Effect of machine learning models on clinician prediction of postoperative complications: the Perioperative ORACLE randomised clinical trial.

acute kidney injury anaesthesiology risk assessment artificial intelligence clinical trial machine learning postoperative complications postoperative death

Journal

British journal of anaesthesia
ISSN: 1471-6771
Titre abrégé: Br J Anaesth
Pays: England
ID NLM: 0372541

Informations de publication

Date de publication:
10 Sep 2024
Historique:
received: 23 05 2024
revised: 19 07 2024
accepted: 07 08 2024
medline: 12 9 2024
pubmed: 12 9 2024
entrez: 11 9 2024
Statut: aheadofprint

Résumé

Anaesthesiologists might be able to mitigate risk if they know which patients are at greatest risk for postoperative complications. This trial examined the impact of machine learning models on clinician risk assessment. This single-centre, prospective, randomised clinical trial enrolled surgical patients aged ≥18 yr. Anaesthesiologists and nurse anaesthetists providing remote telemedicine support reviewed electronic health records with (assisted group) or without (unassisted group) reviewing machine learning predictions. Clinicians predicted the likelihood of postoperative 30-day all-cause mortality and postoperative acute kidney injury (AKI) within 7 days. The primary outcome was area under the receiver operating characteristic curve (AUROC) for clinician predictions of mortality and AKI, comparing AUROCs between assisted and unassisted assessments. We analysed 5071 patients (mean [range] age: 58 [18-100] yr; 52% female) assessed by 89 clinicians. Of these, 98 (2.2%) patients died within 30 days of surgery and 450 (11.1%) patients sustained AKI. Clinician predictions agreed with the models more strongly in the assisted vs unassisted group (weighted kappa 0.75 vs 0.62 for death, mean difference: 0.13 [95% CI 0.10-0.17]; and 0.79 vs 0.54 for AKI, mean difference: 0.25 [95% CI 0.21-0.29]). Clinical prediction of death was similar between the assisted (AUROC 0.793) and unassisted (AUROC 0.780) groups (mean difference: 0.013 [95% CI -0.070 to 0.097]; P=0.76). Prediction of AKI had an AUROC of 0.734 in the assisted group vs 0.688 in the unassisted group (difference 0.046 [95% CI -0.003 to 0.091]; P=0.06). Clinician performance was not improved by machine learning assistance. Further work is needed to clarify the role of machine learning in real-time perioperative risk stratification. NCT05042804.

Sections du résumé

BACKGROUND BACKGROUND
Anaesthesiologists might be able to mitigate risk if they know which patients are at greatest risk for postoperative complications. This trial examined the impact of machine learning models on clinician risk assessment.
METHODS METHODS
This single-centre, prospective, randomised clinical trial enrolled surgical patients aged ≥18 yr. Anaesthesiologists and nurse anaesthetists providing remote telemedicine support reviewed electronic health records with (assisted group) or without (unassisted group) reviewing machine learning predictions. Clinicians predicted the likelihood of postoperative 30-day all-cause mortality and postoperative acute kidney injury (AKI) within 7 days. The primary outcome was area under the receiver operating characteristic curve (AUROC) for clinician predictions of mortality and AKI, comparing AUROCs between assisted and unassisted assessments.
RESULTS RESULTS
We analysed 5071 patients (mean [range] age: 58 [18-100] yr; 52% female) assessed by 89 clinicians. Of these, 98 (2.2%) patients died within 30 days of surgery and 450 (11.1%) patients sustained AKI. Clinician predictions agreed with the models more strongly in the assisted vs unassisted group (weighted kappa 0.75 vs 0.62 for death, mean difference: 0.13 [95% CI 0.10-0.17]; and 0.79 vs 0.54 for AKI, mean difference: 0.25 [95% CI 0.21-0.29]). Clinical prediction of death was similar between the assisted (AUROC 0.793) and unassisted (AUROC 0.780) groups (mean difference: 0.013 [95% CI -0.070 to 0.097]; P=0.76). Prediction of AKI had an AUROC of 0.734 in the assisted group vs 0.688 in the unassisted group (difference 0.046 [95% CI -0.003 to 0.091]; P=0.06).
CONCLUSIONS CONCLUSIONS
Clinician performance was not improved by machine learning assistance. Further work is needed to clarify the role of machine learning in real-time perioperative risk stratification.
CLINICAL TRIAL REGISTRATION BACKGROUND
NCT05042804.

Identifiants

pubmed: 39261226
pii: S0007-0912(24)00468-9
doi: 10.1016/j.bja.2024.08.004
pii:
doi:

Banques de données

ClinicalTrials.gov
['NCT05042804']

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Informations de copyright

Copyright © 2024 British Journal of Anaesthesia. Published by Elsevier Ltd. All rights reserved.

Auteurs

Bradley A Fritz (BA)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA. Electronic address: bafritz@wustl.edu.

Christopher R King (CR)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Mohamed Abdelhack (M)

Department of Computer Science and Engineering, Washington University McKelvey School of Engineering, Saint Louis, MO, USA; Krembil Centre for Neuroinformatics, Centre for Addiction and Mental Health, Toronto, ON, Canada.

Yixin Chen (Y)

Department of Computer Science and Engineering, Washington University McKelvey School of Engineering, Saint Louis, MO, USA.

Alex Kronzer (A)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Joanna Abraham (J)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA; Institute for Informatics, Data Science, and Biostatistics, Washington University School of Medicine, Saint Louis, MO, USA.

Sandhya Tripathi (S)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Arbi Ben Abdallah (A)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Thomas Kannampallil (T)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA; Institute for Informatics, Data Science, and Biostatistics, Washington University School of Medicine, Saint Louis, MO, USA.

Thaddeus P Budelier (TP)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Daniel Helsten (D)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Arianna Montes de Oca (A)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Divya Mehta (D)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Pratyush Sontha (P)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Omokhaye Higo (O)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Paul Kerby (P)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Stephen H Gregory (SH)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Troy S Wildes (TS)

Department of Anesthesiology, University of Nebraska Medical Center, Omaha, NE, USA.

Michael S Avidan (MS)

Department of Anesthesiology, Washington University School of Medicine, Saint Louis, MO, USA.

Classifications MeSH