Massive reutilization of Electronic Health Records (EHRs) through AI to enhance clinical research and precision medicine

Project Information

SAVANA

Grant agreement ID: 829654

DOI

10.3030/829654

Project closed

EC signature date 25 October 2018

Start date 1 November 2018

End date 31 July 2022

Funded under

• INDUSTRIAL LEADERSHIP - Innovation In SMEs

Total cost

€ 2 408 995,78

EU contribution

€ 1 262 520,00

Coordinated by

MEDSAVANA SL
Spain

Periodic Reporting for period 3 - SAVANA (Massive reutilization of Electronic Health Records (EHRs) through AI to enhance clinical research and precision medicine)

Reporting period: 2021-01-01 to 2022-07-31

Summary of the context and overall objectives of the project

The decline of pharma industry returns on R&D and the need for a new ‘precision medicine’ model:
In the last twenty years, the average return on R&D expenditure in the pharmaceutical industry has dropped from almost 18% to 3.7%. Moreover, annual funding for biomedical research has more than doubled while new drugs approvals have declined by one third. There is a wide consensus that the main cause of this problem is the exhaustion of a model intended to develop ‘broad indications’ and the need for a new ‘precision medicine’ model. However, in many cases we do not know enough about the underlying disease mechanisms, and more research is required to enable the development of more targeted drugs and therapies.
Electronic Health Records (EHRs) have been used for more than ten years in developed countries, and they gather now exhaustive clinical information of millions of patients. Leveraging the potential of EHRs could boost clinical knowledge, accelerate clinical research, and ultimately improve healthcare quality. However, to uncover disease models from EHRs, precision medicine requires massive studies on thousands of patients (often in several countries), considering thousands of variables. And there is no tool capable of: 1) automating the extraction of massive scores of information from clinical narratives, and 2) solving the privacy concerns raised by EHRs reutilization. Current manual methods are simply unpractical and economically inviable for this purpose.

SAVANA RESEARCH uses Natural Language Processing (NLP) and big data technologies to extract structured data from massive amounts of EHRs’ clinical narratives. SAVANA RESEARCH has the following advantages intended to make a leap in clinical research efficiency:

▪ SAVANA RESEARCH uses only de-identified clinical records and hospitals always retain data control. Our concept of “differential privacy” (analysis of aggregate data, and inclusion of security by design) has been identified as a very unique process during Phase 1 Freedom to Operate analysis.
▪ It is capable of decoding ten times more EHRs in half of the time than any alternative in the market
▪ It is capable of identifying 100 times more variables from EHRs.
▪ And SAVANA RESEARCH costs 40% less.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Main objectives and outcomes during the first Project period (from November until July 2019) are:

1. Boost expansion of SAVANA to other priority languages: English, French, and German. The language teams are already in place and performing. Platform for model development is ready to be used to train models as soon as the data on the different languages are available.

2.Fully industrialize our operative processes. Microservice architecture has been achieved. In a more high-level point of view, it is worth mentioning that the achievement of a microservice oriented architecture enables the adoption of RAD (Rapid Application Development) approach and to structure and organise team responsibilities around services/functionalities, which brings focus and performance from an operational point of view regarding the software development.

3. Achieve high-impact in demonstrating SAVANA Research to our target market. Agreement with SEPAR to sponsor a massive observational clinical trial at workldwide level on COPD (Sociedad Española de Neumología y Cirugía Torácica), and the Scientific Committee is formed by a group of 9 top worldwide recognized COPD researchers. The primary and secondary objectives of the protocol have been defined, and approved by the Spanish Regulatory Agency.. Our local project managers located in Madrid, London, Paris and Berlin, have visited more than 80 hospitals across Spain, France, Belgium, England, Germany, Austria, Switzerland, USA and Canada. Trial ready to start before the end of 2019.

4. Accelerate the international expansion through an effective communication and dissemination campaign:
- Website around the trial: https://bigcopdata.savanamed.com
- MEDSAVANA Twitter and LinkedIn accounts:
• https://twitter.com/savanamedica?lang=en
• https://www.linkedin.com/company/savanamedica/
- Videos around out technology and benefits to our users and clients:
• Savana user testimonials video https://savanamed.com/
• Savana Corporate video https://savanamed.com/company/about-us/

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Savana impacts health & care services in all its dimensions: It helps Pharma companies to carry out observational clinical research which was impossible in the past; Clinicians, who feel supported into addressing great challenges ahead service provisioning; Health systems themselves, which can improve decision-making based on real-world evidence; and, ultimately, the patients, who will receive better care. This impact is being backed up by the health professionals we are working with, as demonstrated into the video we have recorded with those having cooperated with us for longer: https://savanamed.com/

Now that every year one single hospital generates more information than all clinical databases generated in history, 100% patient-centred medicine is crucial, and there is a unique need for “new technology to allow professionals to achieve this with safety, accuracy and reproducible results” (Dr. Carmen Pantoja, Managing Director of Hospital Infanta Leonor, in Madrid). Savana allows:

▪ “Harnessing information we are not currently harnessing, to offer more precise and personalized treatments, diagnose earlier and, even, try to anticipate high-risk situations” (Dr. Eva Aurin, Head of Innovation & Health in Vall d’Hebron Campus Hospital, in Barcelona).
▪ “Transforming daily clinical operations via user-friendly tools that will be seamlessly integrated into clinical decision making” (Dr. Gloria Antolin, Innovation Coordinator in Valladolid, Head of Hepatology Dept. in Hospital Universitario Rio Ortega).
▪ Increasing clinical value of data sets being accessed by managers and operators, and making it more insightful, an opinion shared by Dr. Raul Piedra, from Medical School on Universidad Family Dr. Azuqueca de Henares. “Transforming data into knowledge” (Dr. Gloria Antolin).
▪ “Enriching clinical research based on detailed analytics of the global population and real-world evidence” (Dr. Gloria Antolin), and “increasing scientific output and work with much broader population in next to no time” (Dr. Raul Piedra). “What took months now can take days, and when hundreds of patients could be helped, we can now support thousands or, even, tens of thousands, with greater quality”.
▪ “Correlating information impossible to identify through alternative means, or even know the significance it carries that, paired, with clinical data, generates genuinely meaningful information we did not have access to before” (Dr. Andres Muñoz, Hospital Gregorio Marañón, one of the largest in Madrid).
▪ “Improving diagnosis processes and reduce variability just in 1 click” (Dr. Carmen Pantoja).
▪ Ultimately: Savana becomes and essential tool and knowledge to help improve patient care (Dr. Raul Piedra).

Logo SavanaMed