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

Abstract

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: 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: 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: 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: NCT05042804.

Keywords: acute kidney injury; anaesthesiology risk assessment; artificial intelligence; clinical trial; machine learning; postoperative complications; postoperative death.

Fig 1

Relationship between TECTONICS trial and ORACLE trial. ORACLE includes a subset of the patient cases included in TECTONICS. CA-3, clinical anaesthesia year 3 (final year of residency training); CRNA, certified registered nurse anaesthetist; ML, machine learning.

Fig 2

CONSORT flow diagram. AKI, acute kidney injury; ML, machine learning.

Fig 3

Distribution of clinician predictions for postoperative death. Stratified by treatment allocation (ML-unassisted group vs ML-assisted group) and by ML prediction. Blue bars represent cases where the clinician prediction matched the categorical ML prediction. ML, machine learning.

Fig 4

Distribution of clinician predictions for postoperative acute kidney injury. Stratified by treatment allocation (ML-unassisted group vs ML-assisted group) and by ML prediction. Blue bars represent cases where the clinician prediction matched the categorical ML prediction. ML, machine learning.

Fig 5

Receiver operating characteristic curves. (a) Prediction of postoperative death within 30 days. (b) Prediction of postoperative acute kidney injury. AUC, area under curve; ML, machine learning.