Home > Journals > Journal of Neurosurgical Sciences > Past Issues > Articles online first > Journal of Neurosurgical Sciences 2018 Feb 23



To subscribe
Submit an article
Recommend to your librarian


Publication history
Cite this article as



Journal of Neurosurgical Sciences 2018 Feb 23

DOI: 10.23736/S0390-5616.18.04299-6


language: English

Artificial neural networks can be effectively used to model changes of intracranial pressure (ICP) during spinal surgery using different non invasive ICP surrogate estimators

Abdulla WATAD 1, 2 , Nicola L. BRAGAZZI 3, 4, 5, Susanna BACIGALUPPI 6, Howard AMITAL 1, 2, Samaa WATAD 7, Kassem SHARIF 1, 2, Bishara BISHARAT 13, Anna SIRI 6, Ala MAHAMID 8, Hakim ABU RAS 8, Ahmed NASR 9, Federico BILOTTA 10, Chiara ROBBA 11, Mohammad ADAWI 12

1 Department of Medicine 'B', Sheba Medical Center, Tel-Hashomer, Israel; 2 Zabludowicz Center for Autoimmune Diseases, Sheba Medical Center, Tel-Hashomer, Israel; 3 School of Public Health, Department of Health Sciences (DISSAL), Genoa, Italy; 4 Department of Neuroscience, Rehabilitation (DINOGMI), University of Genoa, Genoa, Italy; 5 Department of Mathematics (DIMA), University of Genoa, Genoa, Italy; 6 Department of Neurosurgery, Galliera Hospital, Genoa, Italy; 7 Department of Statistics and Operations Research, Tel Aviv University, Tel Aviv, Israel; 8 Department of Anesthesiology, Hillel Yaffe Medical Center, Hadera, Israel; 9 Department of Medicine and Surgery, University Milan Bicocca, San Gerardo Hospital, Monza, Italy; 10 Department of Anaesthesiology, Critical Care and Pain Medicine, University of Rome "La Sapienza", Rome, Italy; 11 Neurosciences Critical Care Unit, Cambridge University Hospitals NHS Foundation Trust, UK; 12 Padeh and Ziv Hospitals, Bar-Ilan Faculty of Medicine, Zefat, Israel; 13 The Society for the Arab Health Population (Israel Medical Association) Health Management Department , Yezrael Valley Academic College, Israel


BACKGROUND: Artificial Intelligence (AI) techniques play a major role in anesthesiology, even though their importance is often overlooked. In the extant literature, AI approaches, such as Artificial Neural Networks (ANNs), have been underutilized, mainly being used to model patient's consciousness state, to predict the precise amount of anesthetic gases, the level of analgesia, or the need of anesthesiological blocks, among others. In the field of neurosurgery, ANNs have been effectively applied to the diagnosis and prognosis of cerebral tumors, seizures, low back pain, and also to the monitoring of intracranial pressure (ICP).
METHODS: A MultiLayer Perceptron (MLP), which is a feedforward ANN, with hyperbolic tangent as activation function in the input/hidden layers, softmax as activation function in the output layer, and cross-entropy as error function, was used to model the impact of prone versus supine position and the use of positive end expiratory pressure (PEEP) on ICP in a sample of 30 patients undergoing spinal surgery. Different non invasive surrogate estimations of ICP have been used and compared: namely, mean optic nerve sheath diameter (ONSD), non invasive estimated cerebral perfusion pressure (NCPP), pulsatility index (PI), ICP derived from PI (ICP-PI), and flow velocity diastolic formula (FVDICP).
RESULTS: ONSD proved to be a more robust surrogate estimation of ICP, with a predictive power of 75%, whilst the power of NCPP, ICP-PI, PI, and FVDICP were 60.5%, 54.8%, 53.1%, and 47.7%, respectively.
CONCLUSIONS: Our MLP analysis confirmed our findings previously obtained with regression, correlation, multivariate Receiving Operator Curve (multi-ROC) analyses. ANNs can be successfully used to predict the effects of prone versus supine position and PEEP on ICP in patients undergoing spinal surgery using different non invasive surrogate estimators of ICP.

KEY WORDS: Artificial intelligence - Artificial neural networks - Computational techniques - Multilayer perceptron - Non invasive surrogate estimators of intracranial pressure

top of page