Natural and Artificial Intelligence in Neurosurgery: A Systematic Review

Development and validation of a predictive machine learning model for postoperative long-term diabetes insipidus following transsphenoidal surgery for sellar lesions

OBJECTIVE

Diabetes Insipidus (DI) is a common complication that occurs following transsphenoidal surgery for sellar lesions. DI is usually transient but can be permanent in select patients. Prior studies have described preoperative risk factors for developing postoperative DI. However, no predictive risk score has been created to risk stratify these patients.

METHODS

A single-center retrospective review from 2017 - 2022 was performed, reviewing all patients who underwent transsphenoidal surgery for resection of a sellar lesion. Longterm DI was defined as a patient who met DI criteria for at least six months and required desmopressin therapy. Baseline patient, operative, and radiographic characteristics were obtained. A machine learning method (Risk-SLIM) was utilized to create a risk stratification score to identify patients at high risk for DI.

RESULTS

In total, 252 patients were identified to have sellar lesions treated with transsphenoidal surgery. Of these, 27 (10.7 %) patients developed long-term DI and required desmopressin therapy. The DI after Transsphenoidal Surgery score (DITSS) was created with an area under the curve of 0.81 and a calibration error (CAL) error of 7.3 %. Predicative factors were tumor pathology, Tumor size, patient age, and endoscopic approach. The probability of developing DI requiring long-term desmopressin therapy ranged from < 1 % for a score of 0 and > 95 % for a score of 10 CONCLUSIONS: The DITSS model is a concise and accurate tool to assist in clinical decision-making for risk stratifying which patients undergoing transsphenoidal surgery for sellar lesions may go on to develop DI.

Deep learning in neurosurgery: a systematic literature review with a structured analysis of applications across subspecialties

Objective

This study systematically reviewed deep learning (DL) applications in neurosurgical practice to provide a comprehensive understanding of DL in neurosurgery. The review process included a systematic overview of recent developments in DL technologies, an examination of the existing literature on their applications in neurosurgery, and insights into the future of neurosurgery. The study also summarized the most widely used DL algorithms, their specific applications in neurosurgical practice, their limitations, and future directions.

Materials and methods

An advanced search using medical subject heading terms was conducted in Medline (via PubMed), Scopus, and Embase databases restricted to articles published in English. Two independent neurosurgically experienced reviewers screened selected articles.

Results

A total of 456 articles were initially retrieved. After screening, 162 were found eligible and included in the study. Reference lists of all 162 articles were checked, and 19 additional articles were found eligible and included in the study. The 181 included articles were divided into 6 categories according to the subspecialties: general neurosurgery (n = 64), neuro-oncology (n = 49), functional neurosurgery (n = 32), vascular neurosurgery (n = 17), neurotrauma (n = 9), and spine and peripheral nerve (n = 10). The leading procedures in which DL algorithms were most commonly used were deep brain stimulation and subthalamic and thalamic nuclei localization (n = 24) in the functional neurosurgery group; segmentation, identification, classification, and diagnosis of brain tumors (n = 29) in the neuro-oncology group; and neuronavigation and image-guided neurosurgery (n = 13) in the general neurosurgery group. Apart from various video and image datasets, computed tomography, magnetic resonance imaging, and ultrasonography were the most frequently used datasets to train DL algorithms in all groups overall (n = 79). Although there were few studies involving DL applications in neurosurgery in 2016, research interest began to increase in 2019 and has continued to grow in the 2020s.

Conclusion

DL algorithms can enhance neurosurgical practice by improving surgical workflows, real-time monitoring, diagnostic accuracy, outcome prediction, volumetric assessment, and neurosurgical education. However, their integration into neurosurgical practice involves challenges and limitations. Future studies should focus on refining DL models with a wide variety of datasets, developing effective implementation techniques, and assessing their affect on time and cost efficiency.

Predictive Modeling of Nonfunctioning Giant Pituitary Neuroendocrine Tumor Resection: A Multi-Planar Perspective

BACKGROUND

Giant pituitary neuroendocrine tumors (GPitNETs) are challenging tumors with low rates of gross total resection (GTR) and high morbidity. Previously reported machine learning (ML) models for prediction of pituitary neuroendocrine tumor extent of resection (EOR) using preoperative imaging included a heterogenous dataset of functional and nonfunctional pituitary neuroendocrine tumors of various sizes leading to variability in results.

METHODS

A retrospective study of 100 large nonfunctioning GPitNETs (≥3 cm diameter, >10 cm³ volume) was conducted to develop predictive models for GTR or EOR based on 5 variables: tumor diameter, shape, revised Knosp grade, and modified Hardy classifications for sellar and extrasellar invasion. Model performance was assessed using receiver operating characteristic-area under the curve (AUC) and confusion matrix metrics.

RESULTS

The median preoperative tumor volume was 17.35 cm3 (interquartile range: 12.4-27.0). The median EOR was 97.6% (interquartile range: 84.9-100), and GTR was achieved in 49% of patients. The most predictive variables were the modified Hardy classification for extrasellar extension and Knosp grade (AUC of 0.771 and 0.713, respectively). Among the constructed ML models, the extreme gradient boost algorithm had the highest predictive capability, with an internal validation AUC of 0.86, while the external validation sensitivity, specificity, positive, and negative predictive values were 84%, 77%, 78%, and 82%, respectively.

CONCLUSIONS

Utilizing preoperative imaging parameters in a 3-dimensional manner proves highly valuable in predicting the EOR for nonfunctioning GPitNETs. These predictions can be easily calculated using an online open-access application: http://emoryskullbase.shinyapps.io/giant_pituitary_adenoma_resection/.

Applications of Artificial Intelligence in Neurosurgery for Improving Outcomes Through Diagnostics, Predictive Tools, and Resident Education

BACKGROUND

Artificial intelligence (AI) has become an increasingly prominent tool in the field of neurosurgery, revolutionizing various aspects of patient care and surgical practices. AI-powered systems can provide real-time feedback to surgeons, enhancing precision and reducing the risk of complications during surgical procedures. The objective of this study is to review the role of AI in training neurosurgical residents, improving accuracy during surgery, and reducing complications.

METHODS

The literature search method involved searching PubMed using relevant keywords to identify English literature publications, including full texts, and concerning human subject matter from its inception until May 2024, initially generating 247,747 results. Articles were then screened for topic relevancy by abstract contents. Further articles were retrieved from the sources cited by the initially reviewed articles. A comprehensive review was then performed on various studies, including observational studies, case-control studies, cohort studies, clinical trials, meta-analyses, and reviews by 4 reviewers individually and then collectively.

RESULTS

Studies on AI in neurosurgery reach more than 4000 produced over a decade alone. The majority of studies regarding clinical diagnosis, risk prediction, and intraoperative guidance remain retrospective in nature. In its current form, AI-based paradigm performed inferiorly to neurosurgery residents in test taking.

CONCLUSIONS

AI has potential for broad applications in neurosurgery from use as a diagnostic, predictive, intraoperative, or educational tool. Further research is warranted for prospective use of AI-based technology for delivery of neurosurgical care.

Neurosurgical Breakthroughs of the Last 50 Years: A Historical Journey Through the Past and Present

This article presented the author's historical perspective on 25 of the most significant neurosurgical breakthrough events of the last 50 years. These breakthroughs have advanced neurosurgical patient care and management. They have improved the management of aneurysms, arteriovenous malformations, tumors, stroke, traumatic brain injury, movement disorders, epilepsy, hydrocephalus, and spine pathologies. Neurosurgery has evolved through research, innovation, and technology. Several neurosurgical breakthroughs were achieved using neuroendoscopy, neuronavigation, radiosurgery, endovascular techniques, and refinements in computer technology. With these breakthroughs, neurosurgery did not change; it just progressed. Neurosurgery should continue its progress through research to obtain new knowledge for the benefit of our patients.

Comparison of surgical approaches to the hippocampal formation with artificial intelligence

The relatively complex functional anatomy of the mediobasal temporal region makes surgical approaches to this area challenging. Several studies describe various surgical approaches, along with their combinations and modifications, to reach lesions of this region. Some of these surgical approaches have been compared using artificial intelligence-based approaches that can be predicted, classified, and analyzed for complex data. Several surgical approaches, such as anterior transsylvian, trans-superior temporal sulcus, trans-middle temporal gyrus, subtemporal-transparahippocampal, presigmoid-retrolabyrinthine, supratentorial-infraoccipital, and paramedian supracerebellar-transtentorial, were selected for comparison. Magnetic resonance images (MRIs) were taken according to the criteria specified by the Radiology Department. With an open-source software tool, volumetric data from cranial MRIs were segmented and anatomical structures in the main regions were reconstructed. The Q-learning algorithm was used to find pathways similar to these standard surgical pathways. The Q-learning scores among the selected pathways are as follows: anterior transsylvian (Q_A) = 31.01, trans-superior temporal sulcus (Q_B) = 25.00, trans-middle temporal gyrus (Q_C) = 28.92, subtemporal-transparahippocampal (Q_D) = 23.51, presigmoid- retrolabyrinthine (Q_E) = 27.54, supratentorial-infraoccipital (Q_F) = 27.2, and paramedian supracerebellar-transtentorial (Q _G) = 21.04. The Q-value score for the supracerebellar transtentorial approach was the highest among the examined approaches and therefore optimal. A difference was also found between the total risk score of all points with pathways drawn by clinicians and the total risk scores of the pathways formed and followed by Q-learning. Artificial intelligence-based approaches may significantly contribute to the success of the surgical approaches examined. Furthermore, artificial intelligence can contribute to clinical outcomes in both preoperative surgical planning and intraoperative technical equipment-assisted neurosurgery. However, further studies with more detailed data are needed for more sensitive results.

Ethical Concerns of AI in Neurosurgery: A Systematic Review

BACKGROUND

The relentless integration of Artificial Intelligence (AI) into neurosurgery necessitates a meticulous exploration of the associated ethical concerns. This systematic review focuses on synthesizing empirical studies, reviews, and opinion pieces from the past decade, offering a nuanced understanding of the evolving intersection between AI and neurosurgical ethics.

MATERIALS AND METHODS

Following PRISMA guidelines, a systematic review was conducted to identify studies addressing AI in neurosurgery, emphasizing ethical dimensions. The search strategy employed keywords related to AI, neurosurgery, and ethics. Inclusion criteria encompassed empirical studies, reviews, and ethical analyses published in the last decade, with English language restriction. Quality assessment using Joanna Briggs Institute tools ensured methodological rigor.

RESULTS

Eight key studies were identified, each contributing unique insights to the ethical considerations associated with AI in neurosurgery. Findings highlighted limitations of AI technologies, challenges in data bias, transparency, and legal responsibilities. The studies emphasized the need for responsible AI systems, regulatory oversight, and transparent decision-making in neurosurgical practices.

CONCLUSIONS

The synthesis of findings underscores the complexity of ethical considerations in the integration of AI in neurosurgery. Transparent and responsible AI use, regulatory oversight, and mitigation of biases emerged as recurring themes. The review calls for the establishment of comprehensive ethical guidelines to ensure safe and equitable AI integration into neurosurgical practices. Ongoing research, educational initiatives, and a culture of responsible innovation are crucial for navigating the evolving landscape of AI-driven advancements in neurosurgery.

Managing thrombosis risk in flow diversion: A review of antiplatelet approaches

Flow diversion is a transformative approach in neurointerventional surgery for intracranial aneurysms that relies heavily on effective antiplatelet therapy. The ideal approach, including the timing of treatment, the use of dual antiplatelet therapy (DAPT), and the number of flow-diverter devices to use, remains unknown. DAPT, which combines aspirin with a thienopyridine like clopidogrel, prasugrel, or ticagrelor, is the standard regimen, balancing thromboembolic protection and hemorrhagic risk. The variable response to clopidogrel, influenced by genetic polymorphisms, necessitates personalized treatment strategies. Alternatives like prasugrel and ticagrelor provide superior efficacy in specific scenarios but require careful consideration of bleeding risks and costs. Platelet function testing plays a critical role in tailoring antiplatelet regimens for patients undergoing flow diversion for intracranial aneurysms. Special considerations were made for ruptured aneurysms, and the implications of the extensive metallic surface of flow diverters on platelet activation were noted. Emerging technologies such as drug-eluting flow diverters and reversal agents for P2Y12 inhibitors suggest a potential shift toward more refined antiplatelet strategies in the future. Personalized medication that is compatible with the stent structure and metal is essential for optimizing patient outcomes in cerebral flow diversion procedures. Ongoing research and multidisciplinary collaboration will be key in refining these strategies and enhancing the safety and efficacy of neurointerventional treatments.

Evaluating Large Language Model-Supported Instructions for Medication Use: First Steps Toward a Comprehensive Model

Objective

To assess the support of large language models (LLMs) in generating clearer and more personalized medication instructions to enhance e-prescription.

Patients and Methods

We established patient-centered guidelines for adequate, acceptable, and personalized directions to enhance e-prescription. A dataset comprising 104 outpatient scenarios, with an array of medications, administration routes, and patient conditions, was developed following the Brazilian national e-prescribing standard. Three prompts were submitted to a closed-source LLM. The first prompt involved a generic command, the second one was calibrated for content enhancement and personalization, and the third one requested bias mitigation. The third prompt was submitted to an open-source LLM. Outputs were assessed using automated metrics and human evaluation. We conducted the study between March 1, 2024 and September 10, 2024.

Results

Adequacy scores of our closed-source LLM's output showed the third prompt outperforming the first and second one. Full and partial acceptability was achieved in 94.3% of texts with the third prompt. Personalization was rated highly, especially with the second and third prompts. The 2 LLMs showed similar adequacy results. Lack of scientific evidence and factual errors were infrequent and unrelated to a particular prompt or LLM. The frequency of hallucinations was different for each LLM and concerned prescriptions issued upon symptom manifestation and medications requiring dosage adjustment or involving intermittent use. Gender bias was found in our closed-source LLM's output for the first and second prompts, with the third one being bias-free. The second LLM's output was bias-free.

Conclusion

This study demonstrates the potential of LLM-supported generation to produce prescription directions and improve communication between health professionals and patients within the e-prescribing system.

The Future of Sustainable Neurosurgery: Is a Moonshot Plan for Artificial Intelligence and Robot-Assisted Surgery Possible in Japan?

Japanese neurosurgery faces challenges such as a declining number of neurosurgeons and their concentration in urban areas. Particularly in rural areas, access to neurosurgical care for patients with conditions, such as stroke, is limited, raising concerns about the collapse of regional healthcare. Robot-assisted surgical technologies have advanced in recent years, contributing to the improved precision and safety of deep brain surgery. This study proposes the "Artificial Intelligence (AI) and Robot-Assisted Surgery Moonshot Plan" for Japan, comprising 5 pillars: 1) establishment of regional medical centers, 2) development of remote surgery systems, 3) enhancement of robotic-assisted surgery training programs, 4) integration of AI technologies, and 5) promotion of industry-academia-government collaboration. In addition, strengthening the approach to spinal surgery is expected to revitalize regional medical centers, optimize the number of neurosurgeons, improve surgical skills, and promote minimally invasive surgery. This study analyzed the current status and challenges of Japanese neurosurgery through a literature review and statistical analysis. AI is used in various aspects of neurosurgery, including diagnostic support, surgical planning and navigation, treatment outcome prediction, intraoperative monitoring, robot-assisted surgery, and rehabilitation. However, challenges, such as data bias, ethical issues, costs, and regulations, remain. In Japan, issues such as the uneven distribution and decline of neurosurgeons, collapse of regional healthcare, and increase in the number of patients with spinal disorders due to aging have been highlighted. The "AI and Robot-Assisted Surgery Moonshot Plan" serves as a guide to overcome the challenges of neurosurgery in Japan and establish a sustainable medical system.

Prediction of 6-Mo Poststroke Spasticity in Patients With Acute First-Ever Stroke by Machine Learning

OBJECTIVE

Poststroke spasticity reduces arm function and leads to low levels of independence. This study suggested applying machine learning from routinely available data to support the clinical management of poststroke spasticity.

DESIGN

One hundred seventy-two patients with acute first-ever stroke were included in this prospective cohort study. Twenty clinical information and rehabilitation assessments were obtained to train various machine learning algorithms for predicting 6-mo poststroke spasticity defined by a modified Ashworth scale score ≥1. Factors significantly relevant were also defined.

RESULTS

The study results indicated that multivariate adaptive regression spline (area under the curve value: 0.916; 95% confidence interval: 0.906-0.923), adaptive boosting (area under the curve: 0.962; 95% confidence interval: 0.952-0.973), random forest (area under the curve: 0.975; 95% confidence interval: 0.968-0.981), support vector machine (area under the curve: 0.980; 95% confidence interval: 0.970-0.989), and outperformed the traditional logistic model (area under the curve: 0.897; 95% confidence interval: 0.884-0.910) ( P < 0.05). Among all of the algorithms, the random forest and support vector machine models outperformed the others ( P < 0.05). Fugl-Meyer Assessment score, days in hospital, age, stroke location, and paretic side were the most important features.

CONCLUSIONS

These findings suggest that machine learning algorithms can help augment clinical decision-making processes for the assessment of poststroke spasticity occurrence, which may enhance the efficacy of management for patients with poststroke spasticity in the future.

The Efficacy of a Food Supplement in the Treatment of Tinnitus with Comorbid Headache: A Statistical and Machine Learning Analysis with a Literature Review

INTRODUCTION

Tinnitus, the perception of sound without an external auditory stimulus, affects approximately 10-15% of the population and is often associated with significant comorbidities such as headaches. These conditions can severely impact the quality of life. The aim of this study was to evaluate the efficacy of a food supplement in reducing the symptoms of both tinnitus and headache in patients experiencing these conditions concurrently.

METHODS

This prospective study included 32 patients (21 males and 11 females) aged between 23 and 68 years (mean age 49.38 years) who were experiencing both tinnitus and headache. The study assessed the impact of a food supplement on tinnitus and headache over a 90-day treatment period using three main instruments: the Tinnitus Handicap Inventory (THI), the Headache Impact Test (HIT-6), and a Visual Analog Scale (VAS) for discomfort. Statistical analyses, including paired t tests, were conducted to compare pre- and posttreatment scores. In the same dataset, Ridge Regression, a linear regression model with L2 regularization, was used to predict posttreatment scores (THI90, HIT90, VAS90).

RESULTS

The results indicated a statistically significant reduction in all three measures after 90 days of treatment. The mean THI score decreased from 29.81 to 27.06 (p = 0.011), the mean HIT-6 score decreased from 50.41 to 48.75 (p = 0.019), and the mean VAS score for discomfort decreased from 7.63 to 7.13 (p = 0.033). The optimal Ridge Regression model was found with an "alpha" value of approximately 3.73. The performance metrics on the test set were as follows: Mean Squared Error (MSE) of 13.91 and an R-squared score of 0.61, indicating that the model explains approximately 61% of the variance in the posttreatment scores. These results indicate that pretreatment scores are significant predictors of posttreatment outcomes, and gender plays a notable role in predicting HIT and VAS scores posttreatment.

CONCLUSION

This study demonstrates that a food supplement is effective in reducing the symptoms of tinnitus and headache in patients suffering from both conditions. The significant improvements in THI, HIT-6, and VAS scores indicate a positive impact on patient quality of life. Further research with larger sample sizes and more detailed subgroup analyses is recommended to fully understand the differential impacts of treatment across various demographics.

Bibliometric Analysis of Machine Learning Applications in Ischemia Research

OBJECTIVE

The objective of this study is to conduct a comprehensive bibliometric analysis to elucidate the landscape of machine learning applications in ischemia research.

METHODS

The analysis can be divided in three sections: part 1 scrutinizes articles and reviews with "ischemia" in their titles, while part 2 further narrows the focus to publications containing both "ischemia" and "machine learning" in their titles. Additionally, part 3 delves into the examination of the top 50 most cited papers, exploring their thematic focus and co-word dynamics.

RESULTS

The findings reveal a significant increase in publications over the years, with notable trends identified through detailed analysis. The growth in publication counts over time, the leading contributors, institutions, geographical distribution of research output and journals are numerically presented for part 1 and part 2. For the top 50 most cited papers the dynamics of co-words, which offer a nuanced understanding of thematic trends and emerging concepts, are presented. Based on the number of citations the top 10 authors were selected, and later for each, total number of publications, h-index, g-index and m-index are provided. Additionally, figures depicting the co-authorship network among authors, departments, and countries involved in the top 50 cited papers may enrich our comprehension of collaborative networks in ischemia research.

CONCLUSION

This comprehensive bibliometric analysis provides valuable insights into the evolving landscape of machine learning applications in ischemia research.

Recent Outcomes and Challenges of Artificial Intelligence, Machine Learning, and Deep Learning in Neurosurgery

Neurosurgeons receive extensive technical training, which equips them with the knowledge and skills to specialise in various fields and manage the massive amounts of information and decision-making required throughout the various stages of neurosurgery, including preoperative, intraoperative, and postoperative care and recovery. Over the past few years, artificial intelligence (AI) has become more useful in neurosurgery. AI has the potential to improve patient outcomes by augmenting the capabilities of neurosurgeons and ultimately improving diagnostic and prognostic outcomes as well as decision-making during surgical procedures. By incorporating AI into both interventional and non-interventional therapies, neurosurgeons may provide the best care for their patients. AI, machine learning (ML), and deep learning (DL) have made significant progress in the field of neurosurgery. These cutting-edge methods have enhanced patient outcomes, reduced complications, and improved surgical planning.

Ethical Incorporation of Artificial Intelligence into Neurosurgery: A Generative Pretrained Transformer Chatbot-Based, Human-Modified Approach

INTRODUCTION

Artificial intelligence (AI) has become increasingly used in neurosurgery. Generative pretrained transformers (GPTs) have been of particular interest. However, ethical concerns regarding the incorporation of AI into the field remain underexplored. We delineate key ethical considerations using a novel GPT-based, human-modified approach, synthesize the most common considerations, and present an ethical framework for the involvement of AI in neurosurgery.

METHODS

GPT-4, ChatGPT, Bing Chat/Copilot, You, Perplexity.ai, and Google Bard were queried with the prompt "How can artificial intelligence be ethically incorporated into neurosurgery?". Then, a layered GPT-based thematic analysis was performed. The authors synthesized the results into considerations for the ethical incorporation of AI into neurosurgery. Separate Pareto analyses with 20% threshold and 10% threshold were conducted to determine salient themes. The authors refined these salient themes.

RESULTS

Twelve key ethical considerations focusing on stakeholders, clinical implementation, and governance were identified. Refinement of the Pareto analysis of the top 20% most salient themes in the aggregated GPT outputs yielded 10 key considerations. Additionally, from the top 10% most salient themes, 5 considerations were retrieved. An ethical framework for the use of AI in neurosurgery was developed.

CONCLUSIONS

It is critical to address the ethical considerations associated with the use of AI in neurosurgery. The framework described in this manuscript may facilitate the integration of AI into neurosurgery, benefitting both patients and neurosurgeons alike. We urge neurosurgeons to use AI only for validated purposes and caution against automatic adoption of its outputs without neurosurgeon interpretation.

Opportunities and Considerations for the Incorporation of Artificial Intelligence into Global Neurosurgery: A Generative Pretrained Transformer Chatbot-Based Approach

OBJECTIVE

Global neurosurgery is a public health focus in neurosurgery that seeks to ensure safe, timely, and affordable neurosurgical care to all individuals worldwide. Although investigators have begun to explore the promise of artificial intelligence (AI) for neurosurgery, its applicability to global neurosurgery has been largely hypothetical. We characterize opportunities and considerations for the incorporation of AI into global neurosurgery by synthesizing key themes yielded from a series of generative pretrained transformers (GPTs), discuss important limitations of GPTs and cautions when using AI in neurosurgery, and develop a framework for the equitable incorporation of AI into global neurosurgery.

METHODS

ChatGPT, Bing Chat/Copilot, You, Perplexity.ai, and Google Bard were queried with the prompt "How can AI be incorporated into global neurosurgery?" A layered ChatGPT-based thematic analysis was performed. The authors synthesized the results into opportunities and considerations for the incorporation of AI in global neurosurgery. A Pareto analysis was conducted to determine common themes.

RESULTS

Eight opportunities and 14 important considerations were synthesized. Six opportunities related to patient care, 1 to education, and another to public health planning. Four of the important considerations were deemed specific to global neurosurgery. The Pareto analysis included all 8 opportunities and 5 considerations.

CONCLUSIONS

AI may be incorporated into global neurosurgery in a variety of capacities requiring numerous considerations. The framework presented in this manuscript may facilitate the incorporation of AI into global neurosurgery initiatives while balancing contextual factors and the reality of limited resources.

Accuracy of machine learning to predict the outcomes of shoulder arthroplasty: a systematic review

BACKGROUND

Artificial intelligence (AI) uses computer systems to simulate cognitive capacities to accomplish goals like problem-solving and decision-making. Machine learning (ML), a branch of AI, makes algorithms find connections between preset variables, thereby producing prediction models. ML can aid shoulder surgeons in determining which patients may be susceptible to worse outcomes and complications following shoulder arthroplasty (SA) and align patient expectations following SA. However, limited literature is available on ML utilization in total shoulder arthroplasty (TSA) and reverse TSA.

METHODS

A systematic literature review in accordance with PRISMA guidelines was performed to identify primary research articles evaluating ML's ability to predict SA outcomes. With duplicates removed, the initial query yielded 327 articles, and after applying inclusion and exclusion criteria, 12 articles that had at least 1 month follow-up time were included.

RESULTS

ML can predict 30-day postoperative complications with a 90% accuracy, postoperative range of motion with a higher-than-85% accuracy, and clinical improvement in patient-reported outcome measures above minimal clinically important differences with a 93%-99% accuracy. ML can predict length of stay, operative time, discharge disposition, and hospitalization costs.

CONCLUSION

ML can accurately predict outcomes and complications following SA and healthcare utilization. Outcomes are highly dependent on the type of algorithms used, data input, and features selected for the model.

LEVEL OF EVIDENCE

III.

Current status of artificial intelligence technologies in pituitary adenoma surgery: a scoping review

PURPOSE

Pituitary adenoma surgery is a complex procedure due to critical adjacent neurovascular structures, variations in size and extensions of the lesions, and potential hormonal imbalances. The integration of artificial intelligence (AI) and machine learning (ML) has demonstrated considerable potential in assisting neurosurgeons in decision-making, optimizing surgical outcomes, and providing real-time feedback. This scoping review comprehensively summarizes the current status of AI/ML technologies in pituitary adenoma surgery, highlighting their strengths and limitations.

METHODS

PubMed, Embase, Web of Science, and Scopus were searched following the PRISMA-ScR guidelines. Studies discussing the use of AI/ML in pituitary adenoma surgery were included. Eligible studies were grouped to analyze the different outcomes of interest of current AI/ML technologies.

RESULTS

Among the 2438 identified articles, 44 studies met the inclusion criteria, with a total of seventeen different algorithms utilized across all studies. Studies were divided into two groups based on their input type: clinicopathological and imaging input. The four main outcome variables evaluated in the studies included: outcome (remission, recurrence or progression, gross-total resection, vision improvement, and hormonal recovery), complications (CSF leak, readmission, hyponatremia, and hypopituitarism), cost, and adenoma-related factors (aggressiveness, consistency, and Ki-67 labeling) prediction. Three studies focusing on workflow analysis and real-time navigation were discussed separately.

CONCLUSION

AI/ML modeling holds promise for improving pituitary adenoma surgery by enhancing preoperative planning and optimizing surgical strategies. However, addressing challenges such as algorithm selection, performance evaluation, data heterogeneity, and ethics is essential to establish robust and reliable ML models that can revolutionize neurosurgical practice and benefit patients.

Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears

OBJECTIVE

The purpose of this systematic review was to summarize the results of original research studies evaluating the characteristics and performance of deep learning models for detection of knee ligament and meniscus tears on MRI.

MATERIALS AND METHODS

We searched PubMed for studies published as of February 2, 2022 for original studies evaluating development and evaluation of deep learning models for MRI diagnosis of knee ligament or meniscus tears. We summarized study details according to multiple criteria including baseline article details, model creation, deep learning details, and model evaluation.

RESULTS

19 studies were included with radiology departments leading the publications in deep learning development and implementation for detecting knee injuries via MRI. Among the studies, there was a lack of standard reporting and inconsistently described development details. However, all included studies reported consistently high model performance that significantly supplemented human reader performance.

CONCLUSION

From our review, we found radiology departments have been leading deep learning development for injury detection on knee MRIs. Although studies inconsistently described DL model development details, all reported high model performance, indicating great promise for DL in knee MRI analysis.

Accurately predicting the risk of unfavorable outcomes after endovascular coil therapy in patients with aneurysmal subarachnoid hemorrhage: an interpretable machine learning model

BACKGROUND

Despite endovascular coiling as a valid modality in treatment of aneurysmal subarachnoid hemorrhage (aSAH), there is a risk of poor prognosis. However, the clinical utility of previously proposed early prediction tools remains limited. We aimed to develop a clinically generalizable machine learning (ML) models for accurately predicting unfavorable outcomes in aSAH patients after endovascular coiling.

METHODS

Functional outcomes at 6 months after endovascular coiling were assessed via the modified Rankin Scale (mRS) and unfavorable outcomes were defined as mRS 3-6. Five ML algorithms (logistic regression, random forest, support vector machine, deep neural network, and extreme gradient boosting) were used for model development. The area under precision-recall curve (AUPRC) and receiver operating characteristic curve (AUROC) was used as main indices of model evaluation. SHapley Additive exPlanations (SHAP) method was applied to interpret the best-performing ML model.

RESULTS

A total of 371 patients were eventually included into this study, and 85.4% of them had favorable outcomes. Among the five models, the DNN model had a better performance with AUPRC of 0.645 (AUROC of 0.905). Postoperative GCS score, size of aneurysm, and age were the top three powerful predictors. The further analysis of five random cases presented the good interpretability of the DNN model.

CONCLUSION

Interpretable clinical prediction models based on different ML algorithms have been successfully constructed and validated, which would serve as reliable tools in optimizing the treatment decision-making of aSAH. Our DNN model had better performance to predict the unfavorable outcomes at 6 months in aSAH patients compared with Yan's nomogram model.

Development and Internal Validation of Machine Learning Models to Predict Mortality and Disability After Mechanical Thrombectomy for Acute Anterior Circulation Large Vessel Occlusion

OBJECTIVE

Mechanical thrombectomy (MT) improves outcomes in patients with LVO but many still experience mortality or severe disability. We sought to develop machine learning (ML) models that predict 90-day outcomes after MT for LVO.

METHODS

Consecutive patients who underwent MT for LVO between 2015-2021 at a Comprehensive Stroke Center were reviewed. Outcomes included 90-day favorable functional status (mRS 0-2), severe disability (mRS 4-6), and mortality. ML models were trained for each outcome using prethrombectomy data (pre) and with thrombectomy data (post).

RESULTS

Three hundred and fifty seven patients met the inclusion criteria. After model screening and hyperparameter tuning the top performing ML model for each outcome and timepoint was random forest (RF). Using only prethrombectomy features, the AUCs for the RFpre models were 0.73 (95% CI 0.62-0.85) for favorable functional status, 0.77 (95% CI 0.65-0.86) for severe disability, and 0.78 (95% CI 0.64-0.88) for mortality. All of these were better than a standard statistical model except for favorable functional status. Each RF model outperformed Pre, SPAN-100, THRIVE, and HIAT scores (P < 0.0001 for all). The most predictive features were premorbid mRS, age, and NIHSS. Incorporating MT data, the AUCs for the RFpost models were 0.80 (95% CI 0.67-0.90) for favorable functional status, 0.82 (95% CI 0.69-0.91) for severe disability, and 0.71 (95% CI 0.55-0.84) for mortality.

CONCLUSIONS

RF models accurately predicted 90-day outcomes after MT and performed better than standard statistical and clinical prediction models.

Emergent Applications of Machine Learning for Diagnosing and Managing Appendicitis: A State-of-the-Art Review

Background: Appendicitis is an inflammatory condition that requires timely and effective intervention. Despite being one of the most common surgically treated diseases, the condition is difficult to diagnose because of atypical presentations. Ultrasound and computed tomography (CT) imaging improve the sensitivity and specificity of diagnoses, yet these tools bear the drawbacks of high operator dependency and radiation exposure, respectively. However, new artificial intelligence tools (such as machine learning) may be able to address these shortcomings. Methods: We conducted a state-of-the-art review to delineate the various use cases of emerging machine learning algorithms for diagnosing and managing appendicitis in recent literature. The query ("Appendectomy" OR "Appendicitis") AND ("Machine Learning" OR "Artificial Intelligence") was searched across three databases for publications ranging from 2012 to 2022. Upon filtering for duplicates and based on our predefined inclusion criteria, 39 relevant studies were identified. Results: The algorithms used in these studies performed with an average accuracy of 86% (18/39), a sensitivity of 81% (16/39), a specificity of 75% (16/39), and area under the receiver operating characteristic curves (AUROCs) of 0.82 (15/39) where reported. Based on accuracy alone, the optimal model was logistic regression in 18% of studies, an artificial neural network in 15%, a random forest in 13%, and a support vector machine in 10%. Conclusions: The identified studies suggest that machine learning may provide a novel solution for diagnosing appendicitis and preparing for patient-specific post-operative complications. However, further studies are warranted to assess the feasibility and advisability of implementing machine learning-based tools in clinical practice.

Exploring the Landscape of Machine Learning Applications in Neurosurgery: A Bibliometric Analysis and Narrative Review of Trends and Future Directions

BACKGROUND

The field of neurosurgery has consistently represented an area of innovation and integration of technology since its inception. As such, machine learning (ML) has found its way into applications within neurosurgery relatively rapidly. Through this bibliometric review and cluster analysis, we seek to identify trends and emerging applications of ML within neurosurgery.

METHODS

A bibliometric analysis was carried out in the Web of Science database on publications from January 2000 to March 2023. The full data set of the 200 most cited publications including title, author information, journal, citation count, keywords, and abstracts for each publication was evaluated in CiteSpace. CiteSpace was used to elucidate publication characteristics, trends, and topic clusters via collaborate network analysis using the Kamada-Kawai algorithm.

RESULTS

The 25 most cited titles were included in our analysis. Harvard University and its affiliates represented the top institution, contributing nearly 25% of publications in the literature. WORLD NEUROSURGERY was the journal with the highest net citation count of 747 (29%). Collaborative network analysis generated 12 unique clusters, the largest of which was machine learning, followed by feature importance and deep brain stimulation.

CONCLUSION

This review highlights the most impactful articles pertaining to ML in the field of neurosurgery. ML has been applied into several sub-specialties within neurosurgery to optimize patient care, with special attention to outcome predictors, patient selection, and surgical decision making.

Understanding Big Data in Neurosurgery

Big data refers to a large amount of data generated and distributed across diverse data sources from open, private, social, and Internet of Things (IoT). Understanding and harnessing the big data in the biomedical sciences, specifically in neurosurgery, is crucial as it can lead to breakthroughs in understanding complex neurological disorders, optimizing surgical interventions, evaluating long-term patient outcomes, and developing predictive models of disease progression, enabling personalized treatment plans tailored to the genetic, molecular, and environmental factors unique to each patient. Furthermore, Big data analytics can facilitate a deeper understanding of the socioeconomic factors contributing to neurological disorders, leading to more effective public health strategies and interventions. By analyzing large-scale patient data across diverse populations, researchers can uncover patterns and risk factors previously obscured in smaller studies, leading to more effective preventative measures and community health initiatives. This chapter provides an overview of big data and its applications in neurosurgery, the challenges associated with its implementation, and the opportunities it presents in transforming neurosurgical care.

Deep Learning: A Primer for Neurosurgeons

This chapter explores the transformative impact of deep learning (DL) on neurosurgery, elucidating its pivotal role in enhancing diagnostic performance, surgical planning, execution, and postoperative assessment. It delves into various deep learning architectures, including convolutional and recurrent neural networks, and their applications in analyzing neuroimaging data for brain tumors, spinal cord injuries, and other neurological conditions. The integration of DL in neurosurgical robotics and the potential for fully autonomous surgical procedures are discussed, highlighting advancements in surgical precision and patient outcomes. The chapter also examines the challenges of data privacy, quality, and interpretability that accompany the implementation of DL in neurosurgery. The potential for DL to revolutionize neurosurgical practices through improved diagnostics, patient-specific surgical planning, and the advent of intelligent surgical robots is underscored, promising a future where technology and healthcare converge to offer unprecedented solutions in neurosurgery.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Exploring the Intersection of Artificial Intelligence and Neurosurgery: Let us be Cautious With ChatGPT

BACKGROUND AND OBJECTIVES

ChatGPT is a novel natural language processing artificial intelligence (AI) module where users enter any question or command and receive a single text response within seconds. As AI becomes more accessible, patients may begin to use it as a resource for medical information and advice. This is the first study to assess the neurosurgical information that is provided by ChatGPT.

METHODS

ChatGPT was accessed in January 2023, and prompts were created requesting treatment information for 40 common neurosurgical conditions. Quantitative characteristics were collected, and four independent reviewers evaluated the responses using the DISCERN tool. Prompts were compared against the American Association of Neurological Surgeons (AANS) "For Patients" webpages.

RESULTS

ChatGPT returned text organized in paragraph and bullet-point lists. ChatGPT responses were shorter (mean 270.1 ± 41.9 words; AANS webpage 1634.5 ± 891.3 words) but more difficult to read (mean Flesch-Kincaid score 32.4 ± 6.7; AANS webpage 37.1 ± 7.0). ChatGPT output was found to be of "fair" quality (mean DISCERN score 44.2 ± 4.1) and significantly inferior to the "good" overall quality of the AANS patient website (57.7 ± 4.4). ChatGPT was poor in providing references/resources and describing treatment risks. ChatGPT provided 177 references, of which 68.9% were inaccurate and 33.9% were completely falsified.

CONCLUSION

ChatGPT is an adaptive resource for neurosurgical information but has shortcomings that limit the quality of its responses, including poor readability, lack of references, and failure to fully describe treatment options. Hence, patients and providers should remain wary of the provided content. As ChatGPT or other AI search algorithms continue to improve, they may become a reliable alternative for medical information.

Computer-vision based analysis of the neurosurgical scene - A systematic review

Introduction

With increasing use of robotic surgical adjuncts, artificial intelligence and augmented reality in neurosurgery, the automated analysis of digital images and videos acquired over various procedures becomes a subject of increased interest. While several computer vision (CV) methods have been developed and implemented for analyzing surgical scenes, few studies have been dedicated to neurosurgery.

Research question

In this work, we present a systematic literature review focusing on CV methodologies specifically applied to the analysis of neurosurgical procedures based on intra-operative images and videos. Additionally, we provide recommendations for the future developments of CV models in neurosurgery.

Material and methods

We conducted a systematic literature search in multiple databases until January 17, 2023, including Web of Science, PubMed, IEEE Xplore, Embase, and SpringerLink.

Results

We identified 17 studies employing CV algorithms on neurosurgical videos/images. The most common applications of CV were tool and neuroanatomical structure detection or characterization, and to a lesser extent, surgical workflow analysis. Convolutional neural networks (CNN) were the most frequently utilized architecture for CV models (65%), demonstrating superior performances in tool detection and segmentation. In particular, mask recurrent-CNN manifested most robust performance outcomes across different modalities.

Discussion and conclusion

Our systematic review demonstrates that CV models have been reported that can effectively detect and differentiate tools, surgical phases, neuroanatomical structures, as well as critical events in complex neurosurgical scenes with accuracies above 95%. Automated tool recognition contributes to objective characterization and assessment of surgical performance, with potential applications in neurosurgical training and intra-operative safety management.

Neurosurgical Management of Cerebrospinal Tumors in the Era of Artificial Intelligence : A Scoping Review

Central nervous system tumors are identified as tumors of the brain and spinal cord. The associated morbidity and mortality of cerebrospinal tumors are disproportionately high compared to other malignancies. While minimally invasive techniques have initiated a revolution in neurosurgery, artificial intelligence (AI) is expediting it. Our study aims to analyze AI's role in the neurosurgical management of cerebrospinal tumors. We conducted a scoping review using the Arksey and O'Malley framework. Upon screening, data extraction and analysis were focused on exploring all potential implications of AI, classification of these implications in the management of cerebrospinal tumors. AI has enhanced the precision of diagnosis of these tumors, enables surgeons to excise the tumor margins completely, thereby reducing the risk of recurrence, and helps to make a more accurate prediction of the patient's prognosis than the conventional methods. AI also offers real-time training to neurosurgeons using virtual and 3D simulation, thereby increasing their confidence and skills during procedures. In addition, robotics is integrated into neurosurgery and identified to increase patient outcomes by making surgery less invasive. AI, including machine learning, is rigorously considered for its applications in the neurosurgical management of cerebrospinal tumors. This field requires further research focused on areas clinically essential in improving the outcome that is also economically feasible for clinical use. The authors suggest that data analysts and neurosurgeons collaborate to explore the full potential of AI.

Artificial Intelligence and Its Role in the Management of Chronic Medical Conditions: A Systematic Review

Due to the increased burden of chronic medical conditions in recent years, artificial intelligence (AI) is suggested in the medical field to optimize health care. Physicians could implement these automated problem-solving tools for their benefit, reducing their workload, assisting in diagnostics, and supporting clinical decision-making. These tools are being considered for future medical assistance in real life. A literature review was performed to assess the impact of AI on the patient population with chronic medical conditions, using standardized guidelines. A MeSH strategy was created, and the database was searched for appropriate studies using specific inclusion and exclusion criteria. The online database yielded 93 results from various databases, of which 10 moderate to high-quality studies were selected to be included in our systematic review after removing the duplicates, screening titles, and articles. Of the 10 studies, nine recommended using AI after considering the potential limitations such as privacy protection, medicolegal implications, and psychosocial aspects. Due to its non-fatigable nature, AI was found to be of immense help in image recognition. It was also found to be valuable in various disciplines related to administration, physician burden, and patient adherence. The newer technologies of Chatbots and eHealth applications are of great help when used safely and effectively after proper patient education. After a careful review conducted by our team members, it is safe to conclude that implementing AI in daily clinical practice could potentiate the cognitive ability of physicians and decrease the workload through various automated technologies such as image recognition, speech recognition, and voice recognition due to its unmatchable speed and non-fatigable nature when compared to clinicians. Despite its vast benefits to the medical field, a few limitations could hinder its effective implementation into real-life practice, which requires enormous research and strict regulations to support its role as a physician's aid. However, AI should only be used as a medical support system, in order to improve the primary outcomes such as reducing waiting time, healthcare costs, and workload. AI should not be meant to replace physicians.

FDA-approved machine learning algorithms in neuroradiology: A systematic review of the current evidence for approval

Over the past decade, machine learning (ML) and artificial intelligence (AI) have become increasingly prevalent in the medical field. In the United States, the Food and Drug Administration (FDA) is responsible for regulating AI algorithms as "medical devices" to ensure patient safety. However, recent work has shown that the FDA approval process may be deficient. In this study, we evaluate the evidence supporting FDA-approved neuroalgorithms, the subset of machine learning algorithms with applications in the central nervous system (CNS), through a systematic review of the primary literature. Articles covering the 53 FDA-approved algorithms with applications in the CNS published in PubMed, EMBASE, Google Scholar and Scopus between database inception and January 25, 2022 were queried. Initial searches identified 1505 studies, of which 92 articles met the criteria for extraction and inclusion. Studies were identified for 26 of the 53 neuroalgorithms, of which 10 algorithms had only a single peer-reviewed publication. Performance metrics were available for 15 algorithms, external validation studies were available for 24 algorithms, and studies exploring the use of algorithms in clinical practice were available for 7 algorithms. Papers studying the clinical utility of these algorithms focused on three domains: workflow efficiency, cost savings, and clinical outcomes. Our analysis suggests that there is a meaningful gap between the FDA approval of machine learning algorithms and their clinical utilization. There appears to be room for process improvement by implementation of the following recommendations: the provision of compelling evidence that algorithms perform as intended, mandating minimum sample sizes, reporting of a predefined set of performance metrics for all algorithms and clinical application of algorithms prior to widespread use. This work will serve as a baseline for future research into the ideal regulatory framework for AI applications worldwide.

Computer-Assisted Microcatheter Shaping for Intracranial Aneurysm Embolization

BACKGROUND

This study investigates the accuracy, stability, and safety of computer-assisted microcatheter shaping for intracranial aneurysm coiling.

METHODS

Using the solid model, a microcatheter was shaped using computer-assisted techniques or manually to investigate the accuracy and delivery of microcatheter-shaping techniques in aneurysm embolization. Then, forty-eight patients were randomly assigned to the computer-assisted microcatheter-shaping (CAMS) group or the manual microcatheter-shaping (MMS) group, and the accuracy, stability, and safety of microcatheter in the patients were compared between the CAMS and MMS groups.

RESULTS

The speed of the successful microcatheter position was significantly faster in the CAMS group than in the MMS group (114.4 ± 23.99 s vs. 201.9 ± 24.54 s, p = 0.015) in vitro. In particular for inexperienced operators, the speed of the microcatheter position with the assistance of computer software is much faster than manual microcatheter shaping (93.6 ± 29.23 s vs. 228.9 ± 31.27 s, p = 0.005). In vivo, the time of the microcatheter position in the MMS group was significantly longer than that in the CAMS group (5.16 ± 0.46 min vs. 2.48 ± 0.32 min, p = 0.0001). However, the mRS score at discharge, the 6-month follow-up, and aneurysm regrowth at the 6-month follow-up were all similar between the groups.

CONCLUSIONS

Computer-assisted microcatheter shaping is a novel and safe method for microcatheter shaping that introduces higher accuracy in microcatheter shaping during the treatment of intracranial aneurysms.

SIGNIFICANT

Endovascular coiling of intracranial aneurysms can be truly revolutionized through computer assistance, which could improve the endovascular treatment of aneurysms.

Development and external validation of clinical prediction models for pituitary surgery

Introduction

Gross total resection (GTR), Biochemical Remission (BR) and restitution of a priorly disrupted hypothalamus pituitary axis (new improvement, IMP) are important factors in pituitary adenoma (PA) resection surgery. Prediction of these metrics using simple and preoperatively available data might help improve patient care and contribute to a more personalized medicine.

Research question

This study aims to develop machine learning models predicting GTR, BR, and IMP in PA resection surgery, using preoperatively available data.

Material and methods

With data from patients undergoing endoscopic transsphenoidal surgery for PAs machine learning models for prediction of GTR, BR and IMP were developed and externally validated. Development was carried out on a registry from Bologna, Italy while external validation was conducted using patient data from Zurich, Switzerland.

Results

The model development cohort consisted of 1203 patients. GTR was achieved in 207 (17.2%, 945 (78.6%) missing), BR in 173 (14.4%, 992 (82.5%) missing) and IMP in 208 (17.3%, 167 (13.9%) missing) cases. In the external validation cohort 206 patients were included and GTR was achieved in 121 (58.7%, 32 (15.5%) missing), BR in 46 (22.3%, 145 (70.4%) missing) and IMP in 42 (20.4%, 7 (3.4%) missing) cases. The AUC at external validation amounted to 0.72 (95% CI: 0.63-0.80) for GTR, 0.69 (0.52-0.83) for BR, as well as 0.82 (0.76-0.89) for IMP.

Discussion and conclusion

All models showed adequate generalizability, performing similarly in training and external validation, confirming the possible potentials of machine learning in helping to adapt surgical therapy to the individual patient.

The application of traditional machine learning and deep learning techniques in mammography: a review

Breast cancer, the most prevalent malignant tumor among women, poses a significant threat to patients' physical and mental well-being. Recent advances in early screening technology have facilitated the early detection of an increasing number of breast cancers, resulting in a substantial improvement in patients' overall survival rates. The primary techniques used for early breast cancer diagnosis include mammography, breast ultrasound, breast MRI, and pathological examination. However, the clinical interpretation and analysis of the images produced by these technologies often involve significant labor costs and rely heavily on the expertise of clinicians, leading to inherent deviations. Consequently, artificial intelligence(AI) has emerged as a valuable technology in breast cancer diagnosis. Artificial intelligence includes Machine Learning(ML) and Deep Learning(DL). By simulating human behavior to learn from and process data, ML and DL aid in lesion localization reduce misdiagnosis rates, and improve accuracy. This narrative review provides a comprehensive review of the current research status of mammography using traditional ML and DL algorithms. It particularly highlights the latest advancements in DL methods for mammogram image analysis and offers insights into future development directions.

Machine learning algorithms for predicting outcomes of traumatic brain injury: A systematic review and meta-analysis

BACKGROUND

Traumatic brain injury (TBI) is a leading cause of death and disability worldwide. The use of machine learning (ML) has emerged as a key advancement in TBI management. This study aimed to identify ML models with demonstrated effectiveness in predicting TBI outcomes.

METHODS

We conducted a systematic review in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis statement. In total, 15 articles were identified using the search strategy. Patient demographics, clinical status, ML outcome variables, and predictive characteristics were extracted. A small meta-analysis of mortality prediction was performed, and a meta-analysis of diagnostic accuracy was conducted for ML algorithms used across multiple studies.

RESULTS

ML algorithms including support vector machine (SVM), artificial neural networks (ANN), random forest, and Naïve Bayes were compared to logistic regression (LR). Thirteen studies found significant improvement in prognostic capability using ML versus LR. The accuracy of the above algorithms was consistently over 80% when predicting mortality and unfavorable outcome measured by Glasgow Outcome Scale. Receiver operating characteristic curves analyzing the sensitivity of ANN, SVM, decision tree, and LR demonstrated consistent findings across studies. Lower admission Glasgow Coma Scale (GCS), older age, elevated serum acid, and abnormal glucose were associated with increased adverse outcomes and had the most significant impact on ML algorithms.

CONCLUSION

ML algorithms were stronger than traditional regression models in predicting adverse outcomes. Admission GCS, age, and serum metabolites all have strong predictive power when used with ML and should be considered important components of TBI risk stratification.

Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future

In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

Exoscopic Microsurgery: A Change of Paradigm in Brain Tumor Surgery? Comparison with Standard Operative Microscope

BACKGROUND

The exoscope is a high-definition telescope recently introduced in neurosurgery. In the past few years, several reports have described the advantages and disadvantages of such technology. No studies have compared results of surgery with standard microscope and exoscope in patients with glioblastoma multiforme (GBM).

METHODS

Our retrospective study encompassed 177 patients operated on for GBM (WHO 2021) between February 2017 and August 2022. A total of 144 patients were operated on with a microscope only and the others with a 3D4K exoscope only. All clinical and radiological data were collected. Progression-free survival (PFS) and overall survival (OS) have been estimated in the two groups and compared by the Cox model adjusting for potential confounders (e.g., sex, age, Karnofsky performance status, gross total resection, MGMT methylated promoter, and operator's experience).

RESULTS

IDH was mutated in 9 (5.2%) patients and MGMT was methylated in 76 (44.4%). Overall, 122 patients received a gross total resection, 14 patients received a subtotal resection, and 41 patients received a partial resection. During follow-up, 139 (73.5%) patients experienced tumor recurrence and 18.7% of them received a second surgery. After truncation to 12 months, the median PFS for patients operated on with the microscope was 8.82 months, while for patients operated on with the exoscope it was >12 months. Instead, the OS was comparable in the two groups. The multivariable Cox model showed that the use of microscope compared to the exoscope was associated with lower progression-free survival (hazard ratio = 3.55, 95%CI = 1.66-7.56, p = 0.001).

CONCLUSIONS

The exoscope has proven efficacy in terms of surgical resection, which was not different to that of the microscope. Furthermore, patients operated on with the exoscope had a longer PFS. A comparable OS was observed between microscope and exoscope, but further prospective studies with longer follow-up are needed.

A Machine Learning-Based Prediction of Diabetes Insipidus in Patients Undergoing Endoscopic Transsphenoidal Surgery for Pituitary Adenoma

BACKGROUND

Diabetes insipidus (DI) is a common complication after endoscopic transsphenoidal surgery (TSS) for pituitary adenoma (PA), which affects the quality of life in patients. Therefore, there is a need to develop prediction models of postoperative DI specifically for patients who undergo endoscopic TSS. This study establishes and validates prediction models of DI after endoscopic TSS for patients with PA using machine learning algorithms.

METHODS

We retrospectively collected information about patients with PA who underwent endoscopic TSS in otorhinolaryngology and neurosurgery departments between January 2018 and December 2020. The patients were randomly split into a training set (70%) and a test set (30%). The 4 machine learning algorithms (logistic regression, random forest, support vector machine, and decision tree) were used to establish the prediction models. Area under the receiver operating characteristic curves were calculated to compare the performance of the models.

RESULTS

A total of 232 patients were included, and 78 patients (33.6%) developed transient DI after surgery. Data were randomly divided into a training set (n = 162) and a test set (n = 70) for development and validation of the model, respectively. The area under the receiver operating characteristic curve was highest in the random forest model (0.815) and lowest in the logistic regression model (0.601). Invasion of pituitary stalk was the most important feature for model performance, closely followed by macroadenomas, size classification of PA, tumor texture, and Hardy-Wilson suprasellar grade.

CONCLUSIONS

Machine learning algorithms identify preoperative features of importance and reliably predict DI after endoscopic TSS for patients with PA. Such a prediction model may enable clinicians to develop individualized treatment strategy and follow-up management.

Systematic review of the performance evaluation of clinicians with or without the aid of machine learning clinical decision support system

Background

For the adoption of machine learning clinical decision support systems (ML-CDSS) it is critical to understand the performance aid of the ML-CDSS. However, it is not trivial, how the performance aid should be evaluated. To design reliable performance evaluation study, both the knowledge from the practical framework of experimental study design and the understanding of domain specific design factors are required.

Objective

The aim of this review study was to form a practical framework and identify key design factors for experimental design in evaluating the performance of clinicians with or without the aid of ML-CDSS.

Methods

The study was based on published ML-CDSS performance evaluation studies. We systematically searched articles published between January 2016 and December 2022. From the articles we collected a set of design factors. Only the articles comparing the performance of clinicians with or without the aid of ML-CDSS using experimental study methods were considered.

Results

The identified key design factors for the practical framework of ML-CDSS experimental study design were performance measures, user interface, ground truth data and the selection of samples and participants. In addition, we identified the importance of randomization, crossover design and training and practice rounds. Previous studies had shortcomings in the rationale and documentation of choices regarding the number of participants and the duration of the experiment.

Conclusion

The design factors of ML-CDSS experimental study are interdependent and all factors must be considered in individual choices.

Supplementary Information

The online version contains supplementary material available at 10.1007/s12553-023-00763-1.

The Use of Machine Learning for Predicting Complications of Free-Flap Head and Neck Reconstruction

BACKGROUND

Machine learning has been increasingly used for surgical outcome prediction, yet applications in head and neck reconstruction are not well-described. In this study, we developed and evaluated the performance of ML algorithms in predicting postoperative complications in head and neck free-flap reconstruction.

METHODS

We conducted a comprehensive review of patients who underwent microvascular head and neck reconstruction between January 2005 and December 2018. Data were used to develop and evaluate nine supervised ML algorithms in predicting overall complications, major recipient-site complication, and total flap loss.

RESULTS

We identified 4000 patients who met inclusion criteria. Overall, 33.7% of patients experienced a complication, 26.5% experienced a major recipient-site complication, and 1.7% suffered total flap loss. The k-nearest neighbors algorithm demonstrated the best overall performance for predicting any complication (AUROC = 0.61, sensitivity = 0.60). Regularized regression had the best performance for predicting major recipient-site complications (AUROC = 0.68, sensitivity = 0.66), and decision trees were the best predictors of total flap loss (AUROC = 0.66, sensitivity = 0.50).

CONCLUSIONS

ML accurately identified patients at risk of experiencing postsurgical complications, including total flap loss. Predictions from ML models may provide insight in the perioperative setting and facilitate shared decision making.

Machine Learning Models to Forecast Outcomes of Pituitary Surgery: A Systematic Review in Quality of Reporting and Current Evidence

Background: The complex nature and heterogeneity involving pituitary surgery results have increased interest in machine learning (ML) applications for prediction of outcomes over the last decade. This study aims to systematically review the characteristics of ML models involving pituitary surgery outcome prediction and assess their reporting quality. Methods: We searched the PubMed, Scopus, and Web of Knowledge databases for publications on the use of ML to predict pituitary surgery outcomes. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to assess report quality. Our search strategy was based on the terms “artificial intelligence”, “machine learning”, and “pituitary”. Results: 20 studies were included in this review. The principal models reported in each article were post-surgical endocrine outcomes (n = 10), tumor management (n = 3), and intra- and postoperative complications (n = 7). Overall, the included studies adhered to a median of 65% (IQR = 60–72%) of TRIPOD criteria, ranging from 43% to 83%. The median reported AUC was 0.84 (IQR = 0.80–0.91). The most popular algorithms were support vector machine (n = 5) and random forest (n = 5). Only two studies reported external validation and adherence to any reporting guideline. Calibration methods were not reported in 15 studies. No model achieved the phase of actual clinical applicability. Conclusion: Applications of ML in the prediction of pituitary outcomes are still nascent, as evidenced by the lack of any model validated for clinical practice. Although studies have demonstrated promising results, greater transparency in model development and reporting is needed to enable their use in clinical practice. Further adherence to reporting guidelines can help increase AI’s real-world utility and improve clinical practice.

Artificial intelligence as a diagnostic aid in cross-sectional radiological imaging of surgical pathology in the abdominopelvic cavity: a systematic review

OBJECTIVES

There is emerging use of artificial intelligence (AI) models to aid diagnostic imaging. This review examined and critically appraised the application of AI models to identify surgical pathology from radiological images of the abdominopelvic cavity, to identify current limitations and inform future research.

DESIGN

Systematic review.

DATA SOURCES

Systematic database searches (Medline, EMBASE, Cochrane Central Register of Controlled Trials) were performed. Date limitations (January 2012 to July 2021) were applied.

ELIGIBILITY CRITERIA

Primary research studies were considered for eligibility using the PIRT (participants, index test(s), reference standard and target condition) framework. Only publications in the English language were eligible for inclusion in the review.

DATA EXTRACTION AND SYNTHESIS

Study characteristics, descriptions of AI models and outcomes assessing diagnostic performance were extracted by independent reviewers. A narrative synthesis was performed in accordance with the Synthesis Without Meta-analysis guidelines. Risk of bias was assessed (Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2)).

RESULTS

Fifteen retrospective studies were included. Studies were diverse in surgical specialty, the intention of the AI applications and the models used. AI training and test sets comprised a median of 130 (range: 5-2440) and 37 (range: 10-1045) patients, respectively. Diagnostic performance of models varied (range: 70%-95% sensitivity, 53%-98% specificity). Only four studies compared the AI model with human performance. Reporting of studies was unstandardised and often lacking in detail. Most studies (n=14) were judged as having overall high risk of bias with concerns regarding applicability.

CONCLUSIONS

AI application in this field is diverse. Adherence to reporting guidelines is warranted. With finite healthcare resources, future endeavours may benefit from targeting areas where radiological expertise is in high demand to provide greater efficiency in clinical care. Translation to clinical practice and adoption of a multidisciplinary approach should be of high priority.

PROSPERO REGISTRATION NUMBER

CRD42021237249.

Machine learning prediction of malignant middle cerebral artery infarction after mechanical thrombectomy for anterior circulation large vessel occlusion

OBJECTIVE

Prediction of malignant middle cerebral artery infarction (MMI) could identify patients for early intervention. We trained and internally validated a ML model that predicts MMI following mechanical thrombectomy (MT) for ACLVO.

METHODS

All patients who underwent MT for ACLVO between 2015 - 2021 at a single institution were reviewed. Data was divided into 80% training and 20% test sets. 10 models were evaluated on the training set. The top 3 models underwent hyperparameter tuning using grid search with nested 5-fold CV to optimize the area under the receiver operating curve (AUROC). Tuned models were evaluated on the test set and compared to logistic regression.

RESULTS

A total of 381 patients met the inclusion criteria. There were 50 (13.1%) patients who developed MMI. Out of the 10 ML models screened on the training set, the top 3 performing were neural network (median AUROC 0.78, IQR 0.72 - 0.83), support vector machine ([SVM] median AUROC 0.77, IQR 0.72 - 0.83), and random forest (median AUROC 0.75, IQR 0.68 - 0.81). On the test set, random forest (median AUROC 0.78, IQR 0.73 - 0.83) and neural network (median AUROC 0.78, IQR 0.73 - 0.83) were the top performing models, followed by SVM (median AUROC 0.77, IQR 0.70 - 0.83). These scores were significantly better than those for logistic regression (AUROC 0.72, IQR 0.66 - 0.78), individual risk factors, and the Malignant Brain Edema score (p < 0.001 for all).

CONCLUSION

ML models predicted MMI with good discriminative ability. They outperformed standard statistical techniques and individual risk factors.

Artificial Intelligence in Neurosurgery: A Bibliometric Analysis

BACKGROUND

Artificial intelligence (AI) has the potential to augment clinicians' diagnostic and decision-making capabilities. It is well suited to identify patterns and correlations within data sets and may be applied to identify elements of importance in complex and data-laden areas such as patient selection, diagnostics, treatment, and outcome prediction. The development of modern neurosurgery has been dependent on major technological advances. In line with this, a growing interest is seen in the use of AI to assist in neurosurgical research and enhance neurosurgical practices.

METHODS

A bibliometric analysis of the 50 most-cited articles alluding to the use of AI in neurosurgery, from inception until July of 2022, was undertaken using the Web of Science database. Statistical analyses were performed on R.

RESULTS

The citation count ranged from 29 to 159 (mean: 51.9, standard deviation: 24.8), and the top-cited article was a 2018 systematic review published in World Neurosurgery. Most articles were published after 2015 (85%). The United States was the largest contributing country on the list with 22 articles. Four first and last authors, each, had 2 or more publications. Female first and last authorship was attributed to 18% and 0% of the articles, respectively.

CONCLUSIONS

This review highlights the most-impactful articles pertaining to AI in the field of neurosurgery. Although female authors were significantly underrepresented on the list, their work was at least as impactful as their male peers. Finally, the striking dominance of articles originating from the developed world raises concerns as to the future of AI in attending to the global health crisis.

Words matter: using natural language processing to predict neurosurgical residency match outcomes

OBJECTIVE

Narrative letters of recommendation (NLORs) are considered by neurosurgical program directors to be among the most important parts of the residency application. However, the utility of these NLORs in predicting match outcomes compared to objective measures has not been determined. In this study, the authors compare the performance of machine learning models trained on applicant NLORs and demographic data to predict match outcomes and investigate whether narrative language is predictive of standardized letter of recommendation (SLOR) rankings.

METHODS

This study analyzed 1498 NLORs from 391 applications submitted to a single neurosurgery residency program over the 2020-2021 cycle. Applicant demographics and match outcomes were extracted from Electronic Residency Application Service applications and training program websites. Logistic regression models using least absolute shrinkage and selection operator were trained to predict match outcomes using applicant NLOR text and demographics. Another model was trained on NLOR text to predict SLOR rankings. Model performance was estimated using area under the curve (AUC).

RESULTS

Both the NLOR and demographics models were able to discriminate similarly between match outcomes (AUCs 0.75 and 0.80; p = 0.13). Words including "outstanding," "seamlessly," and "AOA" (Alpha Omega Alpha) were predictive of match success. This model was able to predict SLORs ranked in the top 5%. Words including "highest," "outstanding," and "best" were predictive of the top 5% SLORs.

CONCLUSIONS

NLORs and demographic data similarly discriminate whether applicants will or will not match into a neurosurgical residency program. However, NLORs potentially provide further insight regarding applicant fit. Because words used in NLORs are predictive of both match outcomes and SLOR rankings, continuing to include narrative evaluations may be invaluable to the match process.

Statistical and machine learning approaches to predict the necessity for computed tomography in children with mild traumatic brain injury

BACKGROUND

Minor head trauma in children is a common reason for emergency department visits, but the risk of traumatic brain injury (TBI) in those children is very low. Therefore, physicians should consider the indication for computed tomography (CT) to avoid unnecessary radiation exposure to children. The purpose of this study was to statistically assess the differences between control and mild TBI (mTBI). In addition, we also investigate the feasibility of machine learning (ML) to predict the necessity of CT scans in children with mTBI.

METHODS AND FINDINGS

The study enrolled 1100 children under the age of 2 years to assess pre-verbal children. Other inclusion and exclusion criteria were per the PECARN study. Data such as demographics, injury details, medical history, and neurological assessment were used for statistical evaluation and creation of the ML algorithm. The number of children with clinically important TBI (ciTBI), mTBI on CT, and controls was 28, 30, and 1042, respectively. Statistical significance between the control group and clinically significant TBI requiring hospitalization (csTBI: ciTBI+mTBI on CT) was demonstrated for all nonparametric predictors except severity of the injury mechanism. The comparison between the three groups also showed significance for all predictors (p<0.05). This study showed that supervised ML for predicting the need for CT scan can be generated with 95% accuracy. It also revealed the significance of each predictor in the decision tree, especially the "days of life."

CONCLUSIONS

These results confirm the role and importance of each of the predictors mentioned in the PECARN study and show that ML could discriminate between children with csTBI and the control group.

Comparison of the impact of skull density ratio with alternative skull metrics on magnetic resonance-guided focused ultrasound thalamotomy for tremor

OBJECTIVE

One of the key metrics that is used to predict the likelihood of success of MR-guided focused ultrasound (MRgFUS) thalamotomy is the overall calvarial skull density ratio (SDR). However, this measure does not fully predict the sonication parameters that would be required or the technical success rates. The authors aimed to assess other skull characteristics that may also contribute to technical success.

METHODS

The authors retrospectively studied consecutive patients with essential tremor who were treated by MRgFUS at their center between 2017 and 2021. They evaluated the correlation between the different treatment parameters, particularly maximum power and energy delivered, with a range of patients' skull metrics and demographics. Machine learning algorithms were applied to investigate whether sonication parameters could be predicted from skull density metrics alone and whether including combined local transducer SDRs with overall calvarial SDR would increase model accuracy.

RESULTS

A total of 62 patients were included in the study. The mean age was 77.1 (SD 9.2) years, and 78% of treatments (49/63) were performed in males. The mean SDR was 0.51 (SD 0.10). Among the evaluated metrics, SDR had the highest correlation with the maximum power used in treatment (ρ = -0.626, p < 0.001; proportion of local SDR values ≤ 0.8 group also had ρ = +0.626, p < 0.001) and maximum energy delivered (ρ = -0.680, p < 0.001). Machine learning algorithms achieved a moderate ability to predict maximum power and energy required from the local and overall SDRs (accuracy of approximately 80% for maximum power and approximately 55% for maximum energy), and high ability to predict average maximum temperature reached from the local and overall SDRs (approximately 95% accuracy).

CONCLUSIONS

The authors compared a number of skull metrics against SDR and showed that SDR was one of the best indicators of treatment parameters when used alone. In addition, a number of other machine learning algorithms are proposed that may be explored to improve its accuracy when additional data are obtained. Additional metrics related to eventual sonication parameters should also be identified and explored.

Estimation of Survival in Patients with Glioblastoma Using an Online Calculator at a Tertiary-Level Hospital in Mexico

Background The mean survival duration of patients with glioblastoma after diagnosis is 15 months (14-21 months), while progression-free survival is 10 months (+/- one month). Although there are well-defined overall survival statistics for glioblastoma, individual survival prediction remains a challenge. Therefore, there is a need to validate an accessible and cost-effective prognostic tool to provide valuable data for decision-making. This study aims to calculate the mean survival of patients with glioblastoma at a tertiary-level hospital in Mexico using the online glioblastoma survival calculator developed by researchers at Harvard Medical School & Brigham and Women's Hospital and compare it with the actual mean survival. Methodology We conducted a retrospective observational study of patients who received a histopathological diagnosis of glioblastoma from the National Institute of Neurology and Neurosurgery "Manuel Velasco Suárez" between 2015 and 2021. We included 50 patients aged 20-83 years, with a tumor size of 15-79 mm, and who had died 30 days after surgery. Patient survival was estimated using the online calculator developed at Harvard Medical School & Brigham and Women's Hospital. The estimated mean survival was then compared with the actual mean survival of the patient. A two-tailed equivalence test for paired samples was performed to conduct this comparison. A value of p < 0.05 was considered significant. Results The mean age of the sample was 55.5 years (confidence interval (CI) 95%, 52.61-58.71). The mean tumor size in our sample was 49.12 mm (±14.9mm). We identified a difference between the mean estimated survival and the mean actual survival of -1.37 months (CI 95%; range of -3.7 to +0.9). After setting the inferior (IL) and superior limits (SL) at -3.8 and +3.8 months, respectively, we found that the difference between the mean estimated survival and the actual mean survival is within the equivalence interval (IL: p = 0.0453; SL: p = 0.0002). Conclusions The actual survival of patients diagnosed with glioblastoma at the National Institute of Neurology and Neurosurgery was equivalent to the estimated survival calculated by the online prediction calculator developed at Harvard Medical School & Brigham and Women's Hospital. This study validates a practical, cost-effective, and accessible tool for predicting patient survival, contributing to significant support for medical and personal decision-making for glioblastoma management.