Stanford Neurosurgical
Artificial Intelligence and Machine Learning Laboratory

The safety and efficacy of surgery is our number one priority. As we enter the era of big data, the onus is upon us to utilize what we have learned to improve medical care for future generations. Using novel, cutting edge artificial intelligence and machine learning techniques, our goal is to mine through millions of patient records to predict outcomes following all types of surgery. Imagine a virtual algorithm, that is capable of providing a true estimate of surgical risk, outcome, and efficacy – based specifically on your characteristics. This is the very foundation of precision medicine, and will empower physicians to deliver outstanding care.

Research

The focus of my laboratory is to utilize precision medicine techniques to improve the diagnosis and treatment of neurologic conditions. From traumatic brain injury to spinal scoliosis, the ability to capture detailed data regarding clinical symptoms and treatment outcomes has empowered us to do better for patients. Utilize data to do better for patients, that’s what we do.


Our Team

The Stanford Neurosurgical Artificial Intelligence and Machine Learning Laboratory is led by Dr. Anand Veeravagu, an Associate Professor of Neurosurgery and Associate Professor of Orthopedic Surgery, by courtesy, and Director of Minimally Invasive NeuroSpine Surgery at Stanford. Our laboratory team includes neurosurgery residents, clinical instructors, and medical students. 

We're Hiring!

Stanford Neurosurgical Artificial Intelligence and Machine Learning Laboratory is inviting applications for a 1-year post-doctoral research position. It offers an excellent opportunity for academic advancement and exposure to clinical neurosurgery. Responsibilities include clinical research productivity, database management, analytics, writing and study coordination. Highly motivated individuals with a medical degree, background analytics and prior neurosurgery experience welcomed. 

To apply, please contact us by email: neurobigdata@stanford.edu


Publications

Featured Publications

Demonstrating the successful application of synthetic learning in spine surgery for training multi-center models with increased patient privacy

From real-time tumor classification to operative outcome prediction, applications of machine learning to neurosurgery are powerful. However, the translation of many of these applications are restricted by the lack of "big data" in neurosurgery. 
 

Sigma-1 receptor expression in a subpopulation of lumbar spinal cord microglia in response to peripheral nerve injury

Sigma-1 Receptor has been shown to localize to sites of peripheral nerve injury and back pain. Radioligand probes have been developed to localize Sigma-1 Receptor and thus image pain source. However, in non-pain conditions, Sigma-1 Receptor expression has also been demonstrated in the central nervous system and dorsal root ganglion. 

 

Other Publications

Associate Professor of Neurosurgery and, by courtesy, of Orthopaedic Surgery

Publications

  • Current state and future perspectives of spinal navigation and robotics-an AO spine survey. Brain & spine Motov, S., Butenschoen, V. M., Krauss, P. E., Veeravagu, A., Yoo, K. H., Stengel, F. C., Hejrati, N., Stienen, M. N. 2025; 5: 104165

    Abstract

    The use of robotics in spine surgery has gained popularity. This study aims to assess the current state of robotics and raise awareness of its educational implications.What are the current adoption trends and barriers to the implementation of robotic assistance in spine surgery?An online questionnaire comprising 27 questions was distributed to AO spine members between October 25th and November 13th, 2023, using the SurveyMonkey platform (https://www.surveymonkey.com; SurveyMonkey Inc., San Mateo, CA, USA). Statistical analyses (descriptive statistics, Pearson Chi-Square tests) and generation of all graphs were performed using SPSS Version 29.0.1.0 (IBM SPSS Statistic).We received 424 responses from AO Spine members (response rate = 9.9 %). The participants were mostly board-certified orthopedic surgeons (46 %, n = 195) and neurosurgeons (32%, n = 136). While 49% (n = 208) of the participants reported occasional or frequent use of navigation assistance, only 18 % (n = 70) indicated the use of robotic assistance for spinal instrumentation. A significant difference based on the country's median income status (p < 0.001) and the respondent's number of annual instrumentation procedures (p < 0.001) has been observed. While 11 % (n = 47) of all surgeons use a spinal robot frequently, 36 % (n = 153) of the participants stated they don't need a robot from a current perspective. Most participants (77%, n = 301) concluded that high acquisition costs are the primary barrier for the implementation of robotics.Although the hype for robotics in spine surgery increased recently, robotic systems remain non-standard equipment due to cost constraints and limited usability.

    View details for DOI 10.1016/j.bas.2024.104165

    View details for PubMedID 39810924

    View details for PubMedCentralID PMC11732222

  • Single Position Lateral Anterior Lumbar Interbody Fusion at L5/S1. Neurosurgery Stienen, M. N., Yoo, K., Schonfeld, E., Shah, V., Abikenari, M., Pangal, D., Chandra, V., Veeravagu, A. 2025; 96 (3S): S17-S25

    Abstract

    Anterior lumbar interbody fusion (ALIF) is an established surgical approach for spinal fusion, offering distinct advantages in restoring lumbar lordosis, indirectly decompressing neural elements, and facilitating high fusion rates because of the increase in the fusion surface area. Traditionally, ALIF is performed with the patient in a supine position, necessitating repositioning for additional posterior interventions, which increases operative time, anesthetic time, and complexity. The recent development of single position lateral ALIF (SPL-ALIF) enables anterior and posterior access without repositioning, enables gravity facilitated retroperitoneal access, and optimizes surgical efficiency, particularly in cases necessitating multilevel anterior column fusion. The current review comprehensively examines SPL-ALIF at the L5-S1 level, presenting technical considerations and comparative benefits over traditional techniques. The approach has demonstrated significant reductions in operative time, blood loss, and postoperative ileus, with equivalent radiographic outcomes compared with supine ALIF. Furthermore, SPL-ALIF has been evidenced to have a similar safety profile to supine ALIF with equivalent vascular, abdominal, and neurological complications, as well as comparable revision rates between the two procedures. However, SPL-ALIF is not without limitations. The technique may be less effective in cases requiring direct decompression or in patients with complex vascular anatomy or extensive retroperitoneal scarring. These challenges necessitate careful patient selection to optimize outcomes and minimize intraoperative risks. Future studies are warranted to validate the clinical benefits of SPL-ALIF, particularly concerning fusion rates, patient-reported outcomes, and complication profiles, thereby solidifying its role in the evolving landscape of minimally invasive spine surgery.

    View details for DOI 10.1227/neu.0000000000003332

    View details for PubMedID 39950780

  • Clinical outcomes and patient-reported outcome measures among patients undergoing posterior lumbar fusion procedures with varying insurance payor status: a propensity score-matching study. Journal of neurosurgery. Spine Shah, A., Schonfeld, E., Haider, G., Marianayagam, N. J., Sadeghzadeh, S., Stienen, M. N., Veeravagu, A. 2025: 1-9

    Abstract

    Posterior lumbar fusion (PLF) is a routinely used procedure for treatment of spinal pathology. Several studies have highlighted disparities in reoperation and postoperative complications and demonstrated associations between differing insurance providers, complication rates, and hospital resource utilization in spine surgery. Previous studies have examined broad spinal procedures but have not extended to uninsured patients, or adjusted for sociodemographic factors or comorbidity history. Understanding relationships between payor status and outcomes following fusion procedures is vital to promoting healthcare equity. The objective of this study was to assess whether patients' insurance impacts postoperative outcomes and patient satisfaction following PLF procedures.The Stanford University Medical Center inpatient registry was used to retrospectively analyze patients who underwent PLF procedures between 2016 and 2022. Propensity score matching was used to compare privately insured with Medicaid patients, as well as comparing uninsured patients with Medicaid patients based on age, sex, and comorbidities. Outcomes data, including 90-day postoperative complications, reoperation, and patient-reported outcome measures scores (Oswestry Disability Index and Patient Health Questionnaire) were collected.A total of 1904 patients fulfilled the inclusion criteria. In unmatched comparisons, statistically significant differences existed within specific types of complications including altered mental status, delirium, neurological complications, and pulmonary complications. A total of 292 privately insured patients were matched to 292 Medicaid patients. Within matched patient groups, the Medicaid group had higher rates of altered mental status (6.2% vs 2.7%, p = 0.042); delirium (9.9% vs 5.1%, p = 0.035); renal dysfunction (6.9% vs 4.1%, p = 0.020); and pulmonary complications (8.9% vs 3.8%, p = 0.049) compared to privately insured patients. Privately insured patients had lower postoperative Oswestry Disability Index scores (30.2 vs 34.4, p = 0.018) compared to Medicaid patients. Following propensity score matching of 88 Medicaid patients to 88 uninsured patients, large but not statistically significant differences existed for neurological complications (12.5% vs 5.7%, p = 0.165) and 5-year revision rates (3.4% vs 1.1%, p = 0.353).The findings indicate that the treatment outcomes, care quality, and patient satisfaction following PLF procedures differ between Medicaid and privately insured patients. Further investigation is warranted to explore relationships between insurance payor status and clinical outcomes in multicenter populations.

    View details for DOI 10.3171/2024.9.SPINE231403

    View details for PubMedID 39889288

  • Treatment of occult radiculopathy in complex regional pain syndrome by anterior cervical discectomy and fusion following localization by [18F]fluorodeoxyglucose radioligand and PET/MRI: illustrative case. Journal of neurosurgery. Case lessons Schonfeld, E., Haider, G., Tawfik, V., Jin, M. C., Yoo, K., Marianayagam, N. J., Biswal, S., Veeravagu, A. 2024; 8 (26)

    Abstract

    The inability to localize pain generators often results in failed back surgery syndrome (FBSS). Structural imaging can identify multiple and/or noncausative abnormalities. Molecular imaging of glucose transporters offers the opportunity to localize metabolically active sites. Using the radiotracer [18F]fluorodeoxyglucose (FDG) with positron emission tomography/magnetic resonance imaging (PET/MRI) has enabled the localization of malignant lesions and pain generators via regions of high inflammation.A 61-year-old woman was diagnosed with complex regional pain syndrome (CRPS) and experienced right greater than left upper-extremity pain. Following PET/MRI with the FDG radioligand for GLUT, increased radiotracer uptake was seen in the right C6 nerve root and dorsal root ganglion, providing additional information to the structural MRI findings of narrowing of the right C5-6 neural foramina. Together with pain relief following a transforaminal steroid injection to the area, these results prompted the authors to perform a C5-6 anterior cervical discectomy and fusion procedure, which resulted in significant symptom relief.The authors present a case of worsening upper-extremity CRPS with an occult radiculopathy that improved following surgery to address a pain generator identified by FDG PET/MRI. Localization of inflammatory sites can reduce FBSS and nonspecific management of pain believed to be resulting from spinal pain generators in a wide array of chronic pain syndromes. https://thejns.org/doi/10.3171/CASE24327.

    View details for DOI 10.3171/CASE24327

    View details for PubMedID 39715553

  • Suspected and surgically managed cauda equina syndrome nationwide: epidemiological trends and socioeconomic factors influencing access to care. Journal of neurosurgical sciences Johnstone, T. M., Shah, V., Haider, G., Yoo, K. H., Stienen, M. N., Veeravagu, A. 2024

    Abstract

    Cauda equina syndrome (CES) is a critical condition requiring timely intervention to prevent severe morbidity. This study investigates the epidemiology and socioeconomic factors influencing access to CES care in USA Emergency Departments.Data was used from the Nationwide Emergency Department Sample (NEDS) from 2016-2020. Encounters for patients presenting with suspected CES were queried using ICD 10 codes. Incidence estimates for suspected and surgically managed CES were constructed. Encounter characteristics were tabulated to describe aspects of a typical CES presentation to a USA ED. Multivariable regression analysis ascertained the impact of hospital and socioeconomic features on in-hospital mortality, surgical management, length of stay, visit costs, and patient transfer.The incidences of suspected and surgically managed CES rose year-by-year (P=0.006; P=0.005). Uninsured patients (P<0.001) and African American (P=0.002) were less likely to be admitted for care. Patients residing in the wealthiest quartile of zip codes were more likely to be admitted for care (P<0.001). In addition, uninsured (P=0.017) and African American patients (P=0.009) were less likely to receive surgical management of suspected CES. Lastly, uninsured (P<0.001), Hispanic (P=0.038), and rurally located patients (P=0.007) were more likely to be transferred, while patients residing in the wealthiest zip codes (P=0.007) were less likely to be transferred.Socioeconomic factors like race, income, insurance, and residence potentially alter CES management, which may inform health policy and future patient care.

    View details for DOI 10.23736/S0390-5616.24.06300-8

    View details for PubMedID 39688602