Singh, Rohin

Artificial intelligence (AI) is reshaping neurosurgery, offering unprecedented opportunities to enhance diagnostics, personalize treatment, and predict outcomes. At the heart of this transformation is the ability to effectively harness big data (BD) within the electronic medical record. Understanding these data structures is essential for making sense of the vast volumes of information generated in modern neurosurgical practice. Equally important are the machine learning (ML) models driving these advancements. From supervised learning and convolutional neural networks to generative AI, these tools are already making a mark in areas such as brain tumor segmentation and spine surgery outcome predictions. Their versatility highlights the potential of ML to complement clinical expertise and streamline decision-making in neurosurgery. However, adopting BD and ML also brings ethical challenges that cannot be ignored. Bias in algorithms threatens to reinforce health disparities, whereas concerns about data privacy demand vigilance in handling sensitive patient information. In addition, the question of liability looms large as ML increasingly influences clinical decisions. The aim of the study was to provide a roadmap for neurosurgeons navigating the evolving intersection of BD, ML, and ethical responsibility in the AI era.

ABSTRACT Introduction Chronic back/neck pain costs the United States around 250 billion dollars annually. Treatment strategies include medication, physical therapy, and specialized procedures. This study aimed to investigate the trends in procedural frequency and Medicare reimbursement rates for common back pain procedures. Methods Data from 2000 to 2020 were extracted from Medicare Part B National Summary Data files, using Current Procedural Terminology (CPT) codes to identify reimbursement for cervical/thoracic and lumbar/sacral epidural injections, radiofrequency ablation, facet joint injections, and spinal cord stimulators (both percutaneous and paddle). Key metrics included annual total physician charges, reimbursements, and the number of procedures performed. Results From 2000 to 2020, 53,208,205 pain procedures were performed. The most common was lumbar/sacral epidural injections, followed by facet joint injections and radiofrequency ablations. Paddle SCS placement was the least common. Percutaneous SCS had the greatest volume growth, increasing from 3595 to 111,172 [+2992%], followed by lumbar/sacral epidural injections with 118,884 to 1,965,445 [+1553%], and cervical/thoracic epidural injections, 22,480–348,642 [+1451%]. All procedures saw a significant increase in volume except for facet joint injections. Inflation‐adjusted reimbursement per service also increased, with paddle SCS demonstrating the largest increase ($618–$2960 [+379.0%]), followed by percutaneous SCS ($353–$1428 [+304.5%]) and cervical/thoracic epidural injections ($128–$153 [+19.5%]). Conclusions Pain management procedures have increased in volume and reimbursement over the last 20 years. This increased reimbursement may allow for broader access to these procedures compared to prior decades and support a shift from traditional and more invasive surgical procedures to minimally invasive treatments for chronic pain patients.

AbstractObjectiveNeuromodulation for pediatric refractory epilepsy (PRE) is preferred when the seizure onset zone is not amenable to surgical resection, due to multifocal onset or involvement of eloquent cortex. Given its rapidly evolving landscape, we describe our institutional experience with neurostimulation therapies including deep brain stimulation (DBS) of the anterior nucleus (DBS‐ANT), the centromedian nucleus (DBS‐CM), responsive neurostimulation (RNS), and chronic subthreshold stimulation (CSS) to treat PRE.MethodsA retrospective chart review was conducted to identify pediatric patients (≤18 years of age) who presented to our institution with PRE. Patients were included who had at least 1 year of follow‐up after neurostimulation was started. Patients with ≥50% seizure frequency reduction at last follow‐up compared to baseline were classified as responders.ResultsA total of 35 patients (21 females) were included in the series. Nine patients underwent DBS‐ANT, 9 underwent DBS‐CM (+ ANT in 7 patients), 5 underwent RNS, and 12 underwent CSS. The median age at seizure onset and surgery was 8 and 16 years, respectively. Structural lesions were the most common etiology of epilepsy (54%). Eighteen patients had prior interventions and 13 received invasive EEG. Post‐operative complications following neurostimulation implantation were noted in three patients (9%). However, no permanent deficits were noted. Median follow‐up time was 46 months (range 13–162 months). Twenty‐three patients (59%) were responders (3/9 DBS‐ANT; 7/9 DBS‐CM; 4/5 RNS; 9/12 CSS). Further, median seizure reduction was 25% (DBS‐ANT), 89% (DBS‐CM), 87% (RNS), and 88% (CSS) across the cohort. Six patients (17%) had improved subjective neurocognitive outcomes while the other 29 had stable neurocognitive outcomes.SignificanceDBS, RNS, and CSS are safe and effective options for PRE. An understanding of treatment approaches can optimize results by tailoring therapy to individual patients.Plain Language SummaryThis study investigates the use of various neurostimulation therapies for treating pediatric refractory epilepsy (PRE) including deep brain stimulation (DBS), responsive neurostimulation (RNS), and chronic subthreshold stimulation (CSS). Overall, neuromodulation was found to be effective in reducing seizures in most patients, with 59% of patients showing at least a 50% reduction in seizure frequency. Additionally, the treatments were generally safe, with few complications and no instances of permanent deficits.

BACKGROUND AND OBJECTIVES: Predicting functional outcomes after surgical management of ruptured aneurysms is essential. This study sought to validate the modified Southwestern Aneurysm Severity Index (mSASI), which predicts functional outcomes 1 year after treatment. METHODS: The surgical arm of a randomized controlled trial, the Barrow Ruptured Aneurysm Trial, was used to validate the mSASI model. mSASI scores incorporating the Hunt and Hess scale, Non-Neurological American Society of Anesthesiologists Physical Classification Status, imaging findings, and other modifiers were assigned and evaluated against the Glasgow Outcome Scale (GOS) score at 1 year. The model's performance was assessed for discrimination and calibration. Similar evaluations were constructed using the modified Rankin Scale (mRS) as the 1-year functional outcome measurement. Long-term outcomes (3, 6, 10 years) were also evaluated. RESULTS: Of 280 clinical trial patients treated surgically, 242 met the inclusion criteria. The mean age was 54.1 ± 12.9 years; 31% were men. Favorable GOS score (4-5) and mRS score (0-2) at 1 year were observed in 73.6% and 66.1% of patients, respectively. The mSASI model predicted unfavorable GOS score at 1 year with fair to good discrimination (area under the curve = 0.75, 95% CI = 0.68-0.82) and accurate calibration (R 2 = 0.98). Similar results were obtained when mRS was used as the outcome measure (area under the curve = 0.75, 95% CI = 0.68-0.82; R 2 = 0.95). CONCLUSION: The mSASI model was externally validated in our cohort to predict functional outcomes using the GOS or mRS scores 1 year after surgery. This index may be used for prognosticating outcomes of patients undergoing surgery for ruptured aneurysms at short-term and long-term intervals.

In a period when the budding field of neurosurgery was believed to have little promise, Dr Alfred Washington Adson founded and led the first neurosurgical department at Mayo Clinic. He was not without reservations—surgical intervention for neurological conditions was rarely pursued because of poor outcomes and high complication rates, and Dr Adson acknowledged his early concerns about the future of neurosurgery in his memoirs. However, his education, mentorship, his training, and his first neurosurgical cases helped to shape the impact he ultimately had on the field and his legacy as a neurosurgeon. Dr Adson trained with several renowned Mayo general surgeons, notably his mentor Dr Emil Beckman, whose desire for operative precision shaped Dr Adson's drive to develop his own skills as a surgeon. Two years into his residency, he became the youngest staff surgeon and was tasked with managing the neurosurgical cases at Mayo. The five neurosurgical cases overseen by Dr Adson in the next year illuminated the opportunity for neurosurgery to drastically improve the lives of patients. Dr Adson, given the option of continuing as either a general surgeon or a neurosurgeon, ultimately chose to pursue neurosurgery. This article seeks to provide a historical perspective on the neurosurgeon Dr Alfred Washington Adson using primary and secondary accounts from the Mayo archives, highlighting his contributions to the early understanding of intracranial pathology and how his early experiences as a trainee developed into a personal passion for self-improvement, education, and advocacy for health care in America.

BACKGROUND AND OBJECTIVE: As incidence of operative spinal pathology continues to grow, so do the rates of lumbar spinal fusion procedures. Comorbidity indices can be used preoperatively to predict potential complications. However, there is a paucity of research defining the optimal comorbidity indices in patients undergoing spinal fusion surgery. We aimed to use modeling strategies to evaluate the predictive validity of various comorbidity indices and combinations thereof. METHODS: Patients who underwent spinal fusion were queried using data from the Nationwide Readmissions Database for the years 2016 through 2019. Using comorbidity indices as predictor variables, receiver operating characteristic curves were developed for pertinent complications such as mortality, nonroutine discharge, top-quartile cost, top-quartile length of stay, and 30-day readmission. RESULTS: A total of 750 183 patients were included. Nonroutine discharges occurred in 161 077 (21.5%) patients. The adjusted all-payer cost for the procedure was $37 616.97 ± $27 408.86 (top quartile: $45 409.20), and the length of stay was 4.1 ± 4.4 days (top quartile: 8.1 days). By comparing receiver operating characteristics of various models, it was found that models using Frailty + Elixhauser Comorbidity Index (ECI) as the primary predictor performed better than other models with statistically significant P -values on post hoc testing. However, for prediction of mortality, the model using Frailty + ECI was not better than the model using ECI alone ( P = .23), and for prediction of all-payer cost, the ECI model outperformed the models using frailty alone ( P < .0001) and the model using Frailty + ECI ( P < .0001). CONCLUSION: This investigation is the first to use big data and modeling strategies to delineate the relative predictive utility of the ECI and Johns Hopkins Adjusted Clinical Groups comorbidity indices for the prognostication of patients undergoing lumbar fusion surgery. With the knowledge gained from our models, spine surgeons, payers, and hospitals may be able to identify vulnerable patients more effectively within their practice who may require a higher degree of resource utilization.

OBJECTIVE Petroclival meningiomas (PCMs) are challenging lesions to treat because of their deep location and proximity to critical neurovascular structures. Patients with these lesions commonly present because of local mass effect. A symptom that proves challenging to definitively manage is trigeminal neuralgia (TN), which occurs in approximately 5% of PCM cases. To date, there is no consensus on whether microsurgical resection or stereotactic radiosurgery (SRS) leads to better outcomes in the treatment of TN secondary to PCM. In this systematic review and meta-analysis, the authors aimed to evaluate the available literature on the efficacy of microsurgical resection versus SRS for controlling TN secondary to PCM. METHODS The Embase, MEDLINE, Scopus, and Cochrane databases were queried from database inception to May 17, 2022, using the search terms “(petroclival AND meningioma) AND (trigeminal AND neuralgia).” Study inclusion criteria were as follows: 1) reports on patients aged ≥ 18 years and diagnosed with TN secondary to PCM, 2) cases treated with microsurgical resection or SRS, 3) cases with at least one posttreatment follow-up report of TN pain, 4) cases with at least one outcome of tumor control, and 5) publications describing randomized controlled trials, comparative or single-arm observational studies, case reports, or case series. Exclusion criteria were 1) literature reviews, technical notes, conference abstracts, or autopsy reports; 2) publications that did not clearly differentiate data on patients with PCMs from data on patients with different tumors or with meningiomas in different locations (other intracranial or spinal meningiomas); 3) publications that contained insufficient data on treatments and outcomes; and 4) publications not written in the English language. References of eligible studies were screened to retrieve additional relevant studies. Data on pain and tumor outcomes were compared between the microsurgical resection and SRS treatment groups. The DerSimonian-Laird random-effects model with Hartung-Knapp-Sidik-Jonkman variance correction was used to pool estimates from the included studies. RESULTS Two comparative observational studies and 6 single-arm observational studies describing outcomes after primary intervention were included in the analyses (138 patients). Fifty-seven patients underwent microsurgical resection and 81 underwent SRS for the management of TN secondary to PCM. By the last follow-up (mean 71 months, range 24–149 months), the resection group had significantly higher rates of pain resolution than the SRS group (82%, 95% CI 50%–100% vs 31%, 95% CI 18%–45%, respectively; p = 0.004). There was also a significantly longer median time to tumor recurrence following resection (43.75 vs 16.7 months, p < 0.01). The resection group showed lower rates of pain persistence (0%, 95% CI 0%–6% vs 25%, 95% CI 13%–39%, p = 0.001) and pain exacerbation (0% vs 12%, 95% CI 3%–23%, p = 0.001). The most common postintervention Barrow Neurological Institute pain score in the surgical group was I (66.7%) compared with III (27.2%) in the SRS group. Surgical reintervention was less frequently required following primary resection (1.8%, 95% CI 0%–37% vs 19%, 95% CI 1%–48%, p < 0.01). CONCLUSIONS Microsurgical resection is associated with higher rates of TN pain resolution and lower rates of pain persistence and exacerbation than SRS in the treatment of PCM. SRS with further TN management is a viable alternative in patients who are not good candidates for microsurgical resection.

OBJECTIVE Lateral lumbar interbody fusion including anterior-to-psoas oblique lumbar interbody fusion has conventionally relied on pedicle screw placement (PSP) for construct stabilization. Single-position surgery with lumbar interbody fusion in the lateral decubitus position with concomitant PSP has been associated with increased operative efficiency. What remains unclear is the accuracy of PSP with robotic guidance when compared with the more familiar prone patient positioning. The present study aimed to compare robot-assisted screw placement accuracy between patients with instrumentation placed in the prone and lateral positions. METHODS The authors identified all consecutive patients treated with interbody fusion and PSP in the prone or lateral position by a single surgeon between January 2019 and October 2022. All pedicle screws placed were analyzed using CT scans to determine appropriate positioning according to the Gertzbein-Robbins classification grading system (grade C or worse was considered as a radiographically significant breach). Multivariate logistic regression models were constructed to identify risk factors for the occurrence of a radiographically significant breach. RESULTS Eighty-nine consecutive patients (690 screws) were included, of whom 46 (477 screws) were treated in the prone position and 43 (213 screws) in the lateral decubitus position. There were fewer breaches in the prone (n = 13, 2.7%) than the lateral decubitus (n = 15, 7.0%) group (p = 0.012). Nine (1.9%) radiographically significant breaches occurred in the prone group compared with 10 (4.7%) in the lateral decubitus group (p = 0.019), for a prone versus lateral decubitus PSP accuracy rate of 98.1% versus 95.3%. There were no significant differences in BMI between prone versus lateral decubitus cohorts (30.1 vs 29.6) or patients with screw breach versus those without (31.2 vs 29.5). In multivariate models, the prone position was the only significant protective factor for screw accuracy; no other significant risk factors for screw breach were identified. CONCLUSIONS The present data suggest that pedicle screws placed with robotic assistance have higher placement accuracy in the prone position. Further studies will be needed to validate the accuracy of PSP in the lateral position as single-position surgery becomes more commonplace in the treatment of spinal disorders.

OBJECTIVE While single-position surgery (SPS) eliminates the need for patient repositioning, the placement of screws in the unconventional lateral position poses unique challenges related to asymmetry relative to the surgical table. Use of robotic guidance or intraoperative navigation can help to overcome this. The aim of this study was to compare the relative accuracies offered by these various navigation modalities for pedicle screws placed in lateral SPS. METHODS According to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, the PubMed/Medline, Embase, and Cochrane Library databases were queried for studies reporting pedicle screw placement accuracy using fluoroscopic, CT-navigated, O-arm, or robotic guidance in lateral SPS, and a systematic review and meta-analysis was performed. Included studies all compared evaluated screw placement accuracy in lateral SPS using a single navigation method. Quality assessment was performed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) system; risk of bias was assessed using the Newcastle-Ottawa Scale and the Joanna Briggs Institute checklist. The primary outcome, rate of pedicle screw breach, was analyzed using random-effects meta-analysis. RESULTS Eleven studies were included comprising 548 patients who underwent the placement of instrumentation with 2488 screws. For the fluoroscopic, CT-navigated, O-arm, and robotic guidance cohorts, there were 3, 2, 3, and 3 studies, respectively. Breach rates by modality were as follows: fluoroscopic guidance (6.6%), CT navigation (4.7%), O-arm (3.9%), and robotic guidance (3.9%). Random-effects meta-analysis showed a significant difference between studies, with an overall breach rate of 4.9% (95% CI 3.1%–7.5%; p < 0.001); however, testing for subgroup differences failed to show a significant difference between guidance modalities (QM = 0.69, df = 3; p = 0.88). Heterogeneity between studies was significant (I2 = 79.0%, τ2 = 0.41, χ2 = 47.65, df = 10; p < 0.001). CONCLUSIONS Robotic guidance of screws is noninferior to alternative guidance modalities in lateral SPS; however, additional prospective studies directly comparing different guidance types are merited.