Search

Journal of neuro-oncology 155(1), 71-80 (2021). doi:10.1007/s11060-021-03844-1, Published by Springer Science + Business Media B.V, Dordrecht [u.a.]

OBJECTIVE Decision-making for intracranial tumor surgery requires balancing the oncological benefit against the risk for resection-related impairment. Risk estimates are commonly based on subjective experience and generalized numbers from the literature, but even experienced surgeons overestimate functional outcome after surgery. Today, there is no reliable and objective way to preoperatively predict an individual patient’s risk of experiencing any functional impairment. METHODS The authors developed a prediction model for functional impairment at 3 to 6 months after microsurgical resection, defined as a decrease in Karnofsky Performance Status of ≥ 10 points. Two prospective registries in Switzerland and Italy were used for development. External validation was performed in 7 cohorts from Sweden, Norway, Germany, Austria, and the Netherlands. Age, sex, prior surgery, tumor histology and maximum diameter, expected major brain vessel or cranial nerve manipulation, resection in eloquent areas and the posterior fossa, and surgical approach were recorded. Discrimination and calibration metrics were evaluated. RESULTS In the development (2437 patients, 48.2% male; mean age ± SD: 55 ± 15 years) and external validation (2427 patients, 42.4% male; mean age ± SD: 58 ± 13 years) cohorts, functional impairment rates were 21.5% and 28.5%, respectively. In the development cohort, area under the curve (AUC) values of 0.72 (95% CI 0.69–0.74) were observed. In the pooled external validation cohort, the AUC was 0.72 (95% CI 0.69–0.74), confirming generalizability. Calibration plots indicated fair calibration in both cohorts. The tool has been incorporated into a web-based application available at https://neurosurgery.shinyapps.io/impairment/. CONCLUSIONS Functional impairment after intracranial tumor surgery remains extraordinarily difficult to predict, although machine learning can help quantify risk. This externally validated prediction tool can serve as the basis for case-by-case discussions and risk-to-benefit estimation of surgical treatment in the individual patient.

Machine learning (ML) and artificial intelligence (AI) applications in the field of neuroimaging have been on the rise in recent years, and their clinical adoption is increasing worldwide. Deep learning (DL) is a field of ML that can be defined as a set of algorithms enabling a computer to be fed with raw data and progressively discover-through multiple layers of representation-more complex and abstract patterns in large data sets. The combination of ML and radiomics, namely the extraction of features from medical images, has proven valuable, too: Radiomic information can be used for enhanced image characterization and prognosis or outcome prediction. This chapter summarizes the basic concepts underlying ML application for neuroimaging and discusses technical aspects of the most promising algorithms, with a specific focus on Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), in order to provide the readership with the fundamental theoretical tools to better understand ML in neuroimaging. Applications are highlighted from a practical standpoint in the last section of the chapter, including: image reconstruction and restoration, image synthesis and super-resolution, registration, segmentation, classification, and outcome prediction.

Selecting a set of features to include in a clinical prediction model is not always a simple task. The goals of creating parsimonious models with low complexity while, at the same time, upholding predictive performance by explaining a large proportion of the variance within the dependent variable must be balanced. With this aim, one must consider the clinical setting and what data are readily available to clinicians at specific timepoints, as well as more obvious aspects such as the availability of computational power and size of the training dataset. This chapter elucidates the importance and pitfalls in feature selection, focusing on applications in clinical prediction modeling. We demonstrate simple methods such as correlation-, significance-, and variable importance-based filtering, as well as intrinsic feature selection methods such as Lasso and tree- or rule-based methods. Finally, we focus on two algorithmic wrapper methods for feature selection that are commonly used in machine learning: Recursive Feature Elimination (RFE), which can be applied regardless of data and model type, as well as Purposeful Variable Selection as described by Hosmer and Lemeshow, specifically for generalized linear models.

For almost a century, classical statistical methods including exponential smoothing and autoregression integrated moving averages (ARIMA) have been predominant in the analysis of time series (TS) and in the pursuit of forecasting future events from historical data. TS are chronological sequences of observations, and TS data are therefore prevalent in many aspects of clinical medicine and academic neuroscience. With the rise of highly complex and nonlinear datasets, machine learning (ML) methods have become increasingly popular for prediction or pattern detection and within neurosciences, including neurosurgery. ML methods regularly outperform classical methods and have been successfully applied to, inter alia, predict physiological responses in intracranial pressure monitoring or to identify seizures in EEGs. Implementing nonparametric methods for TS analysis in clinical practice can benefit clinical decision making and sharpen our diagnostic armory.

In the last decades, modern medicine has evolved into a data-centered discipline, generating massive amounts of granular high-dimensional data exceeding human comprehension. With improved computational methods, machine learning and artificial intelligence (AI) as tools for data processing and analysis are becoming more and more important. At the forefront of neuro-oncology and AI-research, the field of radiomics has emerged. Non-invasive assessments of quantitative radiological biomarkers mined from complex imaging characteristics across various applications are used to predict survival, discriminate between primary and secondary tumors, as well as between progression and pseudo-progression. In particular, the application of molecular phenotyping, envisioned in the field of radiogenomics, has gained popularity for both primary and secondary brain tumors. Although promising results have been obtained thus far, the lack of workflow standardization and availability of multicenter data remains challenging. The objective of this review is to provide an overview of novel applications of machine learning- and deep learning-based radiomics in primary and secondary brain tumors and their implications for future research in the field.

Advancements in population neuroscience are spurred by the availability of large scale, open datasets, such as the Human Connectome Project or recently introduced UK Biobank. With the increasing data availability, analyses of brain imaging data employ more and more sophisticated machine learning algorithms. However, all machine learning algorithms must balance generalization and complexity. As the detail of neuroimaging data leads to high-dimensional data spaces, model complexity and hence the chance of overfitting increases. Different methodological approaches can be applied to alleviate the problems that arise in high-dimensional settings by reducing the original information into meaningful and concise features. One popular approach is dimensionality reduction, which allows to summarize high-dimensional data into low-dimensional representations while retaining relevant trends and patterns. In this paper, principal component analysis (PCA) is discussed as widely used dimensionality reduction method based on current examples of population-based neuroimaging analyses.

We review the concept of overfitting, which is a well-known concern within the machine learning community, but less established in the clinical community. Overfitted models may lead to inadequate conclusions that may wrongly or even harmfully shape clinical decision-making. Overfitting can be defined as the difference among discriminatory training and testing performance, while it is normal that out-of-sample performance is equal to or ever so slightly worse than training performance for any adequately fitted model, a massively worse out-of-sample performance suggests relevant overfitting. We delve into resampling methods, specifically recommending k-fold cross-validation and bootstrapping to arrive at realistic estimates of out-of-sample error during training. Also, we encourage the use of regularization techniques such as L1 or L2 regularization, and to choose an appropriate level of algorithm complexity for the type of dataset used. Data leakage is addressed, and the importance of external validation to assess true out-of-sample performance and to-upon successful external validation-release the model into clinical practice is discussed. Finally, for highly dimensional datasets, the concepts of feature reduction using principal component analysis (PCA) as well as feature elimination using recursive feature elimination (RFE) are elucidated.

Advancements in neuroimaging and the availability of large-scale datasets enable the use of more sophisticated machine learning algorithms. In this chapter, we non-exhaustively discuss relevant analytical steps for the analysis of neuroimaging data using machine learning (ML), while the field of radiomics will be addressed separately (c.f., Chap. 18 -Radiomics). Broadly classified into supervised and unsupervised approaches, we discuss the encoding/decoding framework, which is often applied in cognitive neuroscience, and the use of ML for the analysis of unlabeled data using clustering.

The applications of artificial intelligence (AI) and machine learning (ML) in modern medicine are growing exponentially, and new developments are fast-paced. However, the lack of trust and appropriate legislation hinder its clinical implementation. Recently, there is a clear increase of directives and considerations on Ethical AI. However, most literature broadly deals with ethical tensions on a meta-level without offering hands-on advice in practice. In this article, we non-exhaustively cover basic practical guidelines regarding AI-specific ethical aspects, including transparency and explicability, equity and mitigation of biases, and lastly, liability.

We illustrate the steps required to train and validate a simple, machine learning-based clinical prediction model for any binary outcome, such as, for example, the occurrence of a complication, in the statistical programming language R. To illustrate the methods applied, we supply a simulated database of 10,000 glioblastoma patients who underwent microsurgery, and predict the occurrence of 12-month survival. We walk the reader through each step, including import, checking, and splitting of datasets. In terms of pre-processing, we focus on how to practically implement imputation using a k-nearest neighbor algorithm, and how to perform feature selection using recursive feature elimination. When it comes to training models, we apply the theory discussed in Parts I-III. We show how to implement bootstrapping and to evaluate and select models based on out-of-sample error. Specifically for classification, we discuss how to counteract class imbalance by using upsampling techniques. We discuss how the reporting of a minimum of accuracy, area under the curve (AUC), sensitivity, and specificity for discrimination, as well as slope and intercept for calibration-if possible alongside a calibration plot-is paramount. Finally, we explain how to arrive at a measure of variable importance using a universal, AUC-based method. We provide the full, structured code, as well as the complete glioblastoma survival database for the readers to download and execute in parallel to this section.

We provide explanations on the general principles of machine learning, as well as analytical steps required for successful machine learning-based predictive modeling, which is the focus of this series. In particular, we define the terms machine learning, artificial intelligence, as well as supervised and unsupervised learning, continuing by introducing optimization, thus, the minimization of an objective error function as the central dogma of machine learning. In addition, we discuss why it is important to separate predictive and explanatory modeling, and most importantly state that a prediction model should not be used to make inferences. Lastly, we broadly describe a classical workflow for training a machine learning model, starting with data pre-processing and feature engineering and selection, continuing on with a training structure consisting of a resampling method, hyperparameter tuning, and model selection, and ending with evaluation of model discrimination and calibration as well as robust internal or external validation of the fully developed model. Methodological rigor and clarity as well as understanding of the underlying reasoning of the internal workings of a machine learning approach are required, otherwise predictive applications despite being strong analytical tools are not well accepted into the clinical routine.

This chapter goes through the steps required to train and validate a simple, machine learning-based clinical prediction model for any continuous outcome. We supply fully structured code for the readers to download and execute in parallel to this section, as well as a simulated database of 10,000 glioblastoma patients who underwent microsurgery, and predict survival from diagnosis in months. We walk the reader through each step, including import, checking, splitting of data. In terms of pre-processing, we focus on how to practically implement imputation using a k-nearest neighbor algorithm. We also illustrate how to select features based on recursive feature elimination and how to use k-fold cross validation. We demonstrate a generalized linear model, a generalized additive model, a random forest, a ridge regressor, and a Least Absolute Shrinkage and Selection Operator (LASSO) regressor. Specifically for regression, we discuss how to evaluate root mean square error (RMSE), mean average error (MAE), and the R2 statistic, as well as how a quantile-quantile plot can be used to assess the performance of the regressor along the spectrum of the outcome variable, similarly to calibration when dealing with binary outcomes. Finally, we explain how to arrive at a measure of variable importance using a universal, nonparametric method.

Various available metrics to describe model performance in terms of discrimination (area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 Score) and calibration (slope, intercept, Brier score, expected/observed ratio, Estimated Calibration Index, Hosmer-Lemeshow goodness-of-fit) are presented. Recalibration is introduced, with Platt scaling and Isotonic regression as proposed methods. We also discuss considerations regarding the sample size required for optimal training of clinical prediction models-explaining why low sample sizes lead to unstable models, and offering the common rule of thumb of at least ten patients per class per input feature, as well as some more nuanced approaches. Missing data treatment and model-based imputation instead of mean, mode, or median imputation is also discussed. We explain how data standardization is important in pre-processing, and how it can be achieved using, e.g. centering and scaling. One-hot encoding is discussed-categorical features with more than two levels must be encoded as multiple features to avoid wrong assumptions. Regarding binary classification models, we discuss how to select a sensible predicted probability cutoff for binary classification using the closest-to-(0,1)-criterion based on AUC or based on the clinical question (rule-in or rule-out). Extrapolation is also discussed.

Humans survive and thrive through social exchange. Yet, social dependency also comes at a cost. Perceived social isolation, or loneliness, affects physical and mental health, cognitive performance, overall life expectancy, and increases vulnerability to Alzheimer's disease-related dementias. Despite severe consequences on behavior and health, the neural basis of loneliness remains elusive. Using the UK Biobank population imaging-genetics cohort (n = ~40,000, aged 40-69 years when recruited, mean age = 54.9), we test for signatures of loneliness in grey matter morphology, intrinsic functional coupling, and fiber tract microstructure. The loneliness-linked neurobiological profiles converge on a collection of brain regions known as the 'default network'. This higher associative network shows more consistent loneliness associations in grey matter volume than other cortical brain networks. Lonely individuals display stronger functional communication in the default network, and greater microstructural integrity of its fornix pathway. The findings fit with the possibility that the up-regulation of these neural circuits supports mentalizing, reminiscence and imagination to fill the social void.

Introduction The postoperative functional status of patients with intracranial tumors is influenced by patient-specific factors, including age. Research question This study aimed to elucidate the association between age and postoperative morbidity or mortality following the resection of brain tumors. Material and methods A multicenter database was retrospectively reviewed. Functional status was assessed before and 3–6 months after tumor resection by the Karnofsky Performance Scale (KPS). Uni- and multivariable linear regression were used to estimate the association of age with postoperative change in KPS. Logistic regression models for a ≥10-point decline in KPS or mortality were built for patients ≥75 years. Results The total sample of 4864 patients had a mean age of 56.4 ​± ​14.4 years. The mean change in pre-to postoperative KPS was −1.43. For each 1-year increase in patient age, the adjusted change in postoperative KPS was −0.11 (95% CI -0.14 - - 0.07). In multivariable analysis, patients ≥75 years had an odds ratio of 1.51 to experience postoperative functional decline (95%CI 1.21–1.88) and an odds ratio of 2.04 to die (95%CI 1.33–3.13), compared to younger patients. Discussion Patients with intracranial tumors treated surgically showed a minor decline in their postoperative functional status. Age was associated with this decline in function, but only to a small extent. Conclusion Patients ≥75 years were more likely to experience a clinically meaningful decline in function and about two times as likely to die within the first 6 months after surgery, compared to younger patients.

We recently read the article by Yokoyama and colleagues ([1][1]), in which the authors report a predictive model integrating DNA methylation status of three mucin genes to predict overall survival at a designated 5-year interval in pancreatic cancer. They collected samples from 191 patients and

Background Recent technological advances have led to the development and implementation of machine learning (ML) in various disciplines, including neurosurgery. Our goal was to conduct a comprehensive survey of neurosurgeons to assess the acceptance of and attitudes toward ML in neurosurgical practice and to identify factors associated with its use. Methods The online survey consisted of nine or ten mandatory questions and was distributed in February and March 2019 through the European Association of Neurosurgical Societies (EANS) and the Congress of Neurosurgeons (CNS). Results Out of 7280 neurosurgeons who received the survey, we received 362 responses, with a response rate of 5%, mainly in Europe and North America. In total, 103 neurosurgeons (28.5%) reported using ML in their clinical practice, and 31.1% in research. Adoption rates of ML were relatively evenly distributed, with 25.6% for North America, 30.9% for Europe, 33.3% for Latin America and the Middle East, 44.4% for Asia and Pacific and 100% for Africa with only two responses. No predictors of clinical ML use were identified, although academic settings and subspecialties neuro-oncology, functional, trauma and epilepsy predicted use of ML in research. The most common applications were for predicting outcomes and complications, as well as interpretation of imaging. Conclusions This report provides a global overview of the neurosurgical applications of ML. A relevant proportion of the surveyed neurosurgeons reported clinical experience with ML algorithms. Future studies should aim to clarify the role and potential benefits of ML in neurosurgery and to reconcile these potential advantages with bioethical considerations.

Objective: Patient-reported outcome measures following elective lumbar fusion surgery demonstrate major heterogeneity. Individualized prediction tools can provide valuable insights for shared decision-making. We externally validated the spine surgical care and outcomes assessment programme/comparative effectiveness translational network (SCOAP-CERTAIN) model for prediction of 12-month minimum clinically important difference in Oswestry Disability Index (ODI) and in numeric rating scales for back (NRS-BP) and leg pain (NRS-LP) after elective lumbar fusion. Methods: Data from a prospective registry were obtained. We calculated the area under the curve (AUC), calibration slope and intercept, and Hosmer–Lemeshow values to estimate discrimination and calibration of the models. Results: We included 100 patients, with average age of 50.4 ± 11.4 years. For 12-month ODI, AUC was 0.71 while the calibration intercept and slope were 1.08 and 0.95, respectively. For NRS-BP, AUC was 0.72, with a calibration intercept of 1.02, and slope of 0.74. For NRS-LP, AUC was 0.83, with a calibration intercept of 1.08, and slope of 0.95. Sensitivity ranged from 0.64 to 1.00, while specificity ranged from 0.38 to 0.65. A lack of fit was found for all three models based on Hosmer–Lemeshow testing. Conclusions: The SCOAP-CERTAIN tool can accurately predict which patients will achieve favourable outcomes. However, the predicted probabilities—which are the most valuable in clinical practice—reported by the tool do not correspond well to the true probability of a favourable outcome. We suggest that any prediction tool should first be externally validated before it is applied in routine clinical practice. Graphic abstract: These slides can be retrieved under Electronic Supplementary Material.[Figure not available: see fulltext.]