Delirium prediction in the ICU: designing a screening tool for preventive interventions.

Introduction: Delirium occurrence is common and preventive strategies are resource intensive. Screening tools can prioritize patients at risk. Using machine learning, we can capture time and treatment effects that pose a challenge to delirium prediction. We aim to develop a delirium prediction model that can be used as a screening tool. Methods: From the eICU Collaborative Research Database (eICU-CRD) and the Medical Information Mart for Intensive Care version III (MIMIC-III) database, patients with one or more Confusion Assessment Method-Intensive Care Unit (CAM-ICU) values and intensive care unit (ICU) length of stay greater than 24 h were included in our study. We validated our model using 21 quantitative clinical parameters and assessed performance across a range of observation and prediction windows, using different thresholds and applied interpretation techniques. We evaluate our models based on stratified repeated cross-validation using 3 algorithms, namely Logistic Regression, Random Forest, and Bidirectional Long Short-Term Memory (BiLSTM). BiLSTM represents an evolution from recurrent neural network-based Long Short-Term Memory, and with a backward input, preserves information from both past and future. Model performance is measured using Area Under Receiver Operating Characteristic, Area Under Precision Recall Curve, Recall, Precision (Positive Predictive Value), and Negative Predictive Value metrics. Results: We evaluated our results on 16 546 patients (47% female) and 6294 patients (44% female) from eICU-CRD and MIMIC-III databases, respectively. Performance was best in BiLSTM models where, precision and recall changed from 37.52% (95% confidence interval [CI], 36.00%-39.05%) to 17.45 (95% CI, 15.83%-19.08%) and 86.1% (95% CI, 82.49%-89.71%) to 75.58% (95% CI, 68.33%-82.83%), respectively as prediction window increased from 12 to 96 h. After optimizing for higher recall, precision and recall changed from 26.96% (95% CI, 24.99%-28.94%) to 11.34% (95% CI, 10.71%-11.98%) and 93.73% (95% CI, 93.1%-94.37%) to 92.57% (95% CI, 88.19%-96.95%), respectively. Comparable results were obtained in the MIMIC-III cohort. Conclusions: Our model performed comparably to contemporary models using fewer variables. Using techniques like sliding windows, modification of threshold to augment recall and feature ranking for interpretability, we addressed shortcomings of current models.

Early Progressive Mobilization of Patients with External Ventricular Drains: Safety and Feasibility.

BACKGROUND/OBJECTIVE: Early mobilization of critically ill patients has been shown to improve functional outcomes. Neurosurgery patients with an external ventricular drain (EVD) due to increased intracranial pressure often remain on bed rest while EVD remains in place. The prevalence of mobilizing patients with EVD has not been described, and the literature regarding the safety and feasibility of mobilizing patients with EVDs is limited. The aim of our study was to describe the outcomes and adverse events of the first mobilization attempt in neurosurgery patients with EVD who participated in early functional mobilization with physical therapy or occupational therapy. METHODS: We performed a single-site, retrospective chart review of 153 patients who underwent placement of an EVD. Hemodynamically stable patients deemed appropriate for mobilization by physical or occupational therapy were included. Mobilization and activity details were recorded. RESULTS: The most common principal diagnoses were subarachnoid hemorrhage (61.4%) and intracerebral hemorrhage (17.0%) requiring EVD for symptomatic hydrocephalus. A total of 117 patients were mobilized (76.5%), and the median time to first mobilization after EVD placement in this group of 117 patients was 38 h. Decreased level of consciousness was the most common reason for lack of mobilization. The highest level of mobility on the patient's first attempt was ambulation (43.6%), followed by sitting on the side of the bed (30.8%), transferring to a bedside chair (17.1%), and standing up from the side of the bed (8.5%). No major safety events, such as EVD dislodgment, occurred in any patient. Transient adverse events with mobilization were infrequent at 6.9% and had no permanent neurological sequelae and were mostly headache, nausea, and transient diastolic blood pressure elevation. CONCLUSION: Early progressive mobilization of neurosurgical intensive care unit patients with external ventricular drains appears safe and feasible.