Machine Learning Approach to Identify Stroke Within 4.5 Hours

Enriching the Study Population for Ischemic Stroke Therapeutic Trials Using a Machine Learning Algorithm

Background

Strokes represent a leading cause of mortality globally. The evolution of developing new therapies is subject to safety and efficacy testing in clinical trials, which operate in a limited timeframe. To maximize the impact of these trials, patient cohorts for whom ischemic stroke is likely during that designated timeframe should be identified. Machine learning may improve upon existing candidate identification methods in order to maximize the impact of clinical trials for stroke prevention and treatment and improve patient safety.

Methods

A retrospective study was performed using 41,970 qualifying patient encounters with ischemic stroke from inpatient visits recorded from over 700 inpatient and ambulatory care sites. Patient data were extracted from electronic health records and used to train and test a gradient boosted machine learning algorithm (MLA) to predict the patients' risk of experiencing ischemic stroke from the period of 1 day up to 1 year following the patient encounter. The primary outcome of interest was the occurrence of ischemic stroke.

Results

After training for optimization, XGBoost obtained a specificity of 0.793, a positive predictive value (PPV) of 0.194, and a negative predictive value (NPV) of 0.985. The MLA further obtained an area under the receiver operating characteristic (AUROC) of 0.88. The Logistic Regression and multilayer perceptron models both achieved AUROCs of 0.862. Among features that significantly impacted the prediction of ischemic stroke were previous stroke history, age, and mean systolic blood pressure.

Conclusion

MLAs have the potential to more accurately predict the near risk of ischemic stroke within a 1-year prediction window for individuals who have been hospitalized. This risk stratification tool can be used to design clinical trials to test stroke prevention treatments in high-risk populations by identifying subjects who would be more likely to benefit from treatment.

Predicting 1-Hour Thrombolysis Effect of r-tPA in Patients With Acute Ischemic Stroke Using Machine Learning Algorithm

Background: Thrombolysis with r-tPA is recommended for patients after acute ischemic stroke (AIS) within 4.5 h of symptom onset. However, only a few patients benefit from this therapeutic regimen. Thus, we aimed to develop an interpretable machine learning (ML)–based model to predict the thrombolysis effect of r-tPA at the super-early stage.

Methods: A total of 353 patients with AIS were divided into training and test data sets. We then used six ML algorithms and a recursive feature elimination (RFE) method to explore the relationship among the clinical variables along with the NIH stroke scale score 1 h after thrombolysis treatment. Shapley additive explanations and local interpretable model–agnostic explanation algorithms were applied to interpret the ML models and determine the importance of the selected features.

Results: Altogether, 353 patients with an average age of 63.0 (56.0–71.0) years were enrolled in the study. Of these patients, 156 showed a favorable thrombolysis effect and 197 showed an unfavorable effect. A total of 14 variables were enrolled in the modeling, and 6 ML algorithms were used to predict the thrombolysis effect. After RFE screening, seven variables under the gradient boosting decision tree (GBDT) model (area under the curve = 0.81, specificity = 0.61, sensitivity = 0.9, and F1 score = 0.79) demonstrated the best performance. Of the seven variables, activated partial thromboplastin clotting time (time), B-type natriuretic peptide, and fibrin degradation products were the three most important clinical characteristics that might influence r-tPA efficiency.

Conclusion: This study demonstrated that the GBDT model with the seven variables could better predict the early thrombolysis effect of r-tPA.

Development and external validation of a stability machine learning model to identify wake-up stroke onset time from MRI

OBJECTIVES

To develop and externally validate a machine learning (ML) model based on diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) to identify the onset time of wake-up stroke from MRI.

METHODS

DWI and FLAIR images of stroke patients within 24 h of clear symptom onset in our hospital (dataset 1, n = 410) and another hospital (dataset 2, n = 177) were included. Seven ML models based on dataset 1 were developed to estimate the stroke onset time for binary classification (≤ 4.5 h or > 4.5 h): Random Forest (RF), support vector machine with kernel (svmLinear) or radial basis function kernel (svmRadial), Bayesian (Bayes), K-nearest neighbor (KNN), adaptive boosting (AdaBoost), and neural network (NNET). ROC analysis and RSD were performed to evaluate the performance and stability of the ML models, respectively, and dataset 2 was externally validated to evaluate the model generalization ability using ROC analysis.

RESULTS

svmRadial achieved the best performance with the highest AUC and accuracy (AUC: 0.896, accuracy: 0.878), and was the most stable (RSD% of AUC: 0.08, RSD% of accuracy: 0.06). The svmRadial model was then selected as the final model, and the AUC of the svmRadial model for predicting the onset time external validation was 0.895, with 0.825 accuracy.

CONCLUSIONS

The svmRadial model using DWI + FLAIR is the most stable and generalizable for identifying the onset time of wake-up stroke patients within 4.5 h of symptom onset.

KEY POINTS

• Machining learning model helps clinicians to identify wake-up stroke patients within 4.5 h of symptom onset. • A prospective study showed that svmRadial model based on DWI + FLAIR was the most stable in predicting the stroke onset time. • External validation showed that svmRadial model has good generalization ability in predicting the stroke onset time.

Ability of weakly supervised learning to detect acute ischemic stroke and hemorrhagic infarction lesions with diffusion-weighted imaging

BACKGROUND

Gradient-recalled echo (GRE) sequence is time-consuming and not routinely performed. Herein, we aimed to investigate the ability of weakly supervised learning to identify acute ischemic stroke (AIS) and concurrent hemorrhagic infarction based on diffusion-weighted imaging (DWI).

METHODS

First, we proposed spatially locating small stroke lesions in different positions and hemorrhagic infarction lesions by residual neural and visual geometry group networks using weakly supervised learning. Next, we compared the sensitivity and specificity for identifying automatically concurrent hemorrhagic infarction in stroke patients with the sensitivity and specificity of human readings of diffusion and b₀ images to evaluate the performance of the weakly supervised methods. Also, the labeling time of the weakly supervised approach was compared with that of the fully supervised approach.

RESULTS

Data from a total of 1,027 patients were analyzed. The residual neural network displayed a higher sensitivity than did the visual geometry group network in spatially locating the small stroke and hemorrhagic infarction lesions. The residual neural network had significantly greater patient-level sensitivity than did the human readers (98.4% versus 86.2%, P=0.008) in identifying concurrent hemorrhagic infarction with GRE as the reference standard; however, their specificities were comparable (95.4% versus 96.9%, P>0.99). Weak labeling of lesions required significantly less time than did full labeling of lesions (2.667 versus 10.115 minutes, P<0.001).

CONCLUSIONS

Weakly supervised learning was able to spatially locate small stroke lesions in different positions and showed more sensitivity than did human reading in identifying concurrent hemorrhagic infarction based on DWI. The proposed approach can reduce the labeling workload.

MRI radiomic features-based machine learning approach to classify ischemic stroke onset time

PURPOSE

We aimed to investigate the ability of MRI radiomics features-based machine learning (ML) models to classify the time since stroke onset (TSS), which could aid in stroke assessment and treatment options.

METHODS

This study involved 84 patients with acute ischemic stroke due to anterior circulation artery occlusion (51 in the training cohort and 33 in the independent test cohort). Region of infarct segmentation was manually outlined by 3D-slicer software. Image processing including registration, normalization and radiomics features calculation were done in R (version 3.6.1). A total of 4312 radiomic features from each image sequence were captured and used in six ML models to estimate stroke onset time for binary classification (≤ 4.5 h). Receiver-operating characteristic curve (ROC) and other parameters were calculated to evaluate the performance of the models in both training and test cohorts.

RESULTS

Twelve radiomics and six clinic features were selected to construct the ML models for TSS classification. The deep learning model-based DWI/ADC radiomic features performed the best for binary TSS classification in the independent test cohort, with an AUC of 0.754, accuracy of 0.788, sensitivity of 0.952, specificity of 0.500, positive predictive value of 0.769, and negative predictive value of 0.857, respectively. Furthermore, adding clinical information did not improve the performance of the DWI/ADC-based deep learning model. The TSS prediction models can be visited at: http://123.57.65.199:3838/deeptss/ .

CONCLUSIONS

A unique deep learning model based on DWI/ADC radiomic features was constructed for TSS classification, which could aid in decision making for thrombolysis in patients with unknown stroke onset.

Machine Learning in Action: Stroke Diagnosis and Outcome Prediction

The application of machine learning has rapidly evolved in medicine over the past decade. In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis. The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis and outcome prediction. Although imaging-based feature recognition and segmentation have significantly facilitated rapid stroke diagnosis and triaging, stroke prognostication is dependent on a multitude of patient specific as well as clinical factors and hence accurate outcome prediction remains challenging. Despite its vital role in stroke diagnosis and prognostication, it is important to recognize that machine learning output is only as good as the input data and the appropriateness of algorithm applied to any specific data set. Additionally, many studies on machine learning tend to be limited by small sample size and hence concerted efforts to collate data could improve evaluation of future machine learning tools in stroke. In the present state, machine learning technology serves as a helpful and efficient tool for rapid clinical decision making while oversight from clinical experts is still required to address specific aspects not accounted for in an automated algorithm. This article provides an overview of machine learning technology and a tabulated review of pertinent machine learning studies related to stroke diagnosis and outcome prediction.

Foundations of Lesion Detection Using Machine Learning in Clinical Neuroimaging

This chapter describes technical considerations and current and future clinical applications of lesion detection using machine learning in the clinical setting. Lesion detection is central to neuroradiology and precedes all further processes which include but are not limited to lesion characterization, quantification, longitudinal disease assessment, prognosis, and prediction of treatment response. A number of machine learning algorithms focusing on lesion detection have been developed or are currently under development which may either support or extend the imaging process. Examples include machine learning applications in stroke, aneurysms, multiple sclerosis, neuro-oncology, neurodegeneration, and epilepsy.

A Semi-Supervised Learning Framework to Leverage Proxy Information for Stroke MRI Analysis

Treating acute ischemic stroke (AIS) patients is a time-sensitive endeavor, as therapies target areas experiencing ischemia to prevent irreversible damage to brain tissue. Depending on how an AIS is progressing, thrombolytics such as tissue-plasminogen activator (tPA) may be administered within a short therapeutic window. The underlying conditions for optimal treatment are varied. While previous clinical guidelines only permitted tPA to be administered to patients with a known onset within 4.5 hours, clinical trials demonstrated that patients with signal intensity differences between diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) sequences in an MRI study can benefit from thrombolytic therapy. This intensity difference, known as DWI-FLAIR mismatch, is prone to high inter-reader variability. Thus, a paradigm exists where onset time serves as a weak proxy for DWI-FLAIR mismatch. In this study, we sought to detect DWI-FLAIR mismatch in an automated fashion, and we compared this to assessments done by three expert neuroradiologists. Our approach involved training a deep learning model on MRI to classify tissue clock and leveraging time clock as a weak proxy label to supplement training in a semi-supervised learning (SSL) framework. We evaluate our deep learning model by testing it on an unseen dataset from an external institution. In total, our proposed framework was able to improve detection of DWI-FLAIR mismatch, achieving a top ROC-AUC of 74.30%. Our study illustrated that incorporating clinical proxy information into SSL can improve model optimization by increasing the fidelity of unlabeled samples included in the training process.

Clinical-Diffusion Mismatch Is Associated with Early Neurological Improvement after Late-Window Endovascular Treatment

BACKGROUND

Clinical-diffusion mismatch (CDM) and perfusion-diffusion mismatch (PDM) are used to select patients for endovascular thrombectomy (EVT) in the late-window period. As CDM well reflects true penumbra, we hypothesized that patients with CDM and PDM would respond better to EVT than those with PDM only at the late-window period.

METHODS

Acute ischemic stroke patients who received EVT 6-24 h after stroke onset were included. PDM (perfusion-/diffusion-weighted image (DWI) lesion volume >1.8) was used to select candidates for EVT in this time-period in our center. CDM was defined according to the DAWN trial criteria. Response to EVT was compared between patients with and without CDM. Early neurological improvement (ENI) was defined as improvement >4 points on National Institutes of Health Stroke Scale (NIHSS) score 1 day after EVT. Multivariable analysis was performed to investigate independent factors associated with ENI. The correlation between DWI lesion volume and NIHSS score was investigated in those with and without CDM.

RESULTS

Among 94 patients enrolled, all patients had PDM and 44 (46.3%) had CDM. Forty-eight patients (51.1%) showed ENI. The prevalence of hypertension, initial NIHSS score, improvement in NIHSS score after EVT, and prevalence of ENI were greater in patients with CDM than those without. ENI was independently associated with onset-to-door time (odds ratio [95% confidence interval]: 0.998 [0.997-1.000]; p = 0.042), complete recanalization (23.912 [2.238-255.489]; p = 0.009), initial NIHSS score (1.180 [1.012-1.377]; p = 0.034), and the presence of CDM (5.160 [1.448-18.386]; p = 0.011). The correlation between DWI lesion volume and initial NIHSS score was strong in patients without CDM (r = 0.731) but only moderate in patients with CDM (r = 0.355).

CONCLUSION

Patients with both CDM and PDM had a better response to late-window EVT than those with PDM only.

A 10-Year Retrospective Review of Prenatal Applications, Current Challenges and Future Prospects of Three-Dimensional Sonoangiography

Realistic reconstruction of angioarchitecture within the morphological landmark with three-dimensional sonoangiography (three-dimensional power Doppler; 3D PD) may augment standard prenatal ultrasound and Doppler assessments. This study aimed to (a) present a technical overview, (b) determine additional advantages, (c) identify current challenges, and (d) predict trajectories of 3D PD for prenatal assessments. PubMed and Scopus databases for the last decade were searched. Although 307 publications addressed our objectives, their heterogeneity was too broad for statistical analyses. Important findings are therefore presented in descriptive format and supplemented with the authors’ 3D PD images. Acquisition, analysis, and display techniques need to be personalized to improve the quality of flow-volume data. While 3D PD indices of the first-trimester placenta may improve the prediction of preeclampsia, research is needed to standardize the measurement protocol. In highly experienced hands, the unique 3D PD findings improve the diagnostic accuracy of placenta accreta spectrum. A lack of quality assurance is the central challenge to incorporating 3D PD in prenatal care. Machine learning may broaden clinical translations of prenatal 3D PD. Due to its operator dependency, 3D PD has low reproducibility. Until standardization and quality assurance protocols are established, its use as a stand-alone clinical or research tool cannot be recommended.

Diagnosis of Acute Central Dizziness With Simple Clinical Information Using Machine Learning

Background: Acute dizziness is a common symptom among patients visiting emergency medical centers. Extensive neurological examinations aimed at delineating the cause of dizziness often require experience and specialized training. We tried to diagnose central dizziness by machine learning using only basic clinical information.

Methods: Patients were enrolled who had visited an emergency medical center with acute dizziness and underwent diffusion-weighted imaging. The enrolled patients were dichotomized as either having central (with a corresponding central lesion) or non-central dizziness. We obtained patient demographics, risk factors, vital signs, and presentation (non-whirling type dizziness or vertigo). Various machine learning algorithms were used to predict central dizziness. The area under the receiver operating characteristic curve (AUROC) was measured to evaluate diagnostic accuracy. The SHapley Additive exPlanations (SHAP) value was used to explain the importance of each factor.

Results: Of the 4,481 visits, 414 (9.2%) were determined as central dizziness. Central dizziness patients were more often older and male and had more risk factors and higher systolic blood pressure. They also presented more frequently with non-whirling type dizziness (79 vs. 54.4%) than non-central dizziness. Catboost model showed the highest AUROC (0.738) with a 94.4% sensitivity and 31.9% specificity in the test set (n = 1,317). The SHAP value was highest for previous stroke presence (mean; 0.74), followed by male (0.33), presentation as non-whirling type dizziness (0.30), and age (0.25).

Conclusions: Machine learning is feasible for classifying central dizziness using demographics, risk factors, vital signs, and clinical dizziness presentation, which are obtainable at the triage.

An automatic machine learning approach for ischemic stroke onset time identification based on DWI and FLAIR imaging

•

We only used two-modal MR image (DWI, FLAIR) for fast time since stroke identification.

•

We constructed cross-modal convolutional network for lesion ROI segmentation in FLAIR. The network used ROI features in DWI as prior information for better FLAIR segmentation.

•

Five independent machine learning classifiers were trained and voted to obtain the final classification label. The voting of five classifiers can improve classification accuracy effectively.

Current thrombolysis for acute ischemic stroke (AIS) treatment strictly relies on the time since stroke (TSS) less than 4.5 h. However, some patients are excluded from thrombolytic treatment because of the unknown TSS. The diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) mismatch can simply identify TSS since lesion intensities are not identical at different onset time. In this paper, we propose an automatic machine learning method to classify the TSS less than or more than 4.5 h. First, we develop a cross-modal convolutional neural network to accurately segment the stroke lesions from DWI and FLAIR images. Second, the features are extracted from DWI and FLAIR according to the segmentation regions of interest (ROI). Finally, the features are fed to machine learning models to identify TSS. In DWI and FLAIR ROI segmentation, the networks obtain high Dice coefficients with 0.803 and 0.647. The classification test results show that our model achieves an accuracy of 0.805, with a sensitivity of 0.769 and a specificity of 0.840. Our approach outperforms human reading DWI-FLAIR mismatch model, illustrating the potential for automatic and fast TSS identification.

Prediction of Progression to Severe Stroke in Initially Diagnosed Anterior Circulation Ischemic Cerebral Infarction

Purpose: Accurate prediction of the progression to severe stroke in initially diagnosed nonsevere patients with acute-subacute anterior circulation nonlacuna ischemic infarction (ASACNLII) is important in making clinical decision. This study aimed to apply a machine learning method to predict if the initially diagnosed nonsevere patients with ASACNLII would progress to severe stroke by using diffusion-weighted images and clinical information on admission. Methods: This retrospective study enrolled 344 patients with ASACNLII from June 2017 to August 2020 on admission, and 108 cases progressed to severe stroke during hospitalization within 3-21 days. The entire data were randomized into a training set (n = 271) and an independent test set (n = 73). A U-Net neural network was employed for automatic segmentation and volume measurement of the ischemic lesions. Predictive models were developed and used for evaluating the progression to severe stroke using different feature sets (the volume data, the clinical data, and the combination) and machine learning methods (random forest, support vector machine, and logistic regression). Results: The U-Net showed high correlation with manual segmentation in terms of Dice coefficient of 0.806 and R 2 value of the volume measurements of 0.960 in the test set. The random forest classifier of the volume + clinical combination achieved the best area under the receiver operating characteristic curve of 0.8358 (95% CI 0.7321-0.9269), and the accuracy, sensitivity, and specificity were 0.7780 (0.7397-0.7945), 0.7695 (0.6102-0.9074), and 0.8686 (0.6923-1.0), respectively. The Shapley additive explanation diagram showed the volume variable as the most important predictor. Conclusion: The U-Net was fully automatic and showed a high correlation with manual segmentation. An integrated approach combining clinical variables and stroke lesion volumes that were derived from the advanced machine learning algorithms had high accuracy in predicting the progression to severe stroke in ASACNLII patients.

Machine Learning-Based Prediction of Brain Tissue Infarction in Patients With Acute Ischemic Stroke Treated With Theophylline as an Add-On to Thrombolytic Therapy: A Randomized Clinical Trial Subgroup Analysis

Background and Purpose: The theophylline in acute ischemic stroke trial investigated the neuroprotective effect of theophylline as an add-on to thrombolytic therapy in patients with acute ischemic stroke. The aim of this pre-planned subgroup analysis was to use predictive modeling to virtually test for differences in the follow-up lesion volumes.

Materials and Methods: A subgroup of 52 patients from the theophylline in acute ischemic stroke trial with multi-parametric MRI data acquired at baseline and at 24-h follow-up were analyzed. A machine learning model using voxel-by-voxel information from diffusion- and perfusion-weighted MRI and clinical parameters was used to predict the infarct volume for each individual patient and both treatment arms. After training of the two predictive models, two virtual lesion outcomes were available for each patient, one lesion predicted for theophylline treatment and one lesion predicted for placebo treatment.

Results: The mean predicted volume of follow-up lesions was 11.4 ml (standard deviation 18.7) for patients virtually treated with theophylline and 11.2 ml (standard deviation 17.3) for patients virtually treated with placebo (p = 0.86).

Conclusions: The predicted follow-up brain lesions for each patient were not significantly different for patients virtually treated with theophylline or placebo, as an add-on to thrombolytic therapy. Thus, this study confirmed the lack of neuroprotective effect of theophylline shown in the main clinical trial and is contrary to the results from preclinical stroke models.

Predictive and diagnosis models of stroke from hemodynamic signal monitoring

This work presents a novel and promising approach to the clinical management of acute stroke. Using machine learning techniques, our research has succeeded in developing accurate diagnosis and prediction real-time models from hemodynamic data. These models are able to diagnose stroke subtype with 30 min of monitoring, to predict the exitus during the first 3 h of monitoring, and to predict the stroke recurrence in just 15 min of monitoring. Patients with difficult access to a CT scan and all patients that arrive at the stroke unit of a specialized hospital will benefit from these positive results. The results obtained from the real-time developed models are the following: stroke diagnosis around 98% precision (97.8% sensitivity, 99.5% specificity), exitus prediction with 99.8% precision (99.8% Sens., 99.9% Spec.), and 98% precision predicting stroke recurrence (98% Sens., 99% Spec.). Graphical abstract depicting the complete process since a patient is monitored until the data collected is used to generate models.

Intra-domain task-adaptive transfer learning to determine acute ischemic stroke onset time

Treatment of acute ischemic strokes (AIS) is largely contingent upon the time since stroke onset (TSS). However, TSS may not be readily available in up to 25% of patients with unwitnessed AIS. Current clinical guidelines for patients with unknown TSS recommend the use of MRI to determine eligibility for thrombolysis, but radiology assessments have high inter-reader variability. In this work, we present deep learning models that leverage MRI diffusion series to classify TSS based on clinically validated thresholds. We propose an intra-domain task-adaptive transfer learning method, which involves training a model on an easier clinical task (stroke detection) and then refining the model with different binary thresholds of TSS. We apply this approach to both 2D and 3D CNN architectures with our top model achieving an ROC-AUC value of 0.74, with a sensitivity of 0.70 and a specificity of 0.81 for classifying TSS < 4.5 h. Our pretrained models achieve better classification metrics than the models trained from scratch, and these metrics exceed those of previously published models applied to our dataset. Furthermore, our pipeline accommodates a more inclusive patient cohort than previous work, as we did not exclude imaging studies based on clinical, demographic, or image processing criteria. When applied to this broad spectrum of patients, our deep learning model achieves an overall accuracy of 75.78% when classifying TSS < 4.5 h, carrying potential therapeutic implications for patients with unknown TSS.

Diffusion weighted imaging in acute ischemic stroke: A review of its interpretation pitfalls and advanced diffusion imaging application

Diffusion weighted imaging (DWI) is a widely used imaging technique to evaluate patients with stroke. It can detect brain ischemia within minutes of stroke onset. However, DWI has few potential pitfalls that should be recognized during interpretation. DWI lesion could be reversible in the early hours of stroke and the entire lesion may not represent ischemic core. False negative DWI could lead to diagnosis of DWI negative stroke or to a missed stroke diagnosis. Ischemic stroke mimics can occur on DWI with non-cerebrovascular neurological conditions. In this article, the history of DWI, its clinical applications, and potential pitfalls for use in acute ischemic stroke are reviewed. Advanced diffusion imaging techniques with reference to Diffusion Kurtosis Imaging and Diffusion Tensor Imaging that has been studied to evaluate ischemic core are discussed.

Machine Learning-Based Automatic Rating for Cardinal Symptoms of Parkinson Disease

OBJECTIVE

We developed and investigated the feasibility of a machine learning-based automated rating for the 2 cardinal symptoms of Parkinson disease (PD): resting tremor and bradykinesia.

METHODS

Using OpenPose, a deep learning-based human pose estimation program, we analyzed video clips for resting tremor and finger tapping of the bilateral upper limbs of 55 patients with PD (110 arms). Key motion parameters, including resting tremor amplitude and finger tapping speed, amplitude, and fatigue, were extracted to develop a machine learning-based automatic Unified Parkinson's Disease Rating Scale (UPDRS) rating using support vector machine (SVM) method. To evaluate the performance of this model, we calculated weighted κ and intraclass correlation coefficients (ICCs) between the model and the gold standard rating by a movement disorder specialist who is trained and certified by the Movement Disorder Society for UPDRS rating. These values were compared to weighted κ and ICC between a nontrained human rater and the gold standard rating.

RESULTS

For resting tremors, the SVM model showed a very good to excellent reliability range with the gold standard rating (κ 0.791; ICC 0.927), with both values higher than that of nontrained human rater (κ 0.662; ICC 0.861). For finger tapping, the SVM model showed a very good reliability range with the gold standard rating (κ 0.700 and ICC 0.793), which was comparable to that for nontrained human raters (κ 0.627; ICC 0.797).

CONCLUSION

Machine learning-based algorithms that automatically rate PD cardinal symptoms are feasible, with more accurate results than nontrained human ratings.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that machine learning-based automated rating of resting tremor and bradykinesia in people with PD has very good reliability compared to a rating by a movement disorder specialist.

Artificial Intelligence and Acute Stroke Imaging

Artificial intelligence technology is a rapidly expanding field with many applications in acute stroke imaging, including ischemic and hemorrhage subtypes. Early identification of acute stroke is critical for initiating prompt intervention to reduce morbidity and mortality. Artificial intelligence can help with various aspects of the stroke treatment paradigm, including infarct or hemorrhage detection, segmentation, classification, large vessel occlusion detection, Alberta Stroke Program Early CT Score grading, and prognostication. In particular, emerging artificial intelligence techniques such as convolutional neural networks show promise in performing these imaging-based tasks efficiently and accurately. The purpose of this review is twofold: first, to describe AI methods and available public and commercial platforms in stroke imaging, and second, to summarize the literature of current artificial intelligence-driven applications for acute stroke triage, surveillance, and prediction.

Deep Learning-Based Method to Differentiate Neuromyelitis Optica Spectrum Disorder From Multiple Sclerosis

Background: Differentiating neuromyelitis optica spectrum disorder (NMOSD) from multiple sclerosis (MS) is crucial in the field of diagnostics because, despite their similarities, the treatments for these two diseases are substantially different, and disease-modifying treatments for MS can worsen NMOSD. As brain magnetic resonance imaging (MRI) is an important tool to distinguish the two diseases, extensive research has been conducted to identify the defining characteristics of MRI images corresponding to these two diseases. However, the application of such research in clinical practice is still limited. In this study, we investigate the applicability of a deep learning-based algorithm for differentiating NMOSD from MS.

Methods: In this study, we included 338 participants (213 patients with MS, 125 patients with NMOSD) who visited the Asan medical center between February 2009 and February 2020. A 3D convolutional neural network, which is a deep learning-based algorithm, was trained using fluid-attenuated inversion recovery images and clinical information of the participants. The performance of the final model in differentiating NMOSD from MS was evaluated and compared with that of two neurologists.

Results: The deep learning-based model exhibited an area under the receiver operating characteristic curve of 0.82 (95% CI, 0.75–0.89). It differentiated NMOSD from MS with an accuracy of 71.1% (sensitivity = 87.8%, specificity = 61.6%), which is comparable to that exhibited by the neurologists. The intra-rater reliability of the two neurologists was moderate (κ = 0.47, 0.50), which was in contrast with the consistent classification of the deep learning-based model.

Conclusion: The proposed model was verified to be capable of differentiating NMOSD from MS with accuracy comparable to that of neurologists, exhibiting the advantage of consistent classification. As a result, it can aid differential diagnosis between two important central nervous system inflammatory diseases in clinical practice.

Promises of artificial intelligence in neuroradiology: a systematic technographic review

PURPOSE

To conduct a systematic review of the possibilities of artificial intelligence (AI) in neuroradiology by performing an objective, systematic assessment of available applications. To analyse the potential impacts of AI applications on the work of neuroradiologists.

METHODS

We identified AI applications offered on the market during the period 2017-2019. We systematically collected and structured information in a relational database and coded for the characteristics of the applications, their functionalities for the radiology workflow and their potential impacts in terms of 'supporting', 'extending' and 'replacing' radiology tasks.

RESULTS

We identified 37 AI applications in the domain of neuroradiology from 27 vendors, together offering 111 functionalities. The majority of functionalities 'support' radiologists, especially for the detection and interpretation of image findings. The second-largest group of functionalities 'extends' the possibilities of radiologists by providing quantitative information about pathological findings. A small but noticeable portion of functionalities seek to 'replace' certain radiology tasks.

CONCLUSION

Artificial intelligence in neuroradiology is not only in the stage of development and testing but also available for clinical practice. The majority of functionalities support radiologists or extend their tasks. None of the applications can replace the entire radiology profession, but a few applications can do so for a limited set of tasks. Scientific validation of the AI products is more limited than the regulatory approval.

Wake-up stroke: imaging-based diagnosis and recanalization therapy

Wake-up stroke (WUS) is a subgroup of ischemic stroke in which patients show no abnormality before sleep while wake up with neurological deficits. In addition to the uncertain onset, WUS patients have difficulty to receive prompt and effective thrombolytic or reperfusion therapy, leading to relatively poor prognosis. A number of researches have indicated that CT or MRI based thrombolysis and endovascular therapy might have benefits for WUS patients. This review article narratively discusses the pathogenesis, risk factors, imaging-based diagnosis and recanalization treatments of WUS with the purpose of expanding current treatment options for this group of stroke patients and exploring better therapeutic methods. The result showed that multimodal MRI or CT scan might be the best methods for extending the time window of WUS and, therefore, a large proportion of WUS patients could have favorable prognosis.