Selection Bias in the Hypotension Prediction Index: Comment

Giustiniano, Enrico; Nisi, Fulvio

doi:10.1097/aln.0000000000004460

Cited by 5 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9,10 The basic relationship between Hypotension Prediction Index and mean arterial pressure HPI has been reported to appear almost a direct transformation/mirror of MAP, that is, each value of HPI corresponds to a narrow range of MAP values. 2,3,12,13 We have not encountered figures with simultaneous time series values of HPI and MAP, where this is not the case. This is, of course, anecdotal information.…”

Section: Is Hypotension Prediction Index Simply a Transformation Of M...mentioning

confidence: 91%

“…This is observed in practice, where MAP can be normal/stable for hours, fluctuating between 70 and 75 mmHg, whereas HPI constantly alerts and calls for treatment of such normotension. 2,3 In principle, when training a prediction model, any data selection is allowed. We believe that the intent with the data selection used for training HPI 4 was to exclude a 'grey zone' of uncertainty concerning the outcome (hypotension or nonhypotension) (see Fig.…”

Section: Selection Bias In the Development/training Of Hypotension Pr...mentioning

confidence: 99%

“…A model developed on such data is probably clinically irrelevant, because it will learn the erroneous fact that a MAP less than 75 mmHg leads to certain hypotension, and learn little from possibly relevant features such as waveform signatures reflective of, for example, early vasodilation. This is observed in practice, where MAP can be normal/stable for hours, fluctuating between 70 and 75 mmHg, whereas HPI constantly alerts and calls for treatment of such normotension 2,3 …”

Section: Selection Bias In the Development/training Of Hypotension Pr...mentioning

confidence: 99%

See 2 more Smart Citations

CON: The hypotension prediction index is a validated predictor of hypotension

Vistisen,

Enevoldsen

2023

European Journal of Anaesthesiology

View full text Add to dashboard Cite

The Hypotension Prediction Index (HPI) algorithm is a commercial prediction algorithm developed to predict hypotension, a mean arterial pressure (MAP) below 65 mmHg. Although HPI has been investigated in several studies, recent concerns of have been raised regarding HPI's predictive abilities, which may have been overstated. A selection bias may have forced the HPI algorithm to learn almost exclusively from MAP. This CON position paper describes the selection bias further and summarises the scientific status of HPI's predictive abilities, including the meaning of a recent erratum retracting the primary conclusion of a published HPI validation study. We argue that the HPI algorithm needs re-validation or complete re-development to achieve a clinically relevant ‘added value’ in comparison with the predictive performance of a simple and costless MAP alarm threshold in the range of 70 to 75 mmHg.

show abstract

Section: Is Hypotension Prediction Index Simply a Transformation Of M...mentioning

confidence: 91%

Section: Selection Bias In the Development/training Of Hypotension Pr...mentioning

confidence: 99%

Section: Selection Bias In the Development/training Of Hypotension Pr...mentioning

confidence: 99%

See 1 more Smart Citation

CON: The hypotension prediction index is a validated predictor of hypotension

Vistisen,

Enevoldsen

2023

European Journal of Anaesthesiology

View full text Add to dashboard Cite

show abstract

“…We have read the interesting comment by Giustiniano and Nisi 1 about our article. 2 The authors highlight that the diastolic arterial blood pressure can decrease significantly when the Hypotension Prediction Index (hereafter the Index ) reaches approximately 50 and argue for the possible need for treatment when diastolic arterial blood pressure is very low.…”

Section: In Replymentioning

confidence: 97%

Selection Bias in the Hypotension Prediction Index: Reply

Enevoldsen

Hovgaard²,

Vistisen³

2023

Anesthesiology

View full text Add to dashboard Cite

“…We would like to speculate that the relatively more 'performant' HPI is because of the very strong physiologic/pathophysiologic basis of baroreflexes. The current debates that contest the computational approaches behind the HPI technology 13,[23][24][25] seem to ignore the physiologic/pathophysiologic basis of HPI. Criticism of HPI is relevant in that the performance of HPI should be tested against comparators that may be clinically credible 26 such as the continuous measurement of arterial blood pressure.…”

mentioning

confidence: 99%