Major challenges in hospitals addressed by ENVISION
More than 10% of infected patients have received treatment in Intensive Care Units (ICUs). Insufficient data and limited knowledge on the disease as well as the lack of tools to support the intensivist in making accurate, timely and informed decisions has led to high mortality rates.
Continuous surveillance, the collection and intelligent analysis of data from many sources, including ventilators and electrical impedance tomography, would allow intensivists to decide on the best suitable treatment to accelerate the recovery of the often comorbid COVID-19 patients, while reducing the burden on clinical staff and healthcare costs. This information would also increase our understanding of the yet unknown course of disease, supporting other stakeholders in the quest for new therapies.
ICU ADMISSIONWill the patient require intensive care?
ICU MORTALITYWhat are the chances of survival upon admission?
SEPSISIs the patient in danger of developing sepsis?
ECMOWill the patient require extracorporeal life support?
The aim of the ENVISION project was to provide 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. The developed methods for data collection and best treatment prediction were planned to be incorporated into the medical devices used in ICUs. With the support of our health prediction tool and thanks to its alerting system, ICU staff would be able to respond to any patient health deterioration promptly. Further, the AI-based decision support tool was to provide clear guidance to ICU personnel, allowing them to conduct the appropriate measures, possibly halting the patient’s deterioration and initiating their recovery. This would increase the survival rate in the ICUs and shorten the recovery time of the COVID-19 patients which were the overall objectives of the project.
Cutting-edge technology for clinical decision support
Sandman.IC can be used as a research tool with anonymised data or as a documentation tool in the clinical daily routine with integration into the clinical IT systems. The product’s main components are the iPad app and the ComBox, an adapter system for the connection to patient monitor and ventilator or other medical devices. If the iPad is connected to the ComBox the data from the medical devices are transferred to the iPad automatically. The user can enter additional data manually, such as medication, positioning of the patient or the type of a vascular access. Additionally, administrative data such as patient information, admission and discharge data and the medical history can be documented. The data structure is based on international standards, such as SNOMED CT.
The data will then be saved automatically to a server. How the connection between iPad, ComBox and server is realised, for instance via LAN, WiFi, Bluetooth or cable, can be adapted to the IT infrastructure in each individual clinic and their demands. The system is therefore very adaptable to the different prerequisites in the clinics and can be installed in only a few days. Because of its intuitive handling the training for the user can by conducted in two hours or less.