Can Artificial Intelligence Mitigate Missed Diagnoses by Generating Differential Diagnoses for Neurosurgeons?

BACKGROUND/OBJECTIVE: Neurosurgery emphasizes the criticality of accurate differential diagnoses, with diagnostic delays posing significant health and economic challenges. As large language models (LLMs) emerge as transformative tools in healthcare, this study seeks to elucidate their role in assisting neurosurgeons with the differential diagnosis process, especially during preliminary consultations. METHODS: This study employed 3 chat-based LLMs, ChatGPT (versions 3.5 and 4.0), Perplexity AI, and Bard AI, to evaluate their diagnostic accuracy. Each LLM was prompted using clinical vignettes, and their responses were recorded to generate differential diagnoses for 20 common and uncommon neurosurgical disorders. Disease-specific prompts were crafted using Dynamed, a clinical reference tool. The accuracy of the LLMs was determined based on their ability to identify the target disease within their top differential diagnoses correctly. RESULTS: For the initial differential, ChatGPT 3.5 achieved an accuracy of 52.63%, while ChatGPT 4.0 performed slightly better at 53.68%. Perplexity AI and Bard AI demonstrated 40.00% and 29.47% accuracy, respectively. As the number of considered differentials increased from 2 to 5, ChatGPT 3.5 reached its peak accuracy of 77.89% for the top 5 differentials. Bard AI and Perplexity AI had varied performances, with Bard AI improving in the top 5 differentials at 62.11%. On a disease-specific note, the LLMs excelled in diagnosing conditions like epilepsy and cervical spine stenosis but faced challenges with more complex diseases such as Moyamoya disease and amyotrophic lateral sclerosis. CONCLUSIONS: LLMs showcase the potential to enhance diagnostic accuracy and decrease the incidence of missed diagnoses in neurosurgery.

Impact of environmental pollutants on pediatric brain tumor incidence in New Jersey.

OBJECTIVE: The relationship between environmental contaminants and brain tumor incidence in adults has been thoroughly explored but research into how these contaminants affect pediatric brain tumor (PBT) incidence has not been explored. Children, typically having more limited geographical movement and thus more consistent environmental contaminant exposure, might offer more reliable insights into which environmental contaminants affect the incidence of brain tumors. The present study is the first to focus on exploring whether a possible association exists between the incidence of PBTs and exposure to environmental pollutants in New Jersey (NJ). METHODS: Linear regressions were run between PBT incidence and the concentration of air quality pollutants such as Ozone (O3), Particulate Matter 2.5 (PM2.5), Particulate Matter 10 (PM10), and Carbon Monoxide (CO). Similarly, linear regressions were run between PBT incidence and Elevated Blood Lead Levels (BLL). RESULTS: The study observed a significant positive relationship between O3 and PBT incidence (ß = 0.34, p = 0.028). However, the relationship between PBT incidence, and environmental pollutants such as CO (ß = 0.0047, p = 0.098), PM2.5 (ß = -0.2624, p = 0.74), and PM10 (ß = -0.7353, p = 0.073) were found to be nonsignificant. For elevated BLL, nonsignificant relationships with PBT incidence were observed at 10-14 µg/dL (ß = -39.38, p = 0.30), 15-19 µg/dL (ß = -67.00, p = 0.21), and 20-44 µg/dL (ß = -201.98, p = 0.12). CONCLUSIONS: The results indicate a possible impact of O3 on the incidence of PBTs in NJ. In contrast to the significant links found in prior studies of adult brain tumors, the associations between PBT occurrence and particulate matter were not significant. These findings highlight the importance of further investigating how environmental factors, especially O3, relate to PBTs.

Analysis of Concussions Reported in American Professional Football Injury Reports in the 2019 Through 2023 Regular Seasons.

OBJECTIVE: The National Football League (NFL) has seen increasing scrutiny regarding its management of concussions, especially following an on-field incident involving the Miami Dolphins' quarterback Tua Tagovailoa in the 2022 season. We hope to elucidate the recent trends in the diagnosis and management of concussions during the course of 5 NFL seasons from 2019 to 2023. METHODS: We queried the NFL injury reports from the 2019 through 2023 database recording players listed with concussions. The weeks missed were calculated using the NFL game logs. Players' concussions that did not occur in the games, those complicated by other injuries, and those affected by roster status were excluded. RESULTS: Searches of the NFL injury reports resulted in the identification of 664 of 692 concussions (96%) that occurred in regular season games across the 2019-2023 seasons. During the course of these 5 seasons, 31% of the players returned without missing a game, 39% of the players missed 1 game, and 30% of the players missed ≥2 games. No significant difference in the number of concussions per game or weeks missed was observed across the seasons observed. Players with concussions on teams that made the playoffs saw fewer weeks missed than those on non-playoff teams (0.86 vs. 1.37; P = 0.002). CONCLUSIONS: Since the start of the 2021 NFL season, an increasing incidence of concussions has been noted; however, there was no change observed in the number of weeks missed after the concussions. Trends in the rates of concussions across the seasons remain largely stable, despite increased scrutiny over concussions in the sport.

Assessing Diversity, Equity, and Inclusion in Patient-Facing Websites in Neurosurgical Departments in the United States.

BACKGROUND: Patient-facing websites serve as essential platforms for disseminating information, engaging with patients, and increasing access to neurosurgical resources and services. Diversity, Equity, and Inclusion are at the forefront of issues facing the field of neurosurgery, especially concerning race and gender disparities in regards to providers in the field. METHODS: Data were collected in regards to the race and gender of patients and providers displayed on the neurosurgery department's patient-facing website in addition to accommodations for disabilities, decreased ability to pay, and language. RESULTS: Patients who were White were depicted more commonly than those of color (69% vs. 31%, P < 0.00001). White patients also were over-represented when compared with the average demographics of the communities in which the hospitals served (P = 0.03846). Neurosurgical providers who were White outnumbered those of color (70% vs. 30%, P < 0.00001). The racial depiction of providers was comparable with racial disparities currently observed in neurosurgery (P = 0.59612). Female neurosurgery providers were seen less than male providers on patient-facing websites (P < 0.00001) but were seen more commonly on patient-facing websites than the percentage of practicing neurosurgeons they currently comprise (28% vs. 8%, P < 0.00001). CONCLUSIONS: The results of this study suggest that patient-facing websites of neurosurgical departments are an area of improvement in regards to Diversity, Equity, and Inclusion in the field of neurosurgery. Disparities are noted in regards to the racial depiction of patients and further call to attention racial and gender disparities in the field of neurosurgery.

Endoscopic Endonasal Transsphenoidal Surgery for the Resection of Pituitary Adenomas: A Prime Candidate for a Shortened Length of Stay Enhanced Recovery after Surgery Protocol? A Systematic Review.

BACKGROUND: Enhanced Recovery After Surgery (ERAS) is a perioperative model of care aimed at optimizing postoperative rehabilitation and reducing hospital length of stay (LOS). Decreasing LOS avoids hospital-acquired complications, reduces cost of care, and improves patient satisfaction. Given the lack of ERAS protocols for endoscopic endonasal transsphenoidal surgery (EETS) resection of pituitary adenomas, a systematic review of EETS was performed to compile patient outcomes and analyze factors that may lead to increased LOS, reoperation, and readmission rates with the intention to contribute to the development of a successful ERAS protocol for EETS. METHODS: The authors performed a Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines-based systematic review of the literature. Information was extracted regarding patient LOS, surgery complications, and readmission/reoperation rates. Pearson's correlations to LOS and reoperation/readmission rates were performed with variables normalized to the number of participants. Statistical significance was set at P value <0.05. RESULTS: Fourteen studies were included, consisting of 2083 patients. The most common complications were cerebrospinal fluid leaks (37%) and postoperative diabetes insipidus (DI) (9%). Transient DI was significantly correlated with shorter LOS. Functional pituitary adenomas were significantly correlated with lower readmission rates while nonfunctional pituitary adenomas were correlated with higher readmission rates. No other factor was found to be significantly correlated with a change in LOS or reoperation rate. CONCLUSIONS: EETS may be an ideal candidate for the development of ERAS cranial protocols. While our data largely supports the safe implementation of shortened LOS protocols in EETS, our findings highlight the importance of transient DI and nonfunctional pituitary adenomas management when formulating ERAS protocols.

Excelencia en Neurocirugía: María Cristina García-Sancho, the First Latina Neurosurgeon in the World.

BACKGROUND: Neurosurgery is a specialty that has been dominated by males. Although there has been an increase in the number of women in the field, it is not yet close to being equal. Some noteworthy women who have carved the path for other women to follow in their footsteps include Drs. Sofía Ionescu and Diana Beck, the first and second female neurosurgeons worldwide, respectively. However, there are limited publications on Dr. María Cristina García-Sancho, the first Latina neurosurgeon. METHODS: The purpose of this review was to illuminate the neurosurgical community on the life of Dr. García-Sancho. A thorough literature was performed on medical and non-medical publications that were either authored by Dr. García-Sancho or mentioned her directly. RESULTS: Dr. García-Sancho earned her medical degree at the School of Medicine of the National Autonomous University of Mexico under the guidance of Dr. Clemente Robles, who founded Mexico's first neurosurgical department. Her training took her worldwide. CONCLUSIONS: Her expertise allowed her to pioneer a revolutionary advancement known as the one-step bilateral cordotomy. Her perseverance led her to becoming the head of the Department of Neurosurgery at the National Cancer Institute of Mexico and co-found the Mexican Society of Neurological Surgery, where she served on the board of directors. This review aims to advocate for an equitable environment in the field of neurosurgery with Dr. García-Sancho's story.

Can Publicly Available Artificial Intelligence Successfully Identify Current Procedural Terminology Codes for Common Procedures in Neurosurgery?

OBJECTIVE: Coding for neurosurgical procedures is a complex process that is dynamically changing year to year, through the annual introduction and removal of codes and modifiers. The authors hoped to elucidate if publicly available artificial intelligence (AI) could offer solutions for neurosurgeons with regard to coding. METHODS: Multiple publicly available AI platforms were asked to provide Current Procedural Terminology (CPT) codes and Revenue Value Units (RVU) values for common neurosurgical procedures of the brain and spine with a given indication for the procedure. The responses of platforms were recorded and compared to the currently valid CPT codes used for the procedure and the amount of RVUs that would be gained. RESULTS: Six platforms and Google were asked for the appropriate CPT codes for 10 endovascular, spinal, and cranial procedures each. The highest performing platforms were as follows: Perplexity.AI identified 70% of endovascular, BingAI identified 55% of spinal, and ChatGPT 4.0 with Bing identified 75% of cranial CPT codes. With regard to RVUs, the top performer gained 78% of endovascular, 42% of spinal, and 70% of cranial possible RVUs. With regard to accuracy, AI platforms on average outperformed Google (45% vs. 25%, P = 0.04236). CONCLUSIONS: The ability of publicly available AIs to successfully code for neurosurgical procedures holds great promise in the future. Future development of AI should focus on improving accuracy with regard to CPT codes and providing supporting documentation for its decisions. Improvement on the existing capabilities of AI platforms can allow for increased operational efficiency and cost savings for practices.

Sonolucent Cranial Implants: A Window into the Future of Management of Neurosurgical Patients? A Systematic Review and Cost Analysis.

BACKGROUND: Computeed tomography (CT) is a cornerstone of the identification and management of acute changes in neurosurgery patients. In addition to the monetary expense of CT scans, further costs are incurred due to the time of patient transport and radiation exposure. Ultrasounds (USs)offer a safe, inexpensive, and bedside alternative to CT but obstacles remain due to decreased penetrance in the adult skull. Sonolucent Cranial Implants (SCIs) offer a window for USs to view intracranial architectures. METHODS: The authors performed a PRISMA guidelines-based systematic review of the literature. Information was extracted from included articles in regards to illness pathology, US imaging feasibility, comparison to standard imaging, infections, and revisions. Costs were collected in regards to price of implant and follow-up imaging. RESULTS: A total of 226 articles resulted, of which 5 were included in the study. Ninety non-duplicate patients who received SCIs were analyzed. The pathologies of included patients is as follows: 51 patients were after extracranial-intracranial bypass, 37 after ventriculoperitoneal shunt placement for hydrocephalus, 1 after tumor resection, and 1 after cranioplasty following decompressive hemicraniectomy. All studies noted feasibility of US and comparability to standard imaging following SCI placement. Follow-up imaging with trans-sonolucent cranial implant ultrasound was estimated to save up to $4,000 per patient depending on the procedure. CONCLUSIONS: Initial studies suggest that US imaging through SCIs is a safe and efficacious alternative to CT imaging in neurosurgical patients. Cost analysis suggests that SCI and subsequent US can offer a cost savings compared with current treatment.

Oncolytic Virotherapy for High-Grade Glioma and Current Evidence and Factors to Consider for Incorporation into Clinical Practice.

Brain tumor incidence is on the rise, and glioblastoma comprises the majority of primary tumors. Despite maximal safe resection and adjuvant chemoradiation, median survival for high-grade glioma remains poor. For this reason, it is important to develop and incorporate new treatment strategies. Oncolytic virotherapy has emerged as a viable new therapeutic entity to fill this gap. Preclinical research has shown oncolytic virotherapy to be a robust and effective treatment option for brain tumors, and clinical trials for both adult and pediatric high-grade glioma are underway. The unique and protected environment of the nervous system, in part due to the blood-brain barrier, prevents traditional systemic therapies from achieving adequate penetration. Brain tumors are also heterogenous in nature due to their diverse molecular profiles, further complicating systemic treatment efforts. Oncolytic viruses may serve to fill this gap in brain tumor treatment given their amenability to genetic modification and ability to target unique tumor epitopes. In addition, direct inoculation of the oncolytic virus agent to the tumor bed following surgical resection absolves risk of systemic side effects and ensures adequate delivery. As virotherapy transitions from bench to bedside, it is important to discuss factors to make this transition more seamless. In this article, we describe the current clinical evidence as it pertains to oncolytic virotherapy and the treatment of brain tumors as well as factors to consider for its incorporation into neurosurgical workflow.

The Evolution of Laser-Induced Thermal Therapy for the Treatment of Gliomas.

Laser-induced thermal therapy (LITT) has evolved over the past two decades to treat a number of intracranial pathologies. Although it initially emerged as a salvage treatment of surgically inoperable tumors or recurrent lesions that had exhausted more conventional treatments, it is now being used as a primary, first-line treatment in certain instances with outcomes comparable to traditional surgical resection. The authors discuss the evolution of LITT in the treatment of gliomas and future directions, which may further enhance the efficacy of this procedure.

Newly Diagnosed Adult Basal Ganglia Gliomas Treated With Laser Interstitial Thermal Therapy: A Comparative Cohort With Needle Biopsy.

BACKGROUND: Few cytoreductive surgical tools are available for newly diagnosed basal ganglia gliomas. Current reports showed high associated morbidity and mortality. Given their deep localization, laser interstitial thermal therapy (LITT) is still a rare indication. Moreover, few reports account for which of the available options have better outcomes. OBJECTIVE: To retrospectively analyze our experience with LITT and compare its safety, feasibility, and efficacy with needle biopsy for the management of adult basal ganglia gliomas. METHODS: Twenty-two patients with gliomas from the midline (e.g. thalamus and lenticular nucleus) managed with either LITT/biopsy or needle biopsy from 2015 to 2021 were included. Records regarding location, diagnosis, Karnofsky Performance Score, length of hospital stay, preoperative lesion and ablation volume, perioperative complications, and data of adjuvant treatment were collected. Overall survival was evaluated with Kaplan-Meier analysis. RESULTS: Seven patients had LITT, and 15 underwent biopsy. The overall mean age was 60.9 years (25-82 years). The average tumor volume in the former was 16.99 cm 3 and 17.65 cm 3 in the latter. No postsurgical complications were found in the LITT group, and 1 patient had a postsurgical hemorrhage after biopsy. The mean overall survival was 20.28 ± 9.63 months in the LITT group, which was greater but not statistically significant than in the biopsy group (13.85 ± 4.48 months; P = .78). CONCLUSION: Our results show that laser ablation may be both feasible and safe in adult basal ganglia gliomas. Given the lack of safe cytoreductive treatment options, LITT should be considered as a valid choice for these patients.

Safety of the utilization of telemedicine for brain tumor neurosurgery follow-up.

Background: There is a need to evaluate the outcomes of patients who underwent brain tumor surgery with subsequent telemedicine or in-person follow-up during the COVID-19 pandemic. Methods: We retrospectively included all patients who underwent surgery for brain tumor resection by a single neurosurgeon at our Institution from the beginning of the COVID-19 pandemic restrictions (March 2020) to August 2021. Outcomes were assessed by stratifying the patients using their preference for follow-up method (telemedicine or in-person). Results: Three-hundred and eighteen (318) brain tumor patients who were included. The follow-up method of choice was telemedicine (TM) in 185 patients (58.17%), and in-person (IP) consults in 133 patients. We found that patients followed by TM lived significantly farther, with a median of 36.34 miles, compared to a median of 22.23 miles in the IP cohort (P = .0025). We found no statistical difference between the TM and the IP group, when comparing visits to the emergency department (ED) within 30 days after surgery (7.3% vs 6.01%, P = .72). Readmission rates, wound infections, and 30-day mortality were similar in both cohorts. These findings were also consistent after matching cohorts using a propensity score. The percentage of telemedicine follow-up consults was higher in the first semester (73.17%) of the COVID-19 pandemic, compared to the second (46.21%), and third semesters (47.86%). Conclusions: Telehealth follow-up alternatives may be safely offered to patients after brain tumor surgery, thereby reducing patient burden in those with longer distances to the hospital or special situations as the COVID-19 pandemic.

Stereotactic radiosurgery for cerebellopontine meningiomas: a systematic review and meta-analysis.

OBJECTIVE: To (1) measure surgical outcomes associated with stereotactic radiosurgery treatment of cerebellopontine angle meningiomas, and (2) determine if differences in radiation dosages or preoperative tumor volumes affect surgical outcomes. METHODS: A systematic search was performed on the PubMed, Medline, Embase and Cochrane Library databases searching for patients under stereotactic radiosurgery for meningiomas of the cerebellopontine angle. After data extraction and Newcastle-Ottawa scale quality assessment, meta-analysis of the data was performed with Review Manager 3.4.5. RESULTS: In total, 6 studies including 406 patients were included. Postprocedure, patients had minimal cranial nerve complications while having an overall tumor control rate of 95.6%. Complications were minimal with facial nerve deficits occurring in 2.4%, sensation deficits of the trigeminal nerve in 4.0%, hearing loss in 5.9%, hydrocephalus in 2.0% and diplopia in 2.6% of all patients. Individuals with tumors extending into the internal auditory canal extension did not have significantly increases in hearing loss. There was a higher likelihood of tumor regression on postprocedure imaging in studies with a median prescription dose of >13 Gy (RR 1.27 [95% CI 1.04-1.56, p = 0.0225). There was no evidence of publication bias detected. CONCLUSIONS: Radiosurgery is an effective modality for offering excellent tumor control of CPA meningiomas while allowing for only minimal complications postprocedure. A higher prescription dose may achieve higher tumor regression at follow up. Future studies should aim at establishing and optimizing accurate dosimetric guidelines for this patient population.

Using machine learning to evaluate large-scale brain networks in patients with brain tumors: Traditional and non-traditional eloquent areas.

Background: Large-scale brain networks and higher cognitive functions are frequently altered in neuro-oncology patients, but comprehensive non-invasive brain mapping is difficult to achieve in the clinical setting. The objective of our study is to evaluate traditional and non-traditional eloquent areas in brain tumor patients using a machine-learning platform. Methods: We retrospectively included patients who underwent surgery for brain tumor resection at our Institution. Preoperative MRI with T1-weighted and DTI sequences were uploaded into the Quicktome platform. We categorized the integrity of nine large-scale brain networks: language, sensorimotor, visual, ventral attention, central executive, default mode, dorsal attention, salience and limbic. Network integrity was correlated with preoperative clinical data. Results: One-hundred patients were included in the study. The most affected network was the central executive network (49%), followed by the default mode network (43%) and dorsal attention network (32%). Patients with preoperative deficits showed a significantly higher number of altered networks before the surgery (3.42 vs 2.19, P < .001), compared to patients without deficits. Furthermore, we found that patients without neurologic deficits had an average 2.19 networks affected and 1.51 networks at-risk, with most of them being related to non-traditional eloquent areas (P < .001). Conclusion: Our results show that large-scale brain networks are frequently affected in patients with brain tumors, even when presenting without evident neurologic deficits. In our study, the most commonly affected brain networks were related to non-traditional eloquent areas. Integrating non-invasive brain mapping machine-learning techniques into the clinical setting may help elucidate how to preserve higher-order cognitive functions associated with those networks.

Traumatic brain injury and subsequent brain tumor development: a systematic review of the literature.

The role of prior head trauma in stimulating brain tumor development has been previously described in the literature but continues to be debated. The goal of this study was to conduct a systematic review interrogating the contemporary literature to delineate any possible relationship between traumatic brain injury and brain tumor development. A systematic review exploring development of post-TBI brain tumor was conducted by searching electronic databases. Abstracts from articles were read and selected for full-text review according to criteria previously established in the scientific literature. Relevant full-text articles were divided into case reports and single-arm studies and epidemiological studies. Of 1070 resultant articles, 18 case reports and single-arm studies (level of evidence of IV and V) with 45 patients were included. The most common cause of TBI was traffic accidents. The average period between TBI and subsequent tumor diagnosis was 12.8 years. Meningiomas represented the largest share of tumors, followed by gliomas. Most post-TBI brain tumors developed in the frontal and temporal lobes. Fifteen epidemiological studies were also interrogated from a variety of countries (level of evidence of III). Case-control studies were more common than cohort studies. There were 9 of 15 studies proposed a possible relationship between history of head trauma and development of brain tumor. The relationship between head trauma and neoplastic growth continues to be heavily debated. There are certainly case reports and epidemiological studies in the literature that suggest a correlational relationship between the two. However, there is no concrete evidence of a causal relationship between TBI and brain tumors. More research is needed to definitively delineate the extent of any such relationship.