Prediction of post-operative delirium with machine learning in abdominal surgery with comorbidity indices and laboratory values

Background: Postoperative delirium (POD) is a complication associated with most types of surgery, and is associated with a number of detrimental effects. Therefore, it is of interest to determine which patients may be at higher risk of POD so that mitigating steps may be taken. We sought to determine whether POD can be accurately predicted with common machine learning (ML) models. Methods: Using the Medical Information Mart for Intensive Care (MIMIC)-IV database, we identified 8026 abdominal surgery procedures across 7215 adult patients. Using demographic information, such as age, type of surgery, sex; as well as commonly measured laboratory values (such as electrolytes and blood counts) and comorbidity indices, we determined to what extend common ML models, such as random forests, support vector machines, extreme gradient boosted machines, and neural networks, could predict POD. Results: Random forests outperformed logistic regression, support vector machines, extreme gradient boosted machines, and neural networks, with respect to individual t-tests. The random forest model had a sensitivity of 73.11, a specificity of 71.14, and an area under the receiver operator characteristic curve of 0.800. Age, comorbidity indices, gender, and alcohol use carried significant predictive weight in this cohort. Conclusions: Machine learning models are effective predictors of postoperative delirium, although further work is required to increase clinical utility of such tools. Markers of inflammation, comorbidity indices, and alcohol use are important predictive features alongside better-known features such as age.