#	Pagina
attuale pagina	/open-h2020/projects/199900/results.html
-1	/open-ted/eng/ca/view-13798-pag-1.html
-2	/open-ted/eng/ca/view-14036-pag-1.html
-3	/open-ted/eng/ca/view-13661-pag-1.html

Report

Teaser, summary, work performed and final results

Periodic Reporting for period 1 - PEPPER (Patient Empowerment through Predictive PERsonalised decision support)

Teaser

Summary

\"Diabetes is a widespread chronic health condition that lasts for life. According to the World Health Organisation, the number of people with diabetes rose from 108 million in 1980 to 422 million in 2014. The cost to society is huge: the International Diabetes Federation reported that the condition accounted for at least $673 billion USD in health expenditure in 2015. Many people with insulin-treated diabetes rely on complex calculations and human memory to estimate their insulin doses, which they must do several times a day. As well as being an enormous mental burden, poor management can lead to additional health problems; a large dose can even be fatal.

PEPPER, short for Patient Empowerment through Predictive PERsonalised decision support, tries to tackle this problem by utilising portable technology, together with artificial intelligence and mathematical modelling, to give people freedom from daily decision-making. The project is creating a tool that makes predictions based on real-time data, gathered from unobtrusive, wearable devices, in order to empower individuals to manage their condition more easily. The resulting application has potential benefit to society by improving health outcomes and thereby reducing costs.

Currently there is no decision support system for insulin dosing on the market that adapts itself based on real-time activity data and blood glucose data. The PEPPER project addresses this by providing personalised decision support on two alternative mobile platforms: one based on a smartphone, and another via the handset of a minimally obtrusive patch pump, which is about the size of a tic-tac box (Fig. 1). Users of the system also wear a fitness band and a continuous glucose monitor, which is around the size of a small USB stick. Additional information, such as carbohydrate consumption and alcohol intake, can be added manually on the handset (Fig. 2). The PEPPER system is also designed to offer improvement in interactions between individuals and health professionals via a secure, cloud-based server.

The system design process involves users at every stage to ensure that it meets patient needs and raises clinical outcomes as well as improving lifestyle, monitoring and quality of life. The first prototype of the system (Fig. 3), was demonstrated in February 2017 to the community of stakeholders including individuals with Type 1 Diabetes, representatives of Diabetes UK, the Juvenile Diabetes Research Foundation (JDRF) and Sociedad EspaÃ±ola de EndocrinologÃa y NutriciÃ³n. Tim Omer, representing the Nightscout (#WeAreNotWaiting) patient community, said \"\"As we capture higher quality and quantity of data about our condition, it is refreshing to finally see progress in assisting the patient with analysing this data to provide actionable feedback to reduce the burden of Type 1 Diabetes\"\".

PEPPER draws together computer scientists, clinicians and industry leaders to create and clinically validate this ground-breaking tool. The project, funded by the Horizon 2020 programme, runs from 1 February 2016 until 31 January 2019 and includes six partners from three countries: Oxford Brookes University, Imperial College London, University de Girona, Institut d\'InvestigaciÃ³ BiomÃ¨dica de Girona Dr. Josep Trueta, Romsoft SRL and Cellnovo Ltd. The approach used and resulting system architecture provide a generic framework for providing adaptive decision support anytime, anywhere, which could be applied to other health conditions that are monitored by wearable technology.

The specific objectives of the project are:
Â· To provide a novel and personalised adaptive decision support system for insulin dosing that combines data from multiple sources;
Â· To maximise safety through prediction of adverse events and fault detection;
Â· To improve patient self-efficacy and adherence to treatment;
Â· To improve interactions between individuals and health professionals;
Â· To optimize security and inter\"

Work performed

The project work is segmented into five phases (Fig. 4). The initial requirements analysis phase (M1-3) is followed by the first implementation and integration cycle (M3-12). The work continues with a testing, development and evaluation phase (M13-24). The project culminates in the clinical validation phase (M25-36), which runs in parallel with the final wrap-up phase (M31-36) focusing on lessons learned, pre-commercial evaluation, and standardisation.

This overview describes the work performed in the first half of the project, from M1-M18. As such, the report offers insight into the accomplishments resulting from the research into the algorithms and patient needs, as well as the design and validation of all the components of the PEPPER system, both individually and integrated in a pre-clinical setting. The algorithmic work focused on development of the artificial intelligence for decision support via case-based reasoning and for the safety system through model based reasoning. Consideration of user needs included patient and clinician consultation during the requirements gathering process and participatory design of the data visualisation aspects. Testing included in silico testing of the algorithms using an FDA approved simulator, software testing and verification, and preliminary testing on users, both for functionality and usability. Two critical milestones were achieved before starting human testing: regulatory approval for the PEPPER prototype from the appropriate agencies of each country (UK, Spain), as well as ethical approval for the two clinical trials involved in the project. Both aspects required substantial work from multiple partners. The period reported also covers the endeavours to build the community and disseminate results. Highlights include two workshops on Artificial Intelligence for Diabetes Management, both co-located with major AI conferences, and consequent journal special issues.

Final results

The first PEPPER prototype goes beyond the state of the art by gathering data automatically from various sources using minimally invasive wearable technology integrated with manually entered data within a single platform. This facilitates a more accurate prediction of the effects of an insulin dose than previously possible, as well as improved, personalised adaptive decision support. It is too early to report the impact on patients, but the industry standard UVA/Padova Type 1 Diabetes simulator has shown improved results when testing each set of algorithms separately: both the adaptive decision support tool and the hypoglycaemia prediction system, including a novel carbohydrate recommendation, perform better than preceding solutions. The two components have also been integrated for combined in silico testing.

Research into data visualisation and new methods for usability testing of mobile devices has also been conducted. The resulting protocol includes elements that will be embedded in the clinical trial so that data analytics can be used to find correlations between user interactions with the system and glycaemic metrics. Whilst the impact on the health of patients cannot be reported at this stage, the project has already had a significant effect on researchers through the creation of a community-building platform and associated series of workshops and journal special issues.