Has artificial intelligence in spine surgery lived up to the hype? A narrative review of recent approaches, current challenges, and the path forward
0 Abstract
Healthcare applications of artificial intelligence (AI) and machine learning (ML) are currently in a stage of exponential growth; however, their adoption into clinical practice across clinical specialties remains uneven. In spine surgery, the presence of challenging clinical problems, advanced intraoperative technologies, and large multi-center datasets positions the field well for the integration of these technologies into the clinic and operating room (OR). Here, we review recent advances in AI/ML applications in several key domains of spine surgery, identify methodological challenges shared by many approaches, and suggest solutions that may lead to these approaches becoming validated, commercialized tools that can reach clinical practice. Ultimately, we aim for this narrative review to help catalyze further progress in the development and commercialization of AI/ML to benefit future spine patients.
Keywords
INTRODUCTION
The past decades have seen spine surgery at the forefront of healthcare innovation, with countless advancements in surgical techniques, robotics, and medical devices positively impacting patient care[1-3]. In parallel, recent advances in artificial intelligence (AI) and machine learning (ML) have already touched nearly every facet of modern life, from industry and transportation to the arts and music. AI and ML rely on large datasets to recognize patterns in data and, when properly deployed, can perform specialized tasks more quickly and accurately than humans. Due to these promises, spine surgeons are looking to AI/ML to usher in the next generation of technical advancements for their patients.
We are currently at an inflection point for the impact of AI/ML in spine surgery. The number of studies on healthcare AI applications continues to grow exponentially[4], a trend that is reflected in spine surgery as well[5]. Furthermore, national funding agencies have established priorities in healthcare AI[6], and the Food and Drug Administration has gained experience in regulating these tools[7]. Simultaneously, private venture funding has grown substantially in healthcare AI[8], but rates of progress have not been equal across applications[4]. In particular, AI diagnostic tools in radiology and pathology have grown faster than other areas of medicine[4], such as the surgical specialties. A better understanding of the landscape of AI/ML in spine surgery could help bridge the gap between research and commercialization of such tools.
Currently, disorders of the spine are among the major contributors to both healthcare costs and disability both in the United States and worldwide[9,10]. Spine surgery is a major contributor to healthcare spending[11,12], and while safety has improved significantly year over year[13], when complications do occur, they cause a substantial impact on patient quality of life and healthcare spending[14]. Due to the wide range of variables that influence patient selection, preoperative planning, intraoperative technique and decision making, opportunities for the potential impact of AI and the possible challenges are high. AI-based tools that could reliably make advances in efficiency, technical proficiency, or complication minimization would have immense clinical and economic impact.
This article provides a targeted primer on AI/ML algorithms and critically reviews select applications of AI/ML to spine surgery. We highlight those that aim to assist in pre-surgical planning, intraoperative assistance, and prediction of postoperative course. These tools span a spectrum of development and commercial deployment, employ a variety of data sources, and interface with clinicians and patients in a number of ways. Through this narrative review, we identify a set of shared challenges facing the field, namely the substantial heterogeneity in patients with spinal disorders, the uncertainty and subjectivity in outcome measures, and the quality and quantity of data available for algorithm development. Finally, we propose solutions to these challenges, which we hope can forecast a path toward incorporating robust AI/ML tools in spine clinics and operating rooms (ORs), thereby achieving the best outcomes for future patients.
AN AI/ML PRIMER FOR SPINE SURGEONS
AI is a group of computational approaches that aim to provide human-level expertise and decision making and predominantly rely on ML, a class of powerful statistical models that recapitulate in silico different facets of human sensory processing and cognition, ranging from vision and language to estimation and prediction tasks[15,16]. While the technical aspects of AI and ML are beyond the scope of this review, we discuss several key concepts that all spine surgeons should familiarize themselves with, as these technologies continue to play an increasing role in our field.
Traditional ML algorithms adapt structured formulas to relate input and output variables and generate future predictions. Common types of these algorithms include logistic regression, decision trees and random forest, and support vector machines[15]. They differ based on the types of input and output variables they can handle, as well as their ability to process noisy and non-linear data, which are prevalent in healthcare applications. The other major class of models is known as ‘deep learning’, which accounts for the many recent groundbreaking applications of AI. These models leverage artificial neural networks, which can learn complex relationships between their complex input data and generate a wide variety of potential outputs, including text, images, and audio[16]. Compared to traditional ML, deep learning is more powerful but requires massively more data and is specialized for data-intensive tasks such as vision and language processing. On the other hand, traditional ML has straightforward ways for users to understand what variables are most important in making predictions, which is particularly true for the more simple methods[15]. Efforts to understand how deep learning makes predictions and how it weighs input data present an evolving challenge[16].
Another key division among AI/ML algorithms is between supervised and unsupervised approaches. Supervised models require training between inputs and desired outputs using labeled data. The process of annotating and curating such datasets can be cumbersome and is particularly challenging in surgical specialties where patient numbers are low and factors such as patient privacy are essential. Unsupervised models such as k-means clustering instead can find patterns inherent in unstructured data; however, they cannot directly make predictions in the same way that supervised algorithms can[15]. While AI algorithms are advancing at a staggering pace, developing a general framework that outlines both the capabilities and limitations of these models will be critical for spine surgeons in the coming decades.
RECENT AI/ML APPLICATIONS IN SPINE SURGERY
Preoperative planning
Spine surgeons face various clinical and radiographic factors in preoperative planning, which they must parse to make often difficult and subjective decisions about patient selection and surgical approach. AI could augment the ability of clinicians to understand patient disease states, weigh factors such as symptoms and disability, and assess anatomic and pathologic parameters from multimodal imaging.
A number of recent studies have used ML to assist in understanding clinical variability and phenotype in patients undergoing spine surgery. Unsupervised clustering of the clinical metadata of patients with degenerative spondylolisthesis revealed distinct phenotypes of disease severity, which had different levels of postoperative improvement, pain, and satisfaction despite sharing the preoperative severity on imaging[17]. Clustering has also been shown to disentangle the interactions between patient characteristics and surgical procedures in adult spinal deformity. By inputting a variety of variables including clinical, disability, and spinopelvic parameters, the initial clustering algorithm grouped patients based on age and prior surgery, followed by a second clustering step based on the type of surgery performed, yielding distinct groups that vary in terms of the risk/benefit of surgery[18]. In spinal deformity, preoperatively oriented algorithms can also forecast fine-grained aspects of postoperative responses to a standardized scoliosis questionnaire[19]. Together, these studies reveal how AI can uncover patterns in clinical data that could guide preoperative patient counseling or patient selection and maximize quality and value.
Patient imaging is central to preoperative planning in spine surgery and its analysis is one of the most promising applications of AI [Figure 1]. Radiographic analysis includes image segmentation, which refers to the accurate identification and delineation of anatomical structures. Previous work has leveraged deep learning to segment spinal cord structures in a fully automated manner[20,21], performing better than previous state-of-the-art techniques that did not leverage ML[22]. Further studies incorporating data from patients with SCI improved on these initial advances. They can capture and identify lesions that correlate with motor scores at admission[23] and predict thoracolumbar injury classification scores from CT alone, which typically require MR imaging to assess ligamentous integrity[24]. Other algorithms can accurately segment other relevant anatomic structures, including vertebral bodies and discs[25,26], as well as paraspinal musculature[27]. The extent of osteoporosis[28] and associated fractures[29] can also be diagnosed by AI.
Figure 1. (A) Example of preoperative planning software. Yellow boxes highlight automated spinopelvic parameters and Cobb angle measurements performed by the software. Purple boxes indicate AI-recommended surgical plans and predicted postoperative spinopelvic parameters. The green box demonstrates the predicted postoperative sagittal standing X-ray with the recommended surgical plan; (B) Postoperative standing sagittal and coronal long-cassette radiographs. AI: Artificial intelligence.
Building upon algorithms that segment spinal imaging, others can interpret degrees of neural element compression and estimate parameters of spinal deformity. In particular, these applications are promising as they are tedious, time-consuming, and subject to error and variability when performed by humans. For example, deep learning can estimate the degree of cervical central and foraminal stenosis[30] and can detect lumbar spondylolisthesis[31] and other important aspects of degeneration, such as the degree of disc degeneration and central canal stenosis with high accuracy[32]. For deformity parameter calculation, AI has been applied to calculate coronal[33,34], sagittal[35,36], and combined coronal-sagittal parameters[37]. By incorporating AI into deformity parameter calculation, clinicians can more accurately and efficiently perform both large deformity surgeries and use deformity principles in more limited surgery to ensure patients achieve the best anatomic and physiologic outcomes. These applications represent an ideal area for the strengths of AI to address current challenges in preoperative spine surgical evaluation, and indeed, these technologies have been among the first to reach clinical practice [Table 1].
Summary of studies discussed in the preoperative planning subsection, highlighting key advancements in ML applications for preoperative radiographic and clinical tools
| Area of investigation | Selected studies |
| Utilizing ML clustering methods to identify distinct phenotypes of spinal pathologies, presentation patterns, and radiographic parameters | Chan et al., 2021[17]; Ames et al., 2019[18] |
| Preoperative counseling based on patient specific factors | Ames et al., 2019[19] |
| Automated segmentation of anatomical structures from patient radiographs and films | Spinal cord: Gros et al., 2019[20]; Jamaludin et al., 2017[21] Vertebral body and discs: Pang et al., 2022[25]; Pang et al., 2021[26] Paraspinal musculature: Wesselink et al., 2022[27] |
| Building upon segmentation algorithms to identify clinical correlates (e.g., neurologic exam, osteoporosis, disc degeneration, spinal stenosis) | Neurologic motor scores: McCoy et al., 2019[23] Thoracolumbar injury classification: Doerr et al., 2022[24] Osteoporosis and fractures: Zhang et al., 2020[28]; Yabu et al., 2021[29] Spinal and foraminal stenosis: Jardon et al., 2023[30]; Grob et al., 2020[32] Lumbar spondylolisthesis: Trinh et al., 2022[31] |
| Automated spinopelvic parameter calculation | Berlin et al., 2023[33]; Wu et al., 2018[34]; Weng et al., 2019[35]; Korez et al., 2020[36]; Galbusera et al., 2019[37] |
Intraoperative tools
During surgery, a number of promising AI technologies may help clinicians optimize operative technique and efficiency. Compared to tools designed for pre- or postoperative settings, bringing AI into the OR requires algorithms that can deploy in real time and run on equipment that can interface with the patient, surgeon, and available intraoperative data streams.
Perhaps the main application of AI in the OR is to guide the next generation of surgical navigation, which currently relies on intraoperative radiography and the registration between pre- and intraoperative images. Today’s approaches are limited by radiation exposure to the surgical team and patient, delays in operative time caused by acquiring such images, differences in patient anatomy between images acquired in prone and supine positions, and device failure causing navigational inaccuracy.
One promising technology dubbed the ParadigmTM system (Proprio, Seattle, WA) aims to lessen the need for intraoperative CT by using an optical imaging device and computer vision algorithms to align the intraoperative patient with their preoperative imaging, potentially unlocking radiation-free navigation and calculation of spinal anatomic parameters, which could improve safety and speed[38]. Another competing technology, Flash 7DTM (SeaSpine, Carlsbad, CA), also aims to leverage optical imaging-based navigation powered by deep learning and computer vision. These technologies are being applied to instrumentation in lumbar degenerative disease[39], pediatric deformity[40,41], and trauma[42,43], with potential safety benefits and reduced need for fluoroscopy.
Augmented or mixed reality, in which the surgeon wears goggles that permit them to view the operative field with graphic overlays, also leverages devices with the capability of AI-assisted computer vision [Figure 2]. These approaches are under development in spine surgery[44] and also promise to help visualize underlying anatomy[45] to guide pedicle screw placement[46] and to help perform osteotomies. Early research suggests augmented reality (AR)-assisted pedicle screw placement may compare favorably to freehand techniques[47] in spinal deformity cases and is also being studied for screw placement in workhorse approaches such as transforaminal lumbar interbody fusion[48]. Our desire to minimize invasiveness while maximizing visualization of critical structures and accuracy of instrumentation necessitates intraoperative AI to continue making progress [Table 2].
Figure 2. Percutaneous lumbar pedicle screw placement assisted by AR headset (yellow arrow). The green box highlights the AR overlay, which displays the screw trajectory, allowing the surgeon to maintain focus on the operative field without needing to look at monitors. AR: Augmented reality.
Summary of studies discussed in the intraoperative tools subsection
| Area of investigation | Selected studies |
| ML and computer vision tools for optical image-based intraoperative navigation (reduce radiation exposure) | General technique: Berven et al., 2023[38] Lumbar degenerative disease: Abdelrahman et al., 2022[39] Pediatric deformity: Comstock et al., 2023[40]; Lim et al., 2023[41] Trauma: Yeretsian et al., 2022[42]; Malacon et al., 2022[43] |
| Intraoperative AR, VR, and mixed reality tools | Eliahu et al., 2022[44]; Auloge et al., 2020[45]; Burström et al., 2019[46]; Elmi-Terander et al., 2020[47]; Charles et al., 2021[48] |
Postoperative prognostication
One of the most common and accessible applications of AI/ML in spine surgery is predicting postoperative outcomes. National datasets from the NIH, American College of Surgeons, and NeuroPoint Alliance, which capture clinical and demographic data, metrics of surgical success, patient-reported outcomes, and complications, can allow clinicians to build models forecasting both perioperative and long-term outcomes at the patient level. These methods may help identify risk factors that lead to poor outcomes, allowing surgeons to better select patients and tailor appropriate surgical interventions and postoperative care.
A broad spectrum of ML studies have aimed to predict perioperative patient outcomes and complications and identify variables that most strongly drive these events. ML tends to identify common factors that correlate with perioperative outcome, such as age, functional and nutritional status, BMI, Medicaid status, intraoperative blood loss, smoking, and preoperative medical comorbidities, but the exact predictors vary by study[49-53]. Some models tend to predict relatively common events such as postoperative delirium, hospital readmissions, and length of stay, whereas others aim to predict rarer and potentially more catastrophic events such as vascular injury during anterior lumbar surgery[51]. Across tools that aim to quantify adverse events, the approaches that are trained on large databases, receive external validation and testing, and release their tools as open source or commercialized software are most likely to gain the most traction.
In addition to perioperative complications, ML is also well-suited to predict long-term outcomes. In cervical spondylotic myelopathy, previous studies have accurately predicted outcomes years after surgery from preoperative variables, with simple methods such as logistic regression performing well compared to more advanced methods[54,55]. By examining feature importance methods in ML algorithms, drivers of long-term outcomes can be better understood. For example, in patients who underwent lumbar fusion, higher leg pain and back pain preoperatively were predictive of improvements in leg and back pain, respectively[56]. In a separate study of both cervical and thoracolumbar fusion, preoperative axial pain and peripheral pain, nationality, the number of previous spine surgeries, age, type of intervention, preoperative quality-of-life, BMI, number of affected levels, and comorbidity were major predictors of outcome[57]. Similarly, using preoperative MRIs, one study used neural network-based models to predict postoperative proximal junctional kyphosis (PJK). Analysis of the model found that soft tissue features were the strongest drivers of the accuracy of PJK prediction[58]. A natural question is to ask: “How valuable are these models?” Indeed, they primarily identify obvious risk factors as drivers of short-term complications (age, sex, comorbidities), and those of long-term outcomes (how much patients stand to gain from their preoperative level of disability). We argue that the key to these models is to be able to quote and counsel patients about risks and outcomes in a patient-specific manner to improve informed consent and shared decision making [Table 3].
Summary of AI/ML studies discussed in the postoperative prognostication subsection
| Area of investigation | Selected studies |
| Perioperative complication prediction and risk stratification | General technique: Berven et al., 2023[38] Lumbar degenerative disease: Abdelrahman et al., 2022[39] Pediatric deformity: Comstock et al., 2023[40]; Lim et al., 2023[41] Trauma: Yeretsian et al., 2022[42]; Malacon et al., 2022[43] |
| Long-term outcome prognostication | Eliahu et al., 2022[44]; Auloge et al., 2020[45]; Burström et al., 2019[46]; Elmi-Terander et al., 2020[47]; Charles et al., 2021[48] |
CHALLENGES AND OPPORTUNITIES
AI and ML tools throughout the spectrum of spine surgical care hold significant promise to improve patient outcomes; however, those at each point of care have sets of unique challenges. AI/ML focusing on preoperative planning may require prospective studies showing that it improves outcomes to gain traction from physicians and reimbursement from insurance companies. Intraoperative tools and robotics require significant hardware investment and may face regulatory challenges to reach clinical integration, and may encounter resistance from surgeons who fear inefficiencies and potential patient harm associated with early adoption of new technologies[59,60]. Models that predict postoperative complications and long-term outcomes face difficulty in standardizing outcome metrics and in generalizing across centers[61. However, common to all AI/ML tools in spine surgery are several critical challenges, which we detail below, along with our proposed solutions.
Challenge 1: patient and surgical heterogeneity
Our varied clinical and research efforts in spine surgery reflect the immense heterogeneity in the patients we treat. Patients may undergo the same operation for a wide variety of indications, at a wide variety of initial states of health, and similarly, outcomes are driven by a wide variety of physiologic and psychosocial factors. In addition, the same patient with the same pathology may be offered differing surgical plans based on their surgeon’s training and preference. A central challenge in ML is the tradeoff between variables and observations (i.e., patients)[15]. In spine surgery, where patient variability is high, this limitation means that for models to reach the expert level, they must incorporate both many variables and data from a large number of patients. However, as model complexity increases, the ability to understand such models decreases. To mitigate this tradeoff, it may be most expedient to focus AI development efforts on applications that are specifically tailored to quickly and accurately perform highly specific, otherwise time-consuming tasks (i.e., image segmentation of the spine or robotic navigation).
Challenge 2: subjective outcome measures
Despite the aforementioned challenges in developing a broad AI understanding of spine surgery arising from patient heterogeneity, one substantial barrier lies in challenges presented by current outcome measures. Many of the endpoints we follow are subjective or are influenced by a wide variety of factors that AI may not be able to accurately capture in an unbiased manner. For example, endpoints such as pain and functional status may be influenced by psychological factors. Endpoints such as the return to work may be influenced by socioeconomic status. Endpoints such as the need for revision surgery may be influenced by many factors, including preoperative comorbidities and postoperative access to care in addition to the surgery itself. Postoperative pain medication use is influenced by preoperative levels of tolerance and patterns of clinical prescription. It is critical that such models and their predictions do not lead clinicians to select patients or surgical approaches in a way that perpetuates present disparities. Solutions to this problem may be to focus on more immediate rather than long-term measures, on quantitative or radiographic endpoints that can be measured in a validated manner, and potentially to use AI and new technologies to develop novel outcome metrics that better capture the impact of spine surgery on patients’ lives.
Challenge 3: tradeoffs in data quality and quantity
One of the central principles of ML is that capabilities and performance increase with ever-larger datasets[15]. In particular, cutting-edge approaches such as deep learning and large language models (the types of models underlying self-driving cars and ChatGPT, respectively) rely on immense amounts of data to tune hundreds of billions of parameters, from which their intelligence emerges[62]. In spine surgery, large registries such as the Quality Outcomes Database (QOD), British Spine Registry, and International Spine Study Group (ISSG) have aggregated patient data across numerous centers, and the largest ML studies may incorporate thousands of patients. However, these numbers are likely sufficient for certain tasks requiring only simple categorical and numerical variables as inputs rather than complex data such as cross-sectional images, text, and video that require immense amounts of data. Still, healthcare databases often encounter quality issues such as missing or incomplete data and variable practices across the sites where the data were collected. Furthermore, as the number of variables per patient in the database increases, the difficulty of expanding the dataset grows, limiting the number of patients incorporated and increasing the administrative burden on centers that participate.
Due to limitations in data quantity, many studies are validated using withheld patients or cross-validation from the same single-center datasets, which may result in model overfitting and limited clinical utility. Validation using independently collected external datasets will allow for improved assessments of model accuracy and generalizability. Even findings from multi-center studies may be affected by this problem, as the datasets are not completely independent of one another. In addition, some studies used large national datasets that may have limited granularity of clinically relevant variables, potentially limiting their models’ performances. We propose that the standards for multi-center validation and held-out validation and test sets for quantifying performance - standards commonly applied across AI applications - be rigorously applied in AI tools for spine surgery to ensure that published models have the best chance for successful clinical translation.
Future directions
While challenges remain in further integrating AI and ML technologies into spine surgery practice, these technologies have already made an impact on clinical care, operative planning, and procedures in the OR. For AI technologies to continue to develop, the field of spine surgery must make a concerted effort to collect high-quality data in the form of de-identified or HIPAA-compliant large multi-center databases and registries, as these data can be used to fine-tune existing and develop new AI technologies. Future surgical planning and prognostication models should leverage a wide variety of data sources for model training, ranging from demographic and clinical data to patient radiographs and free text from medical records. In addition, surgeons should work closely with industry and academic partners to create robotic and augmented/mixed reality tools. As with all new technology, these efforts will require careful oversight, fine-tuning, and comparison to existing best practices. Should spine surgery as a field successfully apply AI models and tools, our patients stand to benefit the most through patient-specific, data-driven surgical planning tools, increased surgical efficiency, and more accurate short and long-term prognostication.
CONCLUSION
This narrative review highlights a selection of current developments in AI for spine surgery. Despite the challenges discussed in the previous section, AI is already beginning to change how we practice spine surgery. By understanding the current landscape of AI/ML tools across stages of development and clinical scenarios ranging from pre- to intra- and postoperative contexts, we may target our efforts toward incorporating the methods most pertinent to the challenges in our practice. One can easily imagine a near future where AI assists in planning surgical approaches and counseling patients, integrates into intraoperative imaging and navigation systems to enhance anatomical recognition and guide instrumentation, and helps avoid and manage postoperative complications. By highlighting the path forward, we identify strategies that innovation-minded spine surgeons can adopt to expedite the development and clinical translation of these models for the benefit of our patients.
DECLARATIONS
Authors’ contributions
Made substantial contributions to the drafting of the article: Ambati VS, Saggi S, Alan N
Made substantial contributions to background research and review of existing literature: Ambati VS, Saggi S, Dada A
Led the review article (supervising/senior author): Alan N
Availability of data and materials
Not applicable.
Financial support and sponsorship
None.
Conflicts of interest
Alan N serves as a consultant for Globus, Stryker, and Depuy Synthes. The other authors declared that there are no conflicts of interest.
Ethical approval and consent to participate
Not applicable.
Consent for publication
Not applicable.
Copyright
© The Author(s) 2025.
REFERENCES
1. Cornwall GB, Davis A, Walsh WR, Mobbs RJ, Vaccaro A. Innovation and new technologies in spine surgery, circa 2020: a fifty-year review. Front Surg. 2020;7:575318.
2. Kazemi N, Crew LK, Tredway TL. The future of spine surgery: new horizons in the treatment of spinal disorders. Surg Neurol Int. 2013;4:S15-21.
3. Walker CT, Kakarla UK, Chang SW, Sonntag VKH. History and advances in spinal neurosurgery. J Neurosurg Spine. 2019;31:775-85.
4. Zahlan A, Ranjan RP, Hayes D. Artificial intelligence innovation in healthcare: literature review, exploratory analysis, and future research. Technol Soc. 2023;74:102321.
5. Zhou S, Zhou F, Sun Y, et al. The application of artificial intelligence in spine surgery. Front Surg. 2022;9:885599.
7. Clark P, Kim J, Aphinyanaphongs Y. Marketing and US Food and Drug Administration clearance of artificial intelligence and machine learning enabled software in and as medical devices: a systematic review. JAMA Netw Open. 2023;6:e2321792.
8. McNabb NK, Christensen EW, Rula EY, et al. Projected growth in FDA-approved artificial intelligence products given venture capital funding. J Am Coll Radiol. 2024;21:617-23.
9. Hoy D, March L, Brooks P, et al. The global burden of low back pain: estimates from the Global Burden of Disease 2010 study. Ann Rheum Dis. 2014;73:968-74.
10. Stewart Williams J, Ng N, Peltzer K, et al. risk factors and disability associated with low back pain in older adults in low- and middle-income countries. Results from the WHO Study on Global AGEing and Adult Health (SAGE). PLoS One. 2015;10:e0127880.
11. Missios S, Bekelis K. Hospitalization cost after spine surgery in the United States of America. J Clin Neurosci. 2015;22:1632-7.
12. Parker SL, Chotai S, Devin CJ, et al. Bending the cost curve-establishing value in spine surgery. Neurosurgery. 2017;80:S61-9.
13. Jiang F, Wilson JRF, Badhiwala JH, et al. Quality and safety improvement in spine surgery. Global Spine J. 2020;10:17S-28S.
14. Walid MS, Robinson JS Jr. Economic impact of comorbidities in spine surgery. J Neurosurg Spine. 2011;14:318-21.
15. Dangeti P. Statistics for machine learning. Packt Publishing Ltd; 2017. Available from: https://books.google.com/books?id=C-dDDwAAQBAJ&printsec=frontcover&hl=zh-CN#v=onepage&q&f=false. [Last accessed on 28 Dec 2024].
16. Goodfellow I, Bengio Y, Courville A. Deep Learning. MIT Press; 2016. Available from: https://www.deeplearningbook.org/. [Last accessed on 28 Dec 2024].
17. Chan AK, Wozny TA, Bisson EF, et al. Classifying patients operated for spondylolisthesis: a K-means clustering analysis of clinical presentation phenotypes. Neurosurgery. 2021;89:1033-41.
18. Ames CP, Smith JS, Pellisé F, et al; European Spine Study Group, International Spine Study Group. Artificial intelligence based hierarchical clustering of patient types and intervention categories in adult spinal deformity surgery: towards a new classification scheme that predicts quality and value. Spine 2019;44:915-26.
19. Ames CP, Smith JS, Pellisé F, et al; European Spine Study Group, International Spine Study Group. Development of predictive models for all individual questions of SRS-22R after adult spinal deformity surgery: a step toward individualized medicine. Eur Spine J 2019;28:1998-2011.
20. Gros C, De Leener B, Badji A, et al. Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage. 2019;184:901-15.
21. Jamaludin A, Lootus M, Kadir T, et al; Genodisc Consortium. ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist. Eur Spine J 2017;26:1374-83.
22. De Leener B, Cohen-Adad J, Kadoury S. Automatic segmentation of the spinal cord and spinal canal coupled with vertebral labeling. IEEE Trans Med Imaging. 2015;34:1705-18.
23. McCoy DB, Dupont SM, Gros C, et al; TRACK-SCI Investigators. Convolutional neural network-based automated segmentation of the spinal cord and contusion injury: deep learning biomarker correlates of motor impairment in acute spinal cord injury. AJNR Am J Neuroradiol 2019;40:737-44.
24. Doerr SA, Weber-Levine C, Hersh AM, et al. Automated prediction of the thoracolumbar injury classification and severity score from CT using a novel deep learning algorithm. Neurosurg Focus. 2022;52:E5.
25. Pang S, Pang C, Su Z, et al. DGMSNet: spine segmentation for MR image by a detection-guided mixed-supervised segmentation network. Med Image Anal. 2022;75:102261.
26. Pang S, Pang C, Zhao L, et al. SpineParseNet: spine parsing for volumetric MR image by a two-stage segmentation framework with semantic image representation. IEEE Trans Med Imaging. 2021;40:262-73.
27. Wesselink EO, Elliott JM, Coppieters MW, et al. Convolutional neural networks for the automatic segmentation of lumbar paraspinal muscles in people with low back pain. Sci Rep. 2022;12:13485.
28. Zhang B, Yu K, Ning Z, et al. Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: a multicenter retrospective cohort study. Bone. 2020;140:115561.
29. Yabu A, Hoshino M, Tabuchi H, et al. Using artificial intelligence to diagnose fresh osteoporotic vertebral fractures on magnetic resonance images. Spine J. 2021;21:1652-8.
30. Jardon M, Tan ET, Chazen JL, et al. Deep-learning-reconstructed high-resolution 3D cervical spine MRI for foraminal stenosis evaluation. Skeletal Radiol. 2023;52:725-32.
31. Trinh GM, Shao HC, Hsieh KL, et al. Detection of lumbar spondylolisthesis from X-ray images using deep learning network. J Clin Med. 2022;11:5450.
32. Grob A, Loibl M, Jamaludin A, et al. External validation of the deep learning system “SpineNet” for grading radiological features of degeneration on MRIs of the lumbar spine. Eur Spine J. 2022;31:2137-48.
33. Berlin C, Adomeit S, Grover P, et al. Novel AI-based algorithm for the automated computation of coronal parameters in adolescent idiopathic scoliosis patients: a validation study on 100 preoperative full spine X-rays. Global Spine J. 2024;14:1728-37.
34. Wu H, Bailey C, Rasoulinejad P, Li S. Automated comprehensive adolescent idiopathic scoliosis assessment using MVC-Net. Med Image Anal. 2018;48:1-11.
35. Weng CH, Wang CL, Huang YJ, et al. Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework. J Clin Med. 2019;8:1826.
36. Korez R, Putzier M, Vrtovec T. A deep learning tool for fully automated measurements of sagittal spinopelvic balance from X-ray images: performance evaluation. Eur Spine J. 2020;29:2295-305.
37. Galbusera F, Niemeyer F, Wilke HJ, et al. Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach. Eur Spine J. 2019;28:951-60.
38. Berven S, Bisson E, Glassman S, et al. Optimizing surgical alignment: intraoperative assessment of alignment using zero radiation, volumetric intelligence. 2023. Available from: https://assets-global.website-files.com/6296c202ecfe835c15f4e757/649d0b69ba75cbd927e0717b_PROPRIO_WhitePaperLayout_R2.pdf. [Last accessed on 28 Dec 2024].
39. Abdelrahman A, Bangash OK, Bala A. Percutaneous posterior lumbar interbody fusion using optical topographic navigation: operative technique. Interdiscip Neurosur. 2022;29:101561.
40. Comstock CP, Wait E. Novel machine vision image guidance system significantly reduces procedural time and radiation exposure compared with 2-dimensional fluoroscopy-based guidance in pediatric deformity surgery. J Pediatr Orthop. 2023;43:e331-6.
41. Lim KBL, Yeo ISX, Ng SWL, Pan WJ, Lee NKL. The machine-vision image guided surgery system reduces fluoroscopy time, ionizing radiation and intraoperative blood loss in posterior spinal fusion for scoliosis. Eur Spine J. 2023;32:3987-95.
42. Yeretsian T, Lai C, Guha D, Ramjist J, Yang VXD. Machine-vision image guided C4-C5 unilateral cervical pedicle screw insertion: case report and review of literature. AME Case Rep. 2022;6:9.
43. Malacon K, Fatemi P, Zygourakis CC. First reported use of machine vision image guided system for unstable thoracolumbar fusion: technical case report. Interdiscip Neurosur. 2022;30:101641.
44. Eliahu K, Liounakos J, Wang MY. Applications for augmented and virtual reality in robot-assisted spine surgery. Curr Robot Rep. 2022;3:33-7.
45. Auloge P, Cazzato RL, Ramamurthy N, et al. Augmented reality and artificial intelligence-based navigation during percutaneous vertebroplasty: a pilot randomised clinical trial. Eur Spine J. 2020;29:1580-9.
46. Burström G, Buerger C, Hoppenbrouwers J, et al. Machine learning for automated 3-dimensional segmentation of the spine and suggested placement of pedicle screws based on intraoperative cone-beam computer tomography. J Neurosurg Spine. 2019;31:147-54.
47. Elmi-Terander A, Burström G, Nachabé R, et al. Augmented reality navigation with intraoperative 3D imaging vs fluoroscopy-assisted free-hand surgery for spine fixation surgery: a matched-control study comparing accuracy. Sci Rep. 2020;10:707.
48. Charles YP, Cazzato RL, Nachabe R, Chatterjea A, Steib JP, Gangi A. Minimally invasive transforaminal lumbar interbody fusion using augmented reality surgical navigation for percutaneous pedicle screw placement. Clin Spine Surg. 2021;34:E415-24.
49. Zhang Y, Wan DH, Chen M, et al. Automated machine learning-based model for the prediction of delirium in patients after surgery for degenerative spinal disease. CNS Neurosci Ther. 2023;29:282-95.
50. Khazanchi R, Bajaj A, Shah RM, et al. Using machine learning and deep learning algorithms to predict postoperative outcomes following anterior cervical discectomy and fusion. Clin Spine Surg. 2023;36:143-9.
51. Karhade AV, Bongers MER, Groot OQ, et al. Development of machine learning and natural language processing algorithms for preoperative prediction and automated identification of intraoperative vascular injury in anterior lumbar spine surgery. Spine J. 2021;21:1635-42.
52. Karabacak M, Margetis K. A machine learning-based online prediction tool for predicting short-term postoperative outcomes following spinal tumor resections. Cancers. 2023;15:812.
53. Han SS, Azad TD, Suarez PA, Ratliff JK. A machine learning approach for predictive models of adverse events following spine surgery. Spine J. 2019;19:1772-81.
54. Park C, Mummaneni PV, Gottfried ON, et al. Which supervised machine learning algorithm can best predict achievement of minimum clinically important difference in neck pain after surgery in patients with cervical myelopathy? A QOD study. Neurosurg Focus. 2023;54:E5.
55. Khan O, Badhiwala JH, Witiw CD, Wilson JR, Fehlings MG. Machine learning algorithms for prediction of health-related quality-of-life after surgery for mild degenerative cervical myelopathy. Spine J. 2021;21:1659-69.
56. Rushton AB, Jadhakhan F, Verra ML, et al. Predictors of poor outcome following lumbar spinal fusion surgery: a prospective observational study to derive two clinical prediction rules using British Spine Registry data. Eur Spine J. 2023;32:2303-18.
57. Müller D, Haschtmann D, Fekete TF, et al. Development of a machine-learning based model for predicting multidimensional outcome after surgery for degenerative disorders of the spine. Eur Spine J. 2022;31:2125-36.
58. Johnson GW, Chanbour H, Ali MA, et al. Artificial intelligence to preoperatively predict proximal junction kyphosis following adult spinal deformity surgery: soft tissue imaging may be necessary for accurate models. Spine. 2023;48:1688-95.
59. Fiani B, De Stefano F, Kondilis A, Covarrubias C, Reier L, Sarhadi K. Virtual reality in neurosurgery: “Can you see it? World Neurosurg. 2020;141:291-8.
60. Goldberg JL, Härtl R, Elowitz E. Challenges hindering widespread adoption of minimally invasive spinal surgery. World Neurosurg. 2022;163:228-32.
61. Ghanem M, Ghaith AK, El-Hajj VG, et al. Limitations in evaluating machine learning models for imbalanced binary outcome classification in spine surgery: a systematic review. Brain Sci. 2023;13:1723.
62. Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. arXiv. 2020;arXiv:2005.14165. Available from: https://doi.org/10.48550/arXiv.2005.14165. [accessed 28 Dec 2024]
Cite This Article
Open AccessHow to Cite
Ambati, V. S.; Saggi, S.; Dada, A.; Alan, N. Has artificial intelligence in spine surgery lived up to the hype? A narrative review of recent approaches, current challenges, and the path forward. Art. Int. Surg. 2025, 5, 53-64. http://dx.doi.org/10.20517/ais.2024.45
Download Citation
Export Citation File:
Type of Import
Tips on Downloading Citation
Citation Manager File Format
Type of Import
Direct Import: When the Direct Import option is selected (the default state), a dialogue box will give you the option to Save or Open the downloaded citation data. Choosing Open will either launch your citation manager or give you a choice of applications with which to use the metadata. The Save option saves the file locally for later use.
Indirect Import: When the Indirect Import option is selected, the metadata is displayed and may be copied and pasted as needed.
About This Article
Special Issue
Copyright
Data & Comments
Data
0
Comments
Comments must be written in English. Spam, offensive content, impersonation, and private information will not be permitted. If any comment is reported and identified as inappropriate content by OAE staff, the comment will be removed without notice. If you have any queries or need any help, please contact us at support@oaepublish.com.