Natural and Artificial Intelligence in Neurosurgery: A Systematic Review

Neurosurgery - Tập 83 Số 2 - Trang 181-192 - 2018
Joeky T. Senders1,2,3, Omar Arnaout1,2,3, Aditya V. Karhade1,2,3, Hormuzdiyar H. Dasenbrock1,2,3, William B. Gormley1,2,3, Marike L. D. Broekman1,2,3, Timothy R. Smith1,2,3
1Cushing Neurosurgery Outcomes Cen-ter, Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts
2Department of Neurological Surgery, Northwestern University School of Medicine, Chicago, Illinois
3Department of Neurosurgery, University Medical Center, Utrecht, The Netherlands

Tóm tắt

Abstract BACKGROUND Machine learning (ML) is a domain of artificial intelligence that allows computer algorithms to learn from experience without being explicitly programmed. OBJECTIVE To summarize neurosurgical applications of ML where it has been compared to clinical expertise, here referred to as “natural intelligence.” METHODS A systematic search was performed in the PubMed and Embase databases as of August 2016 to review all studies comparing the performance of various ML approaches with that of clinical experts in neurosurgical literature. RESULTS Twenty-three studies were identified that used ML algorithms for diagnosis, presurgical planning, or outcome prediction in neurosurgical patients. Compared to clinical experts, ML models demonstrated a median absolute improvement in accuracy and area under the receiver operating curve of 13% (interquartile range 4-21%) and 0.14 (interquartile range 0.07-0.21), respectively. In 29 (58%) of the 50 outcome measures for which a P-value was provided or calculated, ML models outperformed clinical experts (P < .05). In 18 of 50 (36%), no difference was seen between ML and expert performance (P > .05), while in 3 of 50 (6%) clinical experts outperformed ML models (P < .05). All 4 studies that compared clinicians assisted by ML models vs clinicians alone demonstrated a better performance in the first group. CONCLUSION We conclude that ML models have the potential to augment the decision-making capacity of clinicians in neurosurgical applications; however, significant hurdles remain associated with creating, validating, and deploying ML models in the clinical setting. Shifting from the preconceptions of a human-vs-machine to a human-and-machine paradigm could be essential to overcome these hurdles.

Từ khóa


Tài liệu tham khảo

Ghahramani, 2015, Probabilistic machine learning and artificial intelligence, Nature, 521, 452, 10.1038/nature14541

Obermeyer, 2016, Predicting the future - big data, machine learning, and clinical medicine, N Engl J Med, 375, 1216, 10.1056/NEJMp1606181

Jordan, 2015, Machine learning: trends, perspectives, and prospects, Science, 349, 255, 10.1126/science.aaa8415

Noble, 2006, What is a support vector machine?, Nat Biotechnol, 24, 1565, 10.1038/nbt1206-1565

Deo, 2015, Machine learning in medicine, Circulation, 132, 1920, 10.1161/CIRCULATIONAHA.115.001593

Azimi, 2015, Artificial neural networks in neurosurgery, J Neurol Neurosurg Psychiatry, 86, 251, 10.1136/jnnp-2014-307807

Rodrigues, 2016, On the convergence of nanotechnology and Big Data analysis for computer-aided diagnosis, Nanomedicine (Lond), 11, 959, 10.2217/nnm.16.35

Coveney, 2016, Big data need big theory too, Philos Trans A Math Phys Eng Sci, 374

Mariak, 2000, Intracranial pressure processing with artificial neural networks: classification of signal properties, Acta Neurochir (Wien), 142, 407, 10.1007/s007010050450

Nucci, 2016, Intracranial pressure wave morphological classification: automated analysis and clinical validation, Acta Neurochir (Wien), 158, 581, 10.1007/s00701-015-2672-5

Sieben, 1994, The development of a decision support system for the pathological diagnosis of human cerebral tumours based on a neural network classifier, Acta Neurochir (Wien), 129, 193, 10.1007/BF01406504

Mathew, 1989, Artificial intelligence in the prediction of operative findings in low back surgery, Brit J Neurosurg, 3, 161, 10.3109/02688698909002791

Arle, 1999, Neural network analysis of preoperative variables and outcome in epilepsy surgery, J Neurosurg, 90, 998, 10.3171/jns.1999.90.6.0998

Gazit, 2016, Probabilistic machine learning for the evaluation of presurgical language dominance, J Neurosurg, 125, 1, 10.3171/2015.7.JNS142568

Shi, 2013, In-hospital mortality after traumatic brain injury surgery: a nationwide population-based comparison of mortality predictors used in artificial neural network and logistic regression models, J Neurosurg, 118, 746, 10.3171/2013.1.JNS121130

Azimi, 2014, Predicting endoscopic third ventriculostomy success in childhood hydrocephalus: an artificial neural network analysis, J Neurosurg Pediatr, 13, 426, 10.3171/2013.12.PEDS13423

Azimi, 2015, Prediction of successful ETV outcome in childhood hydrocephalus: an artificial neural networks analysis, J Neurosurg, 122, 426

Chang, 2016, Multimodal imaging patterns predict survival in recurrent glioblastoma patients treated with bevacizumab, Neuro-oncology, 10.1093/neuonc/now086

Jones, 2015, Brain tumor classification using the diffusion tensor image segmentation (D-SEG) technique, Neuro-oncology, 17, 466

Macyszyn, 2016, Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques, Neuro-oncology, 18, 417, 10.1093/neuonc/nov127

Teplyuk, 2012, MicroRNAs in cerebrospinal fluid identify glioblastoma and metastatic brain cancers and reflect disease activity, Neuro-oncology, 14, 689, 10.1093/neuonc/nos074

Zhang, 2017, Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas, Neuro-oncology, 19, 109, 10.1093/neuonc/now121

Fouke, 2012, A machine-learning-based classifier for predicting a multi-parametric probability map of active tumor extent within glioblastoma multiforme, Neuro-oncology, 14, vi124

Kim, 2012, Predicting the location and probability of viable tumor within glioblastoma multiforme with multiparametric magnetic resonance imaging, Neuro-oncology, 14, vi120

Orphanidou-Vlachou, 2014, Texture analysis of T1-and t2-weighted magnetic resonance images to discriminate posterior fossa tumors in children, Neuro-oncology, 16, i123

Rayfield, 2015, Predicting the response to treatment in GBM: Machine learning on clinical images, Neuro-oncology, 17, v167, 10.1093/neuonc/nov225.59

Akbari, 2016, Imaging surrogates of infiltration obtained via multiparametric imaging pattern analysis predict subsequent location of recurrence of glioblastoma, Neurosurgery, 78, 572, 10.1227/NEU.0000000000001202

Mitchell, 2013, A novel data-driven approach to preoperative mapping of functional cortex using resting-state functional magnetic resonance imaging, Neurosurgery, 73, 969, 10.1227/NEU.0000000000000141

Oermann, 2013, Predicting survival in patients with brain metastases treated with radiosurgery using artificial neural networks, Neurosurgery, 72, 944, 10.1227/NEU.0b013e31828ea04b

Taghva, 2010, An automated navigation system for deep brain stimulator placement using hidden Markov models, Neurosurgery, 66, 108

Dumont, 2011, Prediction of symptomatic cerebral vasospasm after aneurysmal subarachnoid hemorrhage with an artificial neural network: feasibility and comparison with logistic regression models, World Neurosurg, 75, 57, 10.1016/j.wneu.2010.07.007

Emblem, 2009, Automatic glioma characterization from dynamic susceptibility contrast imaging: brain tumor segmentation using knowledge-based fuzzy clustering, J Magn Reson Imaging, 30, 1, 10.1002/jmri.21815

Emblem, 2015, A generic support vector machine model for preoperative glioma survival associations, Radiology, 275, 228, 10.1148/radiol.14140770

Rughani, 2010, Use of an artificial neural network to predict head injury outcome, J Neurosurg, 113, 585, 10.3171/2009.11.JNS09857

Arle, 1997, Prediction of posterior fossa tumor type in children by means of magnetic resonance image properties, spectroscopy, and neural networks, J Neurosurg, 86, 755, 10.3171/jns.1997.86.5.0755

Bidiwala, 2004, Neural network classification of pediatric posterior fossa tumors using clinical and imaging data, Pediatr Neurosurg, 40, 8, 10.1159/000076571

Juntu, 2010, Machine learning study of several classifiers trained with texture analysis features to differentiate benign from malignant soft-tissue tumors in T1-MRI images, J Magn Reson Imaging, 31, 680, 10.1002/jmri.22095

Kitajima, 2009, Differentiation of common large sellar-suprasellar masses effect of artificial neural network on radiologists' diagnosis performance, Acad Radiol, 16, 313, 10.1016/j.acra.2008.09.015

Yamashita, 2008, Performance evaluation of radiologists with artificial neural network for differential diagnosis of intra-axial cerebral tumors on MR images, AJNR Am J Neuroradiol, 29, 1153, 10.3174/ajnr.A1037

Dolz, 2016, Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: a clinical study, Comput Med Imaging Graph, 52, 8, 10.1016/j.compmedimag.2016.03.003

Lee, 2000, Localization of epileptogenic zones in F-18 FDG brain PET of patients with temporal lobe epilepsy using artificial neural network, IEEE Trans Med Imaging, 19, 347, 10.1109/42.848185

Tankus, 2009, An automatic measure for classifying clusters of suspected spikes into single cells versus multiunits, J Neural Eng, 6, 056001, 10.1088/1741-2560/6/5/056001

Zhao, 2010, A new method to classify pathologic grades of astrocytomas based on magnetic resonance imaging appearances, Neurol India, 58, 685, 10.4103/0028-3886.72161

Kerr, 2013, Computer-Aided Diagnosis and Localization of Lateralized Temporal Lobe Epilepsy Using Interictal FDG-PET, Front Neurol, 4, 1, 10.3389/fneur.2013.00031

Chiang, 2015, Computer-automated focus lateralization of temporal lobe epilepsy using fMRI, J Magn Reson Imaging, 41, 1689, 10.1002/jmri.24696

Cohen, 2016, Methodological issues in predicting pediatric epilepsy surgery candidates through natural language processing and machine learning, Biomed Inform Insights, 8, 11

Sinha, 2001, Artificial neural network predicts CT scan abnormalities in pediatric patients with closed head injury, J Trauma, 50, 308, 10.1097/00005373-200102000-00018

Kassahun, 2014, Automatic classification of epilepsy types using ontology-based and genetics-based machine learning, Artif Intell Med, 61, 79, 10.1016/j.artmed.2014.03.001

Floyd, 1992, An artificial neural network for lesion detection on single-photon emission computed tomographic images, Invest Radiol, 27, 667, 10.1097/00004424-199209000-00001

Duun-Henriksen, 2012, Channel selection for automatic seizure detection, Clin Neurophysiol, 123, 84, 10.1016/j.clinph.2011.06.001

Christy, 1995, Use of a neural network and a multiple regression model to predict histologic grade of astrocytoma from MRI appearances, Neuroradiology, 37, 89, 10.1007/BF00588619

Campillo-Gimenez, 2013, Full-text automated detection of surgical site infections secondary to neurosurgery in Rennes, France, Stud Health Technol Inform, 192, 572

Abdolmaleki, 1997, Neural networks analysis of astrocytic gliomas from MRI appearances, Cancer Lett, 118, 69, 10.1016/S0304-3835(97)00233-4

Clarke, 1998, MRI measurement of brain tumor response: comparison of visual metric and automatic segmentation, Magn Reson Imaging, 16, 271, 10.1016/S0730-725X(97)00302-0

Chan, 2008, Effect of a computer-aided diagnosis system on clinicians' performance in detection of small acute intracranial hemorrhage on computed tomography, Acad Radiol, 15, 290, 10.1016/j.acra.2007.09.022

Nadkarni, 2011, Natural language processing: an introduction, J Am Med Inform Assoc, 18, 544, 10.1136/amiajnl-2011-000464

Liu, 2011, Natural Language Processing methods and systems for biomedical ontology learning, J Biomed Inform, 44, 163, 10.1016/j.jbi.2010.07.006