Marcus Bloice

Modeling, design, development and evaluation of a hypervideo presentation for digital systems teaching and learning

Hypervideos are multimedia files, which differ from traditional video files in that they can be navigated by using links that are embedded in them. Students can therefore easily access content that explains and clarifies certain points of the lectures that are difficult to understand, while at the same time not interrupting the flow of the original video presentation. In this paper we report on the design, development and evaluation of a hypermedia e-Learning tool for university students. First, the structure of the hypervideo model is presented; once the structure is known, the process of creating hypervideo content is described in detail, as are the various ways in which content can be linked together. Finally, an evaluation is presented, which has been carried out in the context of an engineering class by use of an interactive experiment, involving N = 88 students from a digital systems course. In this study the students were randomly assigned to two groups; one group participated in the course as usual, whilst the second group participated in the same course while also combining the conventional learning with the hypervideo content developed for the course. The students’ learning results showed that the students who had access to the hypervideo content performed significantly better than the comparison group.

On the usage of health records for the design of virtual patients: a systematic review

BackgroundThe process of creating and designing Virtual Patients for teaching students of medicine is an expensive and time-consuming task. In order to explore potential methods of mitigating these costs, our group began exploring the possibility of creating Virtual Patients based on electronic health records. This review assesses the usage of electronic health records in the creation of interactive Virtual Patients for teaching clinical decision-making.MethodsThe PubMed database was accessed programmatically to find papers relating to Virtual Patients. The returned citations were classified and the relevant full text articles were reviewed to find Virtual Patient systems that used electronic health records to create learning modalities.ResultsA total of n = 362 citations were found on PubMed and subsequently classified, of which n = 28 full-text articles were reviewed. Few articles used unformatted electronic health records other than patient CT or MRI scans. The use of patient data, extracted from electronic health records or otherwise, is widespread. The use of unformatted electronic health records in their raw form is less frequent. Patient data use is broad and spans several areas, such as teaching, training, 3D visualisation, and assessment.ConclusionsVirtual Patients that are based on real patient data are widespread, yet the use of unformatted electronic health records, abundant in hospital information systems, is reported less often. The majority of teaching systems use reformatted patient data gathered from electronic health records, and do not use these electronic health records directly. Furthermore, many systems were found that used patient data in the form of CT or MRI scans. Much potential research exists regarding the use of unformatted electronic health records for the creation of Virtual Patients.

On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process

Computational geometry and topology are areas which have much potential for the analysis of arbitrarily high-dimensional data sets. In order to apply geometric or topological methods one must first generate a representative point cloud data set from the original data source, or at least a metric or distance function, which defines a distance between the elements of a given data set. Consequently, the first question is: How to get point cloud data sets? Or more precise: What is the optimal way of generating such data sets? The solution to these questions is not trivial. If a natural image is taken as an example, we are concerned more with the content, with the shape of the relevant data represented by this image than its mere matrix of pixels. Once a point cloud has been generated from a data source, it can be used as input for the application of graph theory and computational topology. In this paper we first describe the case for natural point clouds, i.e. where the data already are represented by points; we then provide some fundamentals of medical images, particularly dermoscopy, confocal laser scanning microscopy, and total-body photography; we describe the use of graph theoretic concepts for image analysis, give some medical background on skin cancer and concentrate on the challenges when dealing with lesion images. We discuss some relevant algorithms, including the watershed algorithm, region splitting (graph cuts), region merging (minimum spanning tree) and finally describe some open problems and future challenges.

Casebook: a virtual patient iPad application for teaching decision-making through the use of electronic health records

BackgroundVirtual Patients are a well-known and widely used form of interactive software used to simulate aspects of patient care that students are increasingly less likely to encounter during their studies. However, to take full advantage of the benefits of using Virtual Patients, students should have access to multitudes of cases. In order to promote the creation of collections of cases, a tablet application was developed which makes use of electronic health records as material for Virtual Patient cases. Because electronic health records are abundantly available on hospital information systems, this results in much material for the basis of case creation.ResultsAn iPad-based Virtual Patient interactive software system was developed entitled Casebook. The application has been designed to read specially formatted patient cases that have been created using electronic health records, in the form of X-ray images, electrocardiograms, lab reports, and physician notes, and present these to the medical student. These health records are organised into a timeline, and the student navigates the case while answering questions regarding the patient along the way. Each health record can also be annotated with meta-information by the case designer, such as insight into the thought processes and the decision-making rationale of the physician who originally worked with the patient. Students learn decision-making skills by observing and interacting with real patient cases in this simulated environment. This paper discusses our approach in detail.ConclusionsOur group is of the opinion that Virtual Patient cases, targeted at undergraduate students, should concern patients who exhibit prototypical symptoms of the kind students may encounter when beginning their first medical jobs. Learning theory research has shown that students learn decision-making skills best when they have access to multitudes of patient cases and it is this plurality that allows students to develop their illness scripts effectively. Casebook emphasises the use of pre-existing electronic health record data as the basis for case creation, thus, it is hoped, making it easier to produce cases in larger numbers. By creating a Virtual Patient system where cases are built from abundantly available electronic health records, collections of cases can be accumulated by institutions.

Development of an interactive application for learning medical procedures and clinical decision making

This paper outlines the development of a Virtual Patient style tablet application for the purpose of teaching decision making to undergraduate students of medicine. In order to objectively compare some of the various technologies available, the application was written using two different languages: one as a native iPad app written in Objective-C, the other as a web-based app written in HTML5, CSS3, and JavaScript. The requirements for both applications were identical, and this paper will discuss the relative advantages and disadvantages of both technologies from both a HCI point of view and from a technological point of view. Application deployment, user-computer interaction, usability, security, and cross-platform interoperability are also discussed. The motivation for developing this application, entitled Casebook, was to create a platform to test the novel approach of using real patient records to teach undergraduate students. These medical records form patient cases, and these cases are navigated using the Casebook application with the goal of teaching decision making and clinical reasoning; the pretext being that real cases more closely match the context of the hospital ward and thereby increase authentic activity. Of course, patient cases must possess a certain level of quality to be useful. Therefore, the quality of documentation and, most importantly, qualitys impact on healthcare is also discussed.

Java's alternatives and the limitations of Java when writing cross-platform applications for mobile devices in the medical domain

In this paper we discuss alternatives to Java ME when writing medical applications for mobile devices across multiple platforms. The Java Virtual Machine, which runs Java programs, is not available for the majority of handheld devices, such as Palm PDAs, Windows Mobile based devices, or the Apple iPhone. As well as this, we conclude that full GUI interaction, such as the interaction provided by Java programs, is not an absolute requirement to make a program useful, and we developed an HTML-based medical information application to illustrate this. This program displays various sample patient parameters to the user in graph form, and was tested on multiple platforms and operating systems to demonstrate its platform/OS independence and usefulness.

Darwin, Lamarck, or Baldwin: Applying Evolutionary Algorithms to Machine Learning Techniques

Evolutionary Algorithms (EAs), inspired by biological mechanisms observed in nature, such as selection and genetic changes, have much potential to find the best solution for a given optimisation problem. Contrary to Darwin, and according to Lamarck and Baldwin, organisms in natural systems learn to adapt over their lifetime and allow to adjust over generations. Whereas earlier research was rather reserved, more recent research underpinned by the work of Lamarck and Baldwin, finds that these theories have much potential, particularly in upcoming fields such as epigenetics. In this paper, we report on some experiments with different evolutionary algorithms with the purpose to improve the accuracy of data mining methods. We explore whether and to what extent an optimisation goal can be reached through a calculation of certain parameters or attribute weightings by use of such evolutionary strategies. We provide a look at different EAs inspired by the theories of Darwin, Lamarck, and Baldwin, as well as the problem solving methods of certain species. In this paper we demonstrate that the modification of well-established machine learning techniques can be achieved in order to include methods from genetic algorithm theory without extensive programming effort. Our results pave the way for much further research at the cross section of machine learning optimisation techniques and evolutionary algorithm research.

On the paradigm shift of search on mobile devices: some remarks on user habits

This paper addresses a paradigm shift in the way the web is being searched. This shift is occurring due to the increasing percentage of search requests being made from mobile devices, changing the way users search the web. This change is occurring for two reasons: first, users of smart phones are no longer searching the web relying on generic, horizontal search engines as they do on the desktop, and second, smart phones are far more aware of the users context than desktop machines. Smart phones typically include multiple sensors that can describe the users current context in a very accurate way, something the standard desktop machine cannot normally do. This shift will mean changes for the information retrieval community, the developers of applications, the developers of online services, usability engineers, and the developers of search engines themselves.

Navigating through very large sets of medical records: an information retrieval evaluation architecture for non-standardized text

Despite the prevalence of informatics and advanced information systems, there exists large amounts of unstructured text data. This is especially true in medicine and health care, where free text is an indispensable part of information representation. In this paper, the motivation behind developing information retrieval systems in medicine and health care is described. An overview of information retrieval evaluation is given, before describing the architecture and the development of an extendible information retrieval evaluation framework. This framework allows different information retrieval tools to be compared to a gold standard in order to test its effectiveness. The paper also gives a review of available gold standards which can be used for research purposes in the area of information retrieval of medical free texts.

A Tutorial on Machine Learning and Data Science Tools with Python

In this tutorial, we will provide an introduction to the main Python software tools used for applying machine learning techniques to medical data. The focus will be on open-source software that is freely available and is cross platform. To aid the learning experience, a companion GitHub repository is available so that you can follow the examples contained in this paper interactively using Jupyter notebooks. The notebooks will be more exhaustive than what is contained in this chapter, and will focus on medical datasets and healthcare problems. Briefly, this tutorial will first introduce Python as a language, and then describe some of the lower level, general matrix and data structure packages that are popular in the machine learning and data science communities, such as NumPy and Pandas. From there, we will move to dedicated machine learning software, such as SciKit-Learn. Finally we will introduce the Keras deep learning and neural networks library. The emphasis of this paper is readability, with as little jargon used as possible. No previous experience with machine learning is assumed. We will use openly available medical datasets throughout.