Periodic Reporting for period 1 - ENVISION (Intelligent plug-and-play digital tool for real-time surveillance of COVID-19 patients and smart decision-making in Intensive Care Units) Reporting period: 2020-12-01 to 2021-09-30 Summary of the context and overall objectives of the project ENVISION aims at providing an artificial intelligence (AI) based tool for the intensive care unit (ICU) personnel to treat COVID-19 patients according to best practices and experiences learned from previous COVID-19 patient data from the ICU – the Sandman.IC. If successful, the developed methods for data collection and best treatment prediction will be incorporated into the medical devices used in ICUs. By collecting data from 13 ICUs located in hospitals across Europe a large set of COVID-19 patient data will be ensured. With the support of our health prediction tool and thanks to its alerting system, ICU staff will be able to respond to any patient health deterioration promptly. Further, the AI-based decision support tool will provide clear guidance to ICU personnel, allowing them to conduct the appropriate measures, possibly halting the patient’s deterioration and initiating their recovery. This will increase the survival rate in the ICUs and shorten the recovery time of the COVID-19 patients which are the overall objectives of the project. Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far Within ENVISION, significant progress has already been made in all areas of the project. On the technical side, a pilot Sandman.IC was trialled at GUF, testing the long-term monitoring and documentation capabilities of the system. Parallel to this, based on the feedback of the clinical partners throughout Europe, important user requirements for the design of Sandman.IC were identified. This also resulted in the definition of several use cases, which serve as the basis in designing the AI system. All clinical partners also successfully applied for their respective local ethics approvals for the usage of Sandman.IC.After the successful pilot project, kits for locally installing Sandman.IC at the clinical partners were prepared and dispatched. Following this, the local installations of the Sandman.IC system started. This process is expected to be concluded by the end of the year 2021. In preparation for creating the planned predictive models, simulated datasets mimicking the expected real patient data structure were created to be used in the development.On the non-technical side, prior to dispatching the Sandman.IC kits, the creation of the required training materials started. The medical staffs at the clinical centres across Europe were trained in using Sandman.IC parallel to the installations. Further, the first health economics models for assessing the economic and societal impact of Sandman.IC were created during this time. The ENVISION project also gained further publicity through several articles in German national magazines and the project’s own website. 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) Most AI-based COVID-19 development projects seem to concentrate on mortality prediction. While this is a relevant topic in the event of ICU bed shortage, ENVISION aims to reduce mortality instead of predicting it. The use cases developed in ENVISION aim at suggesting best-known treatment options to the ICU personnel, thus going beyond the state of the art.When real patient data can be obtained for AI model development, the data will be curated, checked, and entered into various types of AI models. The aims are to develop the treatment decision support tools envisioned in the use cases.If successful, the developed models will be incorporated into the commercial Sandman.IC system in the future. These decision support methods will most likely mean that more COVID-19 patients survive in the ICU or recover faster than without the project. With better treatment options leading to a decrease in mortality of COVID-19, the Sandman.IC could have a tremendous impact on the number of lives saved in Europe. Further, thanks to the shorter recovery time per patient, shortages of ICU beds may be counteracted or even prevented. Envision WP3 meeting in Tampere on 13.9.2021
