Combining open‐source natural language processing tools to parse clinical practice guidelines

Natural language processing (NLP) has been used to process text pertaining to patient records and narratives. However, most of the methods used were developed for specific systems, so new research is necessary to assess whether such methods can be easily retargeted for new applications and goals, with the same performance. In this paper, open‐source tools are reused as building blocks on which a new system is built. The aim of our work is to evaluate the applicability of the current NLP technology to a new domain: automatic knowledge acquisition of diagnostic and therapeutic procedures from clinical practice guideline free‐text documents. In order to do this, two publicly available syntactic parsers, several terminology resources and a tool oriented to identify semantic predications were tailored to increase the performance of each tool individually. We apply this new approach to 171 sentences selected by the experts from a clinical guideline, and compare the results with those of the tools applied with no tailoring. The results of this paper show that with some adaptation, open‐source NLP tools can be retargeted for new tasks, providing an accuracy that is equivalent to the methods designed for specific tasks.     

Experiences developing architectures for realizing thin‐client diagram editing tools

Diagram‐centric applications such as software design tools, project planning tools and business process modelling tools are usually ‘thick‐client’ applications running as stand‐alone desktop applications. There are several advantages to providing such design tools as Web‐based or even PDA‐ and mobile‐phone‐based applications. These include ease of access and upgrade, provision of collaborative work support and Web‐based integration with other applications. However, building such thin‐client diagram editing tools is very challenging. We have developed several thin‐client diagram editing applications realized as a set of plug‐in extensions to a meta‐tool for visual design environment development. In this paper, we discuss key user interaction and software architecture issues, illustrate examples of interacting with our thin‐client diagram editing tools, describe our design and implementation approaches, and present the results of several different evaluations of the resultant applications. Our experiences will be useful for those interested in developing their own thin‐client diagram editing architectures and applications. Copyright © 2007 John Wiley & Sons, Ltd.     

Using natural language sources in model-based knowledge acquisition

This paper introduces a well defined co-operation between domain expert, knowledge engineer, and knowledge acquisition and transformation tools. First, the domain expert supported by a hypertext tool generates an intermediate representation from parts of authentic texts of a domain. As a side effect, this representation serves as human readable documentation. In subsequent steps, this representation is semi-automatically transformed into a formal representation by knowledge acquisition tools. These tools are fully adapted to the expert's domain both in terminology and model structure which are developed by the knowledge engineer from a library of generic models and with preparation tools.     

Sketch‐Based Editing Tools for Tumour Segmentation in 3D Medical Images

In the past years sophisticated automatic segmentation algorithms for various medical image segmentation problems have been developed. However, there are always cases where automatic algorithms fail to provide an acceptable segmentation. In these cases the user needs efficient segmentation editing tools, a problem which has not received much attention in research. We give a comprehensive overview on segmentation editing for three‐dimensional (3D) medical images. For segmentation editing in two‐dimensional (2D) images, we discuss a sketch‐based approach where the user modifies the segmentation in the contour domain. Based on this 2D interface, we present an image‐based as well as an image‐independent method for intuitive and efficient segmentation editing in 3D in the context of tumour segmentation in computed tomography (CT). Our editing tools have been evaluated on a database containing 1226 representative liver metastases, lung nodules and lymph nodes of different shape, size and image quality. In addition, we have performed a qualitative evaluation with radiologists and technical experts, proving the efficiency of our tools.     

A design for a common‐sense knowledge‐enhanced decision‐support system: Integration of high‐frequency market data and real‐time news

According to efficient markets theory, information is an important factor that affects market performance and serves as a source of first‐hand evidence in decision making, in particular with the rapid rise of Internet technologies in recent years. However, a lack of knowledge and inference ability prevents current decision support systems from processing the wide range of available information. In this paper, we propose a common‐sense knowledge‐supported news model. Compared with previous work, our model is the first to incorporate broad common‐sense knowledge into a decision support system, thereby improving the news analysis process through the application of a graphic random‐walk framework. Prototype and experiments based on Hong Kong stock market data have demonstrated that common‐sense knowledge is an important factor in building financial decision models that incorporate news information.     

Bridging the gap between tracking and detecting changes in XML

There are two main approaches to manage changes in XML documents, change‐tracking and diff. Change‐tracking tools, which record edit actions while they are performed on the source document, are able to capture the exact editing process. That is much more difficult for diff algorithms, which have to reconstruct it by comparing two different versions. Interestingly, these algorithms process both text‐centric and data‐centric XML documents the same way. In this paper, we show that more accurate, clear, and human‐readable results can be achieved on text‐centric resources, by employing specific models and algorithms. We describe and discuss a specialized diff algorithm for such a class of documents. We also compare a Java implementation of the algorithm, named JNDiff, with other general‐purpose or data‐oriented diff tools, focusing on the quality of their output. Copyright © 2014 Copyright © 2014 John Wiley & Sons, Ltd.     

MobiGuide: a personalized and patient-centric decision-support system and its evaluation in the atrial fibrillation and gestational diabetes domains

MobiGuide is a ubiquitous, distributed and personalized evidence-based decision-support system (DSS) used by patients and their care providers. Its central DSS applies computer-interpretable clinical guidelines (CIGs) to provide real-time patient-specific and personalized recommendations by matching CIG knowledge with a highly-adaptive patient model, the parameters of which are stored in a personal health record (PHR). The PHR integrates data from hospital medical records, mobile biosensors, data entered by patients, and recommendations and abstractions output by the DSS. CIGs are customized to consider the patients’ psycho-social context and their preferences; shared decision making is supported via decision trees instantiated with patient utilities. The central DSS “projects” personalized CIG-knowledge to a mobile DSS operating on the patients’ smart phones that applies that knowledge locally. In this paper we explain the knowledge elicitation and specification methodologies that we have developed for making CIGs patient-centered and enabling their personalization. We then demonstrate feasibility, in two very different clinical domains, and two different geographic sites, as part of a multi-national feasibility study, of the full architecture that we have designed and implemented. We analyze usage patterns and opinions collected via questionnaires of the 10 atrial fibrillation (AF) and 20 gestational diabetes mellitus (GDM) patients and their care providers. The analysis is guided by three hypotheses concerning the effect of the personal patient model on patients and clinicians’ behavior and on patients’ satisfaction. The results demonstrate the sustainable usage of the system by patients and their care providers and patients’ satisfaction, which stems mostly from their increased sense of safety. The system has affected the behavior of clinicians, which have inspected the patients’ models between scheduled visits, resulting in change of diagnosis for two of the ten AF patients and anticipated change in therapy for eleven of the twenty GDM patients.     

Interactive parallel programming using the ParaScope Editor

The ParaScope Editor, an intelligent interactive editor for parallel Fortran programs, which is the centerpiece of the ParaScope project, an integrated collection of tools to help scientific programmers implement correct and efficient parallel programs, is discussed. ParaScope Editor reveals to users potential hazards of a proposed parallelization in a program. It provides a variety of powerful interactive program transformations that have been shown useful in converting programs to parallel form. ParaScope Editor supports general user editing through a hybrid text and structure editing facility that incrementally analyzes the modified program for potential hazards. It is shown that ParaScope Editor supports an exploratory programming style in which users get immediate feedback on their various strategies for parallelization     

TouchTone: Interactive Local Image Adjustment Using Point‐and‐Swipe

Recent proliferation of camera phones, photo sharing and social network services has significantly changed how we process our photos. Instead of going through the traditional download‐edit‐share cycle using desktop editors, an increasing number of photos are taken with camera phones and published through cellular networks. The immediacy of the sharing process means that on‐device image editing, if needed, should be quick and intuitive. However, due to the limited computational resources and vastly different user interaction model on small screens, most traditional local selection methods can not be directly adapted to mobile devices. To address this issue, we present TouchTone, a new method for edge‐aware image adjustment using simple finger gestures. Our method enables users to select regions within the image and adjust their corresponding photographic attributes simultaneously through a simple point‐and‐swipe interaction. To enable fast interaction, we develop a memory‐ and computation‐efficient algorithm which samples a collection of 1D paths from the image, computes the adjustment solution along these paths, and interpolates the solutions to entire image through bilateral filtering. Our system is intuitive to use, and can support several local editing tasks, such as brightness, contrast, and color balance adjustments, within a minute on a mobile device.     

Ink‐jet printing: The route to production of full‐color P‐OLED displays

Abstract— Ink‐jet‐printing technology for displays has been making rapid progress and is now nearing production. This paper will go through the developments that have been carried out at CDT, Ltd., to achieve this status. The ink‐jet head and machine development that underpin the capability of the RGB printing process to manufacture P‐OLEDs at high speed with high reliability and with the film‐forming properties to achieve the appropriate device performance will be described. The important contribution made by the availability of flexible metrological tools will be discussed.     

Development of a knowledge‐based system for nonpowered hand tools (Tool Expert): Part I—The scientific basis

The need for developing a clear and concise guide for designing, selecting, and using hand tools would minimize if not eliminate acute–chronic trauma exposure factors and help improve efficiency, well‐being, and morale. Despite several research efforts devoted to the exploration and understanding of the interrelation between human capabilities, task requirements, nature of tasks, and ergonomically designed hand tools, there appear to be several problems in utilizing existing knowledge in practical use. One of the most important barriers is the lack of interaction of several specialists from different backgrounds. In this article, TOOL‐EXPERT, a knowledge‐based system developed to assert the ergonomical nonpowered hand tool design, selection, and use, is explained, which will provide a guideline to several users from various backgrounds. The system is designed to run in any IBM‐compatible personal computer system. Knowledge from several domains was included. The type of knowledge used in the research was selected to be a declarative knowledge. Altogether it includes 423 goals, 35 questions, and 40 rules. © 2004 Wiley Periodicals, Inc. Hum Factors Man 14: 257–268, 2004.     

Visual knowledge specification for conceptual design: Definition and tool support

Current CAD tools are not able to support the conceptual design phase, and none of them provides a consistency analysis for sketches produced by architects. This phase is fundamental and crucial for the whole design and construction process of a building. To give architects a better support, we developed a CAD tool for conceptual design and a knowledge specification tool. The knowledge is specific to one class of buildings and it can be reused. Based on a dynamic and domain-specific knowledge ontology, different types of design rules formalize this knowledge in a graph-based form. An expressive visual language provides a user-friendly, human readable representation. Finally, a consistency analysis tool enables conceptual designs to be checked against this formal conceptual knowledge.In this article, we concentrate on the knowledge specification part. For that, we introduce the concepts and usage of a novel visual language and describe its semantics. To demonstrate the usability of our approach, two graph-based visual tools for knowledge specification and conceptual design are explained.     

On‐Site Example‐Based Material Appearance Acquisition

We present a novel example‐based material appearance modeling method suitable for rapid digital content creation. Our method only requires a single HDR photograph of a homogeneous isotropic dielectric exemplar object under known natural illumination. While conventional methods for appearance modeling require prior knowledge on the object shape, our method does not, nor does it recover the shape explicitly, greatly simplifying on‐site appearance acquisition to a lightweight photography process suited for non‐expert users. As our central contribution, we propose a shape‐agnostic BRDF estimation procedure based on binary RGB profile matching. We also model the appearance of materials exhibiting a regular or stationary texture‐like appearance, by synthesizing appropriate mesostructure from the same input HDR photograph and a mesostructure exemplar with (roughly) similar features. We believe our lightweight method for on‐site shape‐agnostic appearance acquisition presents a suitable alternative for a variety of applications that require plausible “rapid‐appearance‐modeling”.     

Development and implementation of clinical guidelines: An artificial intelligence perspective

Clinical practice guidelines in paper format are still the preferred form of delivery of medical knowledge and recommendations to healthcare professionals. Their current support and development process have well identified limitations to which the healthcare community has been continuously searching solutions. Artificial intelligence may create the conditions and provide the tools to address many, if not all, of these limitations.. This paper presents a comprehensive and up to date review of computer-interpretable guideline approaches, namely Arden Syntax, GLIF, PROforma, Asbru, GLARE and SAGE. It also provides an assessment of how well these approaches respond to the challenges posed by paper-based guidelines and addresses topics of Artificial intelligence that could provide a solution to the shortcomings of clinical guidelines. Among the topics addressed by this paper are expert systems, case-based reasoning, medical ontologies and reasoning under uncertainty, with a special focus on methodologies for assessing quality of information when managing incomplete information. Finally, an analysis is made of the fundamental requirements of a guideline model and the importance that standard terminologies and models for clinical data have in the semantic and syntactic interoperability between a guideline execution engine and the software tools used in clinical settings. It is also proposed a line of research that includes the development of an ontology for clinical practice guidelines and a decision model for a guideline-based expert system that manages non-compliance with clinical guidelines and uncertainty.     

农业智能系统的知识获取技术研究

作者及其团队长期针对农业领域的知识获取技术进行了系列性研究.阐述了运用智能引导、机器学习、数据挖掘、智能计算等技术的人工和自动/半自动的知识获取方法.这些方法能够有效地获取领域知识,发现隐含模式,进行知识精化.研发了知识获取工具.这些方法和工具反映了知识获取技术对农业信息工程所起的重要作用.     

Flexible and Accurate Transparent‐Object Matting and Compositing Using Refractive Vector Field

In digital image editing, environment matting and compositing are fundamental and interesting operations that can capture and simulate the refraction and reflection effects of light from an environment. The state‐of‐the‐art real‐time environment matting and compositing method is short of flexibility, in the sense that it has to repeat the entire complex matte acquisition process if the distance between the object and the background is different from that in the acquisition stage, and also lacks accuracy, in the sense that it can only remove noises but not errors. In this paper, we introduce the concept of refractive vector and propose to use a refractive vector field as a new representation for environment matte. Such refractive vector field provides great flexibility for transparent‐object environment matting and compositing. Particularly, with only one process of the matte acquisition and the refractive vector field extraction, we are able to composite the transparent object into an arbitrary background at any distance. Furthermore, we introduce a piecewise vector field fitting algorithm to simultaneously remove both noises and errors contained in the extracted matte data. Experimental results show that our method is less sensitive to artefacts and can generate perceptually good composition results for more general scenarios.     

An integral system‐ergonomic approach for IT‐based process management in complex work environments by example of manufacturing and health care

Recent trends in manufacturing and health care move these two work systems closer together from a system ergonomics point of view. Individual treatment of products, especially patients, by specialists in a distributed environment demand information technology (IT)‐based support suitable for complex systems. IT‐based support of processes in complex systems is difficult due to the lack of standard processes. IT support also means to rethink processes to use efficiency potentials. Close cooperation of users and software developers is needed to increase the ergonomic quality of the system. Therefore, suitable tools are needed: UML is available as the standard industry modeling language, Zope/Plone as the quasi‐standard for content management systems, SimPy as an object‐oriented simulation tool for event‐triggered processes, and ACT‐R as a powerful cognitive architecture for simulation of human information processes. The integration of these tools enables system‐ergonomic support of processes in the complex work system as well as of the development and deployment process. It is the base of an integral system‐ergonomic approach for IT‐based process management. Knowledge gained during process analysis either enters models or leads to the extension and adaptation of the tool chain. The models serve as basis for discussion among system ergonomists, programmers, and specialists from the work system. Further, they are understood by simulation and process support tools. Transcoding efforts between humans with different professional backgrounds and machines are reduced, and the flexibility demanded by complex systems is met. © 2008 Wiley Periodicals, Inc.     

Rule‐based approach for topic maps learning from relational databases

Relational databases (RDBs) have been widely used as back end for information systems. Considering that RDBs have valuable knowledge interwoven in between stored data, how to access, represent and share this knowledge becomes an important challenge. Topic maps (TMs) emerge as a good solution for this problem. However, manual development of TMs is a difficult, time‐consuming and subjective task if there is no common guideline. The existing TMs building approaches mainly consider the meta‐information contained in a RDB, without considering the knowledge residing in the database content (its current state). Other approaches require a predefined configuration for applying a specific data transformation. This paper proposes an automatic method for TM construction based on learning rules. Our method considers the background knowledge of the RDBs during the building process and was implemented and applied on a representative set of 15 RDBs. The resulting TMs were validated syntactically using a standard tool and validated semantically through the inference of information using a formal query language. In addition, an analysis between the relational data (input) and its representation (output) was conducted. The results found in our experiments are encouraging and put in evidence the soundness of the proposed method.     

HIGH‐PRECISION BIO‐MOLECULAR EVENT EXTRACTION FROM TEXT USING PARALLEL BINARY CLASSIFIERS

We have developed a machine learning framework to accurately extract complex genetic interactions from text. Employing type‐specific classifiers, this framework processes research articles to extract various biological events. Subsequently, the algorithm identifies regulation events that take other events as arguments, allowing a nested structure of predictions. All predictions are merged into an integrated network, useful for visualization and for deduction of new biological knowledge. In this paper, we discuss several design choices for an event‐based extraction framework. These detailed studies help improving on existing systems, which is illustrated by the relative performance gain of 10% of our system compared to the official results in the recent BioNLP’09 Shared Task. Our framework now achieves state‐of‐the‐art performance with 37.43 recall, 54.81 precision and 44.48 F‐score. We further present the first study of feature selection for bio‐molecular event extraction from text. While producing more cost‐effective models, feature selection can also lead to a better insight into the complexity of the challenge. Finally, this paper tries to bridge the gap between theoretical relation extraction from text and experimental work on bio‐molecular interactions by discussing interesting opportunities to employ event‐based text mining tools for real‐life tasks such as hypothesis generation, database curation and knowledge discovery.