A new pathway in teaching dermatology

New legislative requirements for medical licensure in 2003 made necessary restructuring of medical education at German universities. Since the hours of patient contact and the proportion of small group teaching were explicitly defined, many curricula had to be changed fundamentally. For the clinical years of its Medical Curriculum Munich (MeCuM^LMU) the medical faculty of the Ludwig‐Maximilian University in Munich (LMU) decided on a modular concept. For dermatology, this meant less lecture time, more student‐patient interaction, the introduction of small group teaching, and the establishing of a catalogue of learning objectives. In cooperation with the Virtual University of Bavaria the internet was integrated into mandatory teaching for the first time. A faculty development program was instituted to increase teaching competence. All measures were designed to create an individual learning setting offering optimal support for every student. The large number of students remains the final nemesis.     

Artificial intelligence and kidney transplantation

Artificial intelligence and its primary subfield, machine learning, have started to gain widespread use in medicine, including the field of kidney transplantation. We made a review of the literature that used artificial intelligence techniques in kidney transplantation. We located six main areas of kidney transplantation that artificial intelligence studies are focused on: Radiological evaluation of the allograft, pathological evaluation including molecular evaluation of the tissue, prediction of graft survival, optimizing the dose of immunosuppression, diagnosis of rejection, and prediction of early graft function. Machine learning techniques provide increased automation leading to faster evaluation and standardization, and show better performance compared to traditional statistical analysis. Artificial intelligence leads to improved computer-aided diagnostics and quantifiable personalized predictions that will improve personalized patient care.     

Therapeutic application of machine learning in psoriasis: A Prisma systematic review

Dermatology, being a predominantly visual-based diagnostic field, has found itself to be at the epitome of artificial intelligence (AI)-based advances. Machine learning (ML), a subset of AI, goes a step further by recognizing patterns from data and teaches machines to automatically learn tasks. Although artificial intelligence in dermatology is mostly developed in melanoma and skin cancer diagnosis, advances in AI and ML have gone far ahead and found its application in ulcer assessment, psoriasis, atopic dermatitis, onychomycosis, etc. This article is focused on the application of ML in the therapeutic aspect of psoriasis.     

Audit of dermatological content of U.K. undergraduate curricula

Background Recommendations for the dermatology content (learning outcomes) of the core undergraduate curriculum were sent to all U.K. medical schools in June 2006. Objective To carry out an audit of the content of the core curriculum in each U.K. medical school against the recommendations for a core undergraduate dermatology curriculum (the criteria) published by the British Association of Dermatologists, to identify areas of good practice and to gather evidence for developing the learning and teaching of dermatology. Methods A questionnaire was circulated to the dermatology teaching leads of all U.K. medical schools (29) and one Irish medical school. Questions which the teaching leads were unable to answer were sent to the relevant deans and responses incorporated into the results. All curricula should include the essential learning outcomes that focus on clinical skills; as this was an audit to benchmark current practice, we did not set standards for the other recommendations for a core curriculum. Results Replies were received from teaching leads in 29 of the 30 medical schools and from 16 of the deans. Essential clinical skills such as taking a dermatological history and examining the skin were included in the curricula of most, but not all, medical schools. Areas of good practice include teaching on tumours, acne and psoriasis, but we found some surprising omissions including the diagnosis of meningococcaemia. Our data suggest that some students have little exposure to dermatology, but dermatology teaching takes place in secondary care in all medical schools. Knowledge‐based assessments are used by 27 medical schools. Conclusions Curricula should be strengthened so that the recommended learning outcomes feature in the core curricula of all medical schools. Teaching leads in all specialties, including those in the community, should communicate so that learning and teaching are integrated horizontally and vertically. The results should provide a baseline for future audits.     

Literature review of perceptual learning modules in medical education: What can we conclude regarding dermatology?

IntroductionVisual pattern recognition is important in many different medical fields, particularly in dermatology. Perceptual learning modules (PLM) are software programs developed to enhance visual pattern recognition through the sequential presentation of images that trainee must quickly diagnose. The aim of this literature review was to determine the scope and effectiveness of PLM in medical education.MethodsWe carried out a search of MEDLINE, EMBASE, Web of Science and ERIC from its inception through to July 1, 2017. All articles describing an educational intervention based on perceptual learning in a medical field were included. Two investigators worked independently on study selection and data extraction.ResultsOf 191 references selected, 5 studies were included in the final analysis: 3 before-after studies and 2 randomized studies comparing 12 to 236 trainees taking PLM with 12 to 316 trainees not taking PLM. Four studies reported a statistically significant increase in diagnostic accuracy (lower error rate) and fluency (shorter response time) following PLM interventions (dermatology, pathology, echocardiography), with long-term persistence of the effect in three studies.ConclusionPLM is a promising educational tool to teach pattern recognition that may be used in dermatology and other medical fields to improve diagnostic accuracy and rapidity in daily practice.     

Confidence of pediatric trainees in dermatologic conditions,preferred learning styles,and suggested improvements to training

Dermatological conditions in children often present initially to general pediatricians. Senior pediatric trainees in the UK were surveyed regarding their experience and confidence in diagnosis and management with skin conditions, and their satisfaction with postgraduate training. Confidence was reasonable in common conditions but lower for emergencies, reflecting a lack of exposure, and satisfaction with training was low. On the job learning and clinic attendance were felt to be most beneficial, alongside learning from specialist review, however dermatologists were not found to be accessible. Informal learning methods are key within postgraduate education and educators must maximise learning opportunities. Dermatologists can play a vital role by encouraging trainees to learn from feedback following specialist review.     

E‐learning in the dermatological education at the Charité: evaluation of the last three years

Background: Numerous e‐learning initiatives have been launched during the last decade. Many of them have not been continued, due to lack of acceptance on the part of the students, low quality or insufficient financial funding. Since 2002, the DEJAVU project has been integrated into the curriculum at the Department of Dermatology at Charité‐Universitätsmedizin Berlin. DEJAVU offers an online archive of recorded lectures, lecture hand outs, structured learning modules, and case reports as well as online information about the courses/classes. Methods: Since beginning of the summer semester 2005, the student's acceptance and utilization of the online offerings was regularly surveyed, using anonymous questionnaires handed out together with the final exams. The teaching staff's opinions about e‐learning were surveyed by means of a single anonymous questionnaire. Results: At the end of winter semester 2006/2007,93.5% of the students were aware of the existence of the e‐learning program. The average amount of time spent with the program was 14.7 hours over the course of one semester. 66.8% of the students considered the program as very useful for their dermatology training. The lecture notes were the most frequently used online resource. Among the teaching staff, 86% considered e‐learning a useful addition to traditional teaching. Conclusions: Our results show that e‐learning is very well accepted by our students. It offers an additional way of acquiring knowledge and should be used to complement traditional ways of teaching.     

人工智能在医学领域的研究进展

【摘要】 随着技术发展,医疗行业正进入“大数据”和“精准医学”的新纪元。人工智能可以辅助诊疗过程,减轻医生的数据分析压力。目前,人工智能在医学领域主要应用于图像识别、遗传学和基因组学、智能诊疗、预测预后等方面,其准确性可接近人类专家水平。其中,图像识别的研究最多,包括皮肤图像识别。在非图像识别领域,人工智能在皮肤科的研究较少。未来,人工智能可提高诊疗效率,使医患双方共同获益。     

Self‐learning digital modules in Dermatology: a pilot study

Background Dermatological diseases are one of the most common problems in outpatient departments. Dermatology teaching unfortunately is facing two major issues: (i) a shortage of trained faculty and (ii) inadequate teaching time. Various methods utilizing modern information technology have been studied to overcome these problems. Objectives We attempted to evaluate the use of a digital self‐learning module in the teaching of dermatology. Methods We created digital modules of dermatology topics, which included power‐point presentations, instructive videos demonstrating signs in dermatological examination, interactive quizzes and images. The module was pilot tested on 48 third semester students, each posted for 2 weeks in dermatology. Evaluation was performed using a 5‐point Likert scale questionnaire for the students. Actual knowledge acquisition was evaluated using a post‐test with two components: section A comprising questions from the sections covered by the digital module and a section B comprising questions from topics taught only in the conventional method. Results The questionnaire analysis revealed that a majority of the students were comfortable using the module and felt that it encouraged them towards further in‐depth self‐learning on the concerned topics. The results from the post‐test were compared between the test and control sections, using the Student’s t‐test, which gave a P‐value of 0.084 (5% significance level) suggesting that the difference was not significant. Conclusion To conclude, we would like to suggest that the use of a ‘play area’ like concept coupled with an interactive information technology‐based self‐learning module might improve dermatology teaching.     

Simulation of a mycological KOH preparation – e‐learning as a practical dermatologic exercise in an undergraduate medical curriculum

Background: Mycological KOH preparation is one of the most popular practical laboratory skills in dermatology. The study addresses the question whether an interactive simulation program enhances knowledge of students about this procedure. Methods: 166 students, 107 female and 59 male, participated. We separated our study in three phases: pretest, completing the simulation three times and post‐test. In the pre‐ and post‐test we recorded the number of correct steps of the mycological KOH preparation listed by the students. The full text feedback was explored by content analysis. Results: In the pre‐test the students listed an average of 3.1 ± 2.2 correct steps, compared to 8.8 ± 1.2 correct steps after completing the simulation (p < 0.001). Furthermore, the improvement was significant for each individual step. There were no significant differences between male and female students. In content analysis of the feedback, positive statements prevailed with 78.3%, compared to only 1.8% critical items. Conclusion: Our study shows that an interactive computer simulation program of mycological KOH preparation results in a significant learning effectiveness as far as recall of the correct procedural steps is concerned. Furthermore, subjective acceptance by students is high.     

Educating patients about malignant melanoma: computer-assisted learning in a pigmented lesion clinic

This prospective controlled study aimed to evaluate the effectiveness and acceptability of a computer program (CAL) designed to educate patients about skin protection including signs of melanoma. Two hundred and twenty-seven patients were recruited either from the Pigmented Lesion Clinic (PLC) or the Orthopaedic Fracture Clinic (OFC). A baseline measure of anxiety was obtained and subjects were allocated to either non-interactive, interactive or control conditions. Measures of anxiety and knowledge about malignant melanoma and skin protection were obtained prior to discharge from the clinic and knowledge was assessed again at 1-week follow-up. Results indicate that, although anxiety in the PLC subjects decreased significantly more than in the OFC patients, there was no significant effect of intervention. There was a significant effect of intervention on knowledge (F = 81.06, d.f. 2, 218, P < 0.0001) with participants having better knowledge on leaving the clinic in the interactive CAL condition than in both the Non-interactive condition and control. Non-interactive CAL was associated with higher knowledge than control. Knowledge gains were maintained at 1-week follow-up.     

A support vector machine for decision support in melanoma recognition

Please cite this paper as: A support vector machine for decision support in melanoma recognition. Experimental Dermatology 2010; 19 : 830–835. Abstract: The early diagnosis of melanoma is critical to achieving reduced mortality and increased survival. Although clinical examination is currently the method of choice for melanocytic lesion assessment, difficulties may arise in the diagnosis of atypical lesions. From both the naked eye and dermoscopic perspective, dysplastic naevi often exhibit a prominent heterogeneity of structure that renders their clinical distinction from melanoma difficult. To address these problems in diagnosis, there exists a heightened interest among researchers regarding the utility of machine learning techniques in computerised image analysis. Here we report on the utility, for dermatologists, of support vector machine (SVM) technology in melanoma diagnosis, using an archive of 199 digital dermoscopic images of excised atypical melanocytic lesions. Our best validation models achieved an average sensitivity and specificity for melanoma diagnosis of 0.86 and 0.72, respectively. Applying the best model to our test set yielded a sensitivity of 0.89, a diagnostic odds ratio of 14.09 and an area under the receiver operated characteristic curve (AUC) of 0.76. Advantages of the procedure implemented are the simplicity of feature extraction and the computationally cheap and efficient nature of SVMs. The derived model generalises well with outcomes that compare favourably with competing algorithms and expert assessment. In line with the concept of the utility of decision support systems in clinical practice, we propose that to reduce the risk of missed melanomas, both the dermatologists’ assessment and the SVM diagnosis be incorporated into the clinical decision‐making process.     

Ultra-high-frequency ultrasound and machine learning approaches for the differential diagnosis of melanocytic lesions

Malignant melanoma (MM) is one of the most dangerous skin cancers. The aim of this study was to present a potential new method for the differential diagnosis of MM from melanocytic naevi (MN). We examined 20 MM and 19 MN with a new ultra-high-frequency ultrasound (UHFUS) equipped with a 70 MHz linear probe. Ultrasonographic images were processed for calculating 8 morphological parameters (area, perimeter, circularity, area ratio, standard deviation of normalized radial range, roughness index, overlap ratio and normalized residual mean square value) and 122 texture parameters. Colour Doppler images were used to evaluate the vascularization. Features reduction was implemented by means of principal component analysis (PCA), and 23 classification algorithms were tested on the reduced features using histological response as ground-truth. Best results were obtained using only the first component of the PCA and the weighted k-nearest neighbour classifier; this combination led to an accuracy of 76.9%, area under the ROC curve of 83%, sensitivity of 84% and specificity of 70%. The histological analysis still remains the gold-standard, but the UHFUS images processing using a machine learning approach could represent a new non-invasive approach.     

Informing a position statement on the use of artificial intelligence in dermatology in Australia

Artificial Intelligence (AI) is the ability for computers to simulate human intelligence. In dermatology, there is substantial interest in using AI to identify skin lesions from images. Due to increasing research and interest in the use of AI, the Australasian College of Dermatologists has developed a position statement to inform its members of appropriate use of AI. This article presents the ACD Position Statement on the use of AI in dermatology, and provides explanatory information that was used to inform the development of this statement.     

以问题为基础的学习模式在武警部队卫生学教学中的应用

目的探讨以问题为基础的学习模式（PBL）在军队卫生学教学中的应用效果和存在问题。方法以武警医学院五年制临床医学本科生138名分为14个小组，每组9，10名学员。7组为实验组，以PBL教学模式为主。另7组设为对照组，以传统教学为主。实验组由组长负责组织本组学习讨论，对本组收集的资料进行筛选、整理和补充，归纳总结，写成书面材料，教员对自学和讨论予以引导，提供教学参考资料，指导查找资料，协调小组活动，对学员的讨论作出点评，解释疑难的问题。6个月后进行考核和自我评价。结果实验组的理论测试平均成绩为（44．21±2．67）分，与对照组无显著性差异[（43．63±2．42），（P〉0．05]。综合能力考核中，实验组的测试成绩为（27．42±1．87）分，显著高于对照组的成绩[（21．36±1．64）分，P〈0．05]。主观自我评价结果表明实验组在学员自主学习、团队合作、参与情感以及军医品质方面均优于对照组。结论PBL教学法的效果优于传统方法，有助于加强学员所学知识的广度和深度，还可促进教员教学技巧的全面提高。     

Evidence that dysregulated DNA mismatch repair characterizes human nonmelanoma skin cancer

BACKGROUND: In addition to an established role in the repair of postreplicative DNA errors, DNA mismatch repair (MMR) proteins also contribute to cellular responses to exogenous DNA damage. Previously, we have shown that Msh2-null mice display increased sensitivity to ultraviolet (UV) B-induced tumorigenesis, but squamous cell carcinomas (SCC) generated are microsatellite stable, suggesting a role for MMR other than postreplicative repair in UV-induced cutaneous tumour formation. OBJECTIVES: We questioned whether there was evidence of MMR dysfunction in human SCC, thus validating the mouse models of MMR-dependent UVB-induced skin cancer. METHODS: Using tissue microarrays we examined both nuclear and cytoplasmic levels of MMR proteins MSH2, MSH6, MSH3, MLH1 and PMS2 in more than 200 cases of cutaneous SCC and basal cell carcinoma (BCC). RESULTS: We found that subsets of these 10 MMR protein measures were increased in nonmelanoma skin cancer (NMSC) compared with normal epidermal samples; this was particularly true of SCC. In fact, based on post hoc tests and MMR protein distribution patterns, BCC was distinct from SCC. With the exception of nuclear MSH2, the BCC had lower levels of identified MMR protein measures than SCC. We believe this to be important because not only is SCC more aggressive than BCC, but evidence suggests that these two NMSC subtypes arise through different molecular pathways. CONCLUSIONS: In combination with previously established roles for MMR proteins in response to UVB-induced DNA damage, our data point towards an expanded perspective of the importance of MMR proteins in the suppression of UVB-induced tumorigenesis and, potentially, tumour behaviour.