Ethical global health in nursing education: An integrative review

AimThe purpose of this integrative review is to provide a comprehensive review of ethical considerations for host communities and nursing programs in planning, implementing and evaluating global health experiences for nursing students.BackgroundGlobal health experiences for nursing students are proliferating rapidly across university settings while at the same time decreasing the average time spent in the host country engaged with local communities. Global health experiences are an area where students can experience ethics as it is applied across varied contexts including resource limited international settings. As nursing education expands its global programming, exploring the ethical implications of designing, implementing and evaluating GHEs becomes pivotal to build respectful, sustainable relationships with global partners and best prepare nursing students for ethical professional practice in an interconnected world.DesignWe conducted an integrative review to examine ethical considerations in development of ethical global health experiences that benefit, rather than harm, host communities and participating nursing student guests.MethodsThe search included articles published in English language, peer-reviewed journals between 1998 and 2021 that discussed ethics in the context of nursing students traveling internationally for global health experiences. Eighteen articles met criteria for review.ResultsOverall, findings demonstrate relatively little research specific to ethical engagement in global health experiences. The articles in this integrative review discussed a range of ethical attributes including reciprocity or collaboration, respect, sustainability or commitment, justice and openness. Recommendations based on research and non-research articles are provided.ConclusionsEthical comportment in global health experiences requires careful planning, implementation and evaluation to assure an equitable and sustainable partnership between host community, faculty and nursing student guests.     

Development and validation of artificial intelligence models for preoperative prediction of inferior mesenteric artery lymph nodes metastasis in left colon and rectal cancer

BackgroundDissection of lymph nodes at the roots of the inferior mesenteric artery (IMAN) should be offered only to selected patients at a major risk of developing IMAN involvement. The aim of this study is to present the first artificial intelligence (AI) models to predict IMAN metastasis risk in the left colon and rectal cancer patients.MethodsA total of 2891 patients with descending colon including splenic flexure, sigmoid colon and rectal cancer undergoing major primary surgery and IMAN dissection were included as a study cohort, which was then split into a training set (67%) and a testing set (33%). Feature selection was conducted using the least absolute shrinkage and selection operator (LASSO) regression model. Seven AI algorithms, namely Support Vector Machine (SVM), Logistic Regression (LR), Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), Decision Tree Classifier (DTC), Random Forest (RF) classifier, and Multilayer Perceptron (MLP), as well as traditional multivariate LR model were employed to construct predictive models. The optimal hyperparameters were determined with 5 fold cross-validation. The predictive performance of models and the expert surgeon was assessed and compared in the testing set independently.ResultsThe IMAN involvement incidence was 4.6%. The optimal set of features selected by LASSO included 10 characteristics: neoadjuvant treatment, age, synchronous liver metastasis, synchronous lung metastasis, signet ring adenocarcinoma, neural invasion, lymphovascular invasion, CA199, endoscopic obstruction, T stage evaluated by MRI. The most accurate model derived from MLP showed excellent prediction power with area under the receiver operating characteristic curve (AUROC) of 0.873 and produced 81.0% recognition sensitivity and 82.5% specificity in the testing set independently. In contrast, the judgment of IMAN metastasis by expert surgeon yield rather imprecise and unreliable results with a significantly lower AUROC of 0.509. Additionally, the proposed MLP had the highest net benefits and the largest reduction of unnecessary IMAN dissection without the cost of additional involved IMAN missed.ConclusionMLP model was able to maintain its prediction accuracy in the testing set better than other models and expert surgeons. Our MLP model could be used to help identify IMA nodal metastasis and to select candidates for individual IMAN dissection.     

Process evaluation of implementation strategies to reduce potentially inappropriate medication prescribing in older population: A scoping review

ObjectivesSeveral implementation strategies can reduce potentially inappropriate medication (PIM) prescribing. Although use of PIMs has declined in recent years, it remains prevalent. Various strategies exist to improve the appropriateness of medication use. However, little is known about the processes of these different implementation strategies. This scoping review aims to investigate how the process evaluation of implementation strategies for reducing PIM prescribing in the older population has been studied.MethodsWe searched for process evaluations of implementation strategies for reducing PIM prescribing in PUBMED, SCOPUS and Web of Science published between January 2000 and November 2019 in English. We applied the following inclusion criteria: patients aged ≥65 years, validated PIM criteria, and implementation process evaluated. The review focuses on decision support for health care professionals. We described the findings of the process evaluations, and compared the authors’ concepts of process evaluation of the included publications to those of Proctor et al.( 2010).ResultOf 9131 publications screened, 29 met our inclusion criteria. Different process evaluation conceptualizations were identified. Most process evaluations took place in the initial stages of the process (acceptability, adoption, appropriateness, and feasibility) and sustainability and implementation costs were seldom evaluated. None of the included publications evaluated fidelity.Multifaceted interventions were the most studied implementation strategies. Medication review was more common in acceptability evaluations, multidisciplinary interventions in adoption evaluations, and computerized systems and educational interventions in feasibility evaluations. Process evaluations were studied from the health care professionals’ viewpoint in most of the included publications, but the management viewpoint was missing.DiscussionThe conceptualization of process evaluation in the field of PIM prescribing is indeterminate. There is also a current gap in the knowledge of sustainability and implementation costs. Clarifying the conceptualization of implementation process evaluation is essential in order to effectively translate research knowledge into practice.     

Exploring peer tutoring from the peer tutor's perspective

IntroductionChanging working practices, student numbers, workforce demands, and deficits, have created a need to consider new ways of radiography student training. One suggestion could be to implement Peer Assisted Learning (PAL) during clinical placements. PAL utilises social constructivist theories, where peer tutors teach lower or same level tutees, reinforcing and practicing material formally taught. The aim of this study was to trial an intervention of PAL, co-designed between the university and students and evaluated to identify opportunities and challenges.MethodsUsing participatory action research 8 final year student volunteers trialled a 3-week intervention, where they delivered PAL to first years, tutoring on first year radiographic clinical practice. Focus groups were held pre and post intervention to gather qualitative data.ResultsFocus group discussions were transcribed and collectively thematically analysed. Two students and the primary researcher took part in the analysis.ConclusionStudents identified benefits and challenges to PAL. Issue around preparing for and being a peer tutor are also discussed.Further study involving experiences of first year students and clinical colleagues is required.Implications for practicePeer-tutoring has potential benefits to students to facilitate the development of skills related to image analysis and critique as well as radiographic anatomy and patient positioning.     

Registries,Databases and Repositories for Developing Artificial Intelligence in Cancer Care

Modern artificial intelligence techniques have solved some previously intractable problems and produced impressive results in selected medical domains. One of their drawbacks is that they often need very large amounts of data. Pre-existing datasets in the form of national cancer registries, image/genetic depositories and clinical datasets already exist and have been used for research. In theory, the combination of healthcare Big Data with modern, data-hungry artificial intelligence techniques should offer significant opportunities for artificial intelligence development, but this has not yet happened. Here we discuss some of the structural reasons for this, barriers preventing artificial intelligence from making full use of existing datasets, and make suggestions as to enable progress. To do this, we use the framework of the 6Vs of Big Data and the FAIR criteria for data sharing and availability (Findability, Accessibility, Interoperability, and Reuse). We share our experience in navigating these barriers through The Brain Tumour Data Accelerator, a Brain Tumour Charity-supported initiative to integrate fragmented patient data into an enriched dataset. We conclude with some comments as to the limits of such approaches.     

基于超声影像组学的乳腺癌预测模型的诊断性能研究

目的评估并比较基于不同机器学习算法建立的乳腺癌超声影像组学预测模型的诊断性能。 方法回顾性收集2017年1月至2019年4月就诊皖南医学院第一附属医院、有明确病理结果的乳腺肿块病例828例，以2018年8月31日为节点将其分为训练集（526例）和验证集（302例），提取肿块的超声影像组学特征并进行特征筛选，运用k最近邻（kNN）、逻辑回归（LR）、朴素贝叶斯（NB）、随机森林（RF）和支持向量机（SVM）5种机器学习算法分别建立预测模型，使用重复交叉验证方法做内部验证，计算比较各模型的敏感度、特异度、阳性预测值（PPV）和阴性预测值（NPV），并实施外部验证，绘制ROC曲线并比较ROC曲线下面积（AUC）以评价模型的鉴别诊断性能，绘制校准曲线评价模型校准度。 结果从提取的109个影像组学特征中筛选出19个特征建立了5种机器学习算法模型。在内部验证中，5种模型的敏感度、特异度、PPV、NPV比较，总体差异均有统计学意义（P均＜0.001）。LR模型的特异度、PPV、NPV中位数分别为0.769、0.816、0.778，3项指标均高于其他4种模型；敏感度中位数为0.824，高于kNN、RF和SVM模型。此外，SVM模型的特异度、PPV、NPV中位数分别为0.706、0.774、0.759，虽均低于LR模型，但均高于其他3种模型。在外部验证中，LR、SVM、RF、kNN和NB的AUC依次为0.890、0.832、0.821、0.746和0.703，其中LR与SVM的AUC差异有统计学意义（P=0.012）；此外，各模型在校准性能上表现并不一致，LR和SVM模型的校准曲线显示乳腺癌实际概率与预测概率之间的一致性较好。 结论以超声影像组学特征为基础，运用不同机器学习算法建立的乳腺癌超声预测模型，均表现出较高的诊断性能，其中LR模型表现最为突出；选择合适的机器学习算法有助于进一步提高预测模型的诊断性能，提供更加准确的量化预测结果。     

Automatic segmentation of thoracic CT images using three deep learning models

PurposeDeep learning (DL) techniques are widely used in medical imaging and in particular for segmentation. Indeed, manual segmentation of organs at risk (OARs) is time-consuming and suffers from inter- and intra-observer segmentation variability. Image segmentation using DL has given very promising results. In this work, we present and compare the results of segmentation of OARs and a clinical target volume (CTV) in thoracic CT images using three DL models.Materials and methodsWe used CT images of 52 patients with breast cancer from a public dataset. Automatic segmentation of the lungs, the heart and a CTV was performed using three models based on the U-Net architecture. Three metrics were used to quantify and compare the segmentation results obtained with these models: the Dice similarity coefficient (DSC), the Jaccard coefficient (J) and the Hausdorff distance (HD).ResultsThe obtained values of DSC, J and HD were presented for each segmented organ and for the three models. Examples of automatic segmentation were presented and compared to the corresponding ground truth delineations. Our values were also compared to recent results obtained by other authors.ConclusionThe performance of three DL models was evaluated for the delineation of the lungs, the heart and a CTV. This study showed clearly that these 2D models based on the U-Net architecture can be used to delineate organs in CT images with a good performance compared to other models. Generally, the three models present similar performances. Using a dataset with more CT images, the three models should give better results.     

Active learning in head and neck trauma: outcomes after an innovative educational course

Excellence in teaching and learning is fundamental to the provision of quality training for doctors and for this a sound knowledge of the principles of adult learning theory is important. We present an educational course in head and neck trauma skills for emergency medicine (EM) registrars, using the pedagogical principle of active learning. Our aim was to provide trainees with skills in the evaluation and management of hard and soft tissue injuries to the head, neck, and mouth. Active learning has been shown to provide a superior experience in classrooms, creating a ‘deep’ understanding of the material. To maximise learning, we used these principles to develop small group seminars led by a diverse range of teachers that allowed trainees to acquire hands-on skills. Questionnaires that were completed before and after the course showed an appreciable educational impact. We conclude that innovative teaching methods facilitate the sharing of knowledge that will benefit patient care.     

Application of computer-generated images to train pattern recognition used in semiquantitative immunohistochemistry scoring

This study aimed to clarify whether the pattern recognition involved in scoring proliferation fractions can be trained by abstract computerized images of virtual tissues. Twenty computer-generated images with randomly distributed blue or red dots were scored by 12 probands (all co-workers or collaborators of the Institute of Pathology, University of Bonn). Afterward, the probands underwent a training phase during which they received an immediate feedback on the actual rate of positivity after each image. Finally, the initial testing series was rescored. In a second round with 15 different probands, 20 Ki-67 immunohistochemistry images of tonsil tissue were scored, followed by the same training phase with computer-generated images, before the immunohistochemistry slides were scored again. Paired t-tests were used to compare the differences in mean rates pre- and post-training. Concerning computerized images, untrained probands scored the percentages of positive dots with a mean deviation from the true rates of 8.2%. Following training, the same testing series was scored significantly better with a mean deviation of 4.9% (mean improvement 3.3%, p < 0.001). Scoring real immunohistochemistry slides, the training with computerized images also improved correct estimations, albeit to a lesser degree (mean improvement 1%, p = 0.03). Abstract computerized images of virtual tissues may be a useful tool to train and improve the accuracy of pattern recognition involved in semiquantitative scoring of immunohistochemistry slides. As a side results, this study highlights the value of computer-generated images to verify the performance of image-analysis software.