Artificial Intelligence for Clinical Decision Support in Acute Ischemic Stroke: A Systematic Review.

BACKGROUND: Established randomized trial-based parameters for acute ischemic stroke group patients into generic treatment groups, leading to attempts using various artificial intelligence (AI) methods to directly correlate patient characteristics to outcomes and thereby provide decision support to stroke clinicians. We review AI-based clinical decision support systems in the development stage, specifically regarding methodological robustness and constraints for clinical implementation. METHODS: Our systematic review included full-text English language publications proposing a clinical decision support system using AI techniques for direct decision support in acute ischemic stroke cases in adult patients. We (1) describe data and outcomes used in those systems, (2) estimate the systems' benefits compared with traditional stroke diagnosis and treatment, and (3) reported concordance with reporting standards for AI in healthcare. RESULTS: One hundred twenty-one studies met our inclusion criteria. Sixty-five were included for full extraction. In our sample, utilized data sources, methods, and reporting practices were highly heterogeneous. CONCLUSIONS: Our results suggest significant validity threats, dissonance in reporting practices, and challenges to clinical translation. We outline practical recommendations for the successful implementation of AI research in acute ischemic stroke treatment and diagnosis.

A precision medicine framework for personalized simulation of hemodynamics in cerebrovascular disease.

BACKGROUND: Cerebrovascular disease, in particular stroke, is a major public health challenge. An important biomarker is cerebral hemodynamics. To measure and quantify cerebral hemodynamics, however, only invasive, potentially harmful or time-to-treatment prolonging methods are available. RESULTS: We present a simulation-based approach which allows calculation of cerebral hemodynamics based on the patient-individual vessel configuration derived from structural vessel imaging. For this, we implemented a framework allowing segmentation and annotation of brain vessels from structural imaging followed by 0-dimensional lumped simulation modeling of cerebral hemodynamics. For annotation, a 3D-graphical user interface was implemented. For 0D-simulation, we used a modified nodal analysis, which was adapted for easy implementation by code. The simulation enables identification of areas vulnerable to stroke and simulation of changes due to different systemic blood pressures. Moreover, sensitivity analysis was implemented allowing the live simulation of changes to simulate procedures and disease progression. Beyond presentation of the framework, we demonstrated in an exploratory analysis in 67 patients that the simulation has a high specificity and low-to-moderate sensitivity to detect perfusion changes in classic perfusion imaging. CONCLUSIONS: The presented precision medicine approach using novel biomarkers has the potential to make the application of harmful and complex perfusion methods obsolete.

Lymphomatoid papulosis: A cutaneous lymphoproliferative disorder in a patient on fingolimod for multiple sclerosis.

BACKGROUND: Fingolimod was the first oral disease-modifying treatment for relapsing-remitting multiple sclerosis. It has previously been associated with the development of lymphoma. OBJECTIVE: To describe a case of lymphomatoid papulosis, a CD30+ cutaneous lymphoproliferative disorder, in a patient taking fingolimod. METHODS: Case study. RESULTS: Our patient developed lymphomatoid papulosis 2 months after starting fingolimod. Histology confirmed the diagnosis. The drug was withdrawn. Resolution began only 2 days later. CONCLUSIONS: Lymphomatoid papulosis is a benign subtype of cutaneous T-cell lymphoma, but up to 20% of cases can transform to a malignant course. Patients on fingolimod and physicians caring for them should be mindful of the need to monitor the skin.

Interleukin 28B gene polymorphisms and Epstein-Barr virus-associated lymphoproliferative diseases.

OBJECTIVES: Single-nucleotide polymorphisms (SNPs) near the interleukin (IL) 28B gene encoding a type III interferon (IFN-λ) are the most important genetic predictors of treatment response to hepatitis C virus (HCV). This retrospective study was undertaken to determine any association between IL28B SNPs and the development of viraemia in Epstein-Barr virus (EBV)-driven acute infectious mononucleosis (IM) and post-transplant lymphoproliferative disease (PTLD). METHODS: Genomic DNA extracted from plasma from 45 EBV seropositive controls and 46 acute IM, 23 non-PTLD (transplant) and 21 PTLD patients was tested by PCR for 2 SNPs within IL28B. EBV DNA levels were tested in IM and PTLD samples by a real-time quantitative PCR. RESULTS: No significant differences were seen in SNP frequencies at rs12979860 and rs8099917 in IM and PTLD patients compared to EBV seropositive controls and transplant patients. EBV DNA levels were lower in IM and PTLD patients with CC (a favourable genotype in HCV) at rs12979860 compared to non-CC genotypes (p = 0.055). Acute IM patients with CC had significantly lower levels of EBV DNA in plasma compared to those with non-CC genotypes (p = 0.011). CONCLUSIONS: Genotype CC may influence anti-viral responses of IFN-λ, thereby allowing better control of EBV viraemia during lymphoproliferation, particularly in IM.

Personalised simulation of hemodynamics in cerebrovascular disease: lessons learned from a study of diagnostic accuracy.

Intracranial atherosclerotic disease (ICAD) poses a significant risk of subsequent stroke but current prevention strategies are limited. Mechanistic simulations of brain hemodynamics offer an alternative precision medicine approach by utilising individual patient characteristics. For clinical use, however, current simulation frameworks have insufficient validation. In this study, we performed the first quantitative validation of a simulation-based precision medicine framework to assess cerebral hemodynamics in patients with ICAD against clinical standard perfusion imaging. In a retrospective analysis, we used a 0-dimensional simulation model to detect brain areas that are hemodynamically vulnerable to subsequent stroke. The main outcome measures were sensitivity, specificity, and area under the receiver operating characteristics curve (ROC AUC) of the simulation to identify brain areas vulnerable to subsequent stroke as defined by quantitative measurements of relative mean transit time (relMTT) from dynamic susceptibility contrast MRI (DSC-MRI). In 68 subjects with unilateral stenosis >70% of the internal carotid artery (ICA) or middle cerebral artery (MCA), the sensitivity and specificity of the simulation were 0.65 and 0.67, respectively. The ROC AUC was 0.68. The low-to-moderate accuracy of the simulation may be attributed to assumptions of Newtonian blood flow, rigid vessel walls, and the use of time-of-flight MRI for geometric representation of subject vasculature. Future simulation approaches should focus on integrating additional patient data, increasing accessibility of precision medicine tools to clinicians, addressing disease burden disparities amongst different populations, and quantifying patient benefit. Our results underscore the need for further improvement of mechanistic simulations of brain hemodynamics to foster the translation of the technology to clinical practice.

A deep learning analysis of stroke onset time prediction and comparison to DWI-FLAIR mismatch.

INTRODUCTION: When time since stroke onset is unknown, DWI-FLAIR mismatch rating is an established technique for patient stratification. A visible DWI lesion without corresponding parenchymal hyperintensity on FLAIR suggests time since onset of under 4.5 h and thus a potential benefit from intravenous thrombolysis. To improve accuracy and availability of the mismatch concept, deep learning might be able to augment human rating and support decision-making in these cases. METHODS: We used unprocessed DWI and coregistered FLAIR imaging data to train a deep learning model to predict dichotomized time since ischemic stroke onset. We analyzed the performance of Group Convolutional Neural Networks compared to other deep learning methods. Unlabeled imaging data was used for pre-training. Prediction performance of the best deep learning model was compared to the performance of four independent junior and senior raters. Additionally, in cases deemed indeterminable by human raters, model ratings were used to augment human performance. Post-hoc gradient-based explanations were analyzed to gain insights into model predictions. RESULTS: Our best predictive model performed comparably to human raters. Using model ratings in cases deemed indeterminable by human raters improved rating accuracy and interrater agreement for junior and senior ratings. Post-hoc explainability analyses showed that the model localized stroke lesions to derive predictions. DISCUSSION: Our analysis shows that deep learning based clinical decision support has the potential to improve the accessibility of the DWI-FLAIR mismatch concept by supporting patient stratification.

A review of the clinical spectrum of BRAT1 disorders and case of developmental and epileptic encephalopathy surviving into adulthood.

Pathogenic variants in BRAT1 are associated with a spectrum of clinical syndromes ranging from Lethal Neonatal Rigidity and Multifocal Seizure syndrome (RMFSL) to Neurodevelopmental Disorder with Cerebellar Atrophy and with or without Seizures (NEDCAS). RMFSL is characterized by early-onset multifocal seizures with microcephaly. Death occurs during infancy although a less severe course with later onset seizures and longer survival into childhood has been described. Here, we summarize published cases of BRAT1 disorders and present the case of a 20-year-old man with two heterozygous BRAT1 variants and a relatively later age of seizure onset with survival into adulthood. This case expands the spectrum of disease associated with BRAT1 variants and highlights the utility of genetic testing to identify the cause of developmental and epileptic encephalopathies where clinical heterogeneity within a spectrum of disease exists.

Anatomical labeling of intracranial arteries with deep learning in patients with cerebrovascular disease.

Brain arteries are routinely imaged in the clinical setting by various modalities, e.g., time-of-flight magnetic resonance angiography (TOF-MRA). These imaging techniques have great potential for the diagnosis of cerebrovascular disease, disease progression, and response to treatment. Currently, however, only qualitative assessment is implemented in clinical applications, relying on visual inspection. While manual or semi-automated approaches for quantification exist, such solutions are impractical in the clinical setting as they are time-consuming, involve too many processing steps, and/or neglect image intensity information. In this study, we present a deep learning-based solution for the anatomical labeling of intracranial arteries that utilizes complete information from 3D TOF-MRA images. We adapted and trained a state-of-the-art multi-scale Unet architecture using imaging data of 242 patients with cerebrovascular disease to distinguish 24 arterial segments. The proposed model utilizes vessel-specific information as well as raw image intensity information, and can thus take tissue characteristics into account. Our method yielded a performance of 0.89 macro F1 and 0.90 balanced class accuracy (bAcc) in labeling aggregated segments and 0.80 macro F1 and 0.83 bAcc in labeling detailed arterial segments on average. In particular, a higher F1 score than 0.75 for most arteries of clinical interest for cerebrovascular disease was achieved, with higher than 0.90 F1 scores in the larger, main arteries. Due to minimal pre-processing, simple usability, and fast predictions, our method could be highly applicable in the clinical setting.

BRAVE-NET: Fully Automated Arterial Brain Vessel Segmentation in Patients With Cerebrovascular Disease.

Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods: BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from three different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD); and via visual qualitative rating. Results: The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165, and 95HD = 29.153. The BRAVE-NET model was also the most resistant toward false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion: We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease and an external set of healthy volunteers. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.

A U-Net Deep Learning Framework for High Performance Vessel Segmentation in Patients With Cerebrovascular Disease.

Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based vessel segmentation algorithms need to be hand-crafted and are insufficiently validated. A specialized deep learning method-the U-net-is a promising alternative. Using labeled data from 66 patients with cerebrovascular disease, the U-net framework was optimized and evaluated with three metrics: Dice coefficient, 95% Hausdorff distance (95HD) and average Hausdorff distance (AVD). The model performance was compared with the traditional segmentation method of graph-cuts. Training and reconstruction was performed using 2D patches. A full and a reduced architecture with less parameters were trained. We performed both quantitative and qualitative analyses. The U-net models yielded high performance for both the full and the reduced architecture: A Dice value of ~0.88, a 95HD of ~47 voxels and an AVD of ~0.4 voxels. The visual analysis revealed excellent performance in large vessels and sufficient performance in small vessels. Pathologies like cortical laminar necrosis and a rete mirabile led to limited segmentation performance in few patients. The U-net outperfomed the traditional graph-cuts method (Dice ~0.76, 95HD ~59, AVD ~1.97). Our work highly encourages the development of clinically applicable segmentation tools based on deep learning. Future works should focus on improved segmentation of small vessels and methodologies to deal with specific pathologies.

Identification of GAA variants through whole exome sequencing targeted to a cohort of 606 patients with unexplained limb-girdle muscle weakness.

BACKGROUND: Late-onset Pompe disease is a rare genetic neuromuscular disorder caused by a primary deficiency of α-glucosidase and the associated accumulation of glycogen in lysosomal vacuoles. The deficiency of α-glucosidase can often be detected using an inexpensive and readily accessible dried blood spot test when Pompe disease is suspected. Like several neuromuscular disorders, Pompe disease typically presents with progressive weakness of limb-girdle muscles and respiratory insufficiency. Due to the phenotypic heterogeneity of these disorders, however, it is often difficult for clinicians to reach a diagnosis for patients with Pompe disease. Six hundred and six patients from a European population were recruited onto our study. Inclusion criteria stipulated that index cases must present with limb-girdle weakness or elevated serum creatine kinase activity. Whole exome sequencing with at least 250 ng DNA was completed using an Illumina exome capture and a 38 Mb baited target. A panel of 169 candidate genes for limb-girdle weakness was analysed for disease-causing variants. RESULTS: A total of 35 variants within GAA were detected. Ten distinct variants in eight unrelated index cases (and four siblings not sequenced in our study) were considered disease-causing, with the patients presenting with heterogeneous phenotypes. The eight unrelated individuals were compound heterozygotes for two variants. Six patients carried the intronic splice site c.-13 T > G transversion and two of the six patients also carried the exonic p.Glu176ArgfsTer45 frameshift. Four of the ten variants were novel in their association with Pompe disease. CONCLUSIONS: Here, we highlight the advantage of using whole exome sequencing as a tool for detecting, diagnosing and treating patients with rare, clinically variable genetic disorders.

Ubiquitin associated protein 1 is a risk factor for frontotemporal lobar degeneration.

Frontotemporal lobar degeneration (FTLD) is now recognised as a common form of early onset dementia. Up to 40% of patients have a family history of disease demonstrating a large genetic component to its etiology. Linkage to chromosome 9p21 has recently been reported in families with this disorder. We undertook a large scale two-stage linkage disequilibrium mapping approach of this region in the Manchester FTLD cohort. We identified association of ubiquitin associated protein 1 (UBAP1; OR 1.42 95% CI 1.08-1.88, P=0.013) with FTLD in this cohort and we replicated this finding in an additional two independent cohorts from the Netherlands (OR 1.33 95% CI 1.04-1.69, P=0.022), the USA (OR 1.4 95% CI 1.02-1.92, P=0.032) and a forth Spanish cohort approached significant association (OR 1.45 95% CI 0.97-2.17, P=0.064). However, we failed to replicate in a fifth cohort from London (OR 0.99 95% CI 0.72-1.37, P=0.989). Quantitative analysis of UBAP1 mRNA extracted from tissue from the Manchester cases demonstrated a significant reduction of expression from the disease-associated haplotype. In addition, we identified a case of familial FTLD that demonstrated colocalisation of UBAP1 and TDP-43 in the neuronal cytoplasmic inclusions in the brain of this individual. Our data for the first time identifies UBAP1 as a genetic risk factor for FTLD and suggests a mechanistic relationship between this protein and TDP-43.