Risa B Myers1, Christos Lazaridis, Christopher M Jermaine, Claudia S Robertson, Craig G Rusin. 1. 1Department of Computer Science, Rice University, Houston, TX.2Division of Neurocritical Care, Department of Neurology, Baylor College of Medicine, Houston, TX.3Department of Neurosurgery, Baylor College of Medicine, Houston, TX.4Department of Pediatrics, Section of Cardiology, Baylor College of Medicine, Houston, TX.
Abstract
OBJECTIVES: To develop computer algorithms that can recognize physiologic patterns in traumatic brain injury patients that occur in advance of intracranial pressure and partial brain tissue oxygenation crises. The automated early detection of crisis precursors can provide clinicians with time to intervene in order to prevent or mitigate secondary brain injury. DESIGN: A retrospective study was conducted from prospectively collected physiologic data. intracranial pressure, and partial brain tissue oxygenation crisis events were defined as intracranial pressure of greater than or equal to 20 mm Hg lasting at least 15 minutes and partial brain tissue oxygenation value of less than 10 mm Hg for at least 10 minutes, respectively. The physiologic data preceding each crisis event were used to identify precursors associated with crisis onset. Multivariate classification models were applied to recorded data in 30-minute epochs of time to predict crises between 15 and 360 minutes in the future. SETTING: The neurosurgical unit of Ben Taub Hospital (Houston, TX). SUBJECTS: Our cohort consisted of 817 subjects with severe traumatic brain injury. MEASUREMENTS AND MAIN RESULTS: Our algorithm can predict the onset of intracranial pressure crises with 30-minute advance warning with an area under the receiver operating characteristic curve of 0.86 using only intracranial pressure measurements and time since last crisis. An analogous algorithm can predict the start of partial brain tissue oxygenation crises with 30-minute advanced warning with an area under the receiver operating characteristic curve of 0.91. CONCLUSIONS: Our algorithms provide accurate and timely predictions of intracranial hypertension and tissue hypoxia crises in patients with severe traumatic brain injury. Almost all of the information needed to predict the onset of these events is contained within the signal of interest and the time since last crisis.
OBJECTIVES: To develop computer algorithms that can recognize physiologic patterns in traumatic brain injurypatients that occur in advance of intracranial pressure and partial brain tissue oxygenation crises. The automated early detection of crisis precursors can provide clinicians with time to intervene in order to prevent or mitigate secondary brain injury. DESIGN: A retrospective study was conducted from prospectively collected physiologic data. intracranial pressure, and partial brain tissue oxygenation crisis events were defined as intracranial pressure of greater than or equal to 20 mm Hg lasting at least 15 minutes and partial brain tissue oxygenation value of less than 10 mm Hg for at least 10 minutes, respectively. The physiologic data preceding each crisis event were used to identify precursors associated with crisis onset. Multivariate classification models were applied to recorded data in 30-minute epochs of time to predict crises between 15 and 360 minutes in the future. SETTING: The neurosurgical unit of Ben Taub Hospital (Houston, TX). SUBJECTS: Our cohort consisted of 817 subjects with severe traumatic brain injury. MEASUREMENTS AND MAIN RESULTS: Our algorithm can predict the onset of intracranial pressure crises with 30-minute advance warning with an area under the receiver operating characteristic curve of 0.86 using only intracranial pressure measurements and time since last crisis. An analogous algorithm can predict the start of partial brain tissue oxygenation crises with 30-minute advanced warning with an area under the receiver operating characteristic curve of 0.91. CONCLUSIONS: Our algorithms provide accurate and timely predictions of intracranial hypertension and tissue hypoxia crises in patients with severe traumatic brain injury. Almost all of the information needed to predict the onset of these events is contained within the signal of interest and the time since last crisis.
Authors: Susan L Bratton; Randall M Chestnut; Jamshid Ghajar; Flora F McConnell Hammond; Odette A Harris; Roger Hartl; Geoffrey T Manley; Andrew Nemecek; David W Newell; Guy Rosenthal; Joost Schouten; Lori Shutter; Shelly D Timmons; Jamie S Ullman; Walter Videtta; Jack E Wilberger; David W Wright Journal: J Neurotrauma Date: 2007 Impact factor: 5.269
Authors: Susan L Bratton; Randall M Chestnut; Jamshid Ghajar; Flora F McConnell Hammond; Odette A Harris; Roger Hartl; Geoffrey T Manley; Andrew Nemecek; David W Newell; Guy Rosenthal; Joost Schouten; Lori Shutter; Shelly D Timmons; Jamie S Ullman; Walter Videtta; Jack E Wilberger; David W Wright Journal: J Neurotrauma Date: 2007 Impact factor: 5.269
Authors: Peter Le Roux; David K Menon; Giuseppe Citerio; Paul Vespa; Mary Kay Bader; Gretchen Brophy; Michael N Diringer; Nino Stocchetti; Walter Videtta; Rocco Armonda; Neeraj Badjatia; Julian Bösel; Randall Chesnut; Sherry Chou; Jan Claassen; Marek Czosnyka; Michael De Georgia; Anthony Figaji; Jennifer Fugate; Raimund Helbok; David Horowitz; Peter Hutchinson; Monisha Kumar; Molly McNett; Chad Miller; Andrew Naidech; Mauro Oddo; DaiWai Olson; Kristine O'Phelan; J Javier Provencio; Corinna Puppo; Richard Riker; Claudia Roberson; Michael Schmidt; Fabio Taccone Journal: Neurocrit Care Date: 2014-12 Impact factor: 3.210
Authors: Shara I Feld; Daniel S Hippe; Ljubomir Miljacic; Nayak L Polissar; Shu-Fang Newman; Bala G Nair; Monica S Vavilala Journal: J Neurosurg Anesthesiol Date: 2021-11-11 Impact factor: 3.969
Authors: Mervyn Singer; Paul J Young; John G Laffey; Pierre Asfar; Fabio Silvio Taccone; Markus B Skrifvars; Christian S Meyhoff; Peter Radermacher Journal: Crit Care Date: 2021-12-19 Impact factor: 9.097