Abstract
Purpose
This narrative review examines the evolving landscape of artificial intelligence (AI) integration in skull base surgery, exploring its multifaceted applications and impact on various aspects of patient care.
Methods
Extensive literature review was conducted to gather insights into the role of AI in skull base surgery. Key aspects such as diagnosis, image analysis, surgical planning, navigation, predictive analytics, clinical decision-making, postoperative care, rehabilitation, and virtual simulations were explored. Studies were sourced from PubMed using keyword search strategy for relevant headings, sub-headings and cross-referencing.
Results
AI enhances early diagnosis through diagnostic algorithms that guide investigations based on clinical and radiological data. AI-driven image analysis enables accurate segmentation of intricate structures and extraction of radiomics data, optimizing preoperative planning and predicting treatment response. In surgical planning, AI aids in identifying critical structures, leading to precise interventions. Real-time AI-based navigation offers adaptive guidance, enhancing surgical accuracy and safety. Predictive analytics empower risk assessment, treatment planning, and outcome prediction. AI-driven clinical decision support systems optimize resource allocation and support shared decision-making. Postoperative care benefits from AI’s monitoring capabilities and personalized rehabilitation protocols. Virtual simulations powered by AI expedite skill development and decision-making in complex procedures.
Conclusion
AI contributes to accurate diagnosis, surgical planning, navigation, predictive analysis, and postoperative care. Ethical considerations and data quality assurance are essential, ensuring responsible AI implementation. While AI serves as a valuable complement to clinical expertise, its potential to enhance decision-making, precision, and efficiency in skull base surgery is evident.
Keywords: Artificial Intelligence; Skull base Surgery; Machine Learning; Deep Learning; Neural Networks, Computer
Introduction
Skull base surgery poses formidable challenges due to intricate anatomy and delicate structures involved. Traditional reliance on clinical experience and case reports for managing cases lacks evidence-based precision. Complex decision-making, interdisciplinary collaboration, and individualized treatments compound surgical planning and patient counselling complexities. Artificial intelligence (AI) integration offers a potential solution, promising enhanced precision, efficiency, and patient outcomes. This review explores the multifaceted role of AI in addressing the challenges in the field of skull base surgery, unveiling its transformative impact on various aspects of patient management.
Methods
Extensive literature review was conducted to gather insights into the role of AI in skull base surgery. Key aspects such as diagnosis, image analysis, surgical planning, navigation, predictive analytics, clinical decision-making, postoperative care, rehabilitation, and virtual simulations were explored. Studies were sourced from PubMed using keyword search strategy for relevant headings, sub-headings and cross-referencing. These keywords included Artificial intelligence; Skull base surgery; Machine learning; Deep learning; Neural Networks, Computer; Radiomics; Navigation; Robotics in various combinations. The results have been compiled and discussed under the following sub-headings.
Results
Role of AI in Diagnosis
The vagueness of clinical presentations, especially early symptoms, renders identification of skull base pathologies a complex challenge. The integration of AI in workflows leverages vast clinical and radiological databases to provide likely diagnoses for skull base lesions, offering clinicians invaluable support in timely detection and tailored management. The potency of AI unfolds as diagnostic algorithms, informed by patient symptoms and clinical/radiological findings, which direct them towards appropriate investigations and referrals. This systematic approach facilitates early diagnosis and subsequent intervention.
For example, MRI is indicated in the evaluation of asymmetrical hearing loss. However only 4.7% have internal auditory meatus or cerebellopontine angle pathology. Asymmetry of 15 dB at 3 kHz is associated with higher probability of abnormal finding on MRI [1]. AI may incorporate these data points i.e., the degree of asymmetry and specific frequencies affected on audiogram to identify cases where MRI is indicated. This refined algorithm enhances the detection of abnormalities on MRI scans.
Patterns of visual field defects may differentiate amongst lesions causing chiasmal compression, optic neuropathy, stroke and idiopathic intracranial hypertension [2]. By integrating such nuanced insights into diagnostic algorithms, AI empowers clinicians to discern underlying pathology in a case presenting with visual field defects, thereby facilitating informed decision-making and timely intervention.
This AI-driven diagnostic approach holds particular promise in resource-limited settings, where the burden on healthcare systems can lead to oversight of uncommon etiologies and rare clinical presentations. By navigating through diagnostic algorithms, AI effectively screens for and identifies obscure conditions, addressing the challenge of timely and accurate diagnosis even within resource-constrained environments.
Enhanced Image Analysis and Radiomics
Radiological imaging stands as a cornerstone for diagnosing skull base pathologies, and AI’s capacity to swiftly process extensive imaging data presents a transformative advantage. AI algorithms excel in accurately identifying and segmenting intricate skull base structures, enabling precise lesion localization and characterization. This rapid pattern recognition is pivotal for distinguishing between various lesions , aiding in narrowing differentials and dictating management approaches. Traditionally, manual measurements by radiologists entail time and variability issues; AI-driven automated quantification of lesion attributes i.e.,size, shape, density, furnish quantitative data vital for monitoring disease progression and treatment planning.
Radiomics, a fast-evolving field, extracts quantitative features from radiological images, employing AI and machine learning to unveil hidden patterns that shape clinical decisions. In skull base surgery, radiomics proves promising for preoperative planning, treatment optimization, and better patient outcomes. Radiomics non-invasively scrutinizes molecular and spatial heterogeneity, heightening diagnostic accuracy and treatment planning. Extracted features from modalities like MRI and CT yield insights into tumor behaviour and vascularity. Analysed through AI, these features create predictive models that guide personalized risk assessment and treatment selection. Moreover, radiomics transcends diagnosis to treatment response prediction and resistance identification. Surgeons leverage this data to tailor approaches, optimize surgical strategies, and minimize complications, fostering safer interventions and improved outcomes [3–6].
Surgical Planning and Intraoperative Assistance
AI algorithms, particularly based on deep learning and convolutional neural networks, have demonstrated exceptional capabilities in accurate structure identification and delineation even in the presence of radiological ‘noise’ and variations in image quality. This in turn accurately identifies and segments critical structures in skull base images, facilitating more precise surgical planning and reducing the risk of complications during the procedure [7].
AI-generated 3D reconstructions of skull base anatomy and augmented reality systems offer enhanced real-time visualisation during complex surgical interventions. This assists in navigation around sensitive areas, identifying obscured structures, ensuring precise and accurate surgical manoeuvres, thereby reducing the risk of unintended damage and complications.
The integration of artificial intelligence (AI) into navigation systems has revolutionized the way surgeons approach skull base surgeries. Conventional navigation relies on static preoperative images, which may not accurately represent intraoperative changes, such as tissue deformation, removal or brain shift. This can lead to discrepancies between the planned and actual surgical path. Surgeons often need to manually update the conventional navigation system when there are changes in patient positioning or anatomy. This can be time-consuming and may introduce errors. Conventional navigation primarily provides spatial guidance, lacking real-time contextual information about critical structures and their relationships.
AI-based navigation integrates advanced machine-learning, deep-learning algorithms and real-time data processing [8]. AI algorithms analyse intraoperative images and sensor data to provide dynamic guidance throughout surgery. AI based navigation provides advantages of real-time adaptation. AI algorithms can continuously analyse intraoperative images, providing real-time updates and adapting to changes in the surgical field. This dynamic adaptation enhances precision and reduces the risk of errors. AI algorithms can alert surgeons to potential complications, such as excessive tissue manipulation or instrument proximity to sensitive areas, enabling timely corrective actions [9].
Robotics provide surgeons with advanced tools for improved dexterity and stability, with precise controlled movements during complex surgical procedures. This has a substantial impact on improving surgical accuracy, enhanced safety and outcomes in skull base surgery. AI-driven robotics go beyond conventional robotics by incorporating machine learning and deep-learning algorithms to improve decision-making, real-time guidance, and adaptability [9]. An example is development of a novel robotic laser guidance system for skull base surgery, combining optic-magnetic tracking which offers real-time augmented reality guidance during microscopic procedures at the lateral skull base, minimizing surgeon workload and enhanced intraoperative visualisation with better depth perception [10].
Computer vision, a crucial component of AI, empowers quantitative analysis of visual data in skull base surgery. This technology facilitates tasks like image classification, object tracking, and feature extraction from intraoperative videos. This holds immense potential for enhancing surgical precision, training, and decision-making [11].
Predictive Analytics
AI tools may be used to train machine learning and deep learning models with applications in various aspects of predictive analysis in skull base surgery.
Classification tasks aimed at identifying and characterizing lesions hold significant promise within clinical workflows. The application of classification, particularly within the realm of prediction and prognosis, also facilitates the stratification of risks. Radiomics delves into the exploration of potentially substantial quantitative data that goes beyond the scope of conventional clinical assessments. Artificial Intelligence (AI) methodologies have the capacity to conduct high-throughput quantification of image phenotypes, extracting a multitude of features based on images. These methodologies can further pinpoint crucial discriminatory attributes which, either individually or in combination, constitute efficacious radiomic markers for purposes of detection, classification, and prediction or prognosis. The successful integration of AI techniques into habitual clinical workflows necessitates a cooperative endeavour between AI researchers and medical practitioners, alongside the implementation of standardized evaluation frameworks. AI techniques have found extensive utility in extracting features to facilitate the classification of suspicious lesions and tumor subtypes, as well as undertaking prediction and prognostication tasks that entail categorizing patients into various risk cohorts [12].
Surgery is the first-line therapy for most benign and malignant skull base tumors. Extent of resection is a metric commonly used for preoperative surgical planning and to predict postoperative outcomes and risk of recurrence. AI may analyse evidence on extent of resection in skull base surgery, including preoperative extent of resection scoring systems, intraoperative extent of resection scoring systems, extent of resection and tumor recurrence, and extent of resection and functional outcomes, essential in optimising care for each patient [13].
Discovering and inferring novel predictive variables can be done using modern machine learning and deep learning techniques and can subsequently be used to predict future outcomes using predictive analytics. For example, machine-learning model has been developed that can classify patients with pituitary adenomas into low and high-risk categories for predicting postoperative complications. Deep neural networks have been used to predict gross total resection after transsphenoidal surgery [13]. Machine learning (ML) algorithm has been developed using radiomic feature analysis to predict Ki-67 in WHO grade I meningiomas preoperatively. Elevated Ki-67 is one crucial factor that has been shown to influence tumor behaviour and clinical outcomes. The ability to preoperatively discern Ki-67 would confer the ability to guide surgical strategy and prognosis [14].
Isocitrate dehydrogenase (IDH) and 1p19q codeletion status are important in providing prognostic information as well as prediction of treatment response in gliomas. Machine learning model trained using preoperative MRI of 538 glioma cases revealed multimodal MRI patterns predictive of isocitrate dehydrogenase and 1p/19q status in diffuse low- and high-grade gliomas. Accurate determination of the IDH mutation status and 1p19q co-deletion prior to surgery may complement invasive tissue sampling and guide treatment decisions [15]. Longitudinal measurement of glioma burden with MRI is the basis for treatment response assessment. Deep learning algorithm to automatically segment glioma-related MRI features and quantify tumor volumes according to Response Assessment in Neuro-Oncology (RANO) criteria has shown strong agreement with manual measurements and repeatability for both preoperative and postoperative glioma assessments, suggesting its potential value in evaluating tumor burden [16].
Patient frailty has been linked to increased surgical morbidity and mortality. Machine learning algorithm has been used for risk stratification and outcomes assessment for 32,465 vestibular schwannoma (VS) resection cases. A customised VS-5 score, incorporating age, hydrocephalus, preoperative cranial nerve palsies, diabetes mellitus, and hypertension, emerged as a superior predictor of mortality, discharge rates, complications, length of stay, and costs compared to existing measures [17]. ML models have been developed to predict prolonged hospital stay, non-routine discharge disposition, and high hospital charges amongst skull base meningioma patients [18].
Common algorithms like Neural Networks and Support Vector Machines have demonstrated higher accuracy and specificity than Linear Regression in predictive modelling [19]. An example of this is a study aimed to predict vestibular schwannoma (VS) recurrence by comparing logistic regression and artificial neural network (ANN) models from 789 VS patients. The ANN model outperformed logistic regression, demonstrating higher sensitivity and specificity in predicting VS recurrence [20].
Clinical Decision Making
AI plays a significant role in clinical decision-making, particularly in risk stratification, patient outcome optimization, and early warning systems. AI models aid in identifying high-risk patients for surgery, optimizing resource allocation, and enabling shared decision-making. Machine learning and deep learning algorithms are integrated into surgical management and perioperative care, surpassing traditional methods in risk prediction accuracy. AI’s ability to process large and diverse datasets enhances perioperative intelligence, including intraoperative data integration. Moreover, AI optimizes patient outcomes through data-driven personalized treatments, aided by techniques like deep reinforcement learning. AI-based early warning systems predict acute decompensation, facilitating timely interventions, particularly in perioperative care [21]. An example is the use of simulated Raman histology combined with AI models for swift and precise intraoperative analysis of skull base tumor specimens, contributing to informed surgical decisions [22]. Deep learning neural network model has been used to predict haemostasis control ability analysing the first minute of surgical video [23].
AI in Postoperative Care and Rehabilitation
Postoperative surveillance and monitoring play a crucial role in the management of skull base surgery patients. For example, AI-based facial asymmetry measurement system has been employed to assess facial nerve grafting outcomes in cases of facial nerve grafting following head and neck and skull base surgery [24]. Radiomics can aid in detecting early signs of recurrence or complications through quantitative analysis of postoperative imaging. By tracking changes in radiomic features over time, AI algorithms can alert clinicians to subtle alterations that may not be discernible through traditional visual inspection alone. This enables timely intervention and facilitates personalized treatment adjustments, optimizing patient outcomes.
AI algorithms have been employed to create personalized rehabilitation protocols ingeniously tailored to individual traits and recovery trajectory. AI-powered remote monitoring systems have been utilized to track patients’ recovery progress and provide real-time feedback. From AI-augmented speech therapy to enhanced physical therapy and even virtual reality based vestibular rehabilitation exercises, the spectrum of AI-powered interventions is wide-ranging and promising.
Virtual Simulations and Training in Skull Base Surgery
One of the remarkable applications of AI is the development of AI-powered virtual simulations, which offer surgeons a risk-free environment to practice and refine their skills for intricate skull base surgeries.
Traditional surgical training involves a steep learning curve, where novice surgeons learn through direct patient encounters and real surgeries. AI-powered virtual simulations significantly expedite this learning process. AI-powered virtual simulations recreate highly realistic surgical scenarios that mimic the complexities of skull base surgeries. These simulations are based on extensive anatomical data and surgical case studies, ensuring accuracy and authenticity. Surgeons can engage in virtual procedures that involve tumor resection, vascular navigation, and other intricate tasks specific to skull base surgery. Surgeons can repeatedly perform procedures in the virtual environment, gaining insights, honing skills without the inherent risks of live surgery.
AI-driven virtual simulations allow surgeons to experiment with different approaches, techniques, and instruments in a controlled setting. Surgeons can receive immediate feedback on their performance, highlighting areas for improvement. This iterative process fosters skill enhancement and ensures that surgeons are better prepared for complex and high-stakes skull base surgeries.
Role of Surgeons in Training AI Algorithms
Surgeons stand as architects of AI tools, their wealth of experience shaping the foundation of AI learning trajectory. Beyond being end-users, surgeons actively contribute to the precision and reliability of AI-algorithms by curating rich, diverse datasets representative of surgical complexities. As primary contributors to AI training data, they wield significant influence over the accuracy and efficacy of AI outcomes, ensuring alignment with the highest standards. Responsibilities encompass ongoing collaboration, data sharing, ensuring quality data and upholding stringent ethical considerations.
Surgeons contribute unique insights and expertise to machine learning (ML) and natural language processing (NLP), for the development, validation, and refinement of tailored algorithms. They play a crucial role in the understanding and extraction of pertinent information from unstructured data and electronic medical records (EMR). This facilitates precise data analysis, and refinement of algorithms for clinical decision-making. In essence, AI becomes a reflection of the collective experience of the surgical community.
Additionally, surgeons contribute to the shift to digital health records, emphasizing the importance of electronic medical record-keeping. EMRs, maintained by surgeons, are crucial repositories for patient information, contributing to the creation of robust datasets for ML and NLP applications.
Surgeons, acting as curators of quality training data, stand at the centre of this collaborative effort, ensuring the responsible development and real-world applicability of AI tools.
Data Quality Considerations
In the rapidly evolving field of AI, the maxim “garbage in, garbage out” rings true. The effectiveness of artificial intelligence in aiding surgeons is heavily reliant on the quality of training data. Much like humans, AI systems “learn” from the information provided to them. The algorithms are only as good as the data they are fed to train.
Precision, accuracy, reliability, relevance and diversity are non-negotiables for quality data and surgeons are the custodians of data employed for training AI. Ensuring the precision and relevance of data directly influences the robustness and fairness of AI-driven systems. The integrity of AI outcomes hinges on the reliability of input data. Diversity in datasets is a strategic imperative, fostering adaptability and generalization of AI models to real-world situations. Moreover, the mitigation of biases is inherently linked to the inclusion of diverse data, promoting equitable outcomes across various patient demographics and surgical scenarios. Real-world applicability demands that data inputs accurately and comprehensively represent the complexities inherent in a broad spectrum of surgical procedures. Ethical dimensions come to the fore, emphasizing the importance of transparency in data sourcing. Rich datasets not only fuel innovation but also build user trust, crucial in the adoption of AI technologies. In summary, the collaborative effort to share high-quality and diverse data stands as the cornerstone of responsible and effective AI development in the realm of skull base surgery.
Ethical Concerns
The ethical concerns tied to AI in healthcare encompass several dimensions. One central issue is maintaining respect for autonomy, ensuring patients make decisions unaffected by external forces. This poses a challenge in AI, particularly with complex “deep learning” algorithms that generate decisions with opaque processes, raising questions about disclosure, risks, and benefits. Patient privacy is jeopardized as AI can infer personal health data, requiring explicit consent processes. Surgeons’ autonomy might be threatened as AI relies on objective evidence, potentially influencing their decisions. Conflicts arise between autonomy and beneficence, as AI’s risk-benefit analyses may not consider individual values. An algorithmic recommendation might benefit one but harm another. Patient refusal of treatment by AI tools, due to distance from human care, underscores the need for empathy and shared decision-making. Ensuring AI safety entails evaluating development, validity, and standards to prevent compromised patient outcomes due to low-quality data or automation bias. Justice concerns arise, with AI potentially favouring privileged patient data and exacerbating socioeconomic disparities. Regulatory efforts for equitable AI distribution face challenges within existing healthcare infrastructures. Addressing these ethical aspects is essential for responsible AI integration in healthcare [25]. It is essential to ensure that patients are adequately informed about AI’s role in their treatment and that they retain autonomy in their decision-making. Informed consent should encompass AI use, data privacy, and the potential implications of AI-generated information on their treatment journey.
Conclusion
In the ever-evolving realm of skull base surgery, AI transcends traditional boundaries, empowering surgeons with novel tools to enhance patient care. This narrative review highlights the multifaceted role of AI across various stages of skull base surgery, and its transformative impact on diagnosis, treatment planning, surgical navigation, postoperative care and training. The AI-driven landscape in skull base surgery is not without challenges. Ethical considerations, data quality assurance, and clinician collaboration are vital factors for success. Although AI tools accelerate data processing and augment surgical decision-making, they should be used cautiously, considering data quality and case-specific complexities. AI serves as a valuable complement to clinical expertise, enhancing decision-making and efficiency, rather than aiming to replace the crucial role of healthcare professionals in patient care.
Funding
None.
Data Availability
All articles cited are available online.
Declarations
Conflict of Interest
None.
Footnotes
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
References
- 1.Ahsan SF, Standring R, Osborn DA, Peterson E, Seidman M, Jain R. Clinical predictors of abnormal magnetic resonance imaging findings in patients with asymmetric sensorineural hearing loss. JAMA Otolaryngol - Head Neck Surg. 2015;141(5):451–456. doi: 10.1001/jamaoto.2015.142. [DOI] [PubMed] [Google Scholar]
- 2.Hepworth LR, Rowe FJ. Programme choice for perimetry in neurological conditions (PoPiN): a systematic review of perimetry options and patterns of visual field loss. BMC Ophthalmol. 2018;18(1):241. doi: 10.1186/s12886-018-0912-1. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3.Bogowicz M, Riesterer O, Stark LS, Studer G, Unkelbach J, Guckenberger M, et al. Comparison of PET and CT radiomics for prediction of local Tumor control in head and neck squamous cell carcinoma. Acta Oncol (Madr) [Internet] 2017;56(11):1531–1536. doi: 10.1080/0284186X.2017.1346382. [DOI] [PubMed] [Google Scholar]
- 4.Aerts HJWL, Velazquez ER, Leijenaar RTH, Parmar C, Grossmann P, Cavalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014;5:4006. doi: 10.1038/ncomms5006. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 5.Kickingereder P, Burth S, Wick A, et al. Radiomic Profiling of Glioblastoma: identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models. Radiology. 2016;280(3):880–889. doi: 10.1148/radiol.2016160845. [DOI] [PubMed] [Google Scholar]
- 6.Zhu M, Li S, Kuang Y, et al. Artificial intelligence in the radiomic analysis of glioblastomas: a review, taxonomy, and perspective. Front Oncol. 2022;12:924245. doi: 10.3389/fonc.2022.924245. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 7.Huang J, Habib AR, Mendis D, et al. An artificial intelligence algorithm that differentiates anterior ethmoidal artery location on sinus computed tomography scans. J Laryngol Otol. 2020;134(1):52–55. doi: 10.1017/S0022215119002536. [DOI] [PubMed] [Google Scholar]
- 8.Neves CA, Tran ED, Blevins NH, Hwang PH. Deep learning automated segmentation of middle skull-base structures for enhanced navigation. Int Forum Allergy Rhinol. 2021;11(12):1694–1697. doi: 10.1002/alr.22856. [DOI] [PubMed] [Google Scholar]
- 9.Sekhar LN, Juric-Sekhar G, Qazi Z, et al. The future of Skull Base Surgery: a View through Tinted glasses. World Neurosurg. 2020;142:29–42. doi: 10.1016/j.wneu.2020.06.172. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 10.Bardosi Z, Plattner C, Ozbek Y, et al. CIGuide: in situ augmented reality laser guidance. Int J Comput Assist Radiol Surg. 2020;15(1):49–57. doi: 10.1007/s11548-019-02066-1. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 11.Pangal DJ, Kugener G, Shahrestani S, Attenello F, Zada G, Donoho DA. A guide to annotation of Neurosurgical Intraoperative Video for Machine Learning Analysis and Computer Vision. World Neurosurg. 2021;150:26–30. doi: 10.1016/j.wneu.2021.03.022. [DOI] [PubMed] [Google Scholar]
- 12.Yousefirizi F, Pierre Decazes, Amyar A, Ruan S, Saboury B, Rahmim A. AI-Based detection, classification and Prediction/Prognosis in medical imaging:towards Radiophenomics. PET Clin. 2022;17(1):183–212. doi: 10.1016/j.cpet.2021.09.010. [DOI] [PubMed] [Google Scholar]
- 13.Hollon T, Fredrickson V, Couldwell WT. Extent of Resection Research in Skull Base Neurosurgery: previous studies and future directions. World Neurosurg. 2022;161:396–404. doi: 10.1016/j.wneu.2021.10.184. [DOI] [PubMed] [Google Scholar]
- 14.Khanna O, Fathi Kazerooni A, Farrell CJ, et al. Machine learning using Multiparametric Magnetic Resonance Imaging Radiomic Feature Analysis to Predict Ki-67 in World Health Organization Grade I meningiomas. Neurosurgery. 2021;89(5):928–936. doi: 10.1093/neuros/nyab307. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 15.Zhou H, Chang K, Bai HX, et al. Machine learning reveals multimodal MRI patterns predictive of isocitrate dehydrogenase and 1p/19q status in diffuse low- and high-grade gliomas. J Neurooncol. 2019;142(2):299–307. doi: 10.1007/s11060-019-03096-0. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 16.Chang K, Beers AL, Bai HX, et al. Automatic assessment of glioma burden: a deep learning algorithm for fully automated volumetric and bidimensional measurement. Neuro Oncol. 2019;21(11):1412–1422. doi: 10.1093/neuonc/noz106. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 17.Tang OY, Bajaj AI, Zhao K, et al. Association of Patient Frailty with Vestibular Schwannoma Resection Outcomes and Machine Learning Development of a vestibular Schwannoma risk stratification score. Neurosurgery. 2022;91(2):312–321. doi: 10.1227/neu.0000000000001998. [DOI] [PubMed] [Google Scholar]
- 18.Jimenez AE, Porras JL, Azad TD, et al. Machine Learning models for Predicting Postoperative outcomes following Skull Base Meningioma Surgery. J Neurol Surg B Skull Base. 2022;83(6):635–645. doi: 10.1055/a-1885-1447. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 19.Buchlak QD, Esmaili N, Leveque JC, et al. Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review. Neurosurg Rev. 2020;43(5):1235–1253. doi: 10.1007/s10143-019-01163-8. [DOI] [PubMed] [Google Scholar]
- 20.AAbouzari M, Goshtasbi K, Sarna B, et al. Prediction of vestibular schwannoma recurrence using artificial neural network. Laryngoscope Investig Otolaryngol. 2020;5(2):278–285. doi: 10.1002/lio2.362. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 21.Giordano C, Brennan M, Mohamed B, Rashidi P, Modave F, Tighe P. Accessing Artificial Intelligence for clinical decision-making. Front Digit Health. 2021;3:645232. doi: 10.3389/fdgth.2021.645232. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 22.Jiang C, Bhattacharya A, Linzey JR, et al. Rapid Automated Analysis of Skull Base Tumor Specimens Using Intraoperative Optical Imaging and Artificial Intelligence. Neurosurgery. 2022;90(6):758–767. doi: 10.1227/neu.0000000000001929. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 23.Pangal DJ, Kugener G, Zhu Y, et al. Expert surgeons and deep learning models can predict the outcome of surgical Hemorrhage from 1 min of video. Sci Rep. 2022;12(1):8137. doi: 10.1038/s41598-022-11549-2. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 24.Hidaka T, Tanaka K, Mori H. Outcome evaluation using an artificial intelligence-based facial measurement software for facial nerve grafting in head and neck and skull base Surgery. Head Neck. 2023;45(6):1572–1580. doi: 10.1002/hed.27374. [DOI] [PubMed] [Google Scholar]
- 25.Arambula AM, Bur AM. Ethical considerations in the Advent of Artificial Intelligence in Otolaryngology. Otolaryngol Head Neck Surg. 2020;162(1):38–39. doi: 10.1177/0194599819889686. [DOI] [PubMed] [Google Scholar]
Associated Data
This section collects any data citations, data availability statements, or supplementary materials included in this article.
Data Availability Statement
All articles cited are available online.