Neural network–based identification of patients at high risk for intraoperative cerebrospinal fluid leaks in endoscopic pituitary surgery

View More View Less
  • 1 Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland;
  • 2 Amsterdam UMC, Vrije Universiteit Amsterdam, Neurosurgery, Amsterdam Movement Sciences, Amsterdam, The Netherlands; and
  • 3 Department of Neurosurgery, Tuscany School of Neurosurgery, University of Firenze, Firenze, Italy
Restricted access

Purchase Now

USD  $45.00

JNS + Pediatrics - 1 year subscription bundle (Individuals Only)

USD  $505.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $600.00
Print or Print + Online

OBJECTIVE

Although rates of postoperative morbidity and mortality have become relatively low in patients undergoing transnasal transsphenoidal surgery (TSS) for pituitary adenoma, cerebrospinal fluid (CSF) fistulas remain a major driver of postoperative morbidity. Persistent CSF fistulas harbor the potential for headache and meningitis. The aim of this study was to investigate whether neural network–based models can reliably identify patients at high risk for intraoperative CSF leakage.

METHODS

From a prospective registry, patients who underwent endoscopic TSS for pituitary adenoma were identified. Risk factors for intraoperative CSF leaks were identified using conventional statistical methods. Subsequently, the authors built a prediction model for intraoperative CSF leaks based on deep learning.

RESULTS

Intraoperative CSF leaks occurred in 45 (29%) of 154 patients. No risk factors for CSF leaks were identified using conventional statistical methods. The deep neural network–based prediction model classified 88% of patients in the test set correctly, with an area under the curve of 0.84. Sensitivity (83%) and specificity (89%) were high. The positive predictive value was 71%, negative predictive value was 94%, and F1 score was 0.77. High suprasellar Hardy grade, prior surgery, and older age contributed most to the predictions.

CONCLUSIONS

The authors trained and internally validated a robust deep neural network–based prediction model that identifies patients at high risk for intraoperative CSF. Machine learning algorithms may predict outcomes and adverse events that were previously nearly unpredictable, thus enabling safer and improved patient care and better patient counseling.

ABBREVIATIONS AUC = area under the curve; CSF = cerebrospinal fluid; EOR = extent of resection; F1 score = harmonic mean of PPV and sensitivity; GTR = gross-total resection; NPV = negative predictive value; PA = pituitary adenoma; PPV = positive predictive value; R ratio = ratio between the maximum horizontal adenoma diameter and the minimum intercarotid distance at the horizontal C4 segment of the internal carotid artery; TSS = transsphenoidal surgery; 3T-iMRI = high–field strength intraoperative 3-Tesla MRI.

Supplementary Materials

    • HDF5 File (ZIP 482 KB)
    • Supplementary Table 1 (PDF 412 KB)

JNS + Pediatrics - 1 year subscription bundle (Individuals Only)

USD  $505.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $600.00

Contributor Notes

Correspondence Carlo Serra: University Hospital Zurich, Switzerland. c.serra@hotmail.it.

INCLUDE WHEN CITING Published online June 21, 2019; DOI: 10.3171/2019.4.JNS19477.

Disclosures The authors report no conflict of interest concerning the materials or methods used in this study or the findings specified in this paper.

  • 1

    Bouthillier A, van Loveren HR, Keller JT: Segments of the internal carotid artery: a new classification. Neurosurgery 38:425433, 1996

    • Search Google Scholar
    • Export Citation
  • 2

    Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP: SMOTE: Synthetic Minority Over-sampling Technique. J Artif Intell Res 16:321357, 2002

  • 3

    Chen CJ, Ironside N, Pomeraniec IJ, Chivukula S, Buell TJ, Ding D, : Microsurgical versus endoscopic transsphenoidal resection for acromegaly: a systematic review of outcomes and complications. Acta Neurochir (Wien) 159:21932207, 2017

    • Search Google Scholar
    • Export Citation
  • 4

    Conger A, Zhao F, Wang X, Eisenberg A, Griffiths C, Esposito F, : Evolution of the graded repair of CSF leaks and skull base defects in endonasal endoscopic tumor surgery: trends in repair failure and meningitis rates in 509 patients. J Neurosurg 130:861875, 2018

    • Search Google Scholar
    • Export Citation
  • 5

    Dhandapani S, Singh H, Negm HM, Cohen S, Anand VK, Schwartz TH: Cavernous sinus invasion in pituitary adenomas: systematic review and pooled data meta-analysis of radiologic criteria and comparison of endoscopic and microscopic surgery. World Neurosurg 96:3646, 2016

    • Search Google Scholar
    • Export Citation
  • 6

    Dlouhy BJ, Madhavan K, Clinger JD, Reddy A, Dawson JD, O’Brien EK, : Elevated body mass index and risk of postoperative CSF leak following transsphenoidal surgery. J Neurosurg 116:13111317, 2012

    • Search Google Scholar
    • Export Citation
  • 7

    Esposito F, Dusick JR, Fatemi N, Kelly DF: Graded repair of cranial base defects and cerebrospinal fluid leaks in transsphenoidal surgery. Neurosurgery 60 (4 Suppl 2):295304, 2007

    • Search Google Scholar
    • Export Citation
  • 8

    Fatemi N, Dusick JR, Mattozo C, McArthur DL, Cohan P, Boscardin J, : Pituitary hormonal loss and recovery after transsphenoidal adenoma removal. Neurosurgery 63:709719, 2008

    • Search Google Scholar
    • Export Citation
  • 9

    Fraser S, Gardner PA, Koutourousiou M, Kubik M, Fernandez-Miranda JC, Snyderman CH, : Risk factors associated with postoperative cerebrospinal fluid leak after endoscopic endonasal skull base surgery. J Neurosurg 128:10661071, 2018

    • Search Google Scholar
    • Export Citation
  • 10

    Jahangiri A, Wagner J, Han SW, Zygourakis CC, Han SJ, Tran MT, : Morbidity of repeat transsphenoidal surgery assessed in more than 1000 operations. J Neurosurg 121:6774, 2014

    • Search Google Scholar
    • Export Citation
  • 11

    Jakimovski D, Bonci G, Attia M, Shao H, Hofstetter C, Tsiouris AJ, : Incidence and significance of intraoperative cerebrospinal fluid leak in endoscopic pituitary surgery using intrathecal fluorescein. World Neurosurg 82:e513e523, 2014

    • Search Google Scholar
    • Export Citation
  • 12

    Karnezis TT, Baker AB, Soler ZM, Wise SK, Rereddy SK, Patel ZM, : Factors impacting cerebrospinal fluid leak rates in endoscopic sellar surgery. Int Forum Allergy Rhinol 6:11171125, 2016

    • Search Google Scholar
    • Export Citation
  • 13

    Laws ER, de los Reyes K, Rincon-Torroella J: Lumbar drains in transsphenoidal surgery. J Neurosurg 118:480481, 2012 (Letter)

  • 14

    LeCun Y, Bengio Y, Hinton G: Deep learning. Nature 521:436444, 2015

  • 15

    Mehta GU, Oldfield EH: Prevention of intraoperative cerebrospinal fluid leaks by lumbar cerebrospinal fluid drainage during surgery for pituitary macroadenomas. J Neurosurg 116:12991303, 2012

    • Search Google Scholar
    • Export Citation
  • 16

    Micko ASG, Wöhrer A, Wolfsberger S, Knosp E: Invasion of the cavernous sinus space in pituitary adenomas: endoscopic verification and its correlation with an MRI-based classification. J Neurosurg 122:803811, 2015

    • Search Google Scholar
    • Export Citation
  • 17

    Mooney MA, Hardesty DA, Sheehy JP, Bird CR, Chapple K, White WL, : Rater reliability of the Hardy classification for pituitary adenomas in the magnetic resonance imaging era. J Neurol Surg B Skull Base 78:413418, 2017

    • Search Google Scholar
    • Export Citation
  • 18

    Mooney MA, Hardesty DA, Sheehy JP, Bird R, Chapple K, White WL, : Interrater and intrarater reliability of the Knosp scale for pituitary adenoma grading. J Neurosurg 126:17141719, 2017

    • Search Google Scholar
    • Export Citation
  • 19

    Oravec CS, Motiwala M, Reed K, Kondziolka D, Barker FG 2nd, Michael LM II, : Big data research in neurosurgery: a critical look at this popular new study design. Neurosurgery 82:728746, 2018

    • Search Google Scholar
    • Export Citation
  • 20

    Patel PN, Stafford AM, Patrinely JR, Smith DK, Turner JH, Russell PT, : Risk factors for intraoperative and postoperative cerebrospinal fluid leaks in endoscopic transsphenoidal sellar surgery. Otolaryngol Head Neck Surg 158:952960, 2018

    • Search Google Scholar
    • Export Citation
  • 21

    Przybylowski CJ, Dallapiazza RF, Williams BJ, Pomeraniec IJ, Xu Z, Payne SC, : Primary versus revision transsphenoidal resection for nonfunctioning pituitary macroadenomas: matched cohort study. J Neurosurg 126:889896, 2017

    • Search Google Scholar
    • Export Citation
  • 22

    Roland PS, Marple BF, Meyerhoff WL, Mickey B: Complications of lumbar spinal fluid drainage. Otolaryngol Head Neck Surg 107:564569, 1992

    • Search Google Scholar
    • Export Citation
  • 23

    Serra C, Burkhardt JK, Esposito G, Bozinov O, Pangalu A, Valavanis A, : Pituitary surgery and volumetric assessment of extent of resection: a paradigm shift in the use of intraoperative magnetic resonance imaging. Neurosurg Focus 40(3):E17, 2016

    • Search Google Scholar
    • Export Citation
  • 24

    Serra C, Maldaner N, Muscas G, Staartjes V, Pangalu A, Holzmann D, : The changing sella: internal carotid artery shift during transsphenoidal pituitary surgery. Pituitary 20:654660, 2017

    • Search Google Scholar
    • Export Citation
  • 25

    Serra C, Staartjes VE, Maldaner N, Muscas G, Akeret K, Holzmann D, : Predicting extent of resection in transsphenoidal surgery for pituitary adenoma. Acta Neurochir (Wien) 160:22552262, 2018

    • Search Google Scholar
    • Export Citation
  • 26

    Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R: Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:19291958, 2014

    • Search Google Scholar
    • Export Citation
  • 27

    Staartjes VE, Serra C, Muscas G, Maldaner N, Akeret K, van Niftrik CHB, : Utility of deep neural networks in predicting gross-total resection after transsphenoidal surgery for pituitary adenoma: a pilot study. Neurosurg Focus 45(5):E12, 2018

    • Search Google Scholar
    • Export Citation
  • 28

    Strickland BA, Lucas J, Harris B, Kulubya E, Bakhsheshian J, Liu C, : Identification and repair of intraoperative cerebrospinal fluid leaks in endonasal transsphenoidal pituitary surgery: surgical experience in a series of 1002 patients. J Neurosurg 129:425429, 2018

    • Search Google Scholar
    • Export Citation
  • 29

    van Aken MO, Feelders RA, de Marie S, van de Berge JH, Dallenga AHG, Delwel EJ, : Cerebrospinal fluid leakage during transsphenoidal surgery: postoperative external lumbar drainage reduces the risk for meningitis. Pituitary 7:8993, 2004

    • Search Google Scholar
    • Export Citation
  • 30

    Wilson CB: Neurosurgical management of large and invasive pituitary tumors, in Tindall GT, Collins WF (eds): Clinical Management of Pituitary Disorders. New York: Raven Press, 1979, pp 335342

    • Search Google Scholar
    • Export Citation

Metrics

All Time Past Year Past 30 Days
Abstract Views 113 113 113
Full Text Views 37 37 37
PDF Downloads 16 16 16
EPUB Downloads 0 0 0