OPTIMIZE 5.5 - Optimizing Impella 5.5 Outcomes Through Advanced Data Science

Condition(s) studied

Investigational drug(s) / intervention(s)

Micro-axial flow pump support: Temporary circulatory support using the Impella 5.5 micro-axial flow pump. The device is surgically placed (typically via the axillary artery) across the aortic valve into the left ventricle to provide active forward flow, unloading the left ventricle and maintaining systemic perfusion during cardiogenic shock. Management of the device includes the collection and analysis of continuous device-derived hemodynamic data and associated clinical parameters throughout the duration of support.

Study summary

The main goal of this observational, study is to develop a clinical decision support tool utilizing Impella 5.5 pump parameters to predict native heart recovery and prevent adverse events, by leveraging data science and real-world clinical data of cardiogenic shock patients.

Therefore, secondary objectives are essential to consolidating a retrospective longitudinal analysis of Impella 5.5 pump data alongside ICU digital health record datasets to:

1. Validate the Impella 5.5 placement signal by comparing it with ICU arterial line waveforms.
2. Integrate pump data with ICU clinical data to identify patterns associated with therapy outcomes, including native heart recovery, heart replacement therapy, and mortality while on device support.
3. Define clinical scenarios linked to hemolysis, HRAEs, and arrhythmias and develop predictive models to mitigate their occurrence.

Eligibility

Primary outcome measure(s)

• Predictive Performance and Optimization of the Clinician Decision Support Tool — From the time of Impella 5.5 insertion up to device explant (estimated average of 5 to 14 days).
  The predictive performance of the developed clinical decision support tool will be evaluated by its ability to classify patient trajectories toward native heart recovery versus adverse outcomes. The model will undergo comprehensive model architecture optimization to identify the structural configuration that yields optimal performance. Model training, validation, and testing will follow a standard data split: 80% of the dataset will be utilized for training and internal validation using 5-fold cross-validation, and the remaining 20% will be held out as a definitive testing dataset. Final classification performance will be quantified using specific metrics derived from Receiver Operating Characteristic (ROC) curve analysis, including: Area Under the Curve (AUC), Sensitivity, Specificity

Trial sites (1)

More Medical University of Vienna trials in Austria

Other trials for the same condition