Background

The Hypotension Prediction Index is designed to predict intraoperative hypotension in a timely manner and is based on arterial waveform analysis using machine learning. It has recently been suggested that this algorithm is highly correlated with the mean arterial pressure itself. Therefore, the aim of this study was to compare the index with mean arterial pressure–based prediction methods, and it is hypothesized that their ability to predict hypotension is comparable.

Methods

In this observational study, the Hypotension Prediction Index was used in addition to routine intraoperative monitoring during moderate- to high-risk elective noncardiac surgery. The agreement in time between the default Hypotension Prediction Index alarm (greater than 85) and different concurrent mean arterial pressure thresholds was evaluated. Additionally, the predictive performance of the index and different mean arterial pressure–based methods were assessed within 5, 10, and 15 min before hypotension occurred.

Results

A total of 100 patients were included. A mean arterial pressure threshold of 73 mmHg agreed 97% of the time with the default index alarm, whereas a mean arterial pressure threshold of 72 mmHg had the most comparable predictive performance. The areas under the receiver operating characteristic curve of the Hypotension Prediction Index (0.89 [0.88 to 0.89]) and concurrent mean arterial pressure (0.88 [0.88 to 0.89]) were almost identical for predicting hypotension within 5 min, outperforming both linearly extrapolated mean arterial pressure (0.85 [0.84 to 0.85]) and delta mean arterial pressure (0.66 [0.65 to 0.67]). The positive predictive value was 31.9 (31.3 to 32.6)% for the default index alarm and 32.9 (32.2 to 33.6)% for a mean arterial pressure threshold of 72 mmHg.

Conclusions

In clinical practice, the Hypotension Prediction Index alarms are highly similar to those derived from mean arterial pressure, which implies that the machine learning algorithm could be substituted by an alarm based on a mean arterial pressure threshold set at 72 or 73 mmHg. Further research on intraoperative hypotension prediction should therefore include comparison with mean arterial pressure–based alarms and related effects on patient outcome.

Editor’s Perspective
What We Already Know about This Topic
  • The Hypotension Prediction Index is an alarm system approved by the Food and Drug Administration used to predict a mean arterial pressure less than 65 mmHg for at least 1 min in the operating room and critical care environments
  • It is based on a proprietary algorithm derived using machine learning from components of the arterial waveform processed using pulse contour analysis methods
  • Preliminary reports have suggested that the Hypotension Prediction Index is highly correlated with mean arterial pressure and that a mean arterial pressure threshold alone might predict imminent hypotension
What This Article Tells Us That Is New
  • Using prospectively obtained observational single-center data from 100 patients undergoing elective noncardiac surgery with invasive arterial monitoring, the authors used correlation, receiver operating characteristic curves, and precision-recall curves analyses to characterize the relationship between the index and simultaneous mean arterial pressure
  • A mean arterial pressure threshold of 73 mmHg correlated 97% of the time with the default Hypotension Prediction Index alarm (greater than 85)
  • A mean arterial pressure threshold of 72 mmHg had the most comparable predictive performance
  • Predictive performance metrics were essentially identical for the index and the mean arterial pressure across all analyses, and both surpassed either linearly extrapolated mean arterial pressure or delta mean arterial pressure
  • The positive predictive value for either the index or a mean arterial pressure threshold of 72 mmHg were both low, suggesting a high rate of false alarms