Predictive Modeling in the Intensive Care Unit

Project Description

Outcome of patients with traumatic brain injury (TBI) is depending on both the severity of primary impact of the trauma and secondary damage to the brain that occurs in the period after the primary impact. Prevention and treatment of this secondary brain injury is the primary aim during admission of these patients at the ICU.

Increased intracranial pressure (ICP); intracranial hypertension (IH), is the most important factor in secondary brain injury. In current clinical practice, IH is recognized at the moment that the ICP exceeds a certain threshold value, resulting in reactive treatment to normalize ICP. In the time between recognition of IH and the effective restoration to normal pressure, increased ICP will reduce cerebral perfusion pressure (CPP) with the risk of cerebral ischemia and secondary deterioration. Instead, a proactive treatment strategy with prevention of IH by timely restitution of ICP lowering therapy is necessary.

An ICP pulse, ensuing to cardiac output, consists of a typical waveform morphology and consists of three peaks, representing the percussion wave (P1), the tidal wave (P2) and the dicrotic wave (P3). P1 is caused by arterial pulsation, P2 by intracranial compliance and P3 by closure of the aortic valve. In case of an increasing intracranial volume, the compliance of the brain decreases according the intracranial pressure-volume curve resulting in an increase in amplitude of P2. When compliance decreases even further P1, P2 and P3 are merged to one peak.

Since changes in ICP morphology precede IH, the aim of this project is to predict IH based on changes in ICP waveform morphology.

People

Ruud van Kaam

Ruud van Kaam

PhD student

Intensive Care Medicine, Radboudumc

Luca Ambrogioni

Luca Ambrogioni

Assistant professor

Artificial Intelligence, Radboud University

Astrid Hoedemaekers

Astrid Hoedemaekers

Intensivist

Intensive Care Medicine, Radboudumc

Marcel van Gerven

Marcel van Gerven

Professor

Artificial Intelligence, Radboud University

Hans van der Hoeven

Hans van der Hoeven

Professor

Intensive Care Medicine, Radboudumc

Tim Frenzel

Tim Frenzel

Intensivist

Intensive Care Medicine, Radboudumc

Jeroen Schouten

Jeroen Schouten

Intensivist

Intensive Care Medicine, Radboudumc