Ten years of knowledge representation for health care (2009-2018): Topics, trends, and challenges

BACKGROUND In the last ten years, the international workshop on knowledge representation for health care (KR4HC) has hosted outstanding contributions of the artificial intelligence in medicine community pertaining to the formalization and representation of medical knowledge for supporting clinical care. Contributions regarding modeling languages, technologies and methodologies to produce these models, their incorporation into medical decision support systems, and practical applications in concrete medical settings have been the main contributions and the basis to define the evolution of this field across Europe and worldwide. OBJECTIVES Carry out a review of the papers accepted in KR4HC in the 2009-2018 decade, analyze and characterize the topics and trends within this field, and identify challenges for the evolution of the area in the near future. METHODS We reviewed the title, the abstract, and the keywords of the 112 papers that were accepted to the workshop, identified the medical and technological topics involved in these works, provided a classification of these papers in medical and technological perspectives and obtained the timeline of these topics in order to determine interest growths and declines. The experience of the authors in the field and the evidences after the review were the basis to propose a list of challenges of knowledge representation in health care for the future. RESULTS The most generic knowledge representation methods are ontologies (31%), semantic web related formalisms (26%), decision tables and rules (19%), logic (14%), and probabilistic models (10%). From a medical informatics perspective, knowledge is mainly represented as computer interpretable clinical guidelines (43%), medical domain ontologies (26%), and electronic health care records (22%). Within the knowledge lifecycle, contributions are found in knowledge generation (38%), knowledge specification (24%), exception detection and management (12%), knowledge enactment (8%), temporal knowledge and reasoning (7%), and knowledge sharing and maintenance (7%). The clinical emphasis of knowledge is mainly related to clinical treatments (27%), diagnosis (13%), clinical quality indicators (13%), and guideline integration for multimorbid patients (12%). According to the level of development of the works presented, we distinguished four maturity levels: formal (22%), implementation (52%), testing (13%), and deployment (2%) levels. Some papers described technologies for specific clinical issues or diseases, mainly cancer (22%) and diseases of the circulatory system (20%). Chronicity and comorbidity were present in 10% and 8% of the papers, respectively. CONCLUSIONS KR4HC is a stable community, still active after ten years. A persistent focus has been knowledge representation, with an emphasis on semantic-web ontologies and on clinical-guideline based decision-support. Among others, two topics receive growing attention: integration of computer-interpretable guideline knowledge for the management of multimorbidity patients, and patient empowerment and patient-centric care.

[1]  Nicolette de Keizer,et al.  Towards the Automated Calculation of Clinical Quality Indicators , 2011, KR4HC.

[2]  Daniele Theseider Dupré,et al.  Answer Set Programming for Temporal Conformance Analysis of Clinical Guidelines Execution , 2015, KR4HC/ProHealth.

[3]  Mor Peleg,et al.  Data Integration for Clinical Decision Support Based on openEHR Archetypes and HL7 Virtual Medical Record , 2012, ProHealth/KR4HC.

[4]  David Riaño,et al.  A Patient Simulation Model Based on Decision Tables for Emergency Shocks , 2015, KR4HC/ProHealth.

[5]  David Riaño,et al.  Rule-Based Combination of Comorbid Treatments for Chronic Diseases Applied to Hypertension, Diabetes Mellitus and Heart Failure , 2012, ProHealth/KR4HC.

[6]  Juan Fernández-Olivares,et al.  Task Network Based Modeling, Dynamic Generation and Adaptive Execution of Patient-Tailored Treatment Plans Based on Smart Process Management Technologies , 2011, KR4HC.

[7]  Yuval Shahar,et al.  Implementation of a System for Intelligent Summarization of Longitudinal Clinical Records , 2013, KR4HC/ProHealth.

[8]  Guus Schrijvers,et al.  The Care Pathway Concept: concepts and theories: an introduction , 2012 .

[9]  Mar Marcos,et al.  Assessment of Clinical Guideline Models Based on Metrics for Business Process Models , 2014, KR4HC@VSL.

[10]  Juan Fernández-Olivares,et al.  Knowledge-Driven Adaptive Execution of Care Pathways Based on Continuous Planning Techniques , 2012, ProHealth/KR4HC.

[11]  Peter J. F. Lucas,et al.  Critiquing Knowledge Representation in Medical Image Interpretation Using Structure Learning , 2010, KR4HC.

[12]  Alessio Bottrighi,et al.  META-GLARE: A Meta-System for Defining Your Own CIG System: Architecture and Acquisition , 2014, KR4HC@VSL.

[13]  Daniele Theseider Dupré,et al.  Temporal Conformance Analysis and Explanation on Comorbid Patients , 2018, HEALTHINF.

[14]  Nicolette de Keizer,et al.  Semantic Integration of Patient Data and Quality Indicators Based on openEHR Archetypes , 2012, ProHealth/KR4HC.

[15]  Dympna O'Sullivan,et al.  A Data- and Expert-driven Decision Support Framework for Helping Patients Adhere to Therapy: Psychobehavioral Targets and Associated Interventions , 2017 .

[16]  Qing Hu,et al.  Knowledge-Driven Paper Retrieval to Support Updating of Clinical Guidelines - A Use Case on PubMed , 2016, KR4HC/ProHealth@HEC.

[17]  Frank van Harmelen,et al.  SemanticCT: A Semantically-Enabled System for Clinical Trials , 2013, KR4HC/ProHealth.

[18]  Mor Peleg,et al.  Computer-interpretable clinical guidelines: A methodological review , 2013, J. Biomed. Informatics.

[19]  Femida Gwadry-Sridhar,et al.  A Markov Analysis of Patients Developing Sepsis Using Clusters , 2010, KR4HC.

[20]  Luigi Portinale,et al.  Flexible and Efficient Retrieval of Haemodialysis Time Series , 2012, ProHealth/KR4HC.

[21]  Samina Raza Abidi,et al.  An Ontology-Driven Personalization Framework for Designing Theory-Driven Self-management Interventions , 2013, KR4HC/ProHealth.

[22]  Yuval Shahar,et al.  The Elicitation, Representation, Application, and Automated Discovery of Time-Oriented Declarative Clinical Knowledge , 2012, ProHealth/KR4HC.

[23]  David Riaño,et al.  Detecting Dominant Alternative Interventions to Reduce Treatment Costs , 2011, KR4HC.

[24]  Alessio Bottrighi,et al.  A General Framework for the Distributed Management of Exceptions and Comorbidities , 2018, HEALTHINF.

[25]  Silvia Miksch,et al.  Knowledge Representation for Health Care , 2015, Lecture Notes in Computer Science.

[26]  Silvia Miksch,et al.  Knowledge Representation for Health-Care. Data, Processes and Guidelines AIME 2009 Workshop KR4HC 2009 , 2010 .

[27]  Jesualdo Tomás Fernández-Breis,et al.  Can Existing Biomedical Ontologies Be More Useful for EHR and CDS? , 2016, KR4HC/ProHealth@HEC.

[28]  Katharina Kaiser,et al.  Identifying Condition-Action Sentences Using a Heuristic-Based Information Extraction Method , 2013, KR4HC/ProHealth.

[29]  Silvia Miksch,et al.  Knowledge Representation for Health-Care , 2010, Lecture Notes in Computer Science.

[30]  Anne Miller,et al.  Integrating computerized clinical decision support systems into clinical work: A meta-synthesis of qualitative research , 2015, Int. J. Medical Informatics.

[31]  Silvia Miksch,et al.  Updating a Protocol-Based Decision-Support System's Knowledge Base: A Breast Cancer Case Study , 2010, KR4HC.

[32]  Catalina Martínez-Costa,et al.  How Ontologies Can Improve Semantic Interoperability in Health Care , 2013, KR4HC/ProHealth.

[33]  Laura Giordano,et al.  Conformance Analysis of the Execution of Clinical Guidelines with Basic Medical Knowledge and Clinical Terminology , 2014, KR4HC@VSL.

[34]  Renata Vieira,et al.  MeSHx-Notes: Web-System for Clinical Notes , 2018, AIH@IJCAI.

[35]  Anthony Hunter,et al.  Argumentation about Treatment Efficacy , 2009, KR4HC.

[36]  Stéfan Jacques Darmoni,et al.  Linguistic and Temporal Processing for Discovering Hospital Acquired Infection from Patient Records , 2010, KR4HC.

[37]  Mar Marcos,et al.  Experiences in the Development of Electronic Care Plans for the Management of Comorbidities , 2009, KR4HC.

[38]  Mar Marcos,et al.  Towards the Interoperability of Computerised Guidelines and Electronic Health Records: An Experiment with openEHR Archetypes and a Chronic Heart Failure Guideline , 2010, KR4HC.

[39]  Martine De Cock,et al.  Generating Conflict-Free Treatments for Patients with Comorbidity Using Answer Set Programming , 2016, KR4HC/ProHealth@HEC.

[40]  Luciano Serafini,et al.  A Hybrid Methodology for Consumer-oriented Healthcare Knowledge Acquisition , 2009, KEOD.

[41]  Arjen Hommersom,et al.  Toward Probabilistic Analysis of Guidelines , 2010, KR4HC.

[42]  Katharina Kaiser,et al.  Supporting Computer-interpretable Guidelines' Modeling by Automatically Classifying Clinical Actions , 2013, KR4HC/ProHealth.

[43]  Yuval Shahar.  The "Human Cli-Knowme" Project: Building a Universal, Formal, Procedural and Declarative Clinical Knowledge Base, for the Automation of Therapy and Research , 2011, KR4HC.

[44]  Peter J. F. Lucas,et al.  Extracting Qualitative Knowledge from Medical Guidelines for Clinical Decision-Support Systems , 2009, KR4HC.

[45]  Silvia Miksch,et al.  Knowledge Representation for Health Care , 2014, Lecture Notes in Computer Science.

[46]  Qing Hu,et al.  Detecting New Evidences for Evidence-Based Medical Guidelines with Journal Filtering , 2016, KR4HC/ProHealth@HEC.

[47]  Samina Raza Abidi.  Ontology-Based Knowledge Modeling to Provide Decision Support for Comorbid Diseases , 2010, KR4HC.

[48]  Diego Martínez Hernández,et al.  A Study of Semantic Proximity between Archetype Terms Based on SNOMED CT Relationships , 2012, ProHealth/KR4HC.

[49]  Yuval Shahar,et al.  Towards a Realistic Clinical-Guidelines Application Framework: Desiderata, Applications, and Lessons Learned , 2012, ProHealth/KR4HC.

[50]  Peter J. F. Lucas,et al.  Discovering Probabilistic Structures of Healthcare Processes , 2013, KR4HC/ProHealth.

[51]  David Sánchez,et al.  Creating Topic Hierarchies for Large Medical Libraries , 2009, KR4HC.

[52]  Yuval Shahar,et al.  iALARM: An Intelligent Alert Language for Activation, Response, and Monitoring of Medical Alerts , 2013, KR4HC/ProHealth.

[53]  T. Vos,et al.  Global, regional, and national incidence and prevalence, and years lived with disability for 328 diseases and injuries in 195 countries, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016 , 2017 .

[54]  Giuseppe De Pietro,et al.  GLM-CDS: A Standards-Based Verifiable Guideline Model for Decision Support in Clinical Applications , 2013, KR4HC/ProHealth.

[55]  Juan Fernández-Olivares,et al.  An Approach for Representing and Managing Medical Exceptions in Care Pathways Based on Temporal Hierarchical Planning Techniques , 2012, ProHealth/KR4HC.

[56]  Mor Peleg.  Sharable Appropriateness Criteria in GLIF3 Using Standards and the Knowledge-Data Ontology Mapper , 2009, KR4HC.

[57]  David Riaño,et al.  Training Residents in the Application of Clinical Guidelines for Differential Diagnosis of the Most Frequent Causes of Arterial Hypertension with Decision Tables , 2014, KR4HC@VSL.

[58]  Vassilis Koutkias,et al.  A Public Health Surveillance Platform Exploiting Free-Text Sources via Natural Language Processing and Linked Data: Application in Adverse Drug Reaction Signal Detection Using PubMed and Twitter , 2016, KR4HC/ProHealth@HEC.

[59]  Alessio Bottrighi,et al.  META-GLARE: A Meta-Engine for Executing Computer Interpretable Guidelines , 2015, KR4HC/ProHealth.

[60]  John Fox,et al.  Challenges in Delivering Decision Support Systems: The MATE Experience , 2009, KR4HC.

[61]  Qing Hu,et al.  Identifying Evidence Quality for Updating Evidence-Based Medical Guidelines , 2015, KR4HC/ProHealth.

[62]  David Riaño.  A Systematic Analysis of Medical Decisions: How to Store Knowledge and Experience in Decision Tables , 2011, KR4HC.

[63]  Albert Gatt,et al.  Towards a Possibility-Theoretic Approach to Uncertainty in Medical Data Interpretation for Text Generation , 2009, KR4HC.

[64]  Yiannis Kompatsiaris,et al.  Applying SPARQL-Based Inference and Ontologies for Modelling and Execution of Clinical Practice Guidelines: A Case Study on Hypertension Management , 2016, KR4HC/ProHealth@HEC.

[65]  Katharina Kaiser,et al.  Identifying Treatment Activities for Modelling Computer-Interpretable Clinical Practice Guidelines , 2010, KR4HC.

[66]  Manuel Campos,et al.  Computing Problem Oriented Medical Records , 2011, KR4HC.

[67]  Zhizheng Zhang,et al.  Preliminary Result on Finding Treatments for Patients with Comorbidity , 2014, KR4HC@VSL.

[68]  Frank van Harmelen,et al.  Towards a Conceptual Model for Enhancing Reasoning About Clinical Guidelines - A Case-Study on Comorbidity , 2014, KR4HC@VSL.

[69]  David Riaño,et al.  Ontology-Based Retrospective and Prospective Diagnosis and Medical Knowledge Personalization , 2010, KR4HC.

[70]  Paola Mello,et al.  Analysis of the GLARE and GPROVE Approaches to Clinical Guidelines , 2009, KR4HC.

[71]  David Riaño.  A Knowledge-Management Architecture to Integrate and to Share Medical and Clinical Data, Information, and Knowledge , 2009, KR4HC.

[72]  Silvia Miksch,et al.  Process Support and Knowledge Representation in Health Care , 2012, Lecture Notes in Computer Science.

[73]  Silvia Miksch,et al.  Bridging an Asbru Protocol to an Existing Electronic Patient Record , 2009, KR4HC.

[74]  Rodrigo Bonacin,et al.  Careflow Personalization Services: Concepts and Tool for the Evaluation of Computer-Interpretable Guidelines , 2011, KR4HC.

[75]  Wil M. P. van der Aalst,et al.  Process Mining in Healthcare: Data Challenges When Answering Frequently Posed Questions , 2012, ProHealth/KR4HC.

[76]  Mathias Weske,et al.  Embedding Conformance Checking in a Process Intelligence System in Hospital Environments , 2012, ProHealth/KR4HC.

[77]  David Riaño,et al.  Inducing Decision Trees from Medical Decision Processes , 2010, KR4HC.

[78]  Paolo Terenziani,et al.  A Mixed-Initiative Approach to the Conciliation of Clinical Guidelines for Comorbid Patients , 2015, KR4HC/ProHealth.

[79]  Frank van Harmelen,et al.  Patterns of Clinical Trial Eligibility Criteria , 2011, KR4HC.

[80]  Szymon Wilk,et al.  Using First-Order Logic to Represent Clinical Practice Guidelines and to Mitigate Adverse Interactions , 2014, KR4HC@VSL.

[81]  David Riaño,et al.  From Natural Language Descriptions in Clinical Guidelines to Relationships in an Ontology , 2009, KR4HC.

[82]  Frank Puppe,et al.  Diaflux: A Graphical Language for Computer-Interpretable Guidelines , 2011, KR4HC.

[83]  Frank van Harmelen,et al.  Identifying Disease-Centric Subdomains in Very Large Medical Ontologies: A Case-Study on Breast Cancer Concepts in SNOMED CT. Or: Finding 2500 Out of 300.000 , 2009, KR4HC.

[84]  Paul Taylor,et al.  Mammographic Knowledge Representation in Description Logic , 2011, KR4HC.

[85]  Syed Sibte Raza Abidi,et al.  Semantic Web-Based Modeling of Clinical Pathways Using the UML Activity Diagrams and OWL-S , 2009, KR4HC.

[86]  Maria Taboada,et al.  A Semantic Web Approach to Integrate Phenotype Descriptions and Clinical Data , 2010, KR4HC.

[87]  Berndt Müller,et al.  Ethical Surveillance: Applying Deep Learning and Contextual Awareness for the Benefit of Persons Living with Dementia , 2018, AIH@IJCAI.