JMIR Publications

ABSTRACT

Background:

Elective surgeries for older adults are increasing. Machine learning could enhance risk assessment, influencing surgical planning and postoperative care. Preoperative cognitive assessment may facilitate early detection and management of postoperative delirium (POD).

Objective:

This study aims to assess machine learning models' predictive ability for POD, focusing on adding neuropsychological assessments before surgery.

Methods:

This retrospective cohort study analyzed data from the multicenter PAWEL and PAWEL-R studies, encompassing older patients (≥70 years) undergoing elective surgeries from July 2017 to April 2019. A total of 1624 patients were included, with POD diagnosis made before discharge. Data included demographics, clinical, surgical, and neuropsychological features collected pre- and perioperatively. Machine learning model performance was evaluated using the area under the receiver operating characteristic curve (AUC), with permutation testing for significance and SHapley Additive exPlanations to identify effective neuropsychological assessments.

Results:

In this cohort of 1624 patients, 52.3% (N=850) were male, with a mean (s.d.) age of 77.9 (4.9) years. Predicting POD before surgery achieved an AUC of 0.786. Incorporating all pre- and perioperative features into the model yielded a slightly higher AUC of 0.806, with no statistically significant difference observed (P= .193). Notably, cognitive factors alone were not strong predictors (AUC=0.611). However, specific tests within neuropsychological assessments, such as the Montreal Cognitive Assessment memory subdomain and Trail Making Test Part B, were found to be crucial for prediction.

Conclusions:

Preoperative risk prediction for POD can increase risk awareness in presurgical assessment and improve postoperative management in older patients with a high risk for delirium. Clinical Trial: The study was registered with the German Clinical Trials Register under the identifiers DRKS12797 and DRKS13311.