Draft Policy Brief on Semantic Interoperability

1. Draft Policy Brief onSemantic Interoperability Editors Dipak Kalra and Mark Musen

2. ARGOS and Semantic Interoperability • The ARGOS Transatlantic Observatory for Meeting Global Health Policy Challenges through ICT Enabled Solutions is an international platform for dialogue and collaboration on health policy issues that surround making Health ICT a success • Co-ordinated by EuroRec, in partnership with AMIA • Semantic interoperability is one of the priority themes • Experts from the EU and US have met during 2010-11 and shared understanding of the problem space, solutions found and priority areas to be tackled • This presentation summarises the strategies proposed

3. Drivers for integrated EHRs • manage increasingly complex clinical care • connect multiple locations of care delivery • support team-based care • deliver evidence-based health care • improve safety through mechanisms that: • reduce errors and inequalities • reduce duplication and delay • improve cost effectiveness of health services • enrich population health management and prevention • empower and involve citizens • protect patient privacy • better inform and exploit biomedical research

4. rapid bench to bed translation real-time knowledge directed care Education Research Epidemiology Data mining Public health Health care management Clinical audit Wellness Fitness Complementary health implied consent implied consent de-identified Teaching Research Clinical trials Social care Occupational health School health Disease registries Screening recall systems Long-term shared care (regional national, global) explicit consent Point of care delivery Citizen in the community Continuing care (within the institution) +/- consent Health information flows needing semantic interoperability

5. Essential needs • Guideline and decision support systems, notification and alerting components, and analytic tools need to process integrated health data drawn from multiple EHR systems in a consistent manner • Intelligent personal health guidelines interoperating with PHRs and EHRs need to support the centring of care on patients • New generation personalised medicine, underpinned by ‘omics sciences and translational research such as the VPH, needs to integrate EHRs with data from research: fundamental biomedical science, clinical and population health research, and clinical trials

6. architecture identifiers for people policy models structural roles functional roles purposes of use care settings pseudonymisation guidelines care pathways decision support algorithms Consistent representation, access and interpretation privacy workflow record structure and context terminologysystems Resources needed to support rich semantic interoperability reference models data types near-patient device interoperability archetypes templates clinical terminology systems classification systems terminology sub-sets value sets and micro-vocabularies post-co-ordination multi-lingual mappings semantic context model categorial structures

7. Semantic interoperability resource priorities • Widespread and dependable access to maintained collections of coherent and quality-assured semantic resources • clinical models, such as archetypes and templates • rules for decision making and monitoring • workflow logic • which are • mapped to EHR interoperability standards • bound to well specified multi-lingual terminology value sets • indexed and correlated with each other via ontologies • referenced from modular (re-usable) care pathway components

8. Practical issues • These resources need to be developed by communities of practice, reflecting real needs • This development must include patients, emphasising citizen engagement in self management and health maintenance • They need to be embedded within EHR systems, and within other systems and services that will analyse and interpret EHR data

9. Nine key recommendations • Nine strategic actions that now need to be championed,as a global mission 1. Establish good practice 2. Scale this up 3. Support translations 4. Track natural language technologies 5. Align and harmonise standardisation efforts 6. Support education 7. Develop business models

10. 1. Establish good practice • Establish projects to develop good practice in the definition and validation of clinical models bound to terminologies and ontologies and guideline-based pathway models • that have a well-grounded and practical relevance to the management of clinical conditions of national and international priority • e.g. chronic conditions, like heart failure • e.g. population health issues, like childhood obesity • BUT: still adopting a holistic - not a piecemeal - approach

11. 2. Scale this up • Develop a sustainable approach to scaling this up across disease areas and stakeholders, importantly with patients • Ensure wide-scale clinical engagement during the design and piloting of clinical models and terminology • Involve other stakeholders who will create or use health data • Address wider health system needs and support future research

12. 3. Support translations • Resources need to be multi-lingual to support cross border shared care, cross border health planning and global scale research • Specifically consider the challenges of supporting multiple levels of “clinical jargon” for different stakeholders including patients and caregivers

13. 4. Track natural language technologies • Monitor the evolving capability and potential uses of natural-language technologies, • including the reliability of such approaches for population-level and patient-level decision making

14. 5. Align and harmonise standardisation efforts • Having understood the clinical modelling that is really needed... • conduct a gap analysis of • interoperability standards • informatics tools • knowledge representation formalisms • clinical content • which are needed to support this scaling up, including • embedding such resources within EHR systems • providing formal recommendations to SDOs on the scope and level of detail that is needed and would be usable

15. 6. Support education • Invest in education that enables clinical and patient/citizen acceptance, creation and use of knowledge-rich EHRs • to create good quality (faithful, accurate) and re-usable information • to better trust and use information from external sources • to take better advantage of semantically interoperable systems and services

16. 7. Develop business models • Develop and align with business models to justify strategic investments in this field • Understand the value propositions (ROI) for key stakeholder groups and decision makers, including • clinicians, patients, citizens • EHR system vendors • healthcare provider organisations • health authorities • insurers • academic, bio-science and pharma research • standards developers • Find win-wins and relevant incentives

17. Continue this Transatlantic Observatory • Support Transatlantic research efforts on • what parts of, and how much of, a health record is useful to structure/code/make interoperable: focus on benefits versus effort • the quality assurance of semantic resources when used together: clinical and technical validation • Collaborate across countries on • common conformance criteria for systems and system components • practical methods for testing interoperability (e.g. for vocabularies, ontologies) • validating the correctness and consistent usability of solutions (including human factors)

18. Leadership and governance are needed • Strong leadership within and across all relevant stakeholders will be essential to drive these actions and oversee benefits realisation • In the longer term a governance organisation is needed • to support, co-ordinate and quality manage the future development of semantic interoperability resources for health • to develop an action plan for future research and educational investments