SURGE-ahead postoperative delirium prediction: external validation and open-source library.

Area of Science:

• Geriatric Medicine
• Artificial Intelligence in Healthcare
• Surgical Patient Care

Background:

• Postoperative delirium (POD) is a frequent complication in older surgical patients.
• POD is associated with adverse outcomes and increased healthcare costs.
• Accurate and early POD prediction is vital for effective management.

Purpose of the Study:

• To externally validate the performance of the SURGE-Ahead predictive algorithm for postoperative delirium.
• To assess the algorithm's utility in supporting geriatric co-management in surgical settings.
• To evaluate the algorithm's predictive accuracy using preoperative data.

Main Methods:

• Prospective external validation study.
• Utilized the SURGE-Ahead algorithm, a linear support vector machine model with 15 features.
• Analyzed data from 173 surgical participants, 50 of whom developed POD.

Main Results:

• The SURGE-Ahead algorithm demonstrated state-of-the-art performance with an AUC of 0.86.
• The algorithm showed good calibration, indicated by a Brier Score of 0.14.
• The algorithm is openly available on GitHub for broader implementation.

Conclusions:

• The validated SURGE-Ahead algorithm reliably predicts POD using preoperative data.
• This AI tool can enhance patient care for hospitalized older adults.
• Findings support the development of robust POD prediction tools for surgical settings.