HealthECCO

Bringing the world’s health knowledge to research and medical decision makers.

Dr. Alexander Jarasch

Dr. Martin Preusse

Jamie Munro

The vast majority of a rapidly expanding corpus of health knowledge is hidden in data silos -  undiscovered, unconnected and underused. This reduces our ability to respond to health crises because decision makers do not have the information they need. Data in the healthcare sector is complex and highly connected. The data is available at different places and neither interoperable with other data sources nor searchable.

This affects various health care stakeholders: Public health policy makers do not have access to the information they need to quickly and efficiently create treatment guidelines. Frontline health workers have to rely on personal experience or hearsay to make the best treatment decision for their patients and health researchers are locked into their domain and cannot translate their knowledge to the emerging health situation. All of these problems are felt more keenly in the developing world where skills and information access may be limited

It also impacts the time-to-market of new treatments for patients worldwide and may slow down the dissemination of accurate guidelines that can help save lives. 

We are building a unique solution to combine, annotate and organise the world’s health knowledge and put it into the hands of the right people.

We see three main groups of users for our solution: Policy makers, health workers and researchers, although there are clearly spillover benefits for other stakeholders like journalists or the interested public.

While their daily problems are different, they all need access to similar data. Policy makers need contextualised knowledge to draft guidelines, health workers have to find the right piece of evidence for the specific patient, and researchers need to combine their speciality with the world’s knowledge to quickly respond to health emergencies.

Our team started with a focus on researchers: We actively collaborate with academics at various universities and research networks. Through our research partners and preliminary work we have already established a community of health workers across Europe, South Africa and the US who define use cases and validate prototypes. The Trinity Challenge network will be pivotal in gaining access to policy makers. For example, we are going to partner with the Clinton Health Access Initiative to further understand requirements of policy makers and deliver tailored solutions.

HealthECCO has encapsulated this in a comprehensive engagement strategy to engage with all our stakeholders.

HealthEcco is a non-profit organisation committed to open-source software and open access to knowledge in order to improve the quality of guideline dissemination/usage and to foster innovative/collaborative global research.

Our objective is public access for all data sources as far as licenses of the original data sources allow. Following the FAIR principles (Findable, Accessible, Interoperable, Reuseable) our knowledge graph will not only reveal hidden connections but will be publicly available and globally accessible. By incorporating ontologies, we make data interoperable so that data can be reused and repurposed. All APIs on top of the knowledge graph will be public to allow the community to develop applications. All code will be published on GitHub and the community is able to further develop code. All tools developed during the project such as the data loading pipeline and data enrichment pipeline are, and will, remain open-source.

We will share key learnings from our projects. In collaboration with the Clinton Health Access Initiative we plan to create process blueprints for health data solution development tailored to the needs of developing countries. We will publish our framework for requirements engineering, application development and solution improvement using insights from all stakeholders.

Our solution will help a diverse set of policy makers to create robust, harmonised health care policies (such as treatment guidelines) faster while accommodating local variations. This will in turn have a huge impact on large cohorts of patients. In collaboration with CHAI we can target health authorities responsible for populations that do not have access to high-quality treatment guidelines yet.

For health workers, the key benefit is a much improved basis for decision making. With limited understanding of emerging diseases, health workers have to identify a guideline, study or case report that is applicable for the patient at hand. Access to established information sources in combination with case reports and grey literature delivers contextualised insights to improve treatment decisions.

For researchers, we provide a much faster way to access information outside of their speciality. For example, one of the first observations during the Corona crisis was that SARS-CoV-2 affects multiple organs. An understanding of this mechanism is only possible by looking at various physiological systems. Further understanding of disease mechanisms and proposals for new treatments also requires a broader understanding. Traditional scientific exchange of information via published reports and clinical trials is too slow to respond to health emergencies.

In the first year we will establish HealthECCO as a non-profit organisation, putting in place sustainable structures, governance and international collaborations.

A key element of successfully scaling our impact is access to our user groups. We plan to expand our existing network significantly in the first year. Through our collaboration with CHAI we will further increase our interaction with the global health community as well as target policy makers as multipliers to create impact for millions of patients globally. We will expand our network of health workers to further understand requirements of this group. With help of the Trinity network and our background in academic research we will disseminate our solution in the global biomedical research community. Here we will also initiate discussions with the pharmaceutical industry to bring our solution to drug development.

In year 2 and 3 we will continue to grow our network but focus on creating the applications that target our user groups. Based on our graph of integrated and enriched knowledge we will deliver the right information to each user group. The cross-sector background of HealthECCO enables us to scale engineering, feedback and improvement cycles that are necessary to deliver solutions with real world use.

Our global impact on patient’s lives is achieved via the three main user groups of our solutions. The key performance indicators are users within these groups and the size of the patient population that each user affects. The number of main users can be measured directly with user analytics. The number of patients reached by the individual users will be estimated in close collaboration with our users and with our partners (e.g. CHAI). Also, the value created by the knowledge we deliver will be assessed in close collaboration with the users. Here, important KPIs are the time required to perform a patient-relevant activity and the quality of the output of that activity.

To promote global awareness of our project we plan to run a number of community and public outreach campaigns including surveys and outreach campaigns including traditional media, print, and social media. 

KPIs for our knowledge graph are the number of data sources, the ratio of connected to unconnected data points, the number of evidence extracted with NLP and the quality of predicted relationships. The frequency of updates and respective changes of KPIs are indicative of our ability to keep up with data growth.

The first barrier is getting HealthECCO operational and acquiring baseline funding for computing infrastructure and administration. Cross-sector and technology projects do not usually attract research funding. We are pursuing funding opportunities through research grants (with academic institutions), global health foundations as well as direct donations.

Global impact of our solution depends on the involvement of stakeholders who can add global/local perspectives to our development as well as dissemination and awareness. Collaboration with CHAI will be key to create a network of policy makers and we are already rooted in academic and pharmaceutical research. Extensive communication will be necessary to build a community of health workers that benefit from our solution.

Technical barriers include uncertainty around the output of NLP pipelines which are still under active research for health care applications. Multilingual NLP also poses challenges. Dr. Evidence as a technology partner will be pivotal.

Our goal of allowing public data access depends on licenses of original data sources where necessary. Legal advice is necessary and we include this in our budget.

There will also be cultural and language barriers to a fully global impact. We aim to include and partner with appropriate local representatives to help overcome these.

HealthECCO core team

• German Center for Diabetes Research (DZD)

• Kaiser & Preusse

• Munro Consulting

• Neo4j

• youSP

• Prodyna SE

Community Development Leads

• yWorks

• Structr

Scientific Collaboration

• University of Greifswald

• University of Oxford

• University of Cambridge

The cross-sector nature of HealthECCO makes it difficult to acquire funding through grants aimed at academic research or innovation in the private sector, respectively. Basic technology development often does not fit into the project based funding logic of research grants. Hence, the Trinity Challenge is a unique opportunity for our organisation to professionalise and scale software development and dissemination.

The impact of our solution depends on users who can multiply the effect to patients. The collaborations facilitated through the Trinity Challenge (CHAI and others) are a fantastic opportunity to work with user groups we do not have in our network yet. The technology partners (Dr. Evidence and others) augment our solution at crucial points and help us to scale the data enrichment process.

Being involved with the Trinity Challenge increases awareness of our project, adds to our credibility and paves the way for future collaborations regardless of the outcome of our application. Another barrier for our solution is global impact in multilingual settings. With the reach of the Trinity Challenge members we can acquire expertise in managing global projects and implement technologies for multilingual NLP.

Trinity Challenge members: We will partner with the Clinton Health Access Initiative to reach policy makers, particularly in the developing world, and scale our impact globally. Dr. Evidence will support development of our NLP pipeline. Dr Shamith Samarajiwa (Cambridge University) will support our efforts targeted at researchers.

HealthECCO core team: The organisations of the core team members are committed to partner with HealthECCO to carry out the contract work. This includes the international IT consulting firm Prodyna as well as the IT SMEs. The German Center for Diabetes Research will continue to function as a gateway to users (researchers, health workers) and support conceptual development. 

Community leads: The organisations that have already supported CovidGraph but will not join the HealthECCO core team will be technology partners for ongoing software development. (e.g. data visualisation company yWorks and the low-code platform Structr.)

Academic collaborations: We have already initiated collaborations with renowned academic researchers, including Prof Karl Morten (Oxford University), Dr Shamith Samarajiwa (Cambridge University), Prof Dagmar Waltemath (Greifswald University) and Dr Davide Mottin (Aarhus University). We aim at a) setting up a scientific advisory board, b) build partnerships for graph-based machine learning and c) co-apply for research grants.