The Hypotension Prediction Index (the index) software is a machine learning algorithm that detects physiologic changes that may lead to hypotension. The original validation used a case control (backward) analysis that has been suggested to be biased. This study therefore conducted a cohort (forward) analysis and compared this to the original validation technique.
A retrospective analysis of data from previously reported studies was conducted. All data were analyzed identically with two different methodologies, and receiver operating characteristic curves were constructed. Both backward and forward analyses were performed to examine differences in area under the receiver operating characteristic curves for the Hypotension Prediction Index and other hemodynamic variables to predict a mean arterial pressure (MAP) less than 65 mmHg for at least 1 min 5, 10, and 15 min in advance.
The analysis included 2,022 patients, yielding 4,152,124 measurements taken at 20-s intervals. The area under the curve for the index predicting hypotension analyzed by backward and forward methodologies respectively was 0.957 (95% CI, 0.947 to 0.964) versus 0.923 (95% CI, 0.912 to 0.933) 5 min in advance, 0.933 (95% CI, 0.924 to 0.942) versus 0.923 (95% CI, 0.911 to 0.933) 10 min in advance, and 0.929 (95% CI, 0.918 to 0.938) versus 0.926 (95% CI, 0.914 to 0.937) 15 min in advance. No variable other than MAP had an area under the curve greater than 0.7. The areas under the curve using forward analysis for MAP predicting hypotension 5, 10, and 15 min in advance were 0.932 (95% CI, 0.920 to 0.940), 0.929 (95% CI, 0.918 to 0.938), and 0.932 (95% CI, 0.921 to 0.940), respectively. The R2 for the variation in the index due to MAP was 0.77.
Using an updated methodology, the study found that the utility of the Hypotension Prediction Index to predict future hypotensive events is high, with an area under the receiver operating characteristics curve similar to that of the original validation method.
- 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.
- A previous simulation study in Anesthesiology suggests that the predictive ability of the index might have been influenced by a selection bias due to use of a “backward” (case control method) in which a gray zone was used.
- It has been suggested that the use of a “forward” (cohort) methodology may be a more clinically appropriate validation method.
- Using a deidentified cohort pooled from nine previous studies involving operative and critical care populations monitored either invasively or noninvasively, this study analyzed the area under the receiver operator curve using either a backward approach with a gray zone or a forward approach without a gray zone, as well as relation of the index to concurrent mean arterial pressure in predicting hypotension 5, 10, and 15 min in advance. Other hemodynamic variables were also assessed as secondary analyses along with clinically based predictive indices.
- The area under the receiver operating characteristics curve values for the index were very high and similar for either the backward or forward approaches, and concurrent mean arterial pressure was the only variable with an area under the receiver operating characteristics curve greater than 0.7 with similar values to the index. The results were similar between clinical cohorts and mode of monitoring.
- Although the areas under the receiver operating characteristics curve were very high, the positive predictive value for either the index or the concurrent mean arterial pressure were high in the backward analysis but low in the forward analysis, suggesting that future clinical studies need to carefully consider this issue in their design.
Leave a Reply
You must be logged in to post a comment.