Cardiothoracic & vascular anesthesia
Leveraging artificial intelligence for the management of postoperative delirium following cardiac surgery
Authors' conclusion
AI is a promising approach with considerable potential and delivered noninferior results compared with the usual approach of structured evaluation of risk factors and questionnaires.
Study context
- Population
- Cardiac surgery patients at a specialised heart surgery centre in Germany, January–July 2021114 analysed
- Participants
- 131 patients
- Comparison
- Postoperative artificial intelligence (AI) vs Pre-operative prediction (all methods)
- Outcome
- Predictive accuracy for postoperative delirium (Confusion Assessment Method for the ICU (CAM-ICU) over three days postoperatively)
- Follow-up
- Three days postoperatively
Methodological detailssingle-centre
- Single-centre
Performance
As reported in the abstract
Prediction of postoperative delirium
| Test or model | AUC | 95% CI | AUC range |
|---|---|---|---|
| Postoperative AI | 0.79 | 0.69-0.87 | |
| Pre-operative prediction (all methods) | 0.55 to 0.66 |
AUC
Postoperative AI0.79
Pre-operative prediction (all methods)— not stated in the abstract
95% CI
Postoperative AI0.69-0.87
Pre-operative prediction (all methods)— not stated in the abstract
AUC range
Postoperative AI— not stated in the abstract
Pre-operative prediction (all methods)0.55 to 0.66
Further findings
Incidence of postoperative delirium
- Postoperative delirium diagnosed
- 23.7%
Associations with postoperative delirium
- Open heart surgery vs endovascular valve replacement
- 33.3% vs. 10.4%, P < 0.01
- Postinterventional hospitalisation
- 12.8 vs. 8.6 days, P < 0.01
- ICU LOS
- 1.7 vs. 0.3 days, P < 0.01
Original publication
Leveraging artificial intelligence for the management of postoperative delirium following cardiac surgery. Eur J Anaesthesiol Intensive Care. Published 8 December 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →