Arturo González-Ferrer

Automated generation of patient-tailored electronic care pathways by translating computer-interpretable guidelines into hierarchical task networks

OBJECTIVE This paper describes a methodology which enables computer-aided support for the planning, visualization and execution of personalized patient treatments in a specific healthcare process, taking into account complex temporal constraints and the allocation of institutional resources. To this end, a translation from a time-annotated computer-interpretable guideline (CIG) model of a clinical protocol into a temporal hierarchical task network (HTN) planning domain is presented. MATERIALS AND METHODS The proposed method uses a knowledge-driven reasoning process to translate knowledge previously described in a CIG into a corresponding HTN Planning and Scheduling domain, taking advantage of HTNs known ability to (i) dynamically cope with temporal and resource constraints, and (ii) automatically generate customized plans. The proposed method, focusing on the representation of temporal knowledge and based on the identification of workflow and temporal patterns in a CIG, makes it possible to automatically generate time-annotated and resource-based care pathways tailored to the needs of any possible patient profile. RESULTS The proposed translation is illustrated through a case study based on a 70 pages long clinical protocol to manage Hodgkins disease, developed by the Spanish Society of Pediatric Oncology. We show that an HTN planning domain can be generated from the corresponding specification of the protocol in the Asbru language, providing a running example of this translation. Furthermore, the correctness of the translation is checked and also the management of ten different types of temporal patterns represented in the protocol. By interpreting the automatically generated domain with a state-of-art HTN planner, a time-annotated care pathway is automatically obtained, customized for the patients and institutional needs. The generated care pathway can then be used by clinicians to plan and manage the patients long-term care. CONCLUSION The described methodology makes it possible to automatically generate patient-tailored care pathways, leveraging an incremental knowledge-driven engineering process that starts from the expert knowledge of medical professionals. The presented approach makes the most of the strengths inherent in both CIG languages and HTN planning and scheduling techniques: for the former, knowledge acquisition and representation of the original clinical protocol, and for the latter, knowledge reasoning capabilities and an ability to deal with complex temporal and resource constraints. Moreover, the proposed approach provides immediate access to technologies such as business process management (BPM) tools, which are increasingly being used to support healthcare processes.

Solving the interoperability challenge of a distributed complex patient guidance system: A data integrator based on HL7’s Virtual Medical Record standard

OBJECTIVE We show how the HL7 Virtual Medical Record (vMR) standard can be used to design and implement a data integrator (DI) component that collects patient information from heterogeneous sources and stores it into a personal health record, from which it can then retrieve data. Our working hypothesis is that the HL7 vMR standard in its release 1 version can properly capture the semantics needed to drive evidence-based clinical decision support systems. MATERIALS AND METHODS To achieve seamless communication between the personal health record and heterogeneous data consumers, we used a three-pronged approach. First, the choice of the HL7 vMR as a message model for all components accompanied by the use of medical vocabularies eases their semantic interoperability. Second, the DI follows a service-oriented approach to provide access to system components. Third, an XML database provides the data layer.Results The DI supports requirements of a guideline-based clinical decision support system implemented in two clinical domains and settings, ensuring reliable and secure access, high performance, and simplicity of integration, while complying with standards for the storage and processing of patient information needed for decision support and analytics. This was tested within the framework of a multinational project (www.mobiguide-project.eu) aimed at developing a ubiquitous patient guidance system (PGS). DISCUSSION The vMR model with its extension mechanism is demonstrated to be effective for data integration and communication within a distributed PGS implemented for two clinical domains across different healthcare settings in two nations.

Automatic generation of temporal planning domains for e-learning problems

AI Planning & Scheduling techniques are being widely used to adapt learning paths to the special features and needs of students both in distance learning and lifelong learning environments. However, instructors strongly rely on Planning & Scheduling experts to encode and review the domains for the planner/scheduler to work. This paper presents an approach to automatically extract a fully operational HTN planning domain and problem from a learning objects repository without requiring the intervention of any planning expert, and thus enabling an easier adoption of this technology in practice. The results of a real experiment with a small group of students within an e-Learning private company in Spain are also shown.

Data integration for clinical decision support based on openEHR archetypes and HL7 virtual medical record

Clinical Decision Support Systems (CDSS) have gained relevance due to their potential to support patient-centric care, but their deployment still has to overcome barriers to become successful. One of these barriers is the integration of patient data with the CDSS engine, a tough challenge given the need to address interoperability with many different existing systems and medical devices. The MobiGuide project aims to build such a CDSS, providing guideline- based clinical decision support through a Personal Health Record (PHR). This PHR is the main component through which the CDSS could access patient data originating from hospital EMRs and wearable sensors, but it also contains the log of the recommendations provided by the CDSS. Using a case study, we compare data-representation standards through which the PHR could be developed, while considering expressiveness and usability requirements. We propose to develop the PHR by combining openEHR archetypes and the HL7 Virtual Medical Record standard, supported by a service oriented framework for data exchange. This proposal aims to close the gap between the HL7 and the ISO/CEN 13606 by using an openEHR-based approach.

From business process models to hierarchical task network planning domains

Hierarchical Task Network (HTN) planning paradigm has been widely used during the last decade to model and solve planning and scheduling (P&S) problems, and it has proved to be very useful in the planning and coordination of human tasks. At the same time, Business Process Management (BPM) tools are being increasingly used in the modeling of organizations’ business practices and processes, but their life cycle has shown to have some shortages (as the possibility to obtain context-dependent plan instances). In this paper we present a methodology and software framework to translate Business Process Models into HTN P&S domains, in order to cover some of these deficiencies. 1 Introduction and motivation Enterprises and organizations are facing today the emerging challenge of integration and automation of their business processes. The complexity of this issue increases when they have to deal with human-centric processes, as they are usually carried out in an informal manner, and the coordination of the different tasks and participants involved in these processes is very difficult to achieve. In this case, new technologies, mostly oriented to support decision making, have to be introduced to help knowledge workers like organization managers and decision makers to successfully achieve this goal.

Understanding requirements of clinical data standards for developing interoperable knowledge-based DSS

Knowledge-based Clinical Decision Support Systems (KB-DSSs) promise to provide patient-specific recommendations, generated by matching the KB with electronic patient data from various sources. The challenge of making KB-DSSs interoperable can be simplified by including those data sources into an integrated Personal Health Record (PHR). This paper aims to identify relevant criteria to support the evaluation of data standards for the PHR, following a case-study approach. 15 functional and non- functional criteria were identified and used to evaluate selected standards (HL7 CDA, HL7 vMR and openEHR). Our evaluation identifies their main advantages and disadvantages to support the development of interoperable, data-integrated KB-DSSs We identify and use 15 functional and non-functional criteria to evaluate standards.We define a methodology based on case-study analysis for the evaluation of the standards.Using a PHR as an intermediate system enables CDSS interoperability with data sources.An online appendix is provided to show the modeling of the case-study examples.

Towards the Use of XPDL as Planning and Scheduling Modeling Tool: The Workflow Patterns Approach

This paper presents a transformation from a business process model diagram stored in XPDL format, into a hierarchical extension of the PDDL planning language, using the concept of workflow patterns as base of the translation process. The proposed architecture is evaluated within a specific teamwork project management scenario: the allocation of human resources and web services for the cooperative development of on-line courses in an e-learning center.

Automatic Generation of User Adapted Learning Designs: An AI-Planning Proposal

A Learning Design(LD) definition under the IMS-LD standard is a complex task for the instructor because it requires a lot of time, effort and previous knowledge of the students group over which will be defined the knowledge objectives. That is why, taking advantage from diffusion of learning objects(LO) labeling using IMS-MD standard, we have proposed to realize a knowledge engineering process, represented as an algorithm, over LO labels and user profiles to automaticaly define a domain that will be used by an intelligent planner to build a LD. This LD will be finally implemented in the ILIAS Learning Management System(LMS).

Analysis of the process of representing clinical statements for decision-support applications: a comparison of openEHR archetypes and HL7 virtual medical record

Delivering patient-specific decision-support based on computer-interpretable guidelines (CIGs) requires mapping CIG clinical statements (data items, clinical recommendations) into patients’ data. This is most effectively done via intermediate data schemas, which enable querying the data according to the semantics of a shared standard intermediate schema. This study aims to evaluate the use of HL7 virtual medical record (vMR) and openEHR archetypes as intermediate schemas for capturing clinical statements from CIGs that are mappable to electronic health records (EHRs) containing patient data and patient-specific recommendations. Using qualitative research methods, we analyzed the encoding of ten representative clinical statements taken from two CIGs used in real decision-support systems into two health information models (openEHR archetypes and HL7 vMR instances) by four experienced informaticians. Discussion among the modelers about each case study example greatly increased our understanding of the capabilities of these standards, which we share in this educational paper. Differing in content and structure, the openEHR archetypes were found to contain a greater level of representational detail and structure while the vMR representations took fewer steps to complete. The use of openEHR in the encoding of CIG clinical statements could potentially facilitate applications other than decision-support, including intelligent data analysis and integration of additional properties of data items from existing EHRs. On the other hand, due to their smaller size and fewer details, the use of vMR potentially supports quicker mapping of EHR data into clinical statements.

Use of the virtual medical record data model for communication among components of a distributed decision-support system

MobiGuide is a distributed decision-support system (DSS) that provides decision support for patients and physicians. Patients receive support using a light-weight Smartphone DSS linked to data arriving from wearable monitoring devices and physicians receive support via a web interface connected to a backend DSS that has access to an integrated personal health record (PHR) that stores hospital EMR data, monitoring data, and recommendations provided for the patient by the DSSs. The patient data model used by the PHR and by all the system components that interact in a service-oriented architecture is based on HL7s virtual medical record (vMR) model. We describe how we used and extended the vMR model to support communication between the system components for the complex workflow needed to support guidance of patients any time everywhere.