Search

It is typical for many digital health research projects to develop IT architectures that will implement integrated care services that may also deliver interventions. As part of compliance with the requirements of the regulation, the components that are considered as a medical device will need to be classified to a medical device category. This is often seen as task that may increase the business risk and a major barrier of the project, particularly during the earlier stages when not all information is available. The paper offers a method assisting with classification of such architectures in the context of the Medical Devices Rregulation, offering a structured way to identifying how the initial deliverables of a project can be used to provide assurance to the justification of the classification.

CIGs languages consist of approach specific concepts. More widely used concepts, such as those in UMLS are not typically used.An evaluation of UMLS concept sufficiency for CIG definition.A popular guideline is mapped to UMLS concepts with NLP. Results are reviewed to evaluate gaps, and appropriateness.A significant number of the guideline text mapped to UMLS concepts.The approach has shown promise and highlighted further challenges.

Background:\ud CIGs languages consist of approach specific concepts. More widely used concepts, such as those in UMLS are not typically used.\ud \ud Objective:\ud An evaluation of UMLS concept sufficiency for CIG definition.\ud \ud Method:\ud A popular guideline is mapped to UMLS concepts with NLP. Results are reviewed to evaluate gaps, and appropriateness.\ud \ud Results:\ud A significant number of the guideline text mapped to UMLS concepts.\ud \ud Conclusions:\ud The approach has shown promise and highlighted further challenges.

Artificial Intelligence (AI) has seen an increased application within digital healthcare interventions (DHIs). DHIs use entails challenges about their safety assurance. Exacerbated by regulatory requirements, in the UK, this places the onus of safety assurance not only on the manufacturer, but also on the operator of a DHI. Clinical Safety claims and evidencing safe implementation and use of AI-based DHIs require expertise, to understand and act to control or mitigate risk. Current health software standards, regulation, and guidance do not provide the insight necessary for safer implementation.To interpret published guidance and policy related to AI and justify clinical safety assurance of DHIs.Assessment of UK health regulation policy, standards, and AI institution insights, utilizing a published Hazard Assessment framework, to structure safety justifications, and articulate hazards relating to AI-based DHIs.AI enabled DHI hazard identification, relating to implementation and use within healthcare delivery organizations.By application of the method, we postulate that UK research of AI DHIs highlighted issues that may affect safety, in need of consideration to justify safety of a DHI.

Background:\ud Artificial Intelligence (AI) has seen an increased application within digital healthcare interventions (DHIs). DHIs use entails challenges about their safety assurance. Exacerbated by regulatory requirements, in the UK, this places the onus of safety assurance not only on the manufacturer, but also on the operator of a DHI. Clinical Safety claims and evidencing safe implementation and use of AI-based DHIs require expertise, to understand and act to control or mitigate risk. Current health software standards, regulation, and guidance do not provide the insight necessary for safer implementation.\ud \ud Objective:\ud To interpret published guidance and policy related to AI and justify clinical safety assurance of DHIs.\ud \ud Method:\ud Assessment of UK health regulation policy, standards, and AI institution insights, utilizing a published Hazard Assessment framework, to structure safety justifications, and articulate hazards relating to AI-based DHIs.\ud \ud Results:\ud AI enabled DHI hazard identification, relating to implementation and use within healthcare delivery organizations.\ud \ud Conclusion:\ud By application of the method, we postulate that UK research of AI DHIs highlighted issues that may affect safety, in need of consideration to justify safety of a DHI.\ud

Multimorbid patients are prescribed a number of medications in parallel, which may often interact with each other, resulting in adverse effects. However, clinical guidelines on prescription of medications predominantly focus on individual conditions do not consider the guidance in the context of other guidelines, resulting in conflicts. C3-Cloud is an integrated care architecture managing multimorbidity, which amongst others, provides clinical decision support, based on reconciled guidelines, and active monitoring of drug interactions. To identify the severe interactions that resulted from multimorbidity management, in order to reevaluate guidelines as well as to identify knowledge gaps in prescribing practice. Method: Descriptive statistical analysis of interactions identified by the C3-Cloud clinical decision support, collected from the C3-Cloud FHIR repository. As part of a feasibility study, a number of interactions were identified, along with variable practice in how chemicals are represented in the EHR. 191 known severe interactions were identified. The Atorvastatin/Verapamil interaction was the most frequent. The approach has identified a number of interactions where the severity was not available, highlighting the need for further clinical review.

Increasing numbers of intelligent healthcare applications are developed by analysing big data, on which they are trained. It is necessary to assure that such applications will be safe for patients; this entails validation against datasets. But datasets cannot be shared easily, due to privacy, and consent issues, resulting in delaying innovation. Realistic Synthetic Datasets (RSDs), equivalent to the real datasets, are seen as a solution to this.To develop the outline for safety justification of an application, validated with an RSD, and identify the safety evidence the RSD developers will need to generate.Assurance case argument development approaches were used, including high level data related risk identification.An outline of the justification of such applications, focusing on the contribution of the RSD.Use of RSD will require specific arguments and evidence, which will affect the adopted methods. Mutually supporting arguments can result in a compelling justification.

Assurance of digital health interventions involves, amongst others, clinical validation, which requires large datasets to test the application in realistic clinical scenarios. Development of such datasets is time consuming and challenging in terms of maintaining patient anonymity and consent.The development of synthetic datasets that maintain the statistical properties of the real datasets.An artificial neural network based, generative adversarial network was implemented and trained, using numerical and categorical variables, including ICD-9 codes from the MIMIC III dataset, to produce a synthetic dataset.The synthetic dataset, exhibits a correlation matrix highly similar to the real dataset, good Jaccard similarity and passing the KS test.The proof of concept was successful with the approach being promising for further work.

Digital health interventions (DHIs) enable improvements in health strategy and address health system challenges. The World Health Organization provides a formal classification for DHIs. However, safety claims, about such interventions, vary in quality and are often vague as to how they are communicated between technical, clinical experts and stakeholders. By combining the classifications with a method of safety analysis and justification, we postulate confidence in the safety of digital technology. Confidence is resulting from the application of the framework to the DHI, using defined health system challenges. The framework and derived safety justifications can be applied to any DHI. It can serve as guideline for health strategy, regulatory and standards based compliance.

Background New patient-centric integrated care models are enabled by the capability to exchange the patient’s data amongst stakeholders, who each specialise in different aspects of the patient’s care. This requires a robust, trusted and flexible mechanism for patients to offer consent to share their data. Furthermore, new IT technologies make it easier to give patients more control over their data, including the right to revoke consent. These characteristics challenge the traditional paper-based, single-organisation-led consent process. The Dovetail digital consent application uses a mobile application and blockchain based infrastructure to offer this capability, as part of a pilot allowing patients to have their data shared amongst digital tools, empowering patients to manage their condition within an integrated care setting. Objective To evaluate patient perceptions towards existing consent processes, and the Dovetail blockchain based digital consent application as a means to manage data sharing in the context of diabetes care. Method Patients with diabetes at a General Practitioner practice were recruited. Data were collected using focus groups and questionnaires. Thematic analysis of the focus group transcripts and descriptive statistics of the questionnaires was performed. Results There was a lack of understanding of existing consent processes in place, and many patients did not have any recollection of having previously given consent. The digital consent application received favourable feedback, with patients recognising the value of the capability offered by the application. Patients overwhelmingly favoured the digital consent application over existing practice. Conclusions Digital consent was received favourably, with patients recognising that it addresses the main limitations of the current process. Feedback on potential improvements was received. Future work includes confirmation of results in a broader demographic sample and across multiple conditions.

Introduction: A growing share of the population in OECD countries is of age 65 and over, expected to reach 22% by 2030 (compared to 15% in 2010). Life expectancy has also significantly increased. People at age of 65 are expected to live for an average of 21 and 17 years for women and men; an almost 40% increase since 1960. The profound success in improving life expectancy has resulted in a new set of challenges.\ud \ud Challenge: Shift of resources was necessary, redirected to address the complex needs of multi-morbidity patients. Furthermore, patients’ needs are not effectively met by current care models, which tend to operate in isolation. This results in static services that patients need to wander. It is common for patients to revisit all levels of care discussing their needs, and reconciling potentially conflicting objectives amongst their conditions (e.g., incompatible lifestyle goals, adverse drug effects and side-effects, undetected conditions). Optimal collaboration and coordination between professionals in the delivery of integrated care have become essential requirements for the provision of high-quality care. Coordinated care aims for the orderly arrangement of individual and group efforts providing unity of action in pursuit of a common goal.\ud \ud Method: C3-Cloud is an e-health based ICT system, offering integrated, patient-centred care, considering all aspects of multi-morbidity and creating a collaborative environment, for all involved stakeholders. The navel of the system consists of the patient care plan, a digital shared picture of the patients’ needs and care regime. The care plan allows all professionals to review and understand the implications of one condition in the presence of others; this by its nature is complex, containing a considerable amount of diverse information. Navigating, understanding, and interpreting all the information can be confounding. The C3-Cloud Clinical Decision Support Service (CDS) offers an automated means of interpreting the available data. CDSS connects to the care plan repository, and continuously searches records for relevant data. The algorithms and integration of recommendations to the service were reviewed and validated by clinicians. Human computer interaction methods were employed to ensure optimal interaction between C3-Cloud and its users.\ud \ud Results: C3-Cloud offers CDSS for diabetes, renal failure, depression and congenital heart failure, with over 300 rules and checks that deliver four best practice guidelines in parallel; whilst reconciling their objectives, and monitoring their outcomes. It creates warnings or recommendations for the patient as well as for formal and informal carers.\ud \ud Discussion and Conclusions: C3-Cloud offers a powerful way to ensure that subtle, as well as critical, information about the patient, is presented to healthcare professionals, along with guideline based recommendations. The rules reconcile potential conflicts amongst conditions. Combined with a single patient and professionals interface, it provides a seamless experience throughout the health and care service. The C3-Cloud CDS service provides support to three pilot sites throughout Europe, currently undergoing evaluation.\ud \ud Acknowledgements: C3-Cloud is funded from the EU Horizon 2020 research and innovation project C3-Cloud, under grant agreement No 6891810.\ud \ud This abstract is based on the work and material of the entire C3-Cloud consortium.

C3-Cloud is a project aiming to provide an ICT infrastructure, which will allow patient centric and integrated care, based on best practice guideline, for patients with multi-morbidity. Clinical Decision Support, by checking the patient's record for known adverse interactions when the medication changes. The drug interaction advisory service provides recommendations in the three languages used in the project's pilot sites, for over 1000 substances, based on the UK's NICE BNF body of knowledge.

Execution of multiple computer-interpretable guidelines (CIGs), enables the creation of patient-centered care plans for multimorbidity, which can be monitored by clinical decision support systems. This paper introduces an execution framework to manage multiple, concurrently implemented CIGs, also discussing the approaches used such as constraint satisfaction.

Drug safety is an important aspect in healthcare, resulting in a number of inadvertent events, which may harm the patients. IT based Clinical Decision Support (CDS), integrated in electronic-prescription or Electronic Health Records (EHR) systems, can provide a means for checking prescriptions for errors. This requires expressing prescription guidelines in a way that can be interpreted by IT systems. The paper uses Natural Language Processing (NLP), to interpret drug guidelines by the UK NICE BNF offered in free text. The employed NLP component, MetaMap, identifies the concepts in the instructions and interprets their semantic meaning. The UMLS semantic types that correspond to these concepts are then processed, in order to understand the concepts that are needed to be implemented in software engineering for a CDS engine.

Integrated care paradigms depend on multiple sources of data. The quality of data used in decision-making will ultimately affect the delivered care to the patient. Quality includes several dimensions, which may affect the result. This paper presents how data quality dimensions may affect the delivered service, and propose a conceptual framework for the classification of confidence in data used in clinical decision-making for integrated care.

As patient numbers continue to rise Emergency Department's (ED's) are struggling to not only control patient wait times but also to maintain the quality of patient care. Improving patient flow through the ED has been a priority for many years with techniques such as Lean Six-Sigma being implemented specifically to help alleviate the problem. The Institute for Healthcare Improvement recently stated that the best opportunities to improving patient flow relate to the front-end of the ED, namely triage. This contribution examines the use of Telehealth initiatives at the front-end of the ED, specifically tele-consultation, to reduce patient loading, provide timelier healthcare (with improved patient outcomes) and reduce costs.

Background:\ud Digitally enabled healthcare services combine socio-technical resources to deliver the required outcomes to patients. Unintended operation of these services may result in adverse effects to the patient. Eliminating avoidable harm requires a systematic way of analysing the causal conditions, identifying opportunities for intervention. Operators of such services may be required to justify, and communicate, their safety. For example, the UK Standardisation Committee for Care Information (SCCI) standards 0129 and 0160 require a safety justification for health IT (superseded versions were known as the Information Standards Board (ISB) 0129 & 0160. Initial as well as current standards are maintained by the NHS Digital.\ud \ud Method:\ud A framework was designed, and applied as proof of concept, to an IT-supported clinical emergencies (A&E) service. Evaluation was done qualitatively based on the authors’ experience, identifying potential benefits of the approach.\ud \ud Results:\ud The applied framework encapsulates analysis, and structures the generated information, into a skeleton of an evidence-based case for safety. The framework improved management of the safety activities, assigning ownership to stakeholders (e.g. IT developer), also creating a clear and compelling safety justification.\ud \ud Conclusions:\ud Application of the framework significantly contributed to systematising an exploratory approach for analysing the service, in addition to existing methods such as reporting. Its application made the causal chain to harm more diaphanous. Constructing a safety case contributed to: (a) identifying potential assurance gaps, (b) planning production of information and evidence, and (c) communication of the justification by graphical unambiguous means.

The paper illustrates how event tree diagrams, used in safety engineering, can be applied to test the design of a healthcare service. Event tree diagrams can be employed to inform quantitative approaches to quality, by providing justification with respect to safety, of operational aspects to be monitored and measured.

Modern Implantable Medical Devices (IMDs), implement capabilities that have contributed significantly to patient outcomes, as well as quality of life. The ever increasing connectivity of IMD's does raise security concerns though there are instances where implemented security measures might impact on patient safety. The paper discusses challenges of addressing both of these attributes in parallel.

The paper presents a concise method for transforming textual representations of healthcare services, to a structured, semantically unambiguous modelling language. The method is designed based on literature, as well as trial and error by the authors, using text descriptions of healthcare services. Employing the method can convert textual descriptions to structured graphical models, facilitating stakeholder collaboration on requirements analysis and simulation.

Root Cause Analysis (RCA) is the most widely used system analysis tool for investigating safety related incidents in healthcare. This contribution reviews RCA techniques, using a Health Informatics example, and discusses barriers to their successful uptake by healthcare organisations. It is concluded that a critical assessment to examine the uptake and evaluate the success of RCA, and other safety related techniques, within healthcare is long overdue.

Health IT, in addition to benefits can also have unintended consequences both in terms of operational and business risks. Understanding the dependencies between operator and manufacturer as well as issues that need to be addressed during procurement is essential to increase confidence in the operation of health IT. The paper provides the context, and a number of issues health IT operators such as clinical organisations, need to investigate during acquisition of health IT.

The paper discusses the motivation behind the safety assurance of health IT, lists pertinent standards and regulation, as well as discussing prominent challenges in the field of health I safety.

The paper describes safety analysis and justification of a clinical service (accidents and emergencies), using a deviation based approaches.

COTS have increasingly been used by industrial practice as a means of maintaining low development costs of a product, whilst offering significant capability upgrades. COTS are multipurpose products driven by commonly used functionality. However, being general purpose products raises certain challenges regarding their ability to be certified. Previously used (process-based) standards stipulated a process that the product needed to adhere to. This involved production of a generic set of evidence known as the certification pack (CertPack). Being the product of a generic test process, the available (CertPack) COTS evidence may not be sufficient or suitable to support the developers’ safety claims. The challenges raised by use of COTS in such assurance frameworks can have ramifications on a project both from a managerial and safety assurance perspective. The paper presents an analysis of the challenges from the use of CertPack and their impact on assurance and project management. Moreover a process is presented that assists de-risking the integration of evidence, as early as possible during system development or upgrade.

Hazards are situations that can result in accidents. Depending on the domain, this can include loss of lives, injuries and economic or environmental disasters. For example, a common hazard in the aviation domain is in flight engine shutdown. Hazard analysis is the process of discovering hazards in a system. This activity has been performed for many years in safety engineering and is a straightforward activity in most domains. In recent years a new class of systems has emerged, distinguished from traditional (monolithic) systems by a combination of characteristics such as autonomous and independently developed components, increased complexity and geographic dispersion. These characteristics introduce a number of challenges for traditional hazard analysis. This paper describes these challenges and proposes two complementary approaches that address them: Dependability Deviation Analysis (DDA) and simulation-based hazard analysis (SimHAZAN). The paper then describes a model-driven approach that combines the two and thereby provides an underlying framework for their application during system development.