Clio Rubinos1,2, Soon Bin Kwon2,3, Murad Megjhani2,3, Kalijah Terilli2,3, Brenda Wong4, Lizbeth Cespedes4, Jenna Ford2, Renz Reyes4, Hannah Kirsch2, Ayham Alkhachroum2, Angela Velazquez2, David Roh2,4, Sachin Agarwal2,4, Jan Claassen2,4, E Sander Connolly4,5, Soojin Park6,7,8,9. 1. Department of Neurology, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. 2. Department of Neurology, Columbia University, 177 Fort Washington Avenue, MHB 8 Center, Room 300, New York, NY, 10032, USA. 3. Program for Hospital and Intensive Care Informatics, Department of Neurology, Columbia University, New York, NY, USA. 4. NewYork-Presbyterian Hospital, Columbia University Irving Medical Center, New York, NY, USA. 5. Department of Neurosurgery, Columbia University, New York, NY, USA. 6. Department of Neurology, Columbia University, 177 Fort Washington Avenue, MHB 8 Center, Room 300, New York, NY, 10032, USA. sp3291@cumc.columbia.edu. 7. Program for Hospital and Intensive Care Informatics, Department of Neurology, Columbia University, New York, NY, USA. sp3291@cumc.columbia.edu. 8. NewYork-Presbyterian Hospital, Columbia University Irving Medical Center, New York, NY, USA. sp3291@cumc.columbia.edu. 9. Department of Biomedical Informatics, Columbia University, New York, NY, USA. sp3291@cumc.columbia.edu.
Abstract
BACKGROUND: Prolonged external ventricular drainage (EVD) in patients with subarachnoid hemorrhage (SAH) leads to morbidity, whereas early removal can have untoward effects related to recurrent hydrocephalus. A metric to help determine the optimal time for EVD removal or ventriculoperitoneal shunt (VPS) placement would be beneficial in preventing the prolonged, unnecessary use of EVD. This study aimed to identify whether dynamics of cerebrospinal fluid (CSF) biometrics can temporally predict VPS dependency after SAH. METHODS: This was a retrospective analysis of a prospective, single-center, observational study of patients with aneurysmal SAH who required EVD placement for hydrocephalus. Patients were divided into VPS-dependent (VPS+) and non-VPS dependent groups. We measured the bicaudate index (BCI) on all available computed tomography scans and calculated the change over time (ΔBCI). We analyzed the relationship of ΔBCI with CSF output by using Pearson's correlation. A k-nearest neighbor model of the relationship between ΔBCI and CSF output was computed to classify VPS. RESULTS: Fifty-eight patients met inclusion criteria. CSF output was significantly higher in the VPS+ group in the 7 days post EVD placement. There was a negative correlation between delta BCI and CSF output in the VPS+ group (negative delta BCI means ventricles become smaller) and a positive correlation in the VPS- group starting from days four to six after EVD placement (p < 0.05). A weighted k-nearest neighbor model for classification had a sensitivity of 0.75, a specificity of 0.70, and an area under the receiver operating characteristic curve of 0.80. CONCLUSIONS: The correlation of ΔBCI and CSF output is a reliable intraindividual biometric for VPS dependency after SAH as early as days four to six after EVD placement. Our machine learning model leverages this relationship between ΔBCI and cumulative CSF output to predict VPS dependency. Early knowledge of VPS dependency could be studied to reduce EVD duration in many centers (intensive care unit length of stay).
BACKGROUND: Prolonged external ventricular drainage (EVD) in patients with subarachnoid hemorrhage (SAH) leads to morbidity, whereas early removal can have untoward effects related to recurrent hydrocephalus. A metric to help determine the optimal time for EVD removal or ventriculoperitoneal shunt (VPS) placement would be beneficial in preventing the prolonged, unnecessary use of EVD. This study aimed to identify whether dynamics of cerebrospinal fluid (CSF) biometrics can temporally predict VPS dependency after SAH. METHODS: This was a retrospective analysis of a prospective, single-center, observational study of patients with aneurysmal SAH who required EVD placement for hydrocephalus. Patients were divided into VPS-dependent (VPS+) and non-VPS dependent groups. We measured the bicaudate index (BCI) on all available computed tomography scans and calculated the change over time (ΔBCI). We analyzed the relationship of ΔBCI with CSF output by using Pearson's correlation. A k-nearest neighbor model of the relationship between ΔBCI and CSF output was computed to classify VPS. RESULTS: Fifty-eight patients met inclusion criteria. CSF output was significantly higher in the VPS+ group in the 7 days post EVD placement. There was a negative correlation between delta BCI and CSF output in the VPS+ group (negative delta BCI means ventricles become smaller) and a positive correlation in the VPS- group starting from days four to six after EVD placement (p < 0.05). A weighted k-nearest neighbor model for classification had a sensitivity of 0.75, a specificity of 0.70, and an area under the receiver operating characteristic curve of 0.80. CONCLUSIONS: The correlation of ΔBCI and CSF output is a reliable intraindividual biometric for VPS dependency after SAH as early as days four to six after EVD placement. Our machine learning model leverages this relationship between ΔBCI and cumulative CSF output to predict VPS dependency. Early knowledge of VPS dependency could be studied to reduce EVD duration in many centers (intensive care unit length of stay).
Authors: Hadie Adams; Vin Shen Ban; Ville Leinonen; Salah G Aoun; Jukka Huttunen; Taavi Saavalainen; Antti Lindgren; Juhana Frosen; Mikael Fraunberg; Timo Koivisto; Juha Hernesniemi; Babu G Welch; Juha E Jaaskelainen; Terhi J Huttunen Journal: Stroke Date: 2016-09-15 Impact factor: 7.914
Authors: Fred Rincon; Errol Gordon; Robert M Starke; Manuel M Buitrago; Andres Fernandez; J Michael Schmidt; Jan Claassen; Katja E Wartenberg; Jennifer Frontera; David B Seder; David Palestrant; E Sander Connolly; Kiwon Lee; Stephan A Mayer; Neeraj Badjatia Journal: J Neurosurg Date: 2010-10 Impact factor: 5.115
Authors: Michael Chan; Ali Alaraj; Mateo Calderon; Sebastian Ramon Herrera; Weihua Gao; Sean Ruland; Ben Zion Roitberg Journal: J Neurosurg Date: 2009-01 Impact factor: 5.115
Authors: Andrew S Little; Joseph M Zabramski; Madelon Peterson; Pamela W Goslar; Scott D Wait; Felipe C Albuquerque; Cameron G McDougall; Robert F Spetzler Journal: Neurosurgery Date: 2008-03 Impact factor: 4.654
Authors: Cian J O'Kelly; Abhaya V Kulkarni; Peter C Austin; David Urbach; M Christopher Wallace Journal: J Neurosurg Date: 2009-11 Impact factor: 5.115