Assistant Tool Research Articles

Efficient diagnostic classification of diverse pathologies through contextual eye movement data analysis with a novel hybrid architecture

The analysis of eye movements has proven valuable for understanding brain function and the neuropathology of various disorders. This research aims to utilize eye movement data analysis as a screening tool for differentiation between eight different groups of pathologies, including scholar, neurologic, and postural disorders. Leveraging a dataset from 20 clinical centers, all employing AIDEAL and REMOBI eye movement technologies this study extends prior research by considering a multi-annotation setting, incorporating information from recordings from saccade and vergence eye movement tests, and using contextual information (e.g. target signals and latency of the eye movement relative to the target and confidence level of the quality of eye movement recording) to improve accuracy while reducing noise interference. Additionally, we introduce a novel hybrid architecture that combines the weight-sharing feature of convolution layers with the long-range capabilities of the transformer architecture to improve model efficiency and reduce the computation cost by a factor of 3.36, while still being competitive in terms of macro F1 score. Evaluated on two diverse datasets, our method demonstrates promising results, the most powerful discrimination being Attention & Neurologic; with a macro F1 score of up to 78.8%; disorder. The results indicate the effectiveness of our approach in classifying eye movement data from different pathologies and different clinical centers accurately, thus enabling the creation of an assistant tool in the future.

Focal cortical dysplasia lesion segmentation using multiscale transformer

ObjectivesAccurate segmentation of focal cortical dysplasia (FCD) lesions from MR images plays an important role in surgical planning and decision but is still challenging for radiologists and clinicians. In this study, we introduce a novel transformer-based model, designed for the end-to-end segmentation of FCD lesions from multi-channel MR images.MethodsThe core innovation of our proposed model is the integration of a convolutional neural network-based encoder-decoder structure with a multiscale transformer to augment the feature representation of lesions in the global field of view. Transformer pathways, composed of memory- and computation-efficient dual-self-attention modules, leverage feature maps from varying depths of the encoder to discern long-range interdependencies among feature positions and channels, thereby emphasizing areas and channels relevant to lesions. The proposed model was trained and evaluated on a public-open dataset including MR images of 85 patients using both subject-level and voxel-level metrics.ResultsExperimental results indicate that our model offers superior performance both quantitatively and qualitatively. It successfully identified lesions in 82.4% of patients, with a low false-positive lesion cluster rate of 0.176 ± 0.381 per patient. Furthermore, the model achieved an average Dice coefficient of 0.410 ± 0.288, outperforming five established methods.ConclusionIntegration of the transformer could enhance the feature presentation and segmentation performance of FCD lesions. The proposed model has the potential to serve as a valuable assistive tool for physicians, enabling rapid and accurate identification of FCD lesions. The source code and pre-trained model weights are available at https://github.com/zhangxd0530/MS-DSA-NET.Critical relevance statementThis multiscale transformer-based model performs segmentation of focal cortical dysplasia lesions, aiming to help radiologists and clinicians make accurate and efficient preoperative evaluations of focal cortical dysplasia patients from MR images.Key PointsThe first transformer-based model was built to explore focal cortical dysplasia lesion segmentation.Integration of global and local features enhances the segmentation performance of lesions.A valuable benchmark for model development and comparative analyses was provided.Graphical

Navigating the artificial intelligence frontier: Strategic imperatives for safeguarding brand integrity

This paper delves into the transformative era of generative artificial intelligence (GenAI) in marketing, underscoring the vast potential of AI to revolutionise marketing strategies through enhanced personalisation and efficiency while highlighting the rapid adoption rate among companies and marketing professionals. Despite the enthusiasm, it navigates through the apprehensions surrounding job displacement, misinformation and brand safety, offering a comprehensive guide to the strategic adoption of artificial intelligence (AI) with a view to harnessing its benefits without compromising brand integrity. It identifies common pitfalls in AI adoption, such as lack of preparation, myopic focus on current use cases, and neglect of strategic planning, emphasising the importance of a thoughtful, multi-disciplinary approach to AI integration. This includes viewing AI as an assistive tool rather than an end goal, understanding its implications for media, fostering internal leadership, and establishing stringent brand protection guardrails. The paper concludes with a call to action for marketers to embrace AI with strategic foresight, leveraging its revolutionary potential to drive innovation while steadfastly upholding ethical standards and brand values.

Economic impact of a vision-based patient monitoring system across five NHS mental health trusts.

A vision-based patient monitoring system (VBPMS), Oxevision, has been introduced in approximately half of National Health Service (NHS) mental health trusts in England. A VBPMS is an assistive tool that supports patient safety by enabling non-contact physiological and physical monitoring. The system aims to help staff deliver safer, higher-quality and more efficient care. This paper summarises the potential health economic impact of using a VBPMS to support clinical practice in two inpatient settings: acute mental health and older adult mental health services. The economic model used a cost calculator approach to evaluate the potential impact of introducing a VBPMS into clinical practice, compared with clinical practice without a VBPMS. The analysis captured the cost differences in night-time observations, one-to-one continuous observations, self-harm incidents, and bedroom falls at night, including those resulting in A&E visits and emergency service callouts. The analysis is based on before and after studies conducted at five mental health NHS trusts, including acute mental health and older adult mental health services. Our findings indicate that the use of a VBPMS results in more efficient night-time observations and reductions in one-to-one observations, self-harm incidents, bedroom falls at night, and A&E visits and emergency service callouts from night-time falls. Substantial staff time in acute mental health and older adult mental health services is spent performing night-time observations, one-to-one observations, and managing incidents. The use of a VBPMS could lead to cost savings and a positive return on investment for NHS mental health trusts. The results do not incorporate all of the potential benefits associated with the use of a VBPMS, such as reductions in medication and length of hospital stay, plus the potential to avoid adverse events which would otherwise have a detrimental impact on a patient's quality of life.

Instance segmentation of cells and nuclei from multi-organ cross-protocol microscopic images.

Light microscopy is a widely used technique in cell biology due to its satisfactory resolution for cellular structure analysis, prevalent availability of fluorescent probes for staining, and compatibility for the dynamic analysis of live cells. However, the segmentation of cells and nuclei from microscopic images is not a straightforward process because it has several challenges such as high variation in morphology and shape, the presence of noise and diverse contrast in backgrounds, clustering or overlapping nature of cells. Dealing with these challenges and facilitating more reliable analysis necessitates the implementation of computer-aided methods that leverage image processing techniques and deep learning algorithms. The major goal of this study is to propose a model, for instance segmentation of cells and nuclei, applying the most cutting-edge deep learning techniques. A fine-tuned You Only Look at Once version 9 extended (YOLOv9-E) model is initially applied as a prompt generator to generate bounding box prompts. Using the generated prompts, a pre-trained segment anything model (SAM) is subsequently applied through zero-short inferencing to produce raw segmentation masks. These segmentation masks are then refined using non-max suppression and simple image processing methods such as image addition and morphological processing. The proposed method is developed and evaluated using an open-sourced dataset called Expert Visual Cell Annotation (EVICAN), which is relatively large and contains 4,738 microscopy images extracted from cross organs using different protocols. Based on the evaluation results on three different levels of EVICAN test sets, the proposed method demonstrates noticeable performances showing average mAP50 [mean average precision at intersection over union (IoU) =0.50] scores of 96.25, 95.05, and 94.18 for cell segmentation, and 68.04, 54.66, and 38.29 for nucleus segmentation on easy, medium, and difficult test sets, respectively. Our proposed method for instance segmentation of cells and nuclei provided favorable performance compared to the existing methods in literature, indicating its potential utility as an assistive tool for cell culture experts, facilitating prompt and reliable analysis.

A Lightweight Visual Understanding System for Enhanced Assistance to the Visually Impaired Using an Embedded Platform

Visually impaired individuals often face significant challenges in navigating their environments due to limited access to visual information. To address this issue, a portable, cost-effective assistive tool is proposed to operate on a low-power embedded system such as the Jetson Nano. The novelty of this research lies in developing an efficient, lightweight video captioning model within constrained resources to ensure its compatibility with embedded platforms. This research aims to enhance the autonomy and accessibility of visually impaired people by providing audio descriptions of their surroundings through the processing of live-streaming videos. The proposed system utilizes two distinct lightweight deep learning modules: an object detection module based on the state-of-the-art YOLOv7 model, and a video captioning module that utilizes both the Video Swin Transformer and 2D-CNN for feature extraction, along with the Transformer network for caption generation. The goal of the object detection module is for providing real-time multiple object identification in the surrounding environment of the blind while the video captioning module is to provide detailed descriptions of the entire visual scenes and activities including objects, actions, and relationships between them. The user interacts via a headphone with the proposed system using a specific audio command to trigger the corresponding module even object detection or video captioning and receiving an audio description output for the visual contents. The system demonstrates satisfactory results, achieving inference speeds between 0.11 to 1.1 seconds for object detection and 0.91 to 1.85 seconds for video captioning, evaluated through both quantitative metrics and subjective assessments.

Technology-Powered Multilingual Professional and Technical Writing: An Integrative Literature Review of Landmark and the Latest Writing Assistance Tools

Technology-Powered Multilingual Professional and Technical Writing: An Integrative Literature Review of Landmark and the Latest Writing Assistance Tools

Artificial intelligence-powered tools and academic writing: to use or not to use ChatGPT

PurposeThis study investigates the potential effectiveness of ChatGPT in enhancing the academic writing skills of Saudi EFL undergraduate students. It also examines the challenges associated with its use and suggests effective ways to address them in the education sector.Design/methodology/approachThe study employed a sequential mixed-methods approach, which involved distributing questionnaires to gather data from students, followed by conducting semi-structured interviews with a purposeful selection of eight students and six teachers.FindingsThe findings revealed that students were generally satisfied with the effectiveness of ChatGPT in enhancing their academic writing skills. However, they also pinpointed some challenges associated with using ChatGPT, including plagiarism, overreliance, inadequate documentation, threats to academic integrity, and inaccurate information. To alleviate these challenges, effective strategies include deploying detection tools, equipping students and educators with training sessions, and revisiting academic policies and assessment methods. It is recommended that ChatGPT be used responsibly as an assistant tool, in conjunction with students' ideas and teachers' feedback. This approach can significantly enhance students' writing skills and facilitate completing their research projects and assignments.Practical implicationsChatGPT can be a valuable tool in the educational landscape, but it is essential to use it judiciously. Therefore, teachers' effective integration of ChatGPT into their classrooms can significantly enhance students' writing abilities and streamline their research process.Originality/valueThis study contributes to recent AI-based research and provides practical insights on the responsible integration of ChatGPT into education while addressing potential challenges.

A Study of Central Bank Swap Line Use: Are They a Suitable Tool for the IMF in Maintaining Central Bank Liquidity for Developing Countries?

Developing countries do not have the same access for swap line use during times of economic stress, currently used by central banks in developed countries to maintain liquidity. Biblically, economic tools should favor all and not just developed nations. As Christians we are commanded to help others by bearing the burden of others and to help the poor. Of course, biblical wisdom is necessary, specifically an understanding of how exactly swap lines may be of benefit before making any recommendations, along with and considering the reality of level of risk when working with developing nations. Swap lines are a currency exchange between two banks where an agreed upon amount is traded-- a liquidity swap between two banks. The research on swap line use is limited, especially when related to use by developing countries. Since developing nations are more vulnerable to economic stress, expanding the use of swap lines from developed countries to developing nations appears reasonable and the IMF being the lender of last resort is the recommended organization to use them. The purpose of the study is to determine if swap lines maintain or improve liquidity between central banks during times of economic stress, which in turn will be considered for feasibility as an additional financial assistance tool the IMF can use for developing countries. A pragmatic mixed approach will be used to determine if swap lines are improving liquidity conditions with the capacity to deliver U.S. dollar funding to institutions in their jurisdiction during times of market stress. The comparisons consider capital flow and foreign exchange rate differences between countries that used swap lines and countries not using swap lines during periods of economic stress. The results will be considered for use by the IMF for developing countries.

A Novel Personalized Strategy for Hip Joint Flexion Assistance Based on Human Physiological State.

Soft exosuits have emerged as potent assistive tools for walking support and rehabilitation training. However, most existing soft exosuit systems rely on preset assistance modes, which may not accurately align with individual physiological states and movement requirements, leading to variable user experiences and efficacy. While existing human-in-the-loop (HIL) research predominantly focuses on optimizing metabolic cost and torque difference parameters, there is a notable absence of real-time monitoring methods that closely reflect the human body's physiological state and strategies that dynamically indicate walking efficiency. Motivated by this, we developed a novel personalized power-assist system. This system optimizes the power-assist output of the hip joint by monitoring the user's physiological and motion signals in real time, including heart rate (HR), blood oxygen saturation (SpO2), and inertial measurement unit (IMU) data, to assist hip flexion based on feedback. The findings from a metabolic expenditure trial demonstrate that the innovative soft exosuit, which is based on a Physiological State Monitoring Control (PSMC) system, achieves a reduction of 7.81% in metabolic expenditure during treadmill walking at a speed of 3.5 km/h compared to walking without the assistance of the exosuit. Additionally, during continuous exercise with varying intensities, the metabolic consumption level is reduced by 5.1%, 5.8%, and 8.2% at speeds of 2, 4, and 6 km per hour, respectively. These results support the design of a novel hip flexion-assisting soft exosuit, demonstrating that applying different assistance forces in consideration of different physiological states is a reasonable approach to reducing metabolic consumption.

Assistant Tools for Medical Diagnostics through Rough Set-Based Data Analysis

Assistant Tools for Medical Diagnostics through Rough Set-Based Data Analysis

Explainable machine learning for assessing upper respiratory tract of racehorses from endoscopy videos

Laryngeal hemiplegia (LH) is a major upper respiratory tract (URT) complication in racehorses. Endoscopy imaging of horse throat is a gold standard for URT assessment. However, current manual assessment faces several challenges, stemming from the poor quality of endoscopy videos and subjectivity of manual grading. To overcome such limitations, we propose an explainable machine learning (ML)-based solution for efficient URT assessment. Specifically, a cascaded YOLOv8 architecture is utilized to segment the key semantic regions and landmarks per frame. Several spatiotemporal features are then extracted from key landmarks points and fed to a decision tree (DT) model to classify LH as Grade 1,2,3 or 4 denoting absence of LH, mild, moderate, and severe LH, respectively. The proposed method, validated through 5-fold cross-validation on 107 videos, showed promising performance in classifying different LH grades with 100%, 91.18%, 94.74% and 100% sensitivity values for Grade 1 to 4, respectively. Further validation on an external dataset of 72 cases confirmed its generalization capability with 90%, 80.95%, 100%, and 100% sensitivity values for Grade 1 to 4, respectively. We introduced several explainability related assessment functions, including: (i) visualization of YOLOv8 output to detect landmark estimation errors which can affect the final classification, (ii) time-series visualization to assess video quality, and (iii) backtracking of the DT output to identify borderline cases. We incorporated domain knowledge (e.g., veterinarian diagnostic procedures) into the proposed ML framework. This provides an assistive tool with clinical-relevance and explainability that can ease and speed up the URT assessment by veterinarians.

Effect of sonoprocessing on the quality of plant-based analog foods: Compatibility to sustainable development goals, drawbacks and limitations

Sonoprocessing (US), as one of the most well-known and widely used green processing techniques, has tremendous benefits to be used in the food industry. The urgent call for global sustainable food production encourages the usage of such techniques more often and effectively. Using ultrasound as a hurdle technology synergistically with other green methods is crucial to improving the efficiency of the protein shift as well as the number of plant-based analog foods (PBAFs) against conventional products. It was revealed that the US has a significant impact when used as an assistant tool with other green technologies rather than being used alone. It increases the protein extraction efficiencies from plant biomasses, improves the techno-functional properties of food compounds, and makes them more applicable for industrial-scale alternative food production in the circular economy. The US aligns well with the objectives outlined in the UN’s Sustainable Development Goals (SDGs), and Planetary Boundaries (PBs) framework, demonstrating promising outcomes in life cycle assessment. However, several challenges such as uncontrolled complex matrix effect, free radical formation, uncontrolled microbial growth/germination or off-flavor formation, removal of aromatic compounds, and Maillard reaction, are revealed in an increased number of studies, all of which need to be considered. In addition to a variety of advantages, this review also discusses the drawbacks and limitations of US focusing on PBAF production.

OligoM-Cancer: A multidimensional information platform for deep phenotyping of heterogenous oligometastatic cancer

Patients with oligometastatic cancer (OMC) exhibit better response to local therapeutic interventions and a more treatable tendency than those with polymetastatic cancers. However, studies on OMC are limited and lack effective integration for systematic comparison and personalized application, and the diagnosis and precise treatment of OMC remain controversial. The application of large language models in medicine remains challenging because of the requirement of high-quality medical data. Moreover, these models must be enhanced using precise domain-specific knowledge. Therefore, we developed the OligoM-Cancer platform (http://oligo.sysbio.org.cn), pioneering knowledge curation that depicts various aspects of oligometastases spectrum, including markers, diagnosis, prognosis, and therapy choices. A user-friendly website was developed using HTML, FLASK, MySQL, Bootstrap, Echarts, and JavaScript. This platform encompasses comprehensive knowledge and evidence of phenotypes and their associated factors. With 4059 items of literature retrieved, OligoM-Cancer includes 1345 valid publications and 393 OMC-associated factors. Additionally, the included clinical assistance tools enhance the interpretability and credibility of clinical translational practice. OligoM-Cancer facilitates knowledge-guided modeling for deep phenotyping of OMC and potentially assists large language models in supporting specialised oligometastasis applications, thereby enhancing their generalization and reliability.

A human-centric methodology for the co-evolution of operators’ skills, digital tools and user interfaces to support the Operator 4.0

The concept of Operator 4.0 has been recently defined to evolve the modern industrial scenarios by defining a knowledge sharing process from/to operators and industrial systems, creating personalized skills, and introducing digital tools towards socially sustainable factories. In this context, dynamic and adaptive user interfaces can make humans part of the intelligent factory system, supporting human work contextually and providing specific contents when needed, preserving the human wellbeing. This paper defines a human-centric methodology for the symbiotic co-evolution of operators’ skills, assistive digital tools and user interfaces, developed within the Horizon Europe project titled “DaCapo - Digital assets and tools for Circular value chains and manufacturing products”. The project focuses on defining a new set of human-centric digital tools and services for the manufacturing industry capable of boosting the application of circular economy (CE) throughout the manufacturing value chains. The proposed methodology can link the specific needs of an industrial case to the definition of the most proper assistive digital tools and functionalities to drive the design of adaptive, proactive user interfaces for the Operator 4.0. The method has been applied and validated on one of the project use cases, involving a manufacturing company operating in warehousing and logistics.

Intraoperative ultrasound and magnetic resonance comparative analysis in brain tumor surgery: a valuable tool to flatten ultrasound's learning curve.

Intraoperative ultrasound (IOUS) is a profitable tool for neurosurgical procedures' assistance, especially in neuro-oncology. It is a rapid, ergonomic and reproducible technique. However, its known handicap is a steep learning curve for neurosurgeons. Here, we describe an interesting postoperative analysis that provides extra feedback after surgery, accelerating the learning process. We conducted a descriptive retrospective unicenter study including patients operated from intra-axial brain tumors using neuronavigation (Curve, Brainlab) and IOUS (BK-5000, BK medical) guidance. All patients had preoperative Magnetic Resonance Imaging (MRI) prior to tumor resection. During surgery, 3D neuronavigated IOUS studies (n3DUS) were obtained through craniotomy N13C5 transducer's integration to the neuronavigation system. At least two n3DUS studies were obtained: prior to tumor resection and at the resection conclusion. A postoperative MRI was performed within 48h. MRI and n3DUS studies were posteriorly fused and analyzed with Elements (Brainlab) planning software, permitting two comparative analyses: preoperative MRI compared to pre-resection n3DUS and postoperative MRI to post-resection n3DUS. Cases with incomplete MRI or n3DUS studies were withdrawn from the study. From April 2022 to March 2024, 73 patients were operated assisted by IOUS. From them, 39 were included in the study. Analyses comparing preoperative MRI and pre-resection n3DUS showed great concordance of tumor volume (p < 0,001) between both modalities. Analysis comparing postoperative MRI and post-resection n3DUS also showed good concordance in residual tumor volume (RTV) in cases where gross total resection (GTR) was not achieved (p < 0,001). In two cases, RTV detected on MRI that was not detected intra-operatively with IOUS could be reviewed in detail to recheck its appearance. Post-operative comparative analyses between IOUS and MRI is a valuable tool for novel ultrasound users, as it enhances the amount of feedback provided by cases and could accelerate the learning process, flattening this technique's learning curve.

Weakly-supervised learning-based pathology detection and localization in 3D chest CT scans.

Recent advancements in anomaly detection have paved the way for novel radiological reading assistance tools that support the identification of findings, aimed at saving time. The clinical adoption of such applications requires a low rate of false positives while maintaining high sensitivity. In light of recent interest and development in multi pathology identification, we present a novel method, based on a recent contrastive self-supervised approach, for multiple chest-related abnormality identification including low lung density area ("LLDA"), consolidation ("CONS"), nodules ("NOD") and interstitial pattern ("IP"). Our approach alerts radiologists about abnormal regions within a computed tomography (CT) scan by providing 3Dlocalization. We introduce a new method for the classification and localization of multiple chest pathologies in 3D Chest CT scans. Our goal is to distinguish four common chest-related abnormalities: "LLDA", "CONS", "NOD", "IP" and "NORMAL". This method is based on a 3D patch-based classifier with a Resnet backbone encoder pretrained leveraging recent contrastive self supervised approach and a fine-tuned classification head. We leverage the SimCLR contrastive framework for pretraining on an unannotated dataset of randomly selected patches and we then fine-tune it on a labeled dataset. During inference, this classifier generates probability maps for each abnormality across the CT volume, which are aggregated to produce a multi-label patient-level prediction. We compare different training strategies, including random initialization, ImageNet weight initialization, frozen SimCLR pretrained weights and fine-tuned SimCLR pretrained weights. Each training strategy is evaluated on a validation set for hyperparameter selection and tested on a test set. Additionally, we explore the fine-tuned SimCLR pretrained classifier for 3D pathology localization and conduct qualitativeevaluation. Validated on 111 chest scans for hyperparameter selection and subsequently tested on 251 chest scans with multi-abnormalities, our method achieves an AUROC of 0.931 (95% confidence interval [CI]: [0.9034, 0.9557], -value < 0.001) and 0.963 (95% CI: [0.952, 0.976], -value < 0.001) in the multi-label and binary (i.e., normal versus abnormal) settings, respectively. Notably, our method surpasses the area under the receiver operating characteristic (AUROC) threshold of 0.9 for two abnormalities: IP (0.974) and LLDA (0.952), while achieving values of 0.853 and 0.791 for NOD and CONS, respectively. Furthermore, our results highlight the superiority of incorporating contrastive pretraining within the patch classifier, outperforming Imagenet pretraining weights and non-pretrained counterparts with uninitialized weights (F1 score = 0.943, 0.792, and 0.677 respectively). Qualitatively, the method achieved a satisfactory 88.8% completeness rate in localization and maintained an 88.3% accuracy rate against falsepositives. The proposed method integrates self-supervised learning algorithms for pretraining, utilizes a patch-based approach for 3D pathology localization and develops an aggregation method for multi-label prediction at patient-level. It shows promise in efficiently detecting and localizing multiple anomalies within a singlescan.

International Language Literacy: Technical Assistance in Proofreading Scientific Articles for Publication in Accredited Journals

This study aims to explore and analyse the process of technical assistance in proofreading scientific articles and measure its impact on the quality of writing and chances of publication in accredited journals. Technical assistance consists of six stages: (1) Needs Identification, (2) Training, (3) Individual Mentoring, (4) Use of Assistance Tools, (5) Evaluation and Feedback, and (6) Application of Results &amp; Submit Articles. This research uses mixed methods, with data collection through questionnaires and documentation. The study population was 20 students, all of whom were sampled using a purposive sampling technique. The mentoring process involved 2 experts and 3 proofreaders. The results showed that this service activity produced 20 articles that were eligible for submission, with an initial score of 420 (70.00%) increasing to 478 (79.67%) at 78.33%. The articles have been written according to the template, corrected, translated, checked for plagiarism, and submitted to Sinta accredited national journals, with details: 1 article to S-5 journal, 14 articles to S-4 journal, 1 article to S-3 journal, 2 articles to S-2 journal, and 2 articles to international proceedings. This research shows that technical assistance is effective in improving the quality of scientific articles and publication opportunities in accredited journals. The findings can serve as a reference for educational and research institutions in developing similar programmes to increase the productivity of scientific publications.

Identifying student profiles in a digital mental rotation task: insights from the 2017 NAEP math assessment

Mental rotation (MR), a key aspect of spatial reasoning, is highly predictive of success in STEM fields. This study analyzed strategies employed by 27,600 eighth-grade students during a digital MR task from the 2017 National Assessment of Educational Progress (NAEP) in mathematics. Utilizing K-means cluster analysis to categorize behavioral and performance patterns, we identified four distinct profiles: Cognitive Offloaders (15% of the sample), Internal Visualizers (55%), External Visualizers (5%), and Non-Triers (25%). Cognitive Offloaders, skilled at minimizing cognitive load by eliminating incorrect options, demonstrated the highest MR accuracy rates at 45%. Internal Visualizers, relying less on digital tools and more on mental strategies, achieved robust performance with an average score of 38%. External Visualizers, despite their extensive use of assistive tools and greater time investment, scored an average of 36%. Non-Triers showed minimal engagement and correspondingly the lowest performance, averaging 29%. These findings not only underscore the diverse strategies students adopt in solving MR tasks but also emphasize the need for educational strategies that are tailored to accommodate different cognitive styles. By integrating MR training into the curriculum and enhancing teacher preparedness to support diverse learning needs, this study advocates for educational reforms to promote equitable outcomes in mathematics and broader STEM fields.

Attitude of aspiring orthopaedic surgeons towards artificial intelligence: a multinational cross-sectional survey study

IntroductionThe purpose of this study was to evaluate the perspectives of aspiring orthopaedic surgeons on artificial intelligence (AI), analysing how gender, AI knowledge, and technical inclination influence views on AI. Additionally, the extent to which recent AI advancements sway career decisions was assessed.Materials and methodsA digital survey was distributed to student members of orthopaedic societies across Germany, Switzerland, and Austria. Subgroup analyses explored how gender, AI knowledge, and technical inclination shape attitudes towards AI.ResultsOf 174 total respondents, 86.2% (n = 150) intended to pursue a career in orthopaedic surgery and were included in the analysis. The majority (74.5%) reported ‘basic’ or ‘no’ knowledge about AI. Approximately 29.3% believed AI would significantly impact orthopaedics within 5 years, with another 35.3% projecting 5–10 years. AI was predominantly seen as an assistive tool (77.8%), without significant fear of job displacement. The most valued AI applications were identified as preoperative implant planning (85.3%), administrative tasks (84%), and image analysis (81.3%). Concerns arose regarding skill atrophy due to overreliance (69.3%), liability (68%), and diminished patient interaction (56%). The majority maintained a ‘neutral’ view on AI (53%), though 32.9% were ‘enthusiastic’. A stronger focus on AI in medical education was requested by 81.9%. Most participants (72.8%) felt recent AI advancements did not alter their career decisions towards or away from the orthopaedic specialty. Statistical analysis revealed a significant association between AI literacy (p = 0.015) and technical inclination (p = 0.003). AI literacy did not increase significantly during medical education (p = 0.091).ConclusionsFuture orthopaedic surgeons exhibit a favourable outlook on AI, foreseeing its significant influence in the near future. AI literacy remains relatively low and showed no improvement during medical school. There is notable demand for improved AI-related education. The choice of orthopaedics as a specialty appears to be robust against the sway of recent AI advancements.Level of evidenceCross-sectional survey study; level IV.