Photo Credit: The best photo for all
The following is a summary of “Explainable artificial intelligence for early prediction of pressure injury risk,” published in the September 2024 issue of Critical Care by Alderden et al.
Individuals with hospital-acquired pressure injuries (HAPIs) affect the outcomes in intensive care units (ICUs). Traditional risk-assessment tools have limitations, while artificial intelligence models offer improved accuracy but lack transparency.
Researchers conducted a retrospective study to develop an artificial intelligence-based HAPI risk-assessment model with an explainable artificial intelligence dashboard to improve the interpretability of patients both globally and independently.
They applied an explainable artificial intelligence approach to examine ICU patient data from the Medical Information Mart for Intensive Care. Predictor variables were limited to the first 48 hours post-ICU admission. Multiple machine-learning algorithms were tested, leading to an ensemble “super learner” model, and its performance was calculated by the area under the receiver operating characteristic curve through 5-fold cross-validation. An explainer dashboard was developed (using synthetic data to maintain patient privacy) with interactive visualizations for detailed model interpretation at both global and local levels.
The results showed that the final sample included 28,395 patients with a 4.9% incidence of HAPIs. The ensemble super learner model performed well (area under curve = 0.80). The explainer dashboard provided global and patient-level interactive visualizations of model predictions, showing each variable’s impact on the risk-assessment outcome.
Investigators concluded that the model and its dashboard provide clinicians with a transparent, interpretable artificial intelligence-based risk-assessment system for HAPIs that may enable more effective and timely preventive interventions.
Source: aacnjournals.org/ajcconline/article/33/5/373/32528/Explainable-Artificial-Intelligence-for-Early
