CyberKnife stereotactic radiosurgery for extramedullary plasmacytoma in the external auditory canal: illustrative case.

BACKGROUND: Plasmacytoma, a rare plasma cell disorder, often presents as a solitary or multiple tumors within the bone marrow or soft tissues, typically associated with multiple myeloma. Extramedullary plasmacytomas (EMPs), particularly those located in the external auditory canal (EAC), are exceedingly rare and pose significant treatment challenges given their location, anatomical complexity, and high risk of recurrence. OBSERVATIONS: The authors report the case of a 72-year-old male with a history of multiple myeloma, presenting with recurrent left EAC plasmacytoma. After initial conventional radiotherapy for the lesion, a recurrence was documented in 7 years. The patient subsequently underwent stereotactic radiosurgery, which proved successful, leading to complete resolution of the lesion without any long-term adverse effects or radiation-related complications over a 45-month period. LESSONS: This case is a unique instance of utilizing stereotactic radiosurgery for recurrent EMP in the EAC, highlighting its potential as an effective approach in managing complex plasmacytomas.

Deep Learning Prediction of Cervical Spine Surgery Revision Outcomes Using Standard Laboratory and Operative Variables.

BACKGROUND: Cervical spine procedures represent a major proportion of all spine surgery. Mitigating the revision rate following cervical procedures requires careful patient selection. While complication risk has successfully been predicted, revision risk has proven more challenging. This is likely due to the absence of granular variables in claims databases. The objective of this study was to develop a state-of-the-art model of revision prediction of cervical spine surgery using laboratory and operative variables. METHODS: Using the Stanford Research Repository, patients undergoing a cervical spine procedure between 2016 and 2022 were identified (N = 3151), and recent laboratory values were collected. Patients were classified into separate cohorts by revision outcome and time frame. Machine and deep learning models were trained to predict each revision outcome from laboratory and operative variables. RESULTS: Red blood cell count, hemoglobin, hematocrit, mean corpuscular hemoglobin concentration, red blood cell distribution width, platelet count, carbon dioxide, anion gap, and calcium all were significantly associated with ≥1 revision cohorts. For the prediction of 3-month revision, the deep neural network achieved an area under the receiver operating characteristic curve of 0.833. The model demonstrated increased performance for anterior versus posterior and arthrodesis versus decompression procedures. CONCLUSIONS: Our deep learning approach successfully predicted 3-month revision outcomes from demographic variables, standard laboratory values, and operative variables in a cervical spine surgery cohort. This work used standard laboratory values and operative codes as meaningful predictive variables for revision outcome prediction. The increased performance on certain procedures evidences the need for careful development and validation of one-size-fits-all risk scores for spine procedures.

Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations.

Machine learning can predict neurosurgical diagnosis and outcomes, power imaging analysis, and perform robotic navigation and tumor labeling. State-of-the-art models can reconstruct and generate images, predict surgical events from video, and assist in intraoperative decision-making. In this review, we will detail the neurosurgical applications of machine learning, ranging from simple to advanced models, and their potential to transform patient care. As machine learning techniques, outputs, and methods become increasingly complex, their performance is often more impactful yet increasingly difficult to evaluate. We aim to introduce these advancements to the neurosurgical audience while suggesting major potential roadblocks to their safe and effective translation. Unlike the previous generation of machine learning in neurosurgery, the safe translation of recent advancements will be contingent on neurosurgeons' involvement in model development and validation.

Evaluating Computer Vision, Large Language, and Genome-Wide Association Models in a Limited Sized Patient Cohort for Pre-Operative Risk Stratification in Adult Spinal Deformity Surgery.

Background: Adult spinal deformities (ASD) are varied spinal abnormalities, often necessitating surgical intervention when associated with pain, worsening deformity, or worsening function. Predicting post-operative complications and revision surgery is critical for surgical planning and patient counseling. Due to the relatively small number of cases of ASD surgery, machine learning applications have been limited to traditional models (e.g., logistic regression or standard neural networks) and coarse clinical variables. We present the novel application of advanced models (CNN, LLM, GWAS) using complex data types (radiographs, clinical notes, genomics) for ASD outcome prediction. Methods: We developed a CNN trained on 209 ASD patients (1549 radiographs) from the Stanford Research Repository, a CNN pre-trained on VinDr-SpineXR (10,468 spine radiographs), and an LLM using free-text clinical notes from the same 209 patients, trained via Gatortron. Additionally, we conducted a GWAS using the UK Biobank, contrasting 540 surgical ASD patients with 7355 non-surgical ASD patients. Results: The LLM notably outperformed the CNN in predicting pulmonary complications (F1: 0.545 vs. 0.2881), neurological complications (F1: 0.250 vs. 0.224), and sepsis (F1: 0.382 vs. 0.132). The pre-trained CNN showed improved sepsis prediction (AUC: 0.638 vs. 0.534) but reduced performance for neurological complication prediction (AUC: 0.545 vs. 0.619). The LLM demonstrated high specificity (0.946) and positive predictive value (0.467) for neurological complications. The GWAS identified 21 significant (p < 10-5) SNPs associated with ASD surgery risk (OR: mean: 3.17, SD: 1.92, median: 2.78), with the highest odds ratio (8.06) for the LDB2 gene, which is implicated in ectoderm differentiation. Conclusions: This study exemplifies the innovative application of cutting-edge models to forecast outcomes in ASD, underscoring the utility of complex data in outcome prediction for neurosurgical conditions. It demonstrates the promise of genetic models when identifying surgical risks and supports the integration of complex machine learning tools for informed surgical decision-making in ASD.

Spinal metastases of pineal region glioblastoma with primitive neuroectodermal features highlighting the importance of molecular diagnoses: illustrative case.

BACKGROUND: Glioblastoma (GBM) is the most common primary brain tumor with poor patient prognosis. Spinal leptomeningeal metastasis has been rarely reported, with long intervals between the initial discovery of the primary tumor in the brain and eventual spine metastasis. OBSERVATIONS: Here, the authors present the case of a 51-year-old male presenting with 7 days of severe headache, nausea, and vomiting. Magnetic resonance imaging of the brain and spine demonstrated a contrast-enhancing mass in the pineal region, along with spinal metastases to T8, T12, and L5. Initial frozen-section diagnosis led to the treatment strategy for medulloblastoma, but further molecular analysis revealed characteristics of isocitrate dehydrogenase-wild type, grade 4 GBM. LESSONS: Glioblastoma has the potential to show metastatic spread at the time of diagnosis. Spinal imaging should be considered in patients with clinical suspicion of leptomeningeal spread. Furthermore, molecular analysis should be confirmed following pathological diagnosis to fine-tune treatment strategies.

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

Sigma-1 Receptor has been shown to localize to sites of peripheral nerve injury and back pain. Radioligand probes have been developed to localize Sigma-1 Receptor and thus image pain source. However, in non-pain conditions, Sigma-1 Receptor expression has also been demonstrated in the central nervous system and dorsal root ganglion. This work aimed to study Sigma-1 Receptor expression in a microglial cell population in the lumbar spine following peripheral nerve injury. A publicly available transcriptomic dataset of 102,691 L4/5 mouse microglial cells from a sciatic-sural nerve spared nerve injury model and 93,027 age and sex matched cells from a sham model was used. At each of three time points-postoperative day 3, postoperative day 14, and postoperative month 5-gene expression data was recorded for both spared nerve injury and Sham cell groups. For all cells, 27,998 genes were sequenced. All cells were clustered into 12 distinct subclusters and gene set enrichment pathway analysis was performed. For both the spared nerve injury and Sham groups, Sigma-1 Receptor expression significantly decreased at each time point following surgery. At the 5-month postoperative time point, only one of twelve subclusters showed significantly increased Sigma-1 Receptor expression in spared nerve injury cells as compared to Sham cells (p = 0.0064). Pathway analysis of this cluster showed a significantly increased expression of the inflammatory response pathway in the spared nerve injury cells relative to Sham cells at the 5-month time point (p = 6.74e-05). A distinct subcluster of L4/5 microglia was identified which overexpress Sigma-1 Receptor following peripheral nerve injury consistent with neuropathic pain inflammatory response functioning. This indicates that upregulated Sigma-1 Receptor in the central nervous system characterizes post-acute peripheral nerve injury and may be further developed for clinical use in the differentiation between low back pain secondary to peripheral nerve injury and low back pain not associated with peripheral nerve injury in cases where the pain cannot be localized.