1,721,118 research outputs found
Exception Management in Healthcare Processes
No full textThis chapter describes how abnormal events, also known as ``exceptions''index{Exception}, can be captured and properly managed within an healthcare process model. The chapter initially describes the different types of exceptions, their definition and their classification: then, the chapter provides the reader with some examples of exceptions in the healthcare domain. Next, the chapter describes a methodology (ie , a set of steps, criteria and good practices to be followed at design time) helpful in defining exceptions and in executing them even if the deployed process engine doesn't come with an exception management unit. Finally, the chapter sketches out some conclusions
Models and Architectures for the Enactment of Healthcare Processes
No full textThis chapter introduces the reader to the world of healthcare process management, focusing on modeling approaches and architectures for process enactment. First, the need and the application of process design and execution in healthcare is discussed. As for process modeling, the fundamentals of the Business Process Model and Notation, which is the leading standard for process design, are provided. Then, the relationships between organization, process and information perspectives involved in process management are discussed by means of examples taken from the clinical domain. The chapter ends with an overview of the architecture of a typical Workflow Management System (WfMS), also known as Business Process Engine (BPE), describing its software modules, components, and functionalities
Sistema portatile ed indossabile per la acquisizione, visualizzazione, memorizzazione ed elaborazione prossimale del segnale elettrocardiografico (ECG), per il riconoscimento di eventi aritmici ed ischemici, con trasmissione a distanza
No full textIs My Model Up-to-date? Detecting CoViD-19 Variants by Machine Learning
Full text linkMachine learning extracts models from huge quantities of data. Models trained and validated over past data can be deployed in making forecasts as well as in classifying new incoming data. The real world which generates data may change over time, making the deployed model an obsolete one. To preserve the quality of the currently deployed model, continuous machine learning is required. Our approach retrospectively evaluates in an online fashion the behaviour of the currently deployed model. A drift detector detects any performance slump, and, in case, can replace the previous model with an up-to-date one. The approach experiments on a dataset of 8642 hematochemical examinations from hospitalized patients gathered over 6 months: the outcome of the model predicts the RT-PCR test result about CoViD-19. The method reached an area under the curve (AUC) of 0.794, 6% better than offline and 5% better than standard online-binary classification techniques
Temporal representation and reasoning in medicine
No full textTemporal representation and reasoning is a very challenging research topic in several areas of computer science: among them, we mention here databases, artificial intelligence, theoretical computer science, computational linguistics, real time systems, and medical informatics.
The scientific interest for temporal representation and reasoning is confirmed by a solid tradition of international events, as conferences and workshops, hosting new research on these arguments. Moreover, in the last decade there have been several specific events on the topic, which attracted specialized people sharing their results. Among these events, the TIME Symposium is emerging as the annual event where people from different areas of computer science discuss on time related issues; since 1996 TIME proceedings have been published by IEEE Computer Society. Several special issues of well known scientific journals in the last decade confirm that the interest of the scientific community for the considered topic is stable and sound, even though time and related issues are not a topic suddenly attracting huge quantities of research scientists
Workfklow Management Systems - Exercise Book
No full textThis book collects some written exercises and solutions from the classworks of the course “Workgroup and Workflow Systems” at the Como campus of the Politecnico di Milano, Milano, Italy.
Throughout the book, two approaches will be presented to describe business processes: the first approach is based on the UML (Unified Modelling Language) notation (including use case diagrams, class diagrams, activity diagrams) and on the BPMN (Business Process Modelling Notation) notation; the second approach is based on the WIDE (Worfklow on Intelligent Distributed database Environments) methodology, derived from the EU-funded project WIDE
Aiding the Development of Active Applications
No full textActive applications are characterized by the need for expressing, evaluating, and maintaining a set of rules that implement the application’s active behavior. Typically, rules follow the Event-Condition-Action (ECA) paradigm, yet oftentimes their actual implementation is buried in the application code, as their enactment requires a tight integration with the concepts and modules of the application. In this article, we propose a rule management system that allows developers to easily expand its rule processing logic with such concepts and modules and, hence, to decouple the management of their active rules from the application code. Our system derives from an exception manager that has previously been developed in the context of an industry-scale workflow management system and effectively allows developers to separate active and non-active design concern
A database schema for public-domain medical software
No full textThe quantity of public-domain medical software available is huge, and a classification schema may be therefore helpful. We developed a schema that includes identification data (name of the software, author, etc.), description (hardware and software requirements), classification (software category, application domain, etc.) and evaluation data (external quality and internal quality factors). The schema was tested on the public-domain software available at the SCAMC meetings (about 36 Mb). We also classified the software by employing students from a master course in computer science and medical informatics. We stored the high quantity of information collected in a database we developed using Paradox
Guest Editorial for the ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
No full textIt is our great pleasure to present this special issue of the
IEEE/ACM Transactions on Computational Biology and Bioinformatics. The special issue includes six papers, which were invited from the ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM BCB) in 2017. ACM BCB is the flagship conference of the ACM SIG on Bioinformatics, Computational Biology and Biomedical Informatics (SIGBio). In total, 212 papers were submitted to the ACM BCB conference in 2017, among which 50 were accepted as regular papers. Of these, six were invited for the special section. These papers were significantly extended from their earlier versions and went through a separate revision process. These papers cover a broad spectrum of applications, and have great potential to further bioinformatics and computational biology research
- …
