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.
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.
- Commentary: The Enforceability of Noncompete Clauses in the Medical Profession: A Review by the Workforce Committee and the Medico-legal Committee of the Council of State Neurosurgical Societies. Neurosurgery 2020 Hide More
Medical malpractice in spine surgery: a review
2020; 49 (5): E16
Medical malpractice is an important but often underappreciated topic within neurosurgery, particularly for surgeons in the early phases of practice. The practice of spinal neurosurgery involves substantial risk for litigation, as both the natural history of the conditions being treated and the operations being performed almost always carry the risk of permanent damage to the spinal cord or nerve roots, a cardiopulmonary event, death, or other dire outcomes. In this review, the authors discuss important topics related to medical malpractice in spine surgery, including tort reform, trends and frequency of litigation claims in spine surgery, wrong-level and wrong-site surgery, catastrophic outcomes including spinal cord injury and death, and ethical considerations.
View details for DOI 10.3171/2020.8.FOCUS20602
View details for Web of Science ID 000585759900016
View details for PubMedID 33130625
Fostering Reproducibility and Generalizability in Machine Learning for Clinical Prediction Modeling in Spine Surgery.
The spine journal : official journal of the North American Spine Society
As the use of machine learning algorithms in the development of clinical prediction models has increased, researchers are becoming more aware of the deleterious that stem from the lack of reporting standards. One of the most obvious consequences is the insufficient reproducibility found in current prediction models. In an attempt to characterize methods to improve reproducibility and to allow for better clinical performance, we utilize a previously proposed taxonomy that separates reproducibility into three components: technical, statistical, and conceptual reproducibility. By following this framework, we discuss common errors that lead to poor reproducibility, highlight the importance of generalizability when evaluating a ML model's performance, and provide suggestions to optimize generalizability to ensure adequate performance. These efforts are a necessity before such models are applied to patient care.
View details for DOI 10.1016/j.spinee.2020.10.006
View details for PubMedID 33065274
Predictive Modeling of Long-Term Opioid and Benzodiazepine Use after Intradural Tumor Resection.
The spine journal : official journal of the North American Spine Society
INTRODUCTION: Despite increased awareness of the ongoing opioid epidemic, opioid and benzodiazepine use remain high after spine surgery. In particular, long-term co-prescription of opioids and benzodiazepines have been linked to high risk of overdose-associated death. Tumor patients represent a unique subset of spine surgery patients and few studies have attempted to develop predictive models to anticipate long-term opioid and benzodiazepine use after spinal tumor resection.METHODS: The IBM Watson Health MarketScan Database and Medicare Supplement were assessed to identify admissions for intradural tumor resection between 2007 and 2015. Adult patients were required to have at least 6-months of continuous pre-admission baseline data and 12-months of continuous post-discharge follow-up. Primary outcomes were long-term opioid and benzodiazepine use, defined as at least 6 prescriptions within 12 months. Secondary outcomes were durations of opioid and benzodiazepine prescribing. Logistic regression models, with and without regularization, were trained on an 80% training sample and validated on the withheld 20%.RESULTS: A total of 1,942 patients were identified. The majority of tumors were extramedullary (74.8%) and benign (62.5%). A minority of patients received arthrodesis (9.2%) and most patients were discharged to home (79.1%). Factors associated with post-discharge opioid use duration include tumor malignancy (vs benign, B=19.8 prescribed-days/year, 95% CI 1.1 to 38.5) and intramedullary compartment (vs extramedullary, B=18.1 prescribed-days/year, 95% CI 3.3 to 32.9). Pre- and peri-operative use of prescribed NSAIDs and gabapentin/pregabalin were associated with shorter and longer duration opioid use, respectively. History of opioid and history of benzodiazepine use were both associated with increased post-discharge opioid and benzodiazepine use. Intramedullary location was associated with longer duration post-discharge benzodiazepine use (B=10.3 prescribed-days/year, 95% CI 1.5 to 19.1). Among assessed models, elastic net regularization demonstrated best predictive performance in the withheld validation cohort when assessing both long-term opioid use (AUC=0.748) and long-term benzodiazepine use (AUC=0.704). Applying our model to the validation set, patients scored as low-risk demonstrated a 4.8% and 2.4% risk of long-term opioid and benzodiazepine use, respectively, compared to 35.2% and 11.1% of high-risk patients.CONCLUSIONS: We developed and validated a parsimonious, predictive model to anticipate long-term opioid and benzodiazepine use early after intradural tumor resection, providing physicians opportunities to consider alternative pain management strategies.
View details for DOI 10.1016/j.spinee.2020.10.010
View details for PubMedID 33065272
Machine learning in neurosurgery: a global survey.
BACKGROUND: Recent technological advances have led to the development and implementation of machine learning (ML) in various disciplines, including neurosurgery. Our goal was to conduct a comprehensive survey of neurosurgeons to assess the acceptance of and attitudes toward ML in neurosurgical practice and to identify factors associated with its use.METHODS: The online survey consisted of nine or ten mandatory questions and was distributed in February and March 2019 through the European Association of Neurosurgical Societies (EANS) and the Congress of Neurosurgeons (CNS).RESULTS: Out of 7280 neurosurgeons who received the survey, we received 362 responses, with a response rate of 5%, mainly in Europe and North America. In total, 103 neurosurgeons (28.5%) reported using ML in their clinical practice, and 31.1% in research. Adoption rates of ML were relatively evenly distributed, with 25.6% for North America, 30.9% for Europe, 33.3% for Latin America and the Middle East, 44.4% for Asia and Pacific and 100% for Africa with only two responses. No predictors of clinical ML use were identified, although academic settings and subspecialties neuro-oncology, functional, trauma and epilepsy predicted use of ML in research. The most common applications were for predicting outcomes and complications, as well as interpretation of imaging.CONCLUSIONS: This report provides a global overview of the neurosurgical applications of ML. A relevant proportion of the surveyed neurosurgeons reported clinical experience with ML algorithms. Future studies should aim to clarify the role and potential benefits of ML in neurosurgery and to reconcile these potential advantages with bioethical considerations.
View details for DOI 10.1007/s00701-020-04532-1
View details for PubMedID 32812067
The Stanford Neurosurgical Ariticial Intelligence and Machine Learning Laboratory is led by Dr. Anand Veeravagu, an Assistant Professor of Neurosurgery and Assistant 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.