Clinical Learning Research Articles

Examining the challenges of blood pressure estimation via photoplethysmogram

The use of observed wearable sensor data (e.g., photoplethysmograms [PPG]) to infer health measures (e.g., glucose level or blood pressure) is a very active area of research. Such technology can have a significant impact on health screening, chronic disease management and remote monitoring. A common approach is to collect sensor data and corresponding labels from a clinical grade device (e.g., blood pressure cuff) and train deep learning models to map one to the other. Although well intentioned, this approach often ignores a principled analysis of whether the input sensor data have enough information to predict the desired metric. We analyze the task of predicting blood pressure from PPG pulse wave analysis. Our review of the prior work reveals that many papers fall prey to data leakage and unrealistic constraints on the task and preprocessing steps. We propose a set of tools to help determine if the input signal in question (e.g., PPG) is indeed a good predictor of the desired label (e.g., blood pressure). Using our proposed tools, we found that blood pressure prediction using PPG has a high multi-valued mapping factor of 33.2% and low mutual information of 9.8%. In comparison, heart rate prediction using PPG, a well-established task, has a very low multi-valued mapping factor of 0.75% and high mutual information of 87.7%. We argue that these results provide a more realistic representation of the current progress toward the goal of wearable blood pressure measurement via PPG pulse wave analysis. For code, see our project page: https://github.com/lirus7/PPG-BP-Analysis

Simulation psychological safety ecosystem: using constructivist grounded theory to explore nurses’ experiences with prelicensure simulation

Introduction Learning through simulation requires psychological safety where participants feel comfortable engaging to their fullest extent, speaking up or asking questions without fear of embarrassment. While professional simulation organizations provide recommendations on fostering psychological safety, anecdotal stories from newly graduated nurses demonstrated variability in their experiences. The study explored nurses’ experience with psychological safety in their prelicensure curricula. Methods Using constructivist grounded theory methodology, the researchers conducted 17 semi-structured interviews with nurses who had experienced simulation in their prelicensure curriculum. They collected and analysed data iteratively using constant comparison to identify categories and explore their relationships. They used theoretical sampling in later stages until data sufficiency was achieved. Results The constructed theory, Simulation Psychological Safety Ecosystem, expresses the variability of nurses’ experiences. Psychological safety is a dynamic, complex process with a spectrum of outcomes from feeling psychologically safe to suffering psychological harm. Factors that influence this outcome include clarification of Expectations, Facilitation from the instructor during scenarios, experience with Observation, and structure and quality of Debriefing/Feedback. Psychological safety is also influenced by nurses’ existing relationships with faculty and peers, and their desire to achieve meaningful clinical learning. Discussion Implications for nursing education reinforce clarifying expectations for equipment and roles, instructor presence, and observation. The findings suggest the benefits of establishing peer and faculty relationships prior to simulation-based education implementation and providing guidelines for faculty and peer feedback. Potential areas for future research include clarifying the ecosystem model and exploring the impact of faculty and peer relationships on psychological safety.

Initial surgical performance in robot-assisted radical prostatectomy is associated with clinical outcomes and learning curves.

The association between surgical performance ratings and clinical outcomes in robotic surgery is poorly understood. Additionally, no studies have reported on the relationship between the surgeon's initial case-skill evaluation and the learning curve in robot-assisted surgery. We evaluated whether an objective surgical technique evaluation score for initial robot-assisted radical prostatectomy (RARP) was associated with clinical outcomes and surgeons' learning curves. Six surgeons who were trained in and started to perform RARP at our institution were included. Anonymized, unedited videos of each surgeon's 10th RARP case were evaluated by three reviewers, using modified Objective Structured Assessment of Technical Skill (OSATS) scores. We then divided the surgeons into two groups on the basis of these OSATS scores. We retrospectively compared the clinical outcomes and learning curves of the console time of the two groups for consecutive RARPs, performed from March 2018 to July 2023. We analyzed 258 RARPs (43 cases/surgeon), including 129 cases performed by high-OSATS score surgeons (18.2-19.3 points) and 129 cases performed by low-OSATS score surgeons (11.9-16.0 points). Overall, the high-OSATS score group had significantly shorter operation and console times than the low-OSATS score group did (both P < 0.01) and their patients' rate of continence recovery by 3months post-RARP was significantly higher (P = 0.03). However, complications, blood loss, and positive margins did not differ between the groups (P = 0.08, P = 0.51, and P = 0.90, respectively). The high-OSATS score group had a significantly shorter console time than the low-OSATS score group did after the 11-20 cases. The OSATS score in early RARP cases can predict subsequent surgical outcomes and surgeons' learning curves.

Development and validation of an artificial intelligence model for predicting de novo distant bone metastasis in breast cancer: a dual-center study

ObjectiveBreast cancer has become the most prevalent malignant tumor in women, and the occurrence of distant metastasis signifies a poor prognosis. Utilizing predictive models to forecast distant metastasis in breast cancer presents a novel approach. This study aims to utilize readily available clinical data and advanced machine learning algorithms to establish an accurate clinical prediction model. The overall objective is to provide effective decision support for clinicians.MethodsData from 239 patients from two centers were analyzed, focusing on clinical blood biomarkers (tumor markers, liver and kidney function, lipid profile, cardiovascular markers). Spearman correlation and the least absolute shrinkage and selection operator regression were employed for feature dimension reduction. A predictive model was built using LightGBM and validated in training, testing, and external validation cohorts. Feature importance correlation analysis was conducted on the clinical model and the comprehensive model, followed by univariate and multivariate regression analysis of these features.ResultsThrough internal and external validation, we constructed a LightGBM model to predict de novo bone metastasis in newly diagnosed breast cancer patients. The area under the receiver operating characteristic curve values of this model in the training, internal validation test, and external validation test1 cohorts were 0.945, 0.892, and 0.908, respectively. Our validation results indicate that the model exhibits high sensitivity, specificity, and accuracy, making it the most accurate model for predicting bone metastasis in breast cancer patients. Carcinoembryonic Antigen, creatine kinase, albumin-globulin ratio, Apolipoprotein B, and Cancer Antigen 153 (CA153) play crucial roles in the model’s predictions. Lipoprotein a, CA153, gamma-glutamyl transferase, α-Hydroxybutyrate dehydrogenase, alkaline phosphatase, and creatine kinase are positively correlated with breast cancer bone metastasis, while white blood cell ratio and total cholesterol are negatively correlated.ConclusionThis study successfully utilized clinical blood biomarkers to construct an artificial intelligence model for predicting distant metastasis in breast cancer, demonstrating high accuracy. This suggests potential clinical utility in predicting and identifying distant metastasis in breast cancer. These findings underscore the potential prospect of developing economically efficient and readily accessible predictive tools in clinical oncology.

Impact of Experiential Learning in a Pro Bono OT Clinic on Clinical Reasoning Development

Abstract Date Presented 03/23/24 This poster will describe the impact of a pro bono OT clinic on clinical reasoning development. It will summarize factors that influence student growth, such as specific clinic structure and learning activities to foster professional growth. Primary Author and Speaker: Julie A. Sandvig Additional Authors and Speakers: Paula H. Kitzenberg, Debra Hanson

Modeling 3D Cardiac Contraction and Relaxation With Point Cloud Deformation Networks.

Global single-valued biomarkers, such as ejection fraction, are widely used in clinical practice to assess cardiac function. However, they only approximate the heart's true 3D deformation process, thus limiting diagnostic accuracy and the understanding of cardiac mechanics. Metrics based on 3D shape have been proposed to alleviate these shortcomings. In this work, we present the Point Cloud Deformation Network (PCD-Net) as a novel geometric deep learning approach for direct modeling of 3D cardiac mechanics of the biventricular anatomy between the extreme ends of the cardiac cycle. Its encoder-decoder architecture combines a low-dimensional latent space with recent advances in point cloud deep learning for effective multi-scale feature learning directly on flexible and memory-efficient point cloud representations of the cardiac anatomy. We first evaluate the PCD-Net's predictive capability for both cardiac contraction and relaxation on a large UK Biobank dataset of over 10,000 subjects and find average Chamfer distances between the predicted and ground truth anatomies below the pixel resolution of the underlying image acquisition. We then show the PCD-Net's ability to capture subpopulation-specific differences in 3D cardiac mechanics between normal and myocardial infarction (MI) subjects and visualize abnormal phenotypes between predicted normal 3D shapes and corresponding observed ones. Finally, we demonstrate that the PCD-Net's learned 3D deformation encodings outperform multiple clinical and machine learning benchmarks by 11% in terms of area under the receiver operating characteristic curve for the tasks of prevalent MI detection and incident MI prediction and by 7% in terms of Harrell's concordance index for MI survival analysis.

Ready, Set, Goal: A Mixed Methods Study of a Goal-Setting Intervention on 2 Competency-Based Geriatric Medicine Rotations.

Background More research is required to understand the effects of implementing structured goal-setting on trainee engagement in competency-based clinical learning environments. Objective To explore how residents experienced a rotation-specific goal-setting intervention on geriatric medicine rotations at 2 hospitals. Methods All rotating residents were expected to complete the intervention, consisting of a SMART-based (Specific, Measurable, Achievable, Relevant, and Time-Bound) goal-setting form and feedback sessions with teaching faculty. From November 2019 to June 2021, we recruited a convenience sample of rotating residents. Study participants completed pre- and postrotation 35-item Dutch Residency Educational Climate Test (D-RECT) questionnaires to compare scores from their rotation before the geriatric rotation and a postrotation semistructured interview, which we transcribed and analyzed using principles of constant comparison and reflexive thematic analysis. Results We interviewed 12 of 58 (20.7%) residents participating in the goal-setting intervention, 11 of whom completed both D-RECT questionnaires. Participants' D-RECT scores favored the geriatric medicine rotation versus the immediately preceding clinical rotation (M=4.29±0.37; M=3.84±0.44, P=.002). Analyses of interview transcripts yielded 3 themes on how participants perceived the intervention influenced their learning experience: (1) structured forms and processes mediate, inform, and constrain goal selection; (2) interactions with faculty, patients, and system factors influenced goal enactment; and (3) unstructured assessments led to uncertainty around goal achievement. Challenges included time restrictions and unpredictable clinical opportunities. Conclusions Goal-setting appeared to help many residents direct their learning efforts and engage in collaborative processes with teaching faculty. We identified challenges limiting residents' engagement with the goal-setting intervention, which may inform the practical implementation of goal-setting in other competency-based curricula.

Nursing students’ knowledge, attitudes and learning occasions about pressure injuries at the time of graduation: A multi-method pre-post pandemic study

IntroductionPressure injuries (PIs) are a significant issue in healthcare system: nursing students are recommended to be prepared to assess the risk, prevent and manage them. However, despite the coronavirus disease-2019 (COVID-19) pandemic significantly affected nursing students’ learning opportunities no data regarding their impact of PIs knowledge, attitudes and learning occasions have been documented to date. AimsTo describe the post-pandemic knowledge and attitudes regarding PI prevention and management and to compare clinical learning opportunities in the field of PIs before and after the COVID-19 pandemic. MethodA descriptive multi-method study involving students at the time of their graduation in the before (n=114) and after the pandemic (n=113). The Italian versions of the Pressure Ulcer Knowledge Assessment Tool (PUKAT-IT) and Attitude Toward Pressure Ulcer Prevention (APuP-IT) scales were used. Data regarding pre- and post-pandemic learning opportunities were retrospectively collected from the Student Portfolio of Skills. ResultsThe average PUKAT-IT score was 57.92% (cut-off 60%), which indicates insufficient knowledge; the average APuP-IT score was 78.19% (cut-off 75%), which shows positive attitudes towards PI. Comparing the pre- and the post-pandemic groups, learning opportunities in PI risk assessment and prevention significantly decreased (overall 38.90 vs 32.27 and 35.26 vs 25.97, respectively) while those regarding the PI management remained stable. ConclusionIn the post-pandemic times, nursing students’ knowledge about PIs remains insufficient while their attitudes are adequate; the pandemic significantly reduced students’ exposure to prevention and assessment learning opportunities during their internship, which suggests a need to update educational strategies to ensure appropriate knowledge and learning experiences in this field.

Development of the Hybrid Clinical Practicum Environment Scale for Nursing Students.

This study aimed to develop a Hybrid Clinical Practicum Environment Scale for Nursing Students (HCPES-NS) and verify its validity and reliability. The HCPES-NS was constructed following the DeVellis guidelines. The initial items were written based on a literature review and individual in-depth interviews. Content validity was verified through an expert panel review. To confirm the validity and reliability of the scale, a survey was conducted with 449 nursing students enrolled in 12 nursing colleges. Data were analyzed using item analysis, exploratory factor analysis, confirmatory factor analysis, concurrent validity, and reliability tests. Factor analysis showed that the HCPES-NS consists of 15 items on five subdomains: clinical site atmosphere, interpersonal relationship, alternative online practicum contents, provision of learning information, and clinical performance facilitation. A higher score indicated a more positive perception of the clinical practicum environment. The concurrent validity of the HCPES-NS was confirmed by its positive correlation with the Clinical Learning Environment Scale (r = .77). The Cronbach's α reliability of the HCPES-NS was .84. The HCPES-NS is both valid and reliable. This scale reflects the clinical practicum environment and includes an online practicum factor. It may be used effectively by faculty members and educators to evaluate nursing students' perceptions of clinical practicum environments.

Obstetrics clinical learning needs: Priorities of undergraduate medical students

Background. The obstetrics clinical learning environment is complex and often not conducive to learning. Understanding the priority clinical learning needs of students with experience in this setting is essential for designing effective educational interventions to optimise clinical learning. Objective. To describe the priority obstetrics-related clinical learning needs of undergraduate medical students informed by their experience of the clinical learning environment. Methods. A multigroup nominal group technique (NGT) was applied to a purposively sampled group of medical students who had experienced obstetrics-related clinical placements in facilities at various levels of care, from primary to tertiary. Individual group priorities were further integrated into themes. Results. Seven priorities emerged: (i) perinatal procedural skills, (ii) teaching approaches to obstetrics, (iii) pregnancy-related screening and complications, (iv) postnatal support for women, (v) interprofessional and gender roles, (vi) orientation to patient care and the clinical environment, and (vii) psychological preparation of students. Conclusion. Educational interventions to optimise the obstetrics clinical learning environment must consider students’ priorities. These priorities extend beyond procedural skills and include collaborative practice and psychological preparation.

Implementation of a Mental Health Objective Structured Clinical Examination (OSCE) Using Standards of Best Practice.

The objective structured clinical examination (OSCE) is effective for the evaluation of clinical competence. Studies examining the use of OSCEs in undergraduate mental health nursing education in the United States are limited. A pilot study and a follow-up study were conducted to establish the reliability and validity of a mental health OSCE to evaluate the clinical competence of prelicensure nursing students. International Nursing Association for Clinical Simulation and Learning Standards of Best Practice were used to guide the design and implementation. Results from both studies provide evidence for the use of OSCE in undergraduate mental health nursing education.

Burnout and predictive factors among medical students: a cross-sectional survey

BackgroundBurnout is a growing problem in medical education, and is usually characterised by three dimensions: emotional exhaustion, cynicism, and reduced professional efficacy. Currently, the majority of burnout studies have been conducted in western high-income countries, overshadowing findings from low- and middle-income countries. Our objective is to investigate burnout and its associated predictive factors in Morocco, aiming to guide intervention strategies, while also assessing differences between the preclinical and clinical years.MethodsA cross-sectional, self-administered online survey assessing burnout dimensions and its main determinants was distributed among medical students at Université Mohammed VI des Sciences et de la Santé (UM6SS, Casablanca, Morocco). Descriptive analyses involved computing mean scores, standard deviations and Pearson correlations. Further, t-tests were performed to check for significant differences in burnout dimensions across the preclinical and clinical learning phase, and stepwise linear regression analyses were conducted using a backward elimination method to estimate the effects of the selected variables on the three burnout dimensions.ResultsA t-test assessing the difference in cynicism found a significant difference between students at the preclinical phase and the clinical phase, t(90) = -2.5, p = 0.01. For emotional exhaustion and reduced professional efficacy no significant difference was observed. A linear regression analysis showed that emotional exhaustion was significantly predicted by workload, work-home conflict, social support from peers and neuroticism. Cynicism was predicted by the learning phase, workload, meaningfulness and neuroticism; and reduced professional efficacy by neuroticism only.ConclusionsOur findings suggest a potential gradual increase in cynicism during medical education in Morocco. Conducting this study in a low- and middle income country has enhanced the scientific understanding of burnout in these regions. Given the identified predictive factors for burnout, such as workload, work-home conflict, support from peers, neuroticism, and meaningfulness, it is necessary to focus on these elements when developing burnout interventions.

Advancing interprofessional workplace learning: Successful implementation of the ‘WILD Series©’ hybrid professional development model

BackgroundThe 2021 NCICLE Pathways to Excellence framework highlights the need for professional development opportunities promoting interprofessional learning to optimize healthcare provider and learner teaming in the clinical learning environment. Despite this priority, research shows some clinicians are not developing their collaborative practice skills. PurposeThis article describes the hybrid Workplace Interprofessional Learning and Development (WILD) Series, which was developed to promote interprofessional preceptor development through workplace learning. MethodThe WILD Series© includes four unique six-week offerings, each dedicated to one Interprofessional Education Collaborative (IPEC) competency area. Each six-week session includes five weeks of one topical, actionable independent email engagement and concludes with a structured, facilitated synchronous debriefing session. DiscussionThe WILD Series© is the first IPE program designed for independently practicing clinicians and preceptors that includes synchronous and asynchronous components. Initial feedback was positive regarding the series format, content, and outcomes. ConclusionThe WILD Series© demonstrates that workplace learning can be an effective strategy for addressing gaps in interprofessional preceptor development.

Lived experience of ethical challenges among undergraduate nursing students during their clinical learning.

Undergraduate nursing students may experience several ethical challenges during their clinical learning placement that can lead to moral distress and intention to leave the profession. Ethical challenges are complex phenomena and ethical frameworks may help improve their understanding and provide actionable recommendations to enhance students' readiness for practice. To explore undergraduate nursing students' ethical challenges experienced during their clinical learning and their suggestions for better ethics education; to illuminate students' experience against a foundational ethical framework. Qualitative study based on interpretative phenomenology. Semi-structured, in-person or at distance, one-to-one interviews were performed, audio-recorded, and transcribed verbatim. The 'Dignity-enhancing care framework' was employed to frame the study findings. Nineteen nursing graduands attending seven sites of one Northwestern Italian University were interviewed. The study protocol was approved by the Ethics Committee of the University of Torino (number 0187646/2023). All participants provided written informed consent. Students experienced several ethical challenges concerning daily practice such as pain control or the decision to restrain patients, and reported deficient professional ethics with healthcare professionals who demonstrated poor caring attitudes and teamwork. Moreover, they perceived professionals poorly committed to their role of educators and complained of poor support in the learning process. When a supportive, dialogical, and relational context lacked, students experienced negative feelings about the profession and the healthcare system and reported the intention to leave the profession. Dialogue with peers, family members or significant others, nursing educators, and clinical nurse supervisors, as well as self-learning activities and discussion-based teaching methods grounded on real scenarios helped to overcome challenging situations. While complying with normative standards, nursing education policies should encourage the adoption of dynamic teaching methods and sustain a regular, dialogical approach within and between the clinical and academic contexts to improve readiness for practice.

Perceptions of Makerere University Undergraduate Radiography Students on Clinical Rotations in Mulago National Referral Hospital

Introduction: Clinical rotations are an integral component of the radiography programs worldwide as it is a practice-based profession and the effectiveness of clinical training is responsible for the competency level demonstrated by radiography students after qualification. Clinical rotations provide opportunities for radiography students to apply theory into practice. The effectiveness of the rotations is greatly affected by the setting of the clinical area. Makerere university undergraduate radiography students experience various circumstances that facilitate or inhibit their clinical learning process in Mulago National Referral Hospital (MNRH). Aim: The study aimed at exploring the perceptions of Makerere University undergraduate radiography students on clinical rotations in Mulago National Referral Hospital. Methodology: A cross-sectional exploratory, qualitative study was done. 19 third- and fourth-year Makerere University undergraduate students offering Bachelor of medical radiography were sampled purposively. Data was collected using semi-structured face to face interviews and analysed thematically. Results: Three major themes emerged from the data: (1) learning experience, (2) effectiveness of clinical rotations in MNRH and (3) challenges faced. Most factors related to the themes above positively impacted the students’ perceptions on clinical rotations in MNRH radiology department with more positives and the rotations meeting expectations of the majority, though with some challenges like limited clinical supervision by university lecturers and inadequate time for practicing some modalities. Conclusion: Clinical rotations can be effective and beneficial when a supportive learning environment is provided. This study reveals mixed student perceptions regarding clinical rotations in radiology department of MNRH, with predominant positive perceptions. Addressing identified challenges can significantly improve the clinical learning environment and thus the effectiveness of clinical rotations.Top of FormBottom of Form

Clinical Learning and LGBTQ+ Health: Summary of a LGBTQ+ Health Clinical Rotation.

People who identify as lesbian, gay, bisexual, transgender, queer, and people who identify as something else (LGBTQ+) experience barriers to health care including a lack of health care providers adequately prepared to care for them. The literature describing LGBTQ+-focused didactic learning activities has increased in recent years, however remains limited with respect to clinical learning experiences. This publication describes the development and implementation of a clinical rotation for Physician Assistant (PA) students focused on caring for LGBTQ+ patients. A 4-week LGBTQ+ Health clinical rotation was developed for PA students through collaboration with multiple clinical sites. Students (n = 6) were surveyed before and after completion of the clinical rotation on their knowledge, comfort, and confidence in caring for LGBTQ+ patients and to identify learning priorities. Paired t tests were used to compare quantitative pre and post data. Two reviewers independently reviewed qualitative data. Improvement in students' knowledge, comfort, and confidence were statistically significant from prerotation to postrotation surveys. Student ratings on standard course evaluations showed positive ratings for all course elements. Qualitative analysis showed that all students identified learning more about trans-related health care as a learning priority. Clinical rotations focused on the care of LGBTQ+ patients are valuable learning experiences which can support increased student knowledge, comfort, and confidence. Clinically based educational interventions may be one strategy in addressing the health disparities experienced by LGBTQ+ people.

Innovations report: A grading committee for a required fourth-year emergency medicine clerkship.

Assessment of medical students in the clinical learning environment is fraught with challenges. Seemingly small variations in clinical clerkship evaluation can significantly impact a student's future. As such, the integrity of the grade selection process must be heavily scrutinized. Group decision making in the form of a clerkship grading committee may be part of a solution to address this complex problem. We conducted a retrospective observational study to describe grading committee decisions for a required fourth-year EM clerkship from August 2021 to April 2022. Literature on best practices for group decision making and assessment were reviewed. This informed the development and implementation of the committee process. Each committee meeting was video recorded and coded for discussion time per student, times the committee grade differed from historical-grade cutoffs with reasoning, and the frequency a committee member voiced a first-hand account of student performance. Data from nine meetings was reviewed (86 students). The mean discussion time per student was 2 min 13 s (range 11 s to 9 min 22 s). The final committee decision differed from historical-grade cutoffs for nine students (10%), six were adjusted above and three below. In 64% (55/86) of student reviews a committee member voiced a first-hand experience of working with the student. Positive grade adjustments were made due to outlier evaluations and negative adjustments were made for professionalism concerns. Grading committees are a means to conduct a comprehensive review of student performance and offer shared ownership of the grade decision among committee members. More study is needed to directly determine their potential benefit and role in clerkship grading.

Fostering the clinician as teacher: A realist review.

Clinician-teachers, physicians with educational responsibilities in either classroom or clinical setting, are assumed to add value by virtue of their dual role. The clinical responsibilities are often prioritised over the educational tasks. How and under which circumstances clinician-teachers are able to perform their educational role and create added value for different stakeholders is currently unclear. To identify for whom, how and under which circumstances educational activities executed by CTs by virtue of their dual role add value to others. CTs activities linking the system of education and clinical practice beyond direct patient interactions and purposefully executed. A realist review was conducted. Databases were searched in two stages: a narrow conventional search, followed by a comprehensive artificial intelligence-aided search. Studies concerning clinician-teachers' dual role were included. Realist analysis was applied to identify in which contexts resource mechanisms triggered reasoning mechanisms, which led to specific outcomes for different stakeholders. Sixty-six studies were included. In contexts where clinician-teachers' dual role was formally recognised and valued, clinician-teachers benefitted from the credibility and legitimacy bestowed on them, making the transfer of domain-specific knowledge more impactful. In contexts where sociocultural differences between both systems existed, CTs were able to mediate and adjust recommendations aligned with stakeholders' perceived relevance. Also, contexts organised to support both roles made resource mechanisms more impactful. Clinician-teachers added value to students' clinical competency and learning environment, and to educational organisations' curricular innovation. In their clinical workspace, clinician-teachers added value by enhancing colleague physicians' teaching expertise, implementing educational innovations and recruiting students for scarce specialisms. Clinician-teachers add value to students, colleague physicians and the clinical and educational contexts at large. Domain-specific knowledge of both systems was important to gain credibility and achieve added value. Openness, formal recognition and allocated time for both roles in educational and clinical contexts towards the dual role are important to strengthen the impact of the dual role.

Navigating the Mobile Learning Landscape in Moroccan Nursing Education: A Descriptive Study with a Focus on Clinical Learning

Navigating the Mobile Learning Landscape in Moroccan Nursing Education: A Descriptive Study with a Focus on Clinical Learning

Integrating Clinical Data and Radiomics and Deep Learning Features for End-to-End Delayed Cerebral Ischemia Prediction on Noncontrast CT.

Delayed cerebral ischemia is hard to diagnose early due to gradual, symptomless development. This study aimed to develop an automated model for predicting delayed cerebral ischemia following aneurysmal SAH on NCCT. This retrospective study included 400 patients with aneurysmal SAH (156 with delayed cerebral ischemia) who underwent NCCT. The study used ATT-Deeplabv3+ for automatically segmenting hemorrhagic regions using semisupervised learning. Principal component analysis was used for reducing the dimensionality of deep learning features extracted from the average pooling layer of ATT-DeepLabv3+. The classification model integrated clinical data, radiomics, and deep learning features to predict delayed cerebral ischemia. Feature selection involved Pearson correlation coefficients, least absolute shrinkage, and selection operator regression. We developed models based on clinical features, clinical-radiomics, and a combination of clinical, radiomics, and deep learning. The study selected logistic regression, Naive Bayes, Adaptive Boosting (AdaBoost), and multilayer perceptron as classifiers. The performance of segmentation and classification models was evaluated on their testing sets using the Dice similarity coefficient for segmentation, and the area under the receiver operating characteristic curve (AUC) and calibration curves for classification. The segmentation process achieved a Dice similarity coefficient of 0.91 and the average time of 0.037 s/image. Seventeen features were selected to calculate the radiomics score. The clinical-radiomics-deep learning model with multilayer perceptron achieved the highest AUC of 0.84 (95% CI, 0.72-0.97), which outperformed the clinical-radiomics model (P = .002) and the clinical features model (P = .001) with multilayer perceptron. The performance of clinical-radiomics-deep learning model using AdaBoost was significantly superior to its clinical-radiomics model (P = .027). The performance of the clinical-radiomics-deep learning model and the clinical-radiomics model with logistic regression notably exceeded that of the model based solely on clinical features (P = .028; P = .046). The AUC of the clinical-radiomics-deep learning model with multilayer perceptron (P < .001) and the clinical-radiomics model with logistic regression (P = .046) were significantly higher than the clinical model with logistic regression. Of all models, the clinical-radiomics-deep learning model with multilayer perceptron showed best calibration. The proposed 2-stage end-to-end model not only achieves rapid and accurate segmentation but also demonstrates superior diagnostic performance with high AUC values and good calibration in the clinical-radiomics-deep learning model, suggesting its potential to enhance delayed cerebral ischemia detection and treatment strategies.