Predictive model for orbital target volume for reconstruction in hyperostotic sphenoid wing meningiomas.

Objective: To devise a predictive model for estimating the requisite volume of the orbit in patients poised for resection of hyperostotic spheno-orbital meningiomas.

Material And Methods: The predictive regression model was conceived through the retrospective analysis of perioperative radiological data from 25 patients who initially underwent surgery at the Burdenko Neurosurgery Center for hyperostotic spheno-orbital meningiomas grade I. The model quality metrics were evaluated utilizing the performance library in the R programming language, including the Akaike Information Criterion, Bayesian Information Criterion, adjusted R-squared, Root Mean Squared Error, and Sigma.

A Neurosurgical Instrument Segmentation Approach to Assess Microsurgical Movements.

The ability to recognize anatomical landmarks, microsurgical instruments, and complex scenes and events in a surgical wound using computer vision presents new opportunities for studying microsurgery effectiveness. In this study, we aimed to develop an artificial intelligence-based solution for detecting, segmenting, and tracking microinstruments using a neurosurgical microscope. We have developed a technique to process videos from microscope camera, which involves creating a segmentation mask for the instrument and subsequently tracking it.

Computer Vision for Assessing Surgical Movements in Neurosurgery.

Objective evaluation of microsurgical technique quality is vital for successful training in neurosurgery. This study aimed to assess the accuracy of automatically detecting a neurosurgeon's proper posture and hand positioning using computer vision. We employed the RTMPose neural network model to identify key anatomical points in the neurosurgeon's projection and calculated various angles formed by connecting these points.

Reproducibility of Radiomic Features in Glial Brain Tumors.

In our recent research, we have effectively demonstrated the feasibility of classifying magnetic resonance images (MRI) of glial tumors into four histological types utilizing standardized volume of interest (VOI), radiomics and machine learning. This research aims to determine the reproducibility of our approach when the locations of VOI are changed. We were able to demonstrate high reproducibility of ML results when the same feature selection methodology was employed across different VOIs.

Radiomics Enhances Diagnostic and Prognostic Value of Diffusion Kurtosis Imaging in Diffuse Axonal Injury.

The aim of our study was to investigate the potential of advanced radiomics in analyzing diffusion kurtosis MRI (DKI) to increase the informativeness of DKI in diffuse axonal injury (DAI). We hypothesized that DKI radiomic features could be used to detect microstructural brain injury and predict outcomes in DAI. The study enrolled 31 patients with DAI (mean age 31.

Radiogenomics in NF2-Associated Schwannomatosis (Neurofibromatosis Type II): Exploratory Data Analysis.

Our pilot study aimed at exploratory radiogenomic data analysis in patients with NF2-associated schwannomatosis (formerly neurofibromatosis type II) to assume the potential of image biomarkers in this pathology. Fifty-three unrelated patients (37 (69.8%) women, avg.

Data Quality Estimation Via Model Performance: Machine Learning as a Validation Tool.

In our recent study, the attempt to classify neurosurgical operative reports into routinely used expert-derived classes exhibited an F-score not exceeding 0.74. This study aimed to test how improving the classifier (target variable) affected the short text classification with deep learning on real-world data.

The Assessment of Glioblastoma Metabolic Activity via 11C-Methionine PET and Radiomics.

Nowadays, the quantitative analysis of PET/CT data in patients with glioblastoma is not strictly standardized in the clinic and does not exclude the human factor. This study aimed to evaluate the relationship between the radiomic features of glioblastoma 11C-methionine PET images and the tumor-to-normal brain (T/N) ratio determined by radiologists in clinical routine. PET/CT data were obtained for 40 patients (mean age 55 ± 12 years; 77.

Predicting the Length of Stay in Neurosurgery with RuGPT-3 Language Model.

In this study, we update the evaluation of the Russian GPT3 model presented in our previous paper in predicting the length of stay (LOS) in neurosurgery. We aimed to assess the performance the Russian GPT-3 (ruGPT-3) language model in LOS prediction using narrative medical records in neurosurgery compared to doctors' and patients' expectations. Doctors appeared to have the most realistic LOS expectations (MAE = 2.

Multinomial Classification of Neurosurgical Operations Using Gradient Boosting and Deep Learning Algorithms.

This study aimed at testing the feasibility of neurosurgical procedures classification into 100+ classes using natural language processing and machine learning. A catboost algorithm and bidirectional recurrent neural network with a gated recurrent unit showed almost the same accuracy of ∼81%, with suggestions of correct class in top 2-3 scored classes up to 98.9%.

Noninvasive Glioma Grading with Deep Learning: A Pilot Study.

Gliomas are the most common neuroepithelial brain tumors, different by various biological tissue types and prognosis. They could be graded with four levels according to the 2007 WHO classification. The emergence of non-invasive histological and molecular diagnostics for nervous system neoplasms can revolutionize the efficacy and safety of medical care and radically reduce healthcare costs.

The Classification of Scientific Abstracts Using Text Statistical Features.

Automated abstracts classification could significantly facilitate scientific literature screening. The classification of short texts could be based on their statistical properties. This research aimed to evaluate the quality of short medical abstracts classification primarily based on text statistical features.

Length of Stay Prediction in Neurosurgery with Russian GPT-3 Language Model Compared to Human Expectations.

Patients, relatives, doctors, and healthcare providers anticipate the evidence-based length of stay (LOS) prediction in neurosurgery. This study aimed to assess the quality of LOS prediction with the GPT3 language model upon the narrative medical records in neurosurgery comparing to doctors' and patients' expectations. We found no significant difference (p = 0.

Semiautomatic Identification of Pulmonary Embolism in Electronic Health Records Through Sentence Labeling.

In this study, we tested the quality of the information extraction algorithm proposed by our group to detect pulmonary embolism (PE) in medical cases through sentence labeling. Having shown a comparable result (F1 = 0.921) to the best machine learning method (random forest, F1 = 0.

Prediction of Postoperative Speech Dysfunction Based on Cortico-Cortical Evoked Potentials and Machine Learning.

The possibility of postoperative speech dysfunction prediction in neurosurgery based on intraoperative cortico-cortical evoked potentials (CCEP) might provide a new basis to refine the criteria for the extent of intracerebral tumor resection and preserve patients' quality of life. In this study, we aimed to test the quality of predicting postoperative speech dysfunction with machine learning based on the initial intraoperative CCEP before tumor removal. CCEP data were reported for 26 patients.

A Comparison of Word Embeddings to Study Complications in Neurosurgery.

Our study aimed to compare the capability of different word embeddings to capture the semantic similarity of clinical concepts related to complications in neurosurgery at the level of medical experts. Eighty-four sets of word embeddings (based on Word2vec, GloVe, FastText, PMI, and BERT algorithms) were benchmarked in a clustering task. FastText model showed the best close to the medical expertise capability to group medical terms by their meaning (adjusted Rand index = 0.

'Moderate global aphasia': A generalized decline of language processing caused by glioma surgery but not stroke.

Unlike stroke, neurosurgical removal of left-hemisphere gliomas acts upon a reorganized language network and involves brain areas rarely damaged by stroke. We addressed whether this causes the profiles of neurosurgery- and stroke-induced language impairments to be distinct. K-means clustering of language assessment data (neurosurgery cohort: N = 88, stroke cohort: N = 95) identified similar profiles in both cohorts.

Inter-Rater Reliability of Unstructured Text Labeling: Artificially vs. Naturally Intelligent Approaches.

Unstructured medical text labeling technologies are expected to be highly demanded since the interest in artificial intelligence and natural language processing arises in the medical domain. Our study aimed to assess the agreement between experts who judged on the fact of pulmonary embolism (PE) in neurosurgical cases retrospectively based on electronic health records and assess the utility of the machine learning approach to automate this process. We observed a moderate agreement between 3 independent raters on PE detection (Light's kappa = 0.

The Classification of Short Scientific Texts Using Pretrained BERT Model.

Automated text classification is a natural language processing (NLP) technology that could significantly facilitate scientific literature selection. A specific topical dataset of 630 article abstracts was obtained from the PubMed database. We proposed 27 parametrized options of PubMedBERT model and 4 ensemble models to solve a binary classification task on that dataset.

Functional linguistic specificity of the left frontal aslant tract for spontaneous speech fluency: Evidence from intraoperative language mapping.

The left frontal aslant tract (FAT) has been proposed to be relevant for language, and specifically for spontaneous speech fluency. However, there is missing causal evidence that stimulation of the FAT affects spontaneous speech, and not language production in general. We present a series of 12 neurosurgical cases with awake language mapping of the cortex near the left FAT.

Classification of Intracranial Hemorrhage Subtypes Using Deep Learning on CT Scans.

Intracranial hemorrhage is a pathological condition that requires fast diagnosis and decision making. Recently, a neural network model for classification of different intracranial hemorrhage types was proposed by a member of our research group Konstantin Kotik as part of the machine learning competition at Kaggle. Our current pilot study aimed to test this model on real-world CT scans from patients with intracranial hemorrhage treated at N.

The Classification of Scientific Literature for Its Topical Tracking on a Small Human-Prepared Dataset.

The number of scientific publications is constantly growing to make their processing extremely time-consuming. We hypothesized that a user-defined literature tracking may be augmented by machine learning on article summaries. A specific dataset of 671 article abstracts was obtained and nineteen binary classification options using machine learning (ML) techniques on various text representations were proposed in a pilot study.

Semiautomated Approach for Muscle Weakness Detection in Clinical Texts.

The automated detection of adverse events in medical records might be a cost-effective solution for patient safety management or pharmacovigilance. Our group proposed an information extraction algorithm (IEA) for detecting adverse events in neurosurgery using documents written in a natural rich-in-morphology language. In this paper, we challenge to optimize and evaluate its performance for the detection of any extremity muscle weakness in clinical texts.

Predicting Postoperative Hospital Stay in Neurosurgery with Recurrent Neural Networks Based on Operative Reports.

This study aimed to predict the duration of the postoperative in-hospital period in neurosurgery based on unstructured operative reports, natural language processing, and deep learning. The recurrent neuronal network (RNN-GRU) was tuned on the word-embedded reports of primary surgical cases retrieved for the period between 2000 and 2017. A new test dataset obtained for the primary operations performed in 2018-2019 was used to evaluate model performance.