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.
Arterial Pressure
Blood Pressure Determination
Decision Support Techniques
Humans
Hypotension
/ diagnosis
Intraoperative Period
Machine Learning
Monitoring, Intraoperative
/ methods
Netherlands
Predictive Value of Tests
Prospective Studies
Randomized Controlled Trials as Topic
Risk Assessment
Risk Factors
Surgical Procedures, Operative
/ adverse effects
Time Factors
Treatment Outcome
Anesthesiology
Artificial intelligence
Blood pressure
Hemodynamics
Perioperative care
Journal
Trials
ISSN: 1745-6215
Titre abrégé: Trials
Pays: England
ID NLM: 101263253
Informations de publication
Date de publication:
11 Oct 2019
11 Oct 2019
Historique:
received:
02
05
2019
accepted:
08
08
2019
entrez:
12
10
2019
pubmed:
12
10
2019
medline:
24
3
2020
Statut:
epublish
Résumé
Intraoperative hypotension is associated with increased morbidity and mortality. Current treatment is mostly reactive. The Hypotension Prediction Index (HPI) algorithm is able to predict hypotension minutes before the blood pressure actually decreases. Internal and external validation of this algorithm has shown good sensitivity and specificity. We hypothesize that the use of this algorithm in combination with a personalized treatment protocol will reduce the time weighted average (TWA) in hypotension during surgery spent in hypotension intraoperatively. We aim to include 100 adult patients undergoing non-cardiac surgery with an anticipated duration of more than 2 h, necessitating the use of an arterial line, and an intraoperatively targeted mean arterial pressure (MAP) of > 65 mmHg. This study is divided into two parts; in phase A baseline TWA data from 40 patients will be collected prospectively. A device (HemoSphere) with HPI software will be connected but fully covered. Phase B is designed as a single-center, randomized controlled trial were 60 patients will be randomized with computer-generated blocks of four, six or eight, with an allocation ratio of 1:1. In the intervention arm the HemoSphere with HPI will be used to guide treatment; in the control arm the HemoSphere with HPI software will be connected but fully covered. The primary outcome is the TWA in hypotension during surgery. The aim of this trial is to explore whether the use of a machine-learning algorithm intraoperatively can result in less hypotension. To test this, the treating anesthesiologist will need to change treatment behavior from reactive to proactive. This trial has been registered with the NIH, U.S. National Library of Medicine at ClinicalTrials.gov, ID: NCT03376347 . The trial was submitted on 4 November 2017 and accepted for registration on 18 December 2017.
Sections du résumé
BACKGROUND
BACKGROUND
Intraoperative hypotension is associated with increased morbidity and mortality. Current treatment is mostly reactive. The Hypotension Prediction Index (HPI) algorithm is able to predict hypotension minutes before the blood pressure actually decreases. Internal and external validation of this algorithm has shown good sensitivity and specificity. We hypothesize that the use of this algorithm in combination with a personalized treatment protocol will reduce the time weighted average (TWA) in hypotension during surgery spent in hypotension intraoperatively.
METHODS/DESIGN
METHODS
We aim to include 100 adult patients undergoing non-cardiac surgery with an anticipated duration of more than 2 h, necessitating the use of an arterial line, and an intraoperatively targeted mean arterial pressure (MAP) of > 65 mmHg. This study is divided into two parts; in phase A baseline TWA data from 40 patients will be collected prospectively. A device (HemoSphere) with HPI software will be connected but fully covered. Phase B is designed as a single-center, randomized controlled trial were 60 patients will be randomized with computer-generated blocks of four, six or eight, with an allocation ratio of 1:1. In the intervention arm the HemoSphere with HPI will be used to guide treatment; in the control arm the HemoSphere with HPI software will be connected but fully covered. The primary outcome is the TWA in hypotension during surgery.
DISCUSSION
CONCLUSIONS
The aim of this trial is to explore whether the use of a machine-learning algorithm intraoperatively can result in less hypotension. To test this, the treating anesthesiologist will need to change treatment behavior from reactive to proactive.
TRIAL REGISTRATION
BACKGROUND
This trial has been registered with the NIH, U.S. National Library of Medicine at ClinicalTrials.gov, ID: NCT03376347 . The trial was submitted on 4 November 2017 and accepted for registration on 18 December 2017.
Identifiants
pubmed: 31601239
doi: 10.1186/s13063-019-3637-4
pii: 10.1186/s13063-019-3637-4
pmc: PMC6788048
doi:
Banques de données
ClinicalTrials.gov
['NCT03376347']
Types de publication
Clinical Trial Protocol
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
582Subventions
Organisme : Edwards Lifesciences
ID : not applicable
Références
Anesthesiology. 2018 Oct;129(4):663-674
pubmed: 29894315
Arch Gerontol Geriatr. 2015 Nov-Dec;61(3):503-9
pubmed: 26272285
Anesthesiology. 2017 Jan;126(1):47-65
pubmed: 27792044
Anesthesiology. 2009 Dec;111(6):1217-26
pubmed: 19934864
JAMA. 2017 Oct 10;318(14):1346-1357
pubmed: 28973220
Br J Anaesth. 2018 Oct;121(4):706-721
pubmed: 30236233
Anesthesiology. 2015 Aug;123(2):307-19
pubmed: 26083768
Anesth Analg. 2016 Oct;123(4):933-9
pubmed: 27636576
Anesthesiology. 2015 Sep;123(3):515-23
pubmed: 26181335
Anesthesiology. 2007 Aug;107(2):213-20
pubmed: 17667564
Eur J Anaesthesiol. 2018 Apr;35(4):273-279
pubmed: 29210843
BMJ. 2013 Jan 08;346:e7586
pubmed: 23303884
Anesth Analg. 2018 Aug;127(2):424-431
pubmed: 29916861
Anesthesiology. 2016 Jan;124(1):35-44
pubmed: 26540148
Minerva Anestesiol. 2013 Sep;79(9):978-90
pubmed: 23719658
Lancet. 2015 Apr 27;385 Suppl 2:S11
pubmed: 26313057
Scott Med J. 2004 Feb;49(1):6-9
pubmed: 15012044