CONSULT: Collaborative Mobile Decision Support for Managing Multiple Morbidities

Lead Research Organisation: King's College London
Department Name: Informatics

Abstract

The provision of healthcare to people with long-term conditions is a growing challenge, which is particularly acute for the growing proportion of the UK population that suffers from multiple morbidities.

Research has established that involving patients in the management of their own disease has long-term health benefits. Advances in wireless sensor technology means that it is practical for patients to monitor a wide range of health and wellness data at home, including blood pressure, heart function and glucose levels, without direct supervision by medical personnel. The advent of smart phone technologies, appearing widely throughout the nation's population, enables the exciting possibility of putting state-of-the-art intelligent decision-support systems into the hands of the general public.

However, such sensor data is currently disconnected both from the patient context, provided by the Electronic Health Record, and from the treatment plan, based on current best-evidence guidelines and customised by the patient's GP. In cases of multi-morbidities, there is no clear strategy for combining multiple guidelines into a coherent whole. Furthermore, personalised treatment plans are rigid and do not dynamically adapt to changes in a patient's circumstances. Finally, the record of patient condition and decisions made is not routinely captured in a standardised way, preventing learning from feedback about treatment effectiveness.

To address these problems, CONSULT will combine wireless "wellness" sensors with intelligent software running on mobile devices, to support patient decision making, and thus actively engage patients in managing their healthcare. Our software will use computational argumentation to help patients follow treatment guidelines and will learn details specific to individuals, personalising treatment advice within medically sound limits. Critically, the software will detect conflicts in treatment guidelines that frequently arise in the management of multiple morbidities. The software will provide advice regarding which treatment options to follow, when the conflicts can be resolved by the patient and when a resolution requires an intervention from a clinician. The software will thus help patients handle routine maintenance of their conditions, while ensuring that medical professionals are consulted when appropriate. This will enable patients to take charge of their own conditions, while being fully supported in both traditional and new ways. By routinely capturing the data provenance of the recommendations made, actions taken and the resulting patient progress, the software will provide valuable insights into the effectiveness of treatments and underlying guidelines in multi-morbidity scenarios.

The technology will be evaluated across multiple dimensions in a proof-of-concept study, engaging stroke patients, their carers and medical professionals, while capitalising on King's College London's world-leading position in stroke research and its established patient groups, particularly those connected to the South London Stroke Register programme.

Helping patients to govern their own care will reduce the demands made on medical professionals, while reaping the health benefits of self-management. Integrating live information from monitoring devices will make it possible to distinguish between situations that need attention from medical professionals, and those that do not, reducing the number of extra appointments that patients and doctors need to schedule. Using live information will also make it possible to detect changes in the course of a disease, allowing pre-emptive actions to be taken, and thus reducing the amount of time that someone suffering from a long-term condition may have to spend in hospital. Overall, our approach will not only provide more efficient care, but also allow care to be better tailored to the needs of each individual.

Planned Impact

Chronic health conditions are widespread in the UK. NHS England estimates that around 15 million people in England (30% of the population) suffer from chronic health conditions. In Scotland and Wales, the proportion of the population affected is even higher. Such conditions require constant management, and they account for 50% of all GP appointments and 64% of all outpatient appointments. With careful monitoring, it is possible for those who are chronically ill to lead high-functioning lives and to have their care managed at home. However, many chronic conditions can easily lead to hospital stays, with the result that 70% of all inpatient bed days are required to treat the chronically ill. The prevalence of chronic conditions is closely correlated with age. For example, 14% of those younger than 40 report a long-term condition, compared with 58% of those over 60. With an ageing population nationwide, dealing with chronic conditions will consume even more resources in the future.

The number of people with more than one chronic disease is also growing. It is predicted that there will be 2.9 million people with two or more long-term conditions by 2018, an increase of one million since 2008. Such multiple morbidities are difficult to navigate because traditionally each disease has been managed separately, so drug regimes and treatment plans are developed in isolation and may conflict with each other. This growth in multiple morbidities presents a further challenge to our healthcare system: by 2018, dealing with them will cost GBP 5 billion more than in 2011.

A key feature of our proposed CONSULT approach is that it goes far beyond what is possible with medical advice web sites. By adopting a collaborative approach based on integrating wellness sensor data with a patient's electronic health record (EHR), it is possible to provide personalised care in home settings, reducing the amount of hospital and GP time required, and improving treatment outcomes. By specifically targeting the issues that arise in handling multiple morbidities, our approach aims to help the most vulnerable members of the chronically ill population.

Specifically, our research will impact several categories of stakeholders:

* Patients will be assisted in the management of their conditions. Our work will literally put up-to-date information and support at their fingertips. Our goal is to help patients sort through what is relevant to them, understand their options, avoid information overload and make the best decisions, even when treatment guidelines conflict. By engaging patients in this way, we aim to help them obtain the health benefits that have been shown for the chronically ill who self-manage their treatment. Overall, our approach offers both economic benefits, reducing the cost of long-term care, and social benefits in terms of increased quality of life.

* Carers will be empowered in the management of patients with chronic conditions. Our work will provide live support and connection to their patients, and the added security of knowing that medical professionals will be informed of any relevant changes in patients' conditions.

* Clinicians' efforts will be better apportioned. Since wellness sensor data will be integrated into the EHR, clinicians will be able to monitor patients' conditions without bringing them into clinic, and receive alarms when there are situations that require immediate attention.

In addition, medical researchers will be able to obtain integrated data from sensors and EHRs to conduct observational studies on efficiency of treatments and accuracy of measurements in the home setting. The provenance of data collected, backing decision support, will enable commissioning bodies to gain unique insight into the efficiency and cost-effectiveness of treatments. Technology will also impact commercial decision-support providers looking to deliver collaborative home care solutions.
 
Description Developing and implementing Machine Learning driven analytics for quality improvement in healthcare
Amount £337,149 (GBP)
Funding ID 707135 
Organisation The Health Foundation 
Sector Charity/Non Profit
Country Denmark
Start 02/2018 
End 09/2021
 
Description London Substantive Site for HDR UK
Amount £6,000,000 (GBP)
Organisation Health Data Research UK 
Start 04/2018 
End 03/2023
 
Description Collaboration with National Institute for Health and Care Excellence on use of provenance for managing recommendations and evidence 
Organisation National Institute for Health and Care Excellence (NICE)
Country United Kingdom 
Sector Public 
PI Contribution My team is applying the Provenance Template modeling method to the challenges that NICE has in managing their research metadata. Specifically, they are interested in exploring the versioning of their guideline recommendations, and its relationship to the changing evidence base.
Collaborator Contribution NICE is conducting a survey of their stakeholders (industrial partners, clinical organizations etc.) to understand their needs with respect to data provenance of NICE guidelines. This is a valuable piece of work that they are uniquely positioned to deliver, and will be of significant use to my team in developing the provenance research portfolio further. As a secondary benefit, the NICE employee placed in my group is advising on the ROAD2H and CONSULT projects which both have elements of guideline modeling, to ensure its applicability to the UK national requirements.
Impact We have jointly obtained the "Towards Computable Guidelines", MRC Industry Proximity Award funding worth £30K, to establish a pilot collaboration through hosting a NICE employee in my group, and are currently working on a paper and a larger grant proposal. This is a multi-disciplinary collaboration that spans informatics and public health.
Start Year 2017
 
Title A Microservice Architecture for Computer-Interpretable Guidelines 
Description As a part of the CONSULT project, we have developed a new microservice architecture design pattern for the construction of guideline processing tools. This architecture has successfully been used to redesign the guideline processing tool developed by Zambolini et al. [1], and this new software is currently being used by the ROAD2H project at Imperial College London, and will ultimately be used in CONSULT itself. [1] Zamborlini, Veruska, et al. "Inferring recommendation interactions in clinical guidelines 1." Semantic Web 7.4 (2016): 421-446. 
Type Of Technology Software 
Year Produced 2018 
Open Source License? Yes  
Impact The tool is currently being used by researchers at Imperial College as part of the EPSRC - Global Challenges Research Fund project Road2H (http://www.road2h.org/) 
URL https://github.com/consult-kcl/drug-interaction
 
Title Nokia Health Middleware 
Description Middleware designed to improve interactions with the Nokia Health API, and thus Nokia Health devices. 
Type Of Technology Software 
Year Produced 2018 
Open Source License? Yes  
Impact None as yet. 
URL https://github.com/consult-kcl/nokia-health
 
Description The International Workshop on Dialogue, Explanation and Argumentation for Human-Agent Interaction (DEXAHAI) at the International Conference on Human-Agent Interaction 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact This was an academic workshop focused on approaches, concepts and applications relevant to supporting dialogue and explainability in intelligent software that interacts with people. Since these are key areas for CONSULT, we decided to organize an event at which we could discuss them with an international set of participants, learn what other researchers are doing, and gain feedback on our work.
Year(s) Of Engagement Activity 2018
URL https://sites.google.com/view/dexahai-18/home
 
Description CONSULT presentation to Guys and St Thomas's Trust NIHR Biomedical Research Centre Analytical Cluster 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Professional Practitioners
Results and Impact A presentation of CONSULT technology for integrating wearable data and Electronic Health Record technology for stroke patient decision support was given to the Analytics cluster of the GSTT NIHR BRC. The audience feedback was very positive and several areas in GSTT hospital settings were identified to potentially pilot the CONSULT technology in follow-up projects.
Year(s) Of Engagement Activity 2019
 
Description MEDRACER18 workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact The talks and papers in MEDRACER focussed mainly on the representation of, and reasoning with, clinical guidelines. Martin Chapman was invited as the representtive of the CONSULT project, and spoke about the work done so far on deriving treatment plans from abstract guidelines, which involves using argumentation to resolve any contradictions within those guidelines based on patient preferences.
Year(s) Of Engagement Activity 2018
URL https://sites.google.com/view/medracer
 
Description Meeting at University of Michigan, Ann Arbor, to set the Learning Health System agenda for decision support 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Funded by the Gordon and Betty Moore Foundation to envision a Learning Health System for diagnostic excellence, University of Michigan held a one-day expert meeting to design and propose in more detail socio-technical infrastructure components for an LHS focused on diagnosis. Vasa Curcin was invited as the UK/European representative to the workshop, bringing in the experiences from CONSULT and ROAD2H.
Year(s) Of Engagement Activity 2019
 
Description Presentation to the Clinical Research Network South London, Stroke Specialty Group 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact The CRN South London Stroke Specialty Group brings together researches and medical professionals engaged in research around stroke. At the meeting on 10th January 2018, Dr Talya Porat gave a presentation to the group about the aims of the CONSULT project.
Year(s) Of Engagement Activity 2018
 
Description Talk to the Petnica Science Camp students in Serbia 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Schools
Results and Impact Presentation on data provenance and the Learning Health System given to 120-odd high school students attending the Petnica Science Camp in Serbia. The talk coincided with the summer term at PSC, and the students present there were all involved in their own research projects. The presentation kick-started a longer discussion on the role of data provenance in alleviating privacy fears around how people's private medical data are being used.
Year(s) Of Engagement Activity 2017
 
Description Tutorial at Human Agent Interaction Conference 2018. 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Members of the project team, along with colleagues from King's and the University of Aberdeen, presented a tutorial "Computational Argumentation in the Context of Human-Agent Interaction", on the core technology at the heart of what we are developing for CONSULT, at the 6th Annual International Conference on Human-Agent Interaction. The audience was drawn from the conference attendees, primarily doctoral students, but also researchers in the field and at least one journalist.
Year(s) Of Engagement Activity 2018
URL http://hai-conference.net/hai2018/programme/tutorial/
 
Description Visit to Erasmus MC, Rotterdam, to present ProvTemp outputs 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Vasa Curcin and Martin Chapman visited Rotterdam to present the data provenance and CONSULT technologies developed in the group to the researchers at Erasmus MC. The specific goal was to see how our provenance template server could be used to provide reproducible features to the tooling around OHDSI Observational Medicines Outcome Partnership's Common Data Model. Several possibilities were identified and we shall aim to submit a joint proposal around it.
Year(s) Of Engagement Activity 2019
 
Description Visit to Mayo Clinic in Scottsdale, AZ 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Martin Chapman visited Adela Grando (https://chs.asu.edu/adela-grando) at the Mayo Clinic in Scottsdale, AZ. The discussion focussed on her current work, which, like CONSULT, involves promoting self-management, but instead for diabetic patients, who are fitted with blood glucose monitors (https://www.researchgate.net/publication/325884737_Design_and_Testing_of_a_Smartphone_Application_for_Real-Time_Self-Tracking_Diabetes_Self-Management_Behaviors). Additionally, we looked into some work she has been doing on logging clinicians' workflows with EHRs, with the aim of supporting clinicians in moving between EHR software provided by different vendors (https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6371265/) which bears direct relevance to the technologies developed in our group.
Year(s) Of Engagement Activity 2018