Electronic patient data is growing exponentially, which can often leave clinicians suffering from information overload.

With this growing volume and variety of data, however, it is now possible to quickly and automatically produce models that can analyze bigger, more complex data and deliver faster, more accurate results.

By using algorithms to build models that uncover connections, we can now help clinicians make better decisions and deliver better patient care. 

Analytic for Hemodynamic Instability

The Analytic for Hemodynamic Instability (AHI) is a clinical decision support tool that predicts hemodynamic instability on monitored patients before it is visually apparent. AHI is a machine learning analytic module that integrates patient ECGs (waveforms), with their respective demographics, labs, drugs and vital signs to generate an output score with predictive clinical decision information to care teams. This 'score' indicates the early onset of hemodynamic instability and alerts key personnel to facilitate early intervention to increase patient survival.

Hemodynamic instability is when blood flow drops and deprives the body of needed oxygen resulting in one of the most common causes of death for critically ill or injured patients.

The Problem

Early detection of hemodynamic decompensation (EDHD) via ECG waveform analysis can be used to prevent decompensation and/or improve patient outcomes whenever a waveform is available.

  • Without this technology decompensation events will continue to occur at current rates.
  • Current monitoring technology is unable perform EDHD automatically and reliable EDHD is not possible even by a trained clinician watching the patient’s vital signs.

Long-Term Desired Clinical Endpoints

We want to reduce complications by identifying when a patient will have hemodynamic instability well before the event occurs so that we can use less invasive means to stabilize the patient.