The objective is this study is the development and implementation of a smart algorithm to compute an early warning indicator able to predict early patient deterioration.
Data will be collected at the three sites using the SomnoTouchTM and MOXTM devices, commercially available and CE approved. Every month, the data will be sent to the KUL and UM to develop the algorithm. Study centers will also send some pre-defined patient characteristics extracted from the patient's EMR to better contextualize the data. The EWS formula has a free interpretation of the vital parameters weighting and the vital parameters to be taken into account in the scoring system. Therefore, many variants of the EWS arose the past decade (i.e. MEWS, NEWS). The algorithm developed in this study should define an objective approach for the EWS formula, diminishing the discordances regarding the weight per parameter. Using a patient-personalized approach, the definite algorithm should be based on the patient's vital parameter measured during his/her whole hospitalization, generating a patient-personalized weight per parameter and an overall reliable EWS scoring system. The EWS score is often only measured twice per day per patient, creating a large window for disease worsening. The algorithm developed in this study could be deployed along the wearable device developed in the WearIT4Health project. The device would continuously feed the algorithm with data acquired from its sensors. Thus, the EWS would be computed every 10 seconds. The EWS scoring system has already been proven to be an effective approach in reducing clinical deterioration, reducing the admission to intensive care units and thus overall reducing mortality. However, as mentioned above the EWS is measured in a rather low frequency. Therefore, estimation of the EWS score via continuous monitored parameters should further increase patient survival. The primary objective of the EAGLE study is to collect continuously monitored vital and activity parameter data and use it to develop an algorithm that can early identify clinical deterioration to optimize the application of the EWS system.
Study Type
OBSERVATIONAL
Enrollment
80
The patient will be equipped with the SomnoTouch device. This device is able to record and estimate the following data: ECG data PPG data Heart rate Respiration rate Blood pressure (mmHg) Oxygen saturation (%). All patient will be stored for further analysis.
The patient will be equipped with the MOX device. This device is able to record and estimate the following data: Accelerometers data Activity Body posture All patient will be stored for further analysis.
Ziekenhuis Oost-Limburg
Genk, Limbourg, Belgium
Centre Hospitalier Universitaire de Liège
Liège, Belgium
Maastricht University Medical Center+
Maastricht, Netherlands
Precision of predictive early warning score algorithm
Precision defined of truepositives divided by the sum of truepositives and truenegatives. This measure indicates how often the predictive EWS was right in identifying adverse events.
Time frame: Up to 1 week
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.