The recent article titled “Hypotension Prediction Index for Prevention of Hypotension during Moderate- to High-risk Noncardiac Surgery” explored whether a “hypotension prediction index algorithm” based on an arterial blood pressure waveform analysis can reduce the duration and severity of intraoperative hypotension.1  The authors suggested that the hypotension prediction index failed to prevent hypotension because of the following: inadequate warning time, a complex treatment algorithm, a set blood pressure threshold, and clinicians ignoring the algorithm recommendation. We agree with the authors’ above reasoning; however, we have some commentary and questions for the authors on their conclusions and plans for subsequent trials.

First, the authors conclude that the main reason the hypotension prediction index did not prevent hypotension is the inadequate warning time and that lowering the intervention alert threshold in the subsequent trial would increase the time the anesthesia clinician has to act. To proceed with such a trial design, there would need to be evidence to show that the sensitivity and specificity of a lower alert threshold to predict hypotension is similar to those with the index threshold of 85.2,3  We are wondering whether the authors could share these data with readers.

Second, because the warning time needs to be increased, would it be possible to eliminate the manual interpretation of the algorithm altogether and use an automatic treatment recommendation algorithm incorporating the advanced hemodynamic parameters?

Third, we would like to see the authors expand on why the anesthesia team declined to intervene in many cases. Was it distrust in the in-operating room researcher interpreting the algorithm and giving the suggestion? Or was it because of a belief that vasoactive substances can cause harm?

We look forward to reading the authors’ future trials because it is a subject of great interest and importance. Given that approximately 40% of patients in both groups had periods of hypotension of mean arterial pressure less than 65 mmHg, effective predictors of hypotension and timely algorithmic interventions could result in massive changes in standard intraoperative anesthetic management.

The authors declare no competing interests.

1.
Maheshwari
K
,
Shimada
T
,
Yang
D
,
Khanna
S
,
Cywinski
JB
,
Irefin
SA
,
Ayad
S
,
Turan
A
,
Ruetzler
K
,
Qiu
Y
,
Saha
P
,
Mascha
EJ
,
Sessler
DI
:
Hypotension prediction index for prevention of hypotension during moderate- to high-risk noncardiac surgery.
Anesthesiology
.
2020
;
133
:
1214
22
2.
Wijnberge
M
,
Schenk
J
,
Terwindt
LE
,
Mulder
MP
,
Hollmann
MW
,
Vlaar
AP
,
Veelo
DP
,
Geerts
BF
:
The use of a machine-learning algorithm that predicts hypotension during surgery in combination with personalized treatment guidance: Study protocol for a randomized clinical trial.
Trials
.
2019
;
20
:
582
3.
Hatib
F
,
Jian
Z
,
Buddi
S
,
Lee
C
,
Settels
J
,
Sibert
K
,
Rinehart
J
,
Cannesson
M
:
Machine-learning algorithm to predict hypotension based on high-fidelity arterial pressure waveform analysis.
Anesthesiology
.
2018
;
129
:
663
74