Affiliation:
1. Departments of Neurosurgery and
2. Neurology, University of Pennsylvania, Philadelphia, Pennsylvania; and
3. IBM Corp., Armonk, New York
Abstract
OBJECTIVE
Avoiding intracranial hypertension after traumatic brain injury (TBI) is a foundation of neurocritical care, to minimize secondary brain injury related to elevated intracranial pressure (ICP). However, this approach at best is reactive to episodes of intracranial hypertension, allowing for periods of elevated ICP before therapies can be initiated. Accurate prediction of ICP crises before they occur would permit clinicians to implement preventive strategies, minimize total time with ICP above threshold, and potentially avoid secondary injury. The objective of this study was to develop an algorithm capable of predicting the onset of ICP crises with sufficient lead time to enable application of preventative therapies.
METHODS
Thirty-six patients admitted to a level I trauma center with severe TBI (Glasgow Coma Scale score < 8) between April 2015 and January 2019 who underwent continuous intraparenchymal ICP monitor placement were retrospectively identified. Continuous ICP data were extracted from each monitoring period (range 4–96 hours of monitoring). An ICP crisis was treated as a binary outcome, defined as ICP > 22 mm Hg for at least 75% of the data within a 5-minute interval. ICP data preceding each ICP crisis were grouped into four total data sets of 1- and 2-hour epochs, each with 10- to 20-minute lead-time intervals before an ICP crisis. Crisis and noncrisis events were identified from continuous time-series data and randomly split into 70% for training and 30% for testing, from a subset of 30 patients. Machine learning algorithms were trained to predict ICP crises, including light gradient boosting, extreme gradient boosting, and random forest. Accuracy and area under the receiver operating characteristic curve (AUC) were measured to compare performance. The most predictive algorithm was optimized using feature selection and hyperparameter tuning to avoid overfitting, and then tested on a validation subset of 5 patients. Precision, recall, F1 score, and accuracy were measured.
RESULTS
The random forest model demonstrated the highest accuracy (range 0.82–0.88) and AUC (range 0.86–0.88) across all four data sets. Further validation testing revealed high precision (0.76), relatively low recall (0.46), and overall strong predictive performance (F1 score 0.57, accuracy 0.86) for ICP crises. Decision curve analysis showed that the model provided net benefit at probability thresholds above 0.1 and below 0.9.
CONCLUSIONS
The presented model can provide accurate and timely forecasts of ICP crises in patients with severe TBI 10–20 minutes prior to their occurrence. If validated and implemented in clinical workflows, this algorithm can enable earlier intervention for ICP crises, more effective treatment of intracranial hypertension, and potentially improved outcomes following severe TBI.
Publisher
Journal of Neurosurgery Publishing Group (JNSPG)
Subject
Genetics,Animal Science and Zoology
Reference33 articles.
1. The International Multidisciplinary Consensus Conference on Multimodality Monitoring in Neurocritical Care: a list of recommendations and additional conclusions: a statement for healthcare professionals from the Neurocritical Care Society and the European Society of Intensive Care Medicine;Le Roux P,2014
2. Current concepts in neurocritical care;Fahy BG,2002
3. Multimodal monitoring and neurocritical care bioinformatics;Hemphill JC,2011
4. Intracranial pressure monitoring and management;Le Roux P,2016
5. Routine intracranial pressure monitoring in acute coma;Forsyth RJ,2015
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献