identification of surface features and enhancing soil erosion risk zoning accuracy.

The Case for a Defect Genome Initiative.

The Materials Genome Initiative (MGI) has streamlined the materials discovery effort by leveraging generic traits of materials, with focus largely on perfect solids. Defects such as impurities and perturbations, however, drive many attractive functional properties of materials. The rich tapestry of charge, spin, and bonding states hosted by defects are not accessible to elements and perfect crystals, and defects can thus be viewed as another class of "elements" that lie beyond the periodic table. Accordingly, a Defect Genome Initiative (DGI) to accelerate functional defect discovery for energy, quantum information, and other applications is proposed. First, major advances made under the MGI are highlighted, followed by a delineation of pathways for accelerating the discovery and design of functional defects under the DGI. Near-term goals for the DGI are suggested. The construction of open defect platforms and design of data-driven functional defects, along with approaches for fabrication and characterization of defects, are discussed. The associated challenges and opportunities are considered and recent advances towards controlled introduction of functional defects at the atomic scale are reviewed. It is hoped this perspective will spur a community-wide interest in undertaking a DGI effort in recognition of the importance of defects in enabling unique functionalities in materials.

Co-design of patient information leaflets for germline predisposition to cancer: recommendations for clinical practice from the UK Cancer Genetics Group (UKCGG), Cancer Research UK (CRUK) funded CanGene-CanVar Programme and the Association of Genetic Nurse Counsellors (AGNC).

BACKGROUND: Testing for germline pathogenic variants (GPVs) in cancer predisposition genes is increasingly offered as part of routine care for patients with cancer. This is often urgent in oncology clinics due to potential implications on treatment and surgical decisions. This also allows identification of family members who should be offered predictive genetic testing. In the UK, it is common practice for healthcare professionals to provide a patient information leaflet (PIL) at point of care for diagnostic genetic testing in patients with cancer, after results disclosure when a GPV is identified, and for predictive testing of at-risk relatives. Services usually create their own PIL, resulting in duplication of effort and wide variability regarding format, content, signposting and patient input in co-design and evaluation. METHODS: Representatives from UK Cancer Genetics Group (UKCGG), Cancer Research UK (CRUK) funded CanGene-CanVar programme and Association of Genetic Nurse Counsellors (AGNC) held a 2-day meeting with the aim of making recommendations for clinical practice regarding co-design of PIL for germline cancer susceptibility genetic testing. Lynch syndrome and haematological malignancies were chosen as exemplar conditions. RESULTS: Meeting participants included patient representatives including as co-chair, multidisciplinary clinicians and other experts from across the UK. High-level consensus for UK recommendations for clinical practice was reached on several aspects of PIL using digital polling, including that PIL should be offered, accessible, co-designed and evaluated with patients. CONCLUSIONS: Recommendations from the meeting are likely to be applicable for PIL co-design for a wide range of germline genetic testing scenarios.

Tissue ultrasound imaging based on wavelet correlation analysis and pulse-inversion technique.

BACKGROUND: Pulse-inversion-based tissue harmonic imaging has been utilized for many years because it can effectively eliminate the harmonic leakage and produce low side-lobe. However, the pulse inversion method is sensitive to imaging object movements, which may result in motion artifacts. Spatial resolution and contrast were limited. OBJECTIVE: To improve ultrasound image quality by a new pulse-inversion-based tissue harmonic imaging technique. METHODS: Continuous wavelet transform is applied to investigate the correlation between mother wavelet and the received echoes from two opposite pulses. To get a better correlation, a novel mother wavelet named 'tissue wavelet' is designed based on the Khokhlov-Zabolotskaya- Kuznetsov (KZK) wave equation. Radio frequency data were obtained from open Ultrasonix SonixTouch imaging system. Experiments were carried on ultrasonic tissue phantom, human carotid artery and human liver. RESULTS: The average improvement of lateral spatial resolution is 49.52% compared to pulse-inversion-based tissue second-harmonic Imaging (PIHI). Contrast ratio (CR) and contrast-to-noise ratio (CNR) increased by 5.55 dB and 1.40 dB over PIHI. Tissue wavelet performs better than Mexh and Morl wavelet in lateral spatial resolution, CR, and CNR. CONCLUSION: The proposed technique effectively improves the imaging quality in lateral spatial resolution, CR, and CNR.

Application of a Two-Dimensional Mapping-Based Visualization Technique: Nutrient-Value-Based Food Grouping.

Worldwide, several food-based dietary guidelines, with diverse food-grouping methods in various countries, have been developed to maintain and promote public health. However, standardized international food-grouping methods are scarce. In this study, we used two-dimensional mapping to classify foods based on their nutrient composition. The Standard Tables of Food Composition in Japan were used for mapping with a novel technique-t-distributed stochastic neighbor embedding-to visualize high-dimensional data. The mapping results showed that most foods formed food group-based clusters in the Standard Tables of Food Composition in Japan. However, the beverages did not form large clusters and demonstrated scattered distribution on the map. Green tea, black tea, and coffee are located within or near the vegetable cluster whereas cocoa is near the pulse cluster. These results were ensured by the k-nearest neighbors. Thus, beverages made from natural materials can be categorized based on their origin. Visualization of food composition could enable an enhanced comprehensive understanding of the nutrients in foods, which could lead to novel aspects of nutrient-value-based food classifications.

Structural renovation of blocks in build-up area of Jiangnan cities, taking Suzhou new district as an example.

The rationality of block scale and structure is the guarantee of vitality and humanization quality, facing complex and diverse problems, and the structure reconstruction of urban built-up areas is one of the most difficult challenges in the process of promoting the block system. The traditional planning-construction strategy, as practice in recent years has demonstrated, faces challenges in terms of construction costs, demolition costs, property rights, and jurisprudence. Based on the interaction of the block structure and external space, the study presents a "implant-reconstruction" model. It investigates possibilities of implanting elements and graphically depicts the potential impact of implant-reconstruction using Space Syntax. The findings indicate that the external space implantation mode may actively encourage the construction of small-scale blocks and has benefits in terms of texture respect, low impact, and ease of operation. The simulation and pre-judgment dynamically illustrate the viable path and gives a scientific reference for block alteration.

Aprendizaje en investigación clínica: experiencia de enseñanza híbrida con estudiantes de medicina / Learning in Clinical Research: Hybrid Teaching Experience with Medical Students

Introducción: la pandemia de COVID-19 indujo un cambio en nuestro sistema de salud y de educación. Los programas formativos también tuvieron que adaptarse y exigieron un cambio rápido. Objetivos: describir una experiencia educativa de enseñanza virtual/híbrida en investigación clínica, entre docentes del Servicio de Clínica de un hospital universitario y estudiantes de Medicina de una institución privada, que participaron del Programa ESIN (EStudiantes en INvestigación). Metodología: los contenidos y las estrategias educativas incluyeron las clases teóricas audiograbadas o videograbadas (asincrónicas y autoadministradas), el aprendizaje basado en proyectos, los talleres prácticos (encuentros sincrónicos virtuales y grupales), mediante la adopción de modelos de aprendizaje como el aula invertida, y la tutoría individual entre docente-estudiante. Los datos se recopilaron mediante la observación en contextos académicos, y basándonos en elementos de encuestas anónimas de satisfacción, previo consentimiento informado de los participantes. Resultados: participaron 14 estudiantes, 6 durante el año 2021 y 8 durante 2022. Todas mujeres y estudiantes de medicina (50% de cuarto año, 35% de sexto año y 15% de quinto año). Las técnicas implementadas favorecieron la participación y promovieron el aprendizaje activo, basado en proyectos. Mencionaron aspectos positivos como el enfoque académico práctico, la disponibilidad del equipo docente para atender cualquier duda, el tiempo y el entusiasmo por enseñar y fomentar la participación. Los videos teóricos resultaron útiles como herramientas de repaso, y los encuentros grupales fueron especialmente valorados, si bien los encuentros individuales fueron destacados como ayuda y apoyo previo a los congresos científicos. En general, manifestaron que fue una experiencia enriquecedora que demostró que se puede lograr lo que se creía imposible. Todas participaron activamente de al menos un congreso científico, y el 50% resultó coautora de una publicación académica. Conclusión: los estudiantes asumieron compromisos y responsabilidades, e incorporaron competencias y habilidades en la implementación y en la difusión de los proyectos. Esta experiencia educativa facilitó que el tiempo de clase pudiera optimizarse para intercambio, discusión y dudas. Los recursos producidos, las actividades desarrolladas y los contenidos abordados quedan disponibles a nivel institución. (AU)

Introduction: the COVID-19 pandemic brought about a change in our health and education system. Training programs also had to adapt and required rapid change. Objectives: to describe an educational experience of virtual/hybrid teaching in clinical research between teachers of the Clinical Service of a university hospital and medical students of a private institution who participated in the ESIN Program (Students in Research). Methodology: the contents and educational strategies included audio or videotaped lectures (asynchronous and self-administered), project-based learning, practical workshops (virtual and group synchronous meetings) by adopting learning models such as the inverted classroom, and individual tutoring between teacher and student. We gathered the data through observation in academic contexts and based on elements of anonymous satisfaction surveys, with prior informed consent of participants. Results: fourteen students participated, six in 2021 and eight in 2022. All were women and medical students (50% fourth year, 35% sixth year, and 15% fifth year). The techniques implemented favored participation and promoted active, project-based learning. They mentioned positive aspects such as the practical academic approach, the availability of the teaching team for any doubts, the time and enthusiasm for teaching, and encouraging participation. The theory videos were a valuable review tool, and team meetings received high praise even if the one-on-one meetings received much attention as help and support before the scientific congresses. In general, they stated that it was an enriching experience that showed that you can achieve what you thought impossible. All of them actively participated in at least one scientific congress, and 50% were co-authors of an academic publication. Conclusion: the students assumed commitments and responsibilities and incorporated competencies and skills in project implementation and dissemination. This educational experience helped to optimize class time for exchange, discussion, and doubts. The resources produced, the activities developed, and the contents addressed are now available at the institutional level. (AU)

What is critical for human-centered AI at work? - Toward an interdisciplinary theory.

Human-centered artificial intelligence (HCAI) has gained momentum in the scientific discourse but still lacks clarity. In particular, disciplinary differences regarding the scope of HCAI have become apparent and were criticized, calling for a systematic mapping of conceptualizations-especially with regard to the work context. This article compares how human factors and ergonomics (HFE), psychology, human-computer interaction (HCI), information science, and adult education view HCAI and discusses their normative, theoretical, and methodological approaches toward HCAI, as well as the implications for research and practice. It will be argued that an interdisciplinary approach is critical for developing, transferring, and implementing HCAI at work. Additionally, it will be shown that the presented disciplines are well-suited for conceptualizing HCAI and bringing it into practice since they are united in one aspect: they all place the human being in the center of their theory and research. Many critical aspects for successful HCAI, as well as minimum fields of action, were further identified, such as human capability and controllability (HFE perspective), autonomy and trust (psychology and HCI perspective), learning and teaching designs across target groups (adult education perspective), as much as information behavior and information literacy (information science perspective). As such, the article lays the ground for a theory of human-centered interdisciplinary AI, i.e., the Synergistic Human-AI Symbiosis Theory (SHAST), whose conceptual framework and founding pillars will be introduced.

Evaluation of a prototype machine learning tool to semi-automate data extraction for systematic literature reviews.

BACKGROUND: Evidence-based medicine requires synthesis of research through rigorous and time-intensive systematic literature reviews (SLRs), with significant resource expenditure for data extraction from scientific publications. Machine learning may enable the timely completion of SLRs and reduce errors by automating data identification and extraction. METHODS: We evaluated the use of machine learning to extract data from publications related to SLRs in oncology (SLR 1) and Fabry disease (SLR 2). SLR 1 predominantly contained interventional studies and SLR 2 observational studies. Predefined key terms and data were manually annotated to train and test bidirectional encoder representations from transformers (BERT) and bidirectional long-short-term memory machine learning models. Using human annotation as a reference, we assessed the ability of the models to identify biomedical terms of interest (entities) and their relations. We also pretrained BERT on a corpus of 100,000 open access clinical publications and/or enhanced context-dependent entity classification with a conditional random field (CRF) model. Performance was measured using the F1 score, a metric that combines precision and recall. We defined successful matches as partial overlap of entities of the same type. RESULTS: For entity recognition, the pretrained BERT+CRF model had the best performance, with an F1 score of 73% in SLR 1 and 70% in SLR 2. Entity types identified with the highest accuracy were metrics for progression-free survival (SLR 1, F1 score 88%) or for patient age (SLR 2, F1 score 82%). Treatment arm dosage was identified less successfully (F1 scores 60% [SLR 1] and 49% [SLR 2]). The best-performing model for relation extraction, pretrained BERT relation classification, exhibited F1 scores higher than 90% in cases with at least 80 relation examples for a pair of related entity types. CONCLUSIONS: The performance of BERT is enhanced by pretraining with biomedical literature and by combining with a CRF model. With refinement, machine learning may assist with manual data extraction for SLRs.

The Changing Tasks of Medicine and Dermatology in the Twenty-First Century: The Need for Improved Information Capture Tools and Processes.

The delivery of dermatology services has undergone dramatic changes in the past century. The goals and timelines of care have evolved as have the diagnostic and therapeutic tools, resulting in the need to capture and manage information differently, both qualitatively and quantitatively. The predominant and basic office-based ambulatory care model has remained relatively unchanged. Patients and providers interact with minimal pre-visit preparation using the "agenda-less" meeting model. This care model is ill-suited to manage the vastly expanded data capture and processing requirement of twenty-first century dermatology. We have developed novel tools to automate pre-visit data collection which allows for more robust information capture which moves data capture outside of the time-constrained clinic visit. These tools capture structured data, integrate into electronic health records, and create summary reports in real time to assist decision-making. These tools, if scaled, can facilitate the information management needs of dermatology care.