Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy. PLoS One. 2014;9:e88225. [PMID: 24520356 PMCID: PMC3919736 DOI: 10.1371/journal.pone.0088225]

Prediction of Clinical Outcome in Patients with Large-Vessel Acute Ischemic Stroke: Performance of Machine Learning versus SPAN-100

BACKGROUND AND PURPOSE

Traditional statistical models and pretreatment scoring systems have been used to predict the outcome for acute ischemic stroke patients (AIS). Our aim was to select the most relevant features in terms of outcome prediction on the basis of machine learning algorithms for patients with acute ischemic stroke and to compare the performance between multiple models and the Stroke Prognostication Using Age and National Institutes of Health Stroke Scale (SPAN-100) index model.

MATERIALS AND METHODS

A retrospective multicenter cohort of 1431 patients with acute ischemic stroke was subdivided into recanalized and nonrecanalized patients. Extreme Gradient Boosting machine learning models were built to predict the mRS score at 90 days using clinical, imaging, combined, and best-performing features. Feature selection was performed using the relative weight and frequency of occurrence in the models. The model with the best performance was compared with the SPAN-100 index model using area under the receiver operating curve analysis.

RESULTS

In 3 groups of patients, the baseline NIHSS was the most significant predictor of outcome among all the parameters, with relative weights of 0.36∼0.69; ischemic core volume on CTP ranked as the most important imaging biomarker with relative weights of 0.29∼0.47. The model with the best-performing features had a better performance than the other machine learning models. The area under the curve of the model with the best-performing features was higher than SPAN-100 model and reached statistical significance for the total (P < .05) and the nonrecanalized patients (P < .001).

CONCLUSIONS

Machine learning-based feature selection can identify parameters with higher performance in outcome prediction. Machine learning models with the best-performing features, especially advanced CTP data, had superior performance of the recovery outcome prediction for patients with stroke at admission in comparison with SPAN-100.

Artificial Intelligence in Colorectal Polyp Detection and Characterization

BACKGROUND

Over the past 20 years, the advancement of artificial intelligence (AI) and deep learning (DL) has allowed for fast sorting and analysis of large sets of data. In the field of gastroenterology, colorectal screening procedures produces an abundance of data through video and imaging. With AI and DL, this information can be used to create systems where automatic polyp detection and characterization is possible. Convoluted Neural Networks (CNNs) have proven to be an effective way to increase polyp detection and ultimately adenoma detection rates. Different methods of polyp characterization of being hyperplastic vs. adenomatous or non-neoplastic vs. neoplastic has also been investigated showing promising results.

FINDINGS

The rate of missed polyps on colonoscopy can be as high as 25%. At the beginning of the 2000s, hand-crafted machine learning (ML) algorithms were created and trained retrospectively on colonoscopy images and videos, achieving high sensitivity, specificity, and accuracy of over 90% in many of the studies. Over time, the advancement of DL and CNNs has allowed algorithms to be trained on non-medical images and applied retrospectively to colonoscopy videos and images with similar results. Within the past few years, these algorithms have been applied in real-time colonoscopies and has shown mixed results, one showing no difference while others showing increased polyp detection.Various methods of polyp characterization have also been investigated. Through AI, DL, and CNNs polyps can be identified has hyperplastic/adenomatous or non-neoplastic/neoplastic with high sensitivity, specificity, and accuracy. One of the research areas in polyp characterization is how to capture the polyp image. This paper looks at different modalities of characterizing polyps such as magnifying narrow band imaging (NBI), endocytoscopy, laser-induced florescent spectroscopy, auto-florescent endoscopy, and white-light endoscopy.

CONCLUSIONS

Overall, much progress has been made in automatic detection and characterization of polyps in real time. Barring ethical or mass adoption setbacks, it is inevitable that AI will be involved in the field of GI, especially in colorectal polyp detection and identification.

Machine-learning-based outcome prediction in stroke patients with middle cerebral artery-M1 occlusions and early thrombectomy

Background and purpose

Clinical outcomes vary substantially among individuals with large vessel occlusion (LVO) stroke. A small infarct core and large imaging mismatch were found to be associated with good recovery. The aim of this study was to investigate whether those imaging variables would improve individual prediction of functional outcome after early (<6 h) endovascular treatment (EVT) in LVO stroke.

Methods

We included 222 patients with acute ischemic stroke due to middle cerebral artery (MCA)‐M1 occlusion who received EVT. As predictors, we used clinical variables and region of interest (ROI)‐based magnetic resonance imaging features. We developed different machine‐learning models and quantified their prediction performance according to the area under the receiver‐operating characteristic curves and the Brier score.

Results

The rate of successful recanalization was 78%, with 54% patients having a favorable outcome (modified Rankin scale score 0–2). Small infarct core was associated with favorable functional outcome. Outcome prediction improved only slightly when imaging was added to patient variables. Age was the driving factor, with a sharp decrease in likelihood of favorable functional outcome above the age of 78 years.

Conclusions

In patients with MCA‐M1 occlusion strokes referred to EVT within 6 h of symptom onset, infarct core volume was associated with outcome. However, ROI‐based imaging variables led to no significant improvement in outcome prediction at an individual patient level when added to a set of clinical predictors. Our study is in concordance with current practice, where imaging mismatch or collateral readouts are not recommended as factors for excluding patients with MCA‐M1 occlusion for early EVT.

Multimodal Predictive Modeling of Endovascular Treatment Outcome for Acute Ischemic Stroke Using Machine-Learning

Background and Purpose:

This study assessed the predictive performance and relative importance of clinical, multimodal imaging, and angiographic characteristics for predicting the clinical outcome of endovascular treatment for acute ischemic stroke.

Methods:

A consecutive series of 246 patients with acute ischemic stroke and large vessel occlusion in the anterior circulation who underwent endovascular treatment between April 2014 and January 2018 was analyzed. Clinical, conventional imaging (electronic Alberta Stroke Program Early CT Score, acute ischemic volume, site of vessel occlusion, and collateral score), and advanced imaging characteristics (CT-perfusion with quantification of ischemic penumbra and infarct core volumes) before treatment as well as angiographic (interval groin puncture-recanalization, modified Thrombolysis in Cerebral Infarction score) and postinterventional clinical (National Institutes of Health Stroke Scale score after 24 hours) and imaging characteristics (electronic Alberta Stroke Program Early CT Score, final infarction volume after 18–36 hours) were assessed. The modified Rankin Scale (mRS) score at 90 days (mRS-90) was used to measure patient outcome (favorable outcome: mRS-90 ≤2 versus unfavorable outcome: mRS-90 >2). Machine-learning with gradient boosting classifiers was used to assess the performance and relative importance of the extracted characteristics for predicting mRS-90.

Results:

Baseline clinical and conventional imaging characteristics predicted mRS-90 with an area under the receiver operating characteristics curve of 0.740 (95% CI, 0.733–0.747) and an accuracy of 0.711 (95% CI, 0.705–0.717). Advanced imaging with CT-perfusion did not improved the predictive performance (area under the receiver operating characteristics curve, 0.747 [95% CI, 0.740–0.755]; accuracy, 0.720 [95% CI, 0.714–0.727]; P =0.150). Further inclusion of angiographic and postinterventional characteristics significantly improved the predictive performance (area under the receiver operating characteristics curve, 0.856 [95% CI, 0.850–0.861]; accuracy, 0.804 [95% CI, 0.799–0.810]; P <0.001). The most important parameters for predicting mRS 90 were National Institutes of Health Stroke Scale score after 24 hours (importance =100%), premorbid mRS score (importance =44%) and final infarction volume on postinterventional CT after 18 to 36 hours (importance =32%).

Conclusions:

Integrative assessment of clinical, multimodal imaging, and angiographic characteristics with machine-learning allowed to accurately predict the clinical outcome following endovascular treatment for acute ischemic stroke. Thereby, premorbid mRS was the most important clinical predictor for mRS-90, and the final infarction volume was the most important imaging predictor, while the extent of hemodynamic impairment on CT-perfusion before treatment had limited importance.

Supervised Machine Learning Models for Prediction of COVID-19 Infection using Epidemiology Dataset

COVID-19 or 2019-nCoV is no longer pandemic but rather endemic, with more than 651,247 people around world having lost their lives after contracting the disease. Currently, there is no specific treatment or cure for COVID-19, and thus living with the disease and its symptoms is inevitable. This reality has placed a massive burden on limited healthcare systems worldwide especially in the developing nations. Although neither an effective, clinically proven antiviral agents' strategy nor an approved vaccine exist to eradicate the COVID-19 pandemic, there are alternatives that may reduce the huge burden on not only limited healthcare systems but also the economic sector; the most promising include harnessing non-clinical techniques such as machine learning, data mining, deep learning and other artificial intelligence. These alternatives would facilitate diagnosis and prognosis for 2019-nCoV pandemic patients. Supervised machine learning models for COVID-19 infection were developed in this work with learning algorithms which include logistic regression, decision tree, support vector machine, naive Bayes, and artificial neutral network using epidemiology labeled dataset for positive and negative COVID-19 cases of Mexico. The correlation coefficient analysis between various dependent and independent features was carried out to determine a strength relationship between each dependent feature and independent feature of the dataset prior to developing the models. The 80% of the training dataset were used for training the models while the remaining 20% were used for testing the models. The result of the performance evaluation of the models showed that decision tree model has the highest accuracy of 94.99% while the Support Vector Machine Model has the highest sensitivity of 93.34% and Naïve Bayes Model has the highest specificity of 94.30%.

Role of Artificial Intelligence in TeleStroke: An Overview

Teleneurology has provided access to neurological expertise and state-of-the-art stroke care where previously they have been inaccessible. The use of Artificial Intelligence with machine learning to assist telestroke care can be revolutionary. This includes more rapid and more reliable diagnosis through imaging analysis as well as prediction of hospital course and 3-month prognosis. Intelligent Electronic Medical Records can search free text and provide decision assistance by analyzing patient charts. Speech recognition has advanced enough to be reliable and highly convenient. Smart contextually aware communication and alert programs can enhance efficiency of patient flow and improve outcomes. Automated data collection and analysis can make quality improvement and research projects quicker and much less burdensome. Despite current challenges, these synergistic technologies hold immense promise in enhancing the clinician experience, helping to reduce physician burnout while improving patient health outcomes at a lower cost. This brief overview discusses the multifaceted potential of AI use in telestroke.

Predicting Clinical Outcome in Acute Ischemic Stroke Using Parallel Multi-parametric Feature Embedded Siamese Network

Stroke is the second leading cause of death and disability worldwide, with ischemic stroke as the most common type. The preferred diagnostic procedure at the acute stage is the acquisition of multi-parametric magnetic resonance imaging (MRI). This type of imaging not only detects and locates the stroke lesion, but also provides the blood flow dynamics that helps clinicians in assessing the risks and benefits of reperfusion therapies. However, evaluating the outcome of these risky therapies beforehand is a complicated task due to the variability of lesion location, size, shape, and cerebral hemodynamics involved. Though the fully automated model for predicting treatment outcomes using multi-parametric imaging would be highly valuable in clinical settings, MRI datasets acquired at the acute stage are mostly scarce and suffer high class imbalance. In this paper, parallel multi-parametric feature embedded siamese network (PMFE-SN) is proposed that can learn with few samples and can handle skewness in multi-parametric MRI data. Moreover, five suitable evaluation metrics that are insensitive to imbalance are defined for this problem. The results show that PMFE-SN not only outperforms other state-of-the-art techniques in all these metrics but also can predict the class with a small number of samples, as well as the class with high number of samples. An accuracy of 0.67 on leave one cross out testing has been achieved with only two samples (minority class) for training and accuracy of 0.61 with the highest number of samples (majority class). In comparison, state-of-the-art using hand crafted features has 0 accuracy for minority class and 0.33 accuracy for majority class.

Noncontrast Computed Tomography-Based Radiomics Analysis in Discriminating Early Hematoma Expansion after Spontaneous Intracerebral Hemorrhage

Objective

To determine whether noncontrast computed tomography (NCCT) models based on multivariable, radiomics features, and machine learning (ML) algorithms could further improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH).

Materials and Methods

We retrospectively reviewed 261 patients with sICH who underwent initial NCCT within 6 hours of ictus and follow-up CT within 24 hours after initial NCCT, between April 2011 and March 2019. The clinical characteristics, imaging signs and radiomics features extracted from the initial NCCT images were used to construct models to discriminate early HE. A clinical-radiologic model was constructed using a multivariate logistic regression (LR) analysis. Radiomics models, a radiomics-radiologic model, and a combined model were constructed in the training cohort (n = 182) and independently verified in the validation cohort (n = 79). Receiver operating characteristic analysis and the area under the curve (AUC) were used to evaluate the discriminative power.

Results

The AUC of the clinical-radiologic model for discriminating early HE was 0.766. The AUCs of the radiomics model for discriminating early HE built using the LR algorithm in the training and validation cohorts were 0.926 and 0.850, respectively. The AUCs of the radiomics-radiologic model in the training and validation cohorts were 0.946 and 0.867, respectively. The AUCs of the combined model in the training and validation cohorts were 0.960 and 0.867, respectively.

Conclusion

NCCT models based on multivariable, radiomics features and ML algorithm could improve the discrimination of early HE. The combined model was the best recommended model to identify sICH patients at risk of early HE.

Predicting Poor Outcome Before Endovascular Treatment in Patients With Acute Ischemic Stroke

Background: Although endovascular treatment (EVT) has greatly improved outcomes in acute ischemic stroke, still one third of patients die or remain severely disabled after stroke. If we could select patients with poor clinical outcome despite EVT, we could prevent futile treatment, avoid treatment complications, and further improve stroke care. We aimed to determine the accuracy of poor functional outcome prediction, defined as 90-day modified Rankin Scale (mRS) score ≥5, despite EVT treatment.

Methods: We included 1,526 patients from the MR CLEAN Registry, a prospective, observational, multicenter registry of ischemic stroke patients treated with EVT. We developed machine learning prediction models using all variables available at baseline before treatment. We optimized the models for both maximizing the area under the curve (AUC), reducing the number of false positives.

Results: From 1,526 patients included, 480 (31%) of patients showed poor outcome. The highest AUC was 0.81 for random forest. The highest area under the precision recall curve was 0.69 for the support vector machine. The highest achieved specificity was 95% with a sensitivity of 34% for neural networks, indicating that all models contained false positives in their predictions. From 921 mRS 0–4 patients, 27–61 (3–6%) were incorrectly classified as poor outcome. From 480 poor outcome patients in the registry, 99–163 (21–34%) were correctly identified by the models.

Conclusions: All prediction models showed a high AUC. The best-performing models correctly identified 34% of the poor outcome patients at a cost of misclassifying 4% of non-poor outcome patients. Further studies are necessary to determine whether these accuracies are reproducible before implementation in clinical practice.

Artificial intelligence in stroke imaging: Current and future perspectives

Artificial intelligence (AI) is a fast-growing research area in computer science that aims to mimic cognitive processes through a number of techniques. Supervised machine learning, a subfield of AI, includes methods that can identify patterns in high-dimensional data using labeled 'ground truth' data and apply these learnt patterns to analyze, interpret, or make predictions on new datasets. Supervised machine learning has become a significant area of interest within the medical community. Radiology and neuroradiology in particular are especially well suited for application of machine learning due to the vast amount of data that is generated. One devastating disease for which neuroimaging plays a significant role in the clinical management is stroke. Within this context, AI techniques can play pivotal roles for image-based diagnosis and management of stroke. This overview focuses on the recent advances of artificial intelligence methods - particularly supervised machine learning and deep learning - with respect to workflow, image acquisition and reconstruction, and image interpretation in patients with acute stroke, while also discussing potential pitfalls and future applications.

Toward a hemorrhagic trauma severity score: fusing five physiological biomarkers

BACKGROUND

To introduce the Hemorrhage Intensive Severity and Survivability (HISS) score, based on the fusion of multi-biomarker data; glucose, lactate, pH, potassium, and oxygen tension, to serve as a patient-specific attribute in hemorrhagic trauma.

MATERIALS AND METHODS

One hundred instances of Sensible Fictitious Rationalized Patient (SFRP) data were synthetically generated and the HISS score assigned by five clinically active physician experts (100 [5]). The HISS score stratifies the criticality of the trauma patient as; low(0), guarded(1), elevated(2), high(3) and severe(4). Standard classifier algorithms; linear support vector machine (SVM-L), multi-class ensemble bagged decision tree (EBDT), artificial neural network with bayesian regularization (ANN:BR) and possibility rule-based using function approximation (PRBF) were evaluated for their potential to similarly classify and predict a HISS score.

RESULTS

SVM-L, EBDT, ANN:BR and PRBF generated score predictions with testing accuracies (majority vote) corresponding to 0.91 ± 0.06, 0.93 ± 0.04, 0.92 ± 0.07, and 0.92 ± 0.03, respectively, with no statistically significant difference (p > 0.05). Targeted accuracies of 0.99 and 0.999 could be achieved with SFRP data size and clinical expert scores of 147[7](0.99) and 154[9](0.999), respectively.

CONCLUSIONS

The predictions of the data-driven model in conjunction with an adjunct multi-analyte biosensor intended for point-of-care continual monitoring of trauma patients, can aid in patient stratification and triage decision-making.

Texture analysis based on ADC maps and T2-FLAIR images for the assessment of the severity and prognosis of ischaemic stroke

OBJECTIVES

To explore the feasibility of texture analysis based on T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) images and apparent diffusion coefficient (ADC) maps in the assessment of the severity and prognosis of ischaemic stroke using the National Institutes of Health Stroke Scale (NIHSS) and modified Rankin scale (mRS) scores, respectively.

METHODS

Overall, 116 patients diagnosed with subacute ischaemic stroke were included in this retrospective study. Based on T2-FLAIR images and ADC maps, 15 texture features were extracted from the ROIs of each patient using grey-level co-occurrence matrix (GLCM) and local binary pattern histogram Fourier (LBP-HF) methods. The correlations of NIHSS score on admission (NIHSS_baseline), NIHSS score 24 h after stroke onset (NIHSS_24h) and mRS score with the texture features were evaluated using Spearman's partial correlations. The receiver operating characteristic (ROC) curve was used to compare the performance of the selected texture features in the evaluation of stroke severity and prognosis.

RESULTS

Texture features derived from the T2-FLAIR images and ADC maps were correlated with NIHSS score and mRS score. Entropy_ADC and 0.75Quantile_T2-FLAIR showed the best diagnostic performance for assessing stroke severity. The combination of Entropy_ADC and 0.75Quantile_T2-FLAIR achieved a better performance in the evaluation of stroke severity (AUC = 0.7, p = 0.01) than either feature alone. Only 0.05Quantile_T2-FLAIR was found to be correlated with mRS score, and none of the texture features were predictive of mRS score.

CONCLUSION

Texture features derived from T2-FLAIR images and ADC maps might serve as biomarkers to evaluate stroke severity, but were insufficient to predict stroke prognosis.

Predictive Supervised Machine Learning Models for Diabetes Mellitus

Diabetes mellitus (DM) is one of the deadliest diseases in the world, especially in developed nations. In recent years, it has become rampant in the developing nations such as Nigeria, posing more threats to individuals in the latter than those in the former. More than 415 million people were reported to suffer from DM worldwide as of 2015, with type 2 of the disease accounting for approximately 90% of the cases. The number of people with DM is expected to rise to 592 million by the year 2035. Therefore, DM is one of the growing public health concerns in Nigeria. In this study, the diagnostic dataset of DM type 2 was collected from the Murtala Mohammed Specialist Hospital, Kano, and used to develop predictive supervised machine learning models based on logistic regression, support vector machine, K-nearest neighbor, random forest, naive Bayes and gradient booting algorithms. The random forest predictive learning-based model appeared to be one of the best developed models with 88.76% in terms of accuracy; however, in terms of receiver operating characteristic curve, random forest and gradient booting predictive learning-based models were found to be the best predictive learning models with 86.28% predictive ability, respectively.

Evaluation of machine learning methods to stroke outcome prediction using a nationwide disease registry

INTRODUCTION

Being able to predict functional outcomes after a stroke is highly desirable for clinicians. This allows clinicians to set reasonable goals with patients and relatives, and to reach shared after-care decisions for recovery or rehabilitation. The aim of this study was to apply various machine learning (ML) methods for 90-day stroke outcome predictions, using a nationwide disease registry.

METHODS

This study used the Taiwan Stroke Registry (TSR) which has prospectively collected data from stroke patients since 2006. Three known ML models (support vector machine, random forest, and artificial neural network), and a hybrid artificial neural network were implemented and evaluated by 10-time repeated hold-out with 10-fold cross-validation.

RESULTS

ML techniques present over 0.94 AUC in both ischemic and hemorrhagic stroke using preadmission and inpatient data. By adding follow-up data, the prediction ability improved to 0.97 AUC. We screened 206 clinical variables to identify 17 important features from the ischemic stroke dataset and 22 features from the hemorrhagic stroke dataset without losing much performance. Error analysis revealed that most prediction errors come from more severe stroke patients.

CONCLUSION

The study showed that ML techniques trained from large, cross-reginal registry datasets were able to predict functional outcome after stroke with high accuracy. The follow-up data is important which can further improve the predictive models' performance. With similar performances among different ML techniques, the algorithm's characteristics and performance on severe stroke patients will be the primary focus when we further develop inference models and artificial intelligence tools for potential medical.

A systematic review of machine learning models for predicting outcomes of stroke with structured data

Background and purpose

Machine learning (ML) has attracted much attention with the hope that it could make use of large, routinely collected datasets and deliver accurate personalised prognosis. The aim of this systematic review is to identify and critically appraise the reporting and developing of ML models for predicting outcomes after stroke.

Methods

We searched PubMed and Web of Science from 1990 to March 2019, using previously published search filters for stroke, ML, and prediction models. We focused on structured clinical data, excluding image and text analysis. This review was registered with PROSPERO (CRD42019127154).

Results

Eighteen studies were eligible for inclusion. Most studies reported less than half of the terms in the reporting quality checklist. The most frequently predicted stroke outcomes were mortality (7 studies) and functional outcome (5 studies). The most commonly used ML methods were random forests (9 studies), support vector machines (8 studies), decision trees (6 studies), and neural networks (6 studies). The median sample size was 475 (range 70–3184), with a median of 22 predictors (range 4–152) considered. All studies evaluated discrimination with thirteen using area under the ROC curve whilst calibration was assessed in three. Two studies performed external validation. None described the final model sufficiently well to reproduce it.

Conclusions

The use of ML for predicting stroke outcomes is increasing. However, few met basic reporting standards for clinical prediction tools and none made their models available in a way which could be used or evaluated. Major improvements in ML study conduct and reporting are needed before it can meaningfully be considered for practice.

Opening the black box of artificial intelligence for clinical decision support: A study predicting stroke outcome

State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide clinical decision support systems to physicians. Modern ML approaches such as artificial neural networks (ANNs) and tree boosting often perform better than more traditional methods like logistic regression. On the other hand, these modern methods yield a limited understanding of the resulting predictions. However, in the medical domain, understanding of applied models is essential, in particular, when informing clinical decision support. Thus, in recent years, interpretability methods for modern ML methods have emerged to potentially allow explainable predictions paired with high performance. To our knowledge, we present in this work the first explainability comparison of two modern ML methods, tree boosting and multilayer perceptrons (MLPs), to traditional logistic regression methods using a stroke outcome prediction paradigm. Here, we used clinical features to predict a dichotomized 90 days post-stroke modified Rankin Scale (mRS) score. For interpretability, we evaluated clinical features' importance with regard to predictions using deep Taylor decomposition for MLP, Shapley values for tree boosting and model coefficients for logistic regression. With regard to performance as measured by Area under the Curve (AUC) values on the test dataset, all models performed comparably: Logistic regression AUCs were 0.83, 0.83, 0.81 for three different regularization schemes; tree boosting AUC was 0.81; MLP AUC was 0.83. Importantly, the interpretability analysis demonstrated consistent results across models by rating age and stroke severity consecutively amongst the most important predictive features. For less important features, some differences were observed between the methods. Our analysis suggests that modern machine learning methods can provide explainability which is compatible with domain knowledge interpretation and traditional method rankings. Future work should focus on replication of these findings in other datasets and further testing of different explainability methods.

Fuzzy cognitive map based approach for determining the risk of ischemic stroke

Stroke is the third major cause of mortality in the world. The diagnosis of stroke is a very complex issue considering controllable and uncontrollable factors. These factors include age, sex, blood pressure, diabetes, obesity, heart disease, smoking, and so on, having a considerable influence on the diagnosis of stroke. Hence, designing an intelligent system leading to immediate and effective treatment is essential. In this study, the soft computing method known as fuzzy cognitive mapping was proposed for diagnosis of the risk of ischemic stroke. Non-linear Hebbian learning method was used for fuzzy cognitive maps training. In the proposed method, the risk rate for each person was determined based on the opinions of the neurologists. The accuracy of the proposed model was tested using 10-fold cross-validation, for 110 real cases, and the results were compared with those of support vector machine and K-nearest neighbours. The proposed system showed a superior performance with a total accuracy of (93.6 ± 4.5)%. The data used in this study is available by emailing the first author for academic and non-commercial purposes.

Classifying intracranial stenosis disease severity from functional MRI data using machine learning

Translation of many non-invasive hemodynamic MRI methods to cerebrovascular disease patients has been hampered by well-known artifacts associated with delayed blood arrival times and reduced microvascular compliance. Using machine learning and support vector machine (SVM) algorithms, we investigated whether arrival time-related artifacts in these methods could be exploited as novel contrast sources to discriminate angiographically confirmed stenotic flow territories. Intracranial steno-occlusive moyamoya patients (n = 53; age = 45 ± 14.2 years; sex = 43 F) underwent (i) catheter angiography, (ii) anatomical MRI, (iii) cerebral blood flow (CBF)-weighted arterial spin labeling, and (iv) cerebrovascular reactivity (CVR)-weighted hypercapnic blood-oxygenation-level-dependent MRI. Mean, standard deviation (std), and 99th percentile of CBF, CVR, CVR_Delay, and CVR_Max were calculated in major anterior and posterior flow territories perfused by vessels with vs. without stenosis (≥70%) confirmed by catheter angiography. These and demographic variables were input into SVMs to evaluate discriminatory capacity for stenotic flow territories using k-fold cross-validation and receiver-operating-characteristic-area-under-the-curve to quantify variable combination relevance. Anterior circulation CBF-std, attributable to heterogeneous endovascular signal and prolonged arterial transit times, was the best performing single variable and CVR_Delay-mean and CBF-std, both reflective of delayed vascular compliance, were a high-performing two-variable combination (specificity = 0.67; sensitivity = 0.75). Findings highlight the relevance of hemodynamic imaging and machine learning for identifying cerebrovascular impairment.

Machine Learning Methods Predict Individual Upper-Limb Motor Impairment Following Therapy in Chronic Stroke

Background. Accurate prediction of clinical impairment in upper-extremity motor function following therapy in chronic stroke patients is a difficult task for clinicians but is key in prescribing appropriate therapeutic strategies. Machine learning is a highly promising avenue with which to improve prediction accuracy in clinical practice. Objectives. The objective was to evaluate the performance of 5 machine learning methods in predicting postintervention upper-extremity motor impairment in chronic stroke patients using demographic, clinical, neurophysiological, and imaging input variables. Methods. A total of 102 patients (female: 31%, age 61 ± 11 years) were included. The upper-extremity Fugl-Meyer Assessment (UE-FMA) was used to assess motor impairment of the upper limb before and after intervention. Elastic net (EN), support vector machines, artificial neural networks, classification and regression trees, and random forest were used to predict postintervention UE-FMA. The performances of methods were compared using cross-validated R². Results. EN performed significantly better than other methods in predicting postintervention UE-FMA using demographic and baseline clinical data (median REN2=0.91,RRF2=0.88,RANN2=0.83,RSVM2=0.79,RCART2=0.70; P < .05). Preintervention UE-FMA and the difference in motor threshold (MT) between the affected and unaffected hemispheres were the strongest predictors. The difference in MT had greater importance than the absence or presence of a motor-evoked potential (MEP) in the affected hemisphere. Conclusion. Machine learning methods may enable clinicians to accurately predict a chronic stroke patient's postintervention UE-FMA. Interhemispheric difference in the MT is an important predictor of chronic stroke patients' response to therapy and, therefore, could be included in prospective studies.

Fighting healthcare rocketing costs with value-based medicine: the case of stroke management

Value-Based Medicine (VBM) is imposing itself as 'a new paradigm in healthcare management and medical practice.In this perspective paper, we discuss the role of VBM in dealing with the large productivity issue of the healthcare industry and examine some of the worldwide industrial and technological trends linked with VBM introduction. To clarify the points, we discuss examples of VBM management of stroke patients.In our conclusions, we support the idea of VBM as a strategic aid to manage rising costs in healthcare, and we explore the idea that VBM, by establishing value-generating networks among different healthcare stakeholders, can serve as the long sought-after redistributive mechanism that compensate patients for the industrial exploitation of their personal medical records.

Machine Learning Approach to Identify Stroke Within 4.5 Hours

Background and Purpose- We aimed to investigate the ability of machine learning (ML) techniques analyzing diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) magnetic resonance imaging to identify patients within the recommended time window for thrombolysis. Methods- We analyzed DWI and FLAIR images of consecutive patients with acute ischemic stroke within 24 hours of clear symptom onset by applying automatic image processing approaches. These processes included infarct segmentation, DWI, and FLAIR imaging registration and image feature extraction. A total of 89 vector features from each image sequence were captured and used in the ML. Three ML models were developed to estimate stroke onset time for binary classification (≤4.5 hours): logistic regression, support vector machine, and random forest. To evaluate the performance of ML models, the sensitivity and specificity for identifying patients within 4.5 hours were compared with the sensitivity and specificity of human readings of DWI-FLAIR mismatch. Results- Data from a total of 355 patients were analyzed. DWI-FLAIR mismatch from human readings identified patients within 4.5 hours of symptom onset with 48.5% sensitivity and 91.3% specificity. ML algorithms had significantly greater sensitivities than human readers (75.8% for logistic regression, P=0.020; 72.7% for support vector machine, P=0.033; 75.8% for random forest, P=0.013) in detecting patients within 4.5 hours, but their specificities were comparable (82.6% for logistic regression, P=0.157; 82.6% for support vector machine, P=0.157; 82.6% for random forest, P=0.157). Conclusions- ML algorithms using multiple magnetic resonance imaging features were feasible even more sensitive than human readings in identifying patients with stroke within the time window for acute thrombolysis.

Machine learning models for identifying preterm infants at risk of cerebral hemorrhage

Intracerebral hemorrhage in preterm infants is a major cause of brain damage and cerebral palsy. The pathogenesis of cerebral hemorrhage is multifactorial. Among the risk factors are impaired cerebral autoregulation, infections, and coagulation disorders. Machine learning methods allow the identification of combinations of clinical factors to best differentiate preterm infants with intra-cerebral bleeding and the development of models for patients at risk of cerebral hemorrhage. In the current study, a Random Forest approach is applied to develop such models for extremely and very preterm infants (23-30 weeks gestation) based on data collected from a cohort of 229 individuals. The constructed models exhibit good prediction accuracy and might be used in clinical practice to reduce the risk of cerebral bleeding in prematurity.

Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke

Background and Purpose- The prediction of long-term outcomes in ischemic stroke patients may be useful in treatment decisions. Machine learning techniques are being increasingly adapted for use in the medical field because of their high accuracy. This study investigated the applicability of machine learning techniques to predict long-term outcomes in ischemic stroke patients. Methods- This was a retrospective study using a prospective cohort that enrolled patients with acute ischemic stroke. Favorable outcome was defined as modified Rankin Scale score 0, 1, or 2 at 3 months. We developed 3 machine learning models (deep neural network, random forest, and logistic regression) and compared their predictability. To evaluate the accuracy of the machine learning models, we also compared them to the Acute Stroke Registry and Analysis of Lausanne (ASTRAL) score. Results- A total of 2604 patients were included in this study, and 2043 (78%) of them had favorable outcomes. The area under the curve for the deep neural network model was significantly higher than that of the ASTRAL score (0.888 versus 0.839; P<0.001), while the areas under the curves of the random forest (0.857; P=0.136) and logistic regression (0.849; P=0.413) models were not significantly higher than that of the ASTRAL score. Using only the 6 variables that are used for the ASTRAL score, the performance of the machine learning models did not significantly differ from that of the ASTRAL score. Conclusions- Machine learning algorithms, particularly the deep neural network, can improve the prediction of long-term outcomes in ischemic stroke patients.

Artificial Intelligence Applied to Gastrointestinal Diagnostics: A Review

Artificial intelligence (AI), a discipline encompassed by data science, has seen recent rapid growth in its application to healthcare and beyond, and is now an integral part of daily life. Uses of AI in gastroenterology include the automated detection of disease and differentiation of pathology subtypes and disease severity. Although a majority of AI research in gastroenterology focuses on adult applications, there are a number of pediatric pathologies that could benefit from more research. As new and improved diagnostic tools become available and more information is retrieved from them, AI could provide physicians a method to distill enormous amounts of data into enhanced decision-making and cost saving for children with digestive disorders. This review provides a broad overview of AI and examples of its possible applications in pediatric gastroenterology.

Risks of Stroke and Mortality in Atrial Fibrillation Patients Treated With Rivaroxaban and Warfarin

Background and Purpose- Oral anticoagulation therapy is standard of care for patients with nonvalvular atrial fibrillation to prevent stroke. This study compared rivaroxaban and warfarin for stroke and all-cause mortality risk reduction in a real-world setting. Methods- This retrospective cohort study (2011-2017) included de-identified patients from the Optum Clinformatics Database who started treatment with rivaroxaban or warfarin within 30 days following initial diagnosis of nonvalvular atrial fibrillation. Before nonvalvular atrial fibrillation diagnosis, patients had 6 months of continuous health plan enrollment and CHA₂DS₂-VASc score ≥2. Stroke severity was determined by the National Institutes of Health Stroke Scale, imputed based on machine learning algorithms. Stroke and all-cause mortality risks were compared by treatment using Cox proportional hazard regression, with inverse probability of treatment weighting to balance cohorts for baseline risk factors. Stratified analysis by treatment duration was also performed. Results- During a mean follow-up of 27 months, 175 (1.33/100 patient-years [PY]) rivaroxaban-treated and 536 (1.66/100 PY) warfarin-treated patients developed stroke. The inverse probability of treatment weighting model showed that rivaroxaban reduced stroke risk by 19% (hazard ratio [HR], 0.81 [95% CI, 0.73-0.91]). Analysis by stroke severity revealed risk reductions by rivaroxaban of 48% for severe stroke (National Institutes of Health Stroke Scale score, 16-42; HR, 0.52 [95% CI, 0.33-0.82]) and 19% for minor stroke (National Institutes of Health Stroke Scale score, 1 to <5; HR, 0.81 [95% CI, 0.68-0.96]), but no difference for moderate stroke (National Institutes of Health Stroke Scale score, 5 to <16; HR, 0.93 [95% CI, 0.78-1.10]). A total of 41 (0.31/100 PY) rivaroxaban-treated and 147 (0.44/100 PY) warfarin-treated patients died poststroke, 12 (0.09/100 PY) and 67 (0.20/100 PY) of whom died within 30 days, representing mortality risk reductions by rivaroxaban of 24% (HR, 0.76 [95% CI, 0.61-0.95]) poststroke and 59% (HR, 0.41 [95% CI, 0.28-0.60]) within 30 days. Conclusions- After the initial diagnosis of atrial fibrillation, patients treated with rivaroxaban versus warfarin had significant risk reduction for stroke, especially severe stroke, and all-cause mortality after a stroke. Findings from this observational study may help inform anticoagulant choice for stroke prevention in patients with nonvalvular atrial fibrillation.

Deep Learning Detection of Penumbral Tissue on Arterial Spin Labeling in Stroke

Background and Purpose- Selection of patients with acute ischemic stroke for endovascular treatment generally relies on dynamic susceptibility contrast magnetic resonance imaging or computed tomography perfusion. Dynamic susceptibility contrast magnetic resonance imaging requires injection of contrast, whereas computed tomography perfusion requires high doses of ionizing radiation. The purpose of this work was to develop and evaluate a deep learning (DL)-based algorithm for assisting the selection of suitable patients with acute ischemic stroke for endovascular treatment based on 3-dimensional pseudo-continuous arterial spin labeling (pCASL). Methods- A total of 167 image sets of 3-dimensional pCASL data from 137 patients with acute ischemic stroke scanned on 1.5T and 3.0T Siemens MR systems were included for neural network training. The concurrently acquired dynamic susceptibility contrast magnetic resonance imaging was used to produce labels of hypoperfused brain regions, analyzed using commercial software. The DL and 6 machine learning (ML) algorithms were trained with 10-fold cross-validation. The eligibility for endovascular treatment was determined retrospectively based on the criteria of perfusion/diffusion mismatch in the DEFUSE 3 trial (Endovascular Therapy Following Imaging Evaluation for Ischemic Stroke). The trained DL algorithm was further applied on twelve 3-dimensional pCASL data sets acquired on 1.5T and 3T General Electric MR systems, without fine-tuning of parameters. Results- The DL algorithm can predict the dynamic susceptibility contrast-defined hypoperfusion region in pCASL with a voxel-wise area under the curve of 0.958, while the 6 ML algorithms ranged from 0.897 to 0.933. For retrospective determination for subject-level endovascular treatment eligibility, the DL algorithm achieved an accuracy of 92%, with a sensitivity of 0.89 and specificity of 0.95. When applied to the GE pCASL data, the DL algorithm achieved a voxel-wise area under the curve of 0.94 and a subject-level accuracy of 92% for endovascular treatment eligibility. Conclusions- pCASL perfusion magnetic resonance imaging in conjunction with the DL algorithm provides a promising approach for assisting decision-making for endovascular treatment in patients with acute ischemic stroke.

Using machine learning models to improve stroke risk level classification methods of China national stroke screening

Background

With the character of high incidence, high prevalence and high mortality, stroke has brought a heavy burden to families and society in China. In 2009, the Ministry of Health of China launched the China national stroke screening and intervention program, which screens stroke and its risk factors and conducts high-risk population interventions for people aged above 40 years old all over China. In this program, stroke risk factors include hypertension, diabetes, dyslipidemia, smoking, lack of exercise, apparently overweight and family history of stroke. People with more than two risk factors or history of stroke or transient ischemic attack (TIA) are considered as high-risk. However, it is impossible for this criterion to classify stroke risk levels for people with unknown values in fields of risk factors. The missing of stroke risk levels results in reduced efficiency of stroke interventions and inaccuracies in statistical results at the national level. In this paper, we use 2017 national stroke screening data to develop stroke risk classification models based on machine learning algorithms to improve the classification efficiency.

Method

Firstly, we construct training set and test sets and process the imbalance training set based on oversampling and undersampling method. Then, we develop logistic regression model, Naïve Bayesian model, Bayesian network model, decision tree model, neural network model, random forest model, bagged decision tree model, voting model and boosting model with decision trees to classify stroke risk levels.

Result

The recall of the boosting model with decision trees is the highest (99.94%), and the precision of the model based on the random forest is highest (97.33%). Using the random forest model (recall: 98.44%), the recall will be increased by about 2.8% compared with the method currently used, and several thousands more people with high risk of stroke can be identified each year.

Conclusion

Models developed in this paper can improve the current screening method in the way that it can avoid the impact of unknown values, and avoid unnecessary rescreening and intervention expenditures. The national stroke screening program can choose classification models according to the practice need.

Artificial Intelligence in Interventional Radiology: A Literature Review and Future Perspectives

The term “artificial intelligence” (AI) includes computational algorithms that can perform tasks considered typical of human intelligence, with partial to complete autonomy, to produce new beneficial outputs from specific inputs. The development of AI is largely based on the introduction of artificial neural networks (ANN) that allowed the introduction of the concepts of “computational learning models,” machine learning (ML) and deep learning (DL). AI applications appear promising for radiology scenarios potentially improving lesion detection, segmentation, and interpretation with a recent application also for interventional radiology (IR) practice, including the ability of AI to offer prognostic information to both patients and physicians about interventional oncology procedures. This article integrates evidence-reported literature and experience-based perceptions to assist not only residents and fellows who are training in interventional radiology but also practicing colleagues who are approaching to locoregional mini-invasive treatments.

Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review

Background and purpose

Acute stroke caused by large vessel occlusions (LVOs) requires emergent detection and treatment by endovascular thrombectomy. However, radiologic LVO detection and treatment is subject to variable delays and human expertise, resulting in morbidity. Imaging software using artificial intelligence (AI) and machine learning (ML), a branch of AI, may improve rapid frontline detection of LVO strokes. This report is a systematic review of AI in acute LVO stroke identification and triage, and characterizes LVO detection software.

Methods

A systematic review of acute stroke diagnostic-focused AI studies from January 2014 to February 2019 in PubMed, Medline, and Embase using terms: ‘artificial intelligence’ or ‘machine learning or deep learning’ and ‘ischemic stroke’ or ‘large vessel occlusion’ was performed.

Results

Variations of AI, including ML methods of random forest learning (RFL) and convolutional neural networks (CNNs), are used to detect LVO strokes. Twenty studies were identified that use ML. Alberta Stroke Program Early CT Score (ASPECTS) commonly used RFL, while LVO detection typically used CNNs. Image feature detection had greater sensitivity with CNN than with RFL, 85% versus 68%. However, AI algorithm performance metrics use different standards, precluding ideal objective comparison. Four current software platforms incorporate ML: Brainomix (greatest validation of AI for ASPECTS, uses CNNs to automatically detect LVOs), General Electric, iSchemaView (largest number of perfusion study validations for thrombectomy), and Viz.ai (uses CNNs to automatically detect LVOs, then automatically activates emergency stroke treatment systems).

Conclusions

AI may improve LVO stroke detection and rapid triage necessary for expedited treatment. Standardization of performance assessment is needed in future studies.

Can clinical audits be enhanced by pathway simulation and machine learning? An example from the acute stroke pathway

OBJECTIVE

To evaluate the application of clinical pathway simulation in machine learning, using clinical audit data, in order to identify key drivers for improving use and speed of thrombolysis at individual hospitals.

DESIGN

Computer simulation modelling and machine learning.

SETTING

Seven acute stroke units.

PARTICIPANTS

Anonymised clinical audit data for 7864 patients.

RESULTS

Three factors were pivotal in governing thrombolysis use: (1) the proportion of patients with a known stroke onset time (range 44%-73%), (2) pathway speed (for patients arriving within 4 hours of onset: per-hospital median arrival-to-scan ranged from 11 to 56 min; median scan-to-thrombolysis ranged from 21 to 44 min) and (3) predisposition to use thrombolysis (thrombolysis use ranged from 31% to 52% for patients with stroke scanned with 30 min left to administer thrombolysis). A pathway simulation model could predict the potential benefit of improving individual stages of the clinical pathway speed, whereas a machine learning model could predict the benefit of 'exporting' clinical decision making from one hospital to another, while allowing for differences in patient population between hospitals. By applying pathway simulation and machine learning together, we found a realistic ceiling of 15%-25% use of thrombolysis across different hospitals and, in the seven hospitals studied, a realistic opportunity to double the number of patients with no significant disability that may be attributed to thrombolysis.

CONCLUSIONS

National clinical audit may be enhanced by a combination of pathway simulation and machine learning, which best allows for an understanding of key levers for improvement in hyperacute stroke pathways, allowing for differences between local patient populations. These models, based on standard clinical audit data, may be applied at scale while providing results at individual hospital level. The models facilitate understanding of variation and levers for improvement in stroke pathways, and help set realistic targets tailored to local populations.

Technical considerations of multi-parametric tissue outcome prediction methods in acute ischemic stroke patients

Decisions regarding acute stroke treatment rely heavily on imaging, but interpretation can be difficult for physicians. Machine learning methods can assist clinicians by providing tissue outcome predictions for different treatment approaches based on acute multi-parametric imaging. To produce such clinically viable machine learning models, factors such as classifier choice, data normalization, and data balancing must be considered. This study gives comprehensive consideration to these factors by comparing the agreement of voxel-based tissue outcome predictions using acute imaging and clinical parameters with manual lesion segmentations derived from follow-up imaging. This study considers random decision forest, generalized linear model, and k-nearest-neighbor machine learning classifiers in conjunction with three data normalization approaches (non-normalized, relative to contralateral hemisphere, and relative to contralateral VOI), and two data balancing strategies (full dataset and stratified subsampling). These classifier settings were evaluated based on 90 MRI datasets from acute ischemic stroke patients. Distinction was made between patients recanalized using intraarterial and intravenous methods, as well as those without successful recanalization. For primary quantitative comparison, the Dice metric was computed for each voxel-based tissue outcome prediction and its corresponding follow-up lesion segmentation. It was found that the random forest classifier outperformed the generalized linear model and the k-nearest-neighbor classifier, that normalization did not improve the Dice score of the lesion outcome predictions, and that the models generated lesion outcome predictions with higher Dice scores when trained with balanced datasets. No significant difference was found between the treatment groups (intraarterial vs intravenous) regarding the Dice score of the tissue outcome predictions.

Predicting Clinical Outcomes of Large Vessel Occlusion Before Mechanical Thrombectomy Using Machine Learning

Background and Purpose- The clinical course of acute ischemic stroke with large vessel occlusion (LVO) is a multifactorial process with various prognostic factors. We aimed to model this process with machine learning and predict the long-term clinical outcome of LVO before endovascular treatment and to compare our method with previously developed pretreatment scoring methods. Methods- The derivation cohort included 387 LVO patients, and the external validation cohort included 115 LVO patients with anterior circulation who were treated with mechanical thrombectomy. The statistical model with logistic regression without regularization and machine learning algorithms, such as regularized logistic regression, linear support vector machine, and random forest, were used to predict good clinical outcome (modified Rankin Scale score of 0-2 at 90 days) with standard and multiple pretreatment clinical variables. Five previously reported pretreatment scoring methods (the Pittsburgh Response to Endovascular Therapy score, the Stroke Prognostication Using Age and National Institutes of Health Stroke Scale index, the Totaled Health Risks in Vascular Events score, the Houston Intra-Arterial Therapy score, and the Houston Intra-Arterial Therapy 2 score) were compared with these models for the area under the receiver operating characteristic curve. Results- The area under the receiver operating characteristic curve of random forest, which was the worst among the machine learning algorithms, was significantly higher than those of the standard statistical model and the best model among the previously reported pretreatment scoring methods in the derivation (the area under the receiver operating characteristic curve were 0.85±0.07 for random forest, 0.78±0.08 for logistic regression without regularization, and 0.77±0.09 for Stroke Prognostication using Age and National Institutes of Health Stroke Scale) and validation cohorts (the area under the receiver operating characteristic curve were 0.87±0.01 for random forest, 0.56±0.07 for logistic regression without regularization, and 0.83±0.00 for Pittsburgh Response to Endovascular Therapy). Conclusions- Machine learning methods with multiple pretreatment clinical variables can predict clinical outcomes of patients with anterior circulation LVO who undergo mechanical thrombectomy more accurately than previously developed pretreatment scoring methods.

Leveraging machine learning techniques for predicting pancreatic neuroendocrine tumor grades using biochemical and tumor markers

BACKGROUND

The incidence of pancreatic neuroendocrine tumors (PNETs) is now increasing rapidly. The tumor grade of PNETs significantly affects the treatment strategy and prognosis. However, there is still no effective way to non-invasively classify PNET grades. Machine learning (ML) algorithms have shown potential in improving the prediction accuracy using comprehensive data.

AIM

To provide a ML approach to predict PNET tumor grade using clinical data.

METHODS

The clinical data of histologically confirmed PNET cases between 2012 and 2018 were collected. A method of minimum P for the Chi-square test was used to divide the continuous variables into binary variables. The continuous variables were transformed into binary variables according to the cutoff value, while the P value was minimum. Four classical supervised ML models, including logistic regression, support vector machine (SVM), linear discriminant analysis (LDA) and multi-layer perceptron (MLP) were trained by clinical data, and the models were labeled with the pathological tumor grade of each PNET patient. The performance of each model, including the weight of the different parameters, were evaluated.

RESULTS

In total, 91 PNET cases were included in this study, in which 32 were G1, 48 were G2 and 11 were G3. The results showed that there were significant differences among the clinical parameters of patients with different grades. Patients with higher grades tended to have higher values of total bilirubin, alpha fetoprotein, carcinoembryonic antigen, carbohydrate antigen 19-9 and carbohydrate antigen 72-4. Among the models we used, LDA performed best in predicting the PNET tumor grade. Meanwhile, MLP had the highest recall rate for G3 cases. All of the models stabilized when the sample size was over 70 percent of the total, except for SVM. Different parameters varied in affecting the outcomes of the models. Overall, alanine transaminase, total bilirubin, carcinoembryonic antigen, carbohydrate antigen 19-9 and carbohydrate antigen 72-4 affected the outcome greater than other parameters.

CONCLUSION

ML could be a simple and effective method in non-invasively predicting PNET grades by using the routine data obtained from the results of biochemical and tumor markers.

Glycated hemoglobin (HbA1c) and outcome following endovascular thrombectomy for ischemic stroke

BACKGROUND

In ischemic stroke, increased glycated hemoglobin (HbA1c) and glucose levels are associated with worse outcome following thrombolysis, and possibly, endovascular thrombectomy.

OBJECTIVE

To evaluate the association between admission HbA1c and glucose levels and outcome following endovascular thrombectomy.

METHODS

Consecutive patients treated with endovascular thrombectomy with admission HbA1c and glucose levels were included. The primary outcome was functional independence, defined as a modified Rankin Scale score of 0-2 at 3 months. Secondary outcomes included successful reperfusion (modified Thrombolysis in Cerebral Infarction 2b-3), early neurological improvement (reduction in National Institutes of Health Stroke Scale (NIHSS) score ≥8 points, or NIHSS score of 0-1 at 24 hours), symptomatic intracerebral hemorrhage (sICH), and mortality at 3 months.

RESULTS

223 patients (136 (61%) men; mean±SD age 64.5±14.6) were included. The median (IQR) HbA1c and glucose were 39 (36-45) mmol/mol and 6.9 (5.8-8.4) mmol/L, respectively. Multiple logistic regression analysis demonstrated that increasing HbA1c levels (per 10 mmol/mol) were associated with reduced functional independence (OR=0.76; 95% CI 0.60-0.96; p=0.02), increased sICH (OR=1.33; 95% CI 1.03 to 1.71; p=0.03), and increased mortality (OR=1.26; 95% CI 1.01 to 1.57; p=0.04). There were no significant associations between glucose levels and outcome measures (all p>0.05).

CONCLUSIONS

HbA1c levels are an independent predictor of worse outcome following endovascular thrombectomy. The addition of HbA1c to decision-support tools for endovascular thrombectomy should be evaluated in future studies.

Intelligent health data analytics: A convergence of artificial intelligence and big data

Healthcare is a living system that generates a significant volume of heterogeneous data. As healthcare systems are pivoting to value-based systems, intelligent and interactive analysis of health data is gaining significance for health system management, especially for resource optimization whilst improving care quality and health outcomes. Health data analytics is being influenced by new concepts and intelligent methods emanating from artificial intelligence and big data. In this article, we contextualize health data and health data analytics in terms of the emerging trends of artificial intelligence and big data. We examine the nature of health data using the big data criterion to understand "how big" is health data. Next, we explain the working of artificial intelligence-based data analytics methods and discuss "what insights" can be derived from a broad spectrum of health data analytics methods to improve health system management, health outcomes, knowledge discovery, and healthcare innovation.

Building Computational Models to Predict One-Year Mortality in ICU Patients with Acute Myocardial Infarction and Post Myocardial Infarction Syndrome

Heart disease remains the leading cause of death in the United States. Compared with risk assessment guidelines that require manual calculation of scores, machine learning-based prediction for disease outcomes such as mortality can be utilized to save time and improve prediction accuracy. This study built and evaluated various machine learning models to predict one-year mortality in patients diagnosed with acute myocardial infarction or post myocardial infarction syndrome in the MIMIC-III database. The results of the best performing shallow prediction models were compared to a deep feedforward neural network (Deep FNN) with back propagation. We included a cohort of 5436 admissions. Six datasets were developed and compared. The models applying Logistic Model Trees (LMT) and Simple Logistic algorithms to the combined dataset resulted in the highest prediction accuracy at 85.12% and the highest AUC at .901. In addition, other factors were observed to have an impact on outcomes as well.

Predictive analytics and machine learning in stroke and neurovascular medicine

Advances in predictive analytics and machine learning supported by an ever-increasing wealth of data and processing power are transforming almost every industry. Accuracy and precision of predictive analytics have significantly increased over the past few years and are evolving at an exponential pace. There have been significant breakthroughs in using Predictive Analytics in healthcare where it is held as the foundation of precision medicine. Yet, although the research in the field is expanding with the profuse volume of papers applying machine learning algorithms to medical data, very few have contributed meaningfully to clinical care. This lack of impact stands in stark contrast to the enormous relevance of machine learning to many other industries. Regardless of the status of its current contribution, the field of predictive analytics is expected to fundamentally change the way we diagnose and treat diseases, as well as the conduct of biomedical science research. In this review, we describe the main tools and techniques in predictive analytics and will analyze the trends in application of these techniques over the recent years. We will also provide examples of its application in medicine and more specifically in stroke and neurovascular research and outline current limitations.

The Neurologist and Artificial Intelligence: Titans at Crossroads

Clinical judgment to reach final diagnosis has remained a challenge since time immemorial. The present times are witness to artificial intelligence (AI) and machine learning programs competing to outperform the seasoned physician in arriving at a differential diagnosis. We discuss here the possible roles of AI in neurology.

Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage

Background and purpose

Delayed cerebral ischemia (DCI) is a severe complication in patients with aneurysmal subarachnoid hemorrhage. Several associated predictors have been previously identified. However, their predictive value is generally low. We hypothesize that Machine Learning (ML) algorithms for the prediction of DCI using a combination of clinical and image data lead to higher predictive accuracy than previously applied logistic regressions.

Materials and methods

Clinical and baseline CT image data from 317 patients with aneurysmal subarachnoid hemorrhage were included. Three types of analysis were performed to predict DCI. First, the prognostic value of known predictors was assessed with logistic regression models. Second, ML models were created using all clinical variables. Third, image features were extracted from the CT images using an auto-encoder and combined with clinical data to create ML models. Accuracy was evaluated based on the area under the curve (AUC), sensitivity and specificity with 95% CI.

Results

The best AUC of the logistic regression models for known predictors was 0.63 (95% CI 0.62 to 0.63). For the ML algorithms with clinical data there was a small but statistically significant improvement in the AUC to 0.68 (95% CI 0.65 to 0.69). Notably, aneurysm width and height were included in many of the ML models. The AUC was highest for ML models that also included image features: 0.74 (95% CI 0.72 to 0.75).

Conclusion

ML algorithms significantly improve the prediction of DCI in patients with aneurysmal subarachnoid hemorrhage, particularly when image features are also included. Our experiments suggest that aneurysm characteristics are also associated with the development of DCI.

Machine Learning in Acute Ischemic Stroke Neuroimaging

Machine Learning (ML) through pattern recognition algorithms is currently becoming an essential aid for the diagnosis, treatment, and prediction of complications and patient outcomes in a number of neurological diseases. The evaluation and treatment of Acute Ischemic Stroke (AIS) have experienced a significant advancement over the past few years, increasingly requiring the use of neuroimaging for decision-making. In this review, we offer an insight into the recent developments and applications of ML in neuroimaging focusing on acute ischemic stroke.

Initial Experiences with Artificial Neural Networks in the Detection of Computed Tomography Perfusion Deficits

BACKGROUND

Head computed tomography (CT) with perfusion imaging has become crucial in the selection of patients for mechanical thrombectomy. In recent years, machine learning has rapidly evolved and found applications in a wide variety of health care tasks. We report our initial experiences with training a neural network to predict the presence and laterality of a perfusion deficit in patients with acute ischemic stroke.

METHODS

CT perfusion images of patients with suspicion for acute ischemic stroke were obtained. The data were split into training and validation sets. A long-term, recurrent convolutional network was constructed, which consisted of a convolutional neural network stacked on top of a long short-term memory layer.

RESULTS

Of the 396 patients, 139 (35.1%) had a right-sided perfusion deficit, 199 (50.3%) had a left-sided deficit, and 58 (14.6%) had no evidence of a deficit. The best model was able to achieve an accuracy of 85.8% on validation data. Receiver operating characteristic curves were generated for each class, and an area under the curve (AUC) was calculated for each class. For right-sided deficits, the AUC was 0.90, for left-sided deficits, the AUC was 0.96, and for no deficit, the AUC was 0.93.

CONCLUSIONS

The field of machine learning, powered by convolutional neural networks for the task of image recognition and processing, has quickly developed in recent years. We constructed an artificial neural network that can identify and classify the presence and laterality of a perfusion deficit on CT perfusion imaging.

Peering Into the Black Box of Artificial Intelligence: Evaluation Metrics of Machine Learning Methods

OBJECTIVE

Machine learning (ML) and artificial intelligence (AI) are rapidly becoming the most talked about and controversial topics in radiology and medicine. Over the past few years, the numbers of ML- or AI-focused studies in the literature have increased almost exponentially, and ML has become a hot topic at academic and industry conferences. However, despite the increased awareness of ML as a tool, many medical professionals have a poor understanding of how ML works and how to critically appraise studies and tools that are presented to us. Thus, we present a brief overview of ML, explain the metrics used in ML and how to interpret them, and explain some of the technical jargon associated with the field so that readers with a medical background and basic knowledge of statistics can feel more comfortable when examining ML applications.

CONCLUSION

Attention to sample size, overfitting, underfitting, cross validation, as well as a broad knowledge of the metrics of machine learning, can help those with little or no technical knowledge begin to assess machine learning studies. However, transparency in methods and sharing of algorithms is vital to allow clinicians to assess these tools themselves.

A Bayesian Network Model for Predicting Post-stroke Outcomes With Available Risk Factors

Bayesian network is an increasingly popular method in modeling uncertain and complex problems, because its interpretability is often more useful than plain prediction. To satisfy the core requirement in medical research to obtain interpretable prediction with high accuracy, we constructed an inference engine for post-stroke outcomes based on Bayesian network classifiers. The prediction system that was trained on data of 3,605 patients with acute stroke forecasts the functional independence at 3 months and the mortality 1 year after stroke. Feature selection methods were applied to eliminate less relevant and redundant features from 76 risk variables. The Bayesian network classifiers were trained with a hill-climbing searching for the qualified network structure and parameters measured by maximum description length. We evaluated and optimized the proposed system to increase the area under the receiver operating characteristic curve (AUC) while ensuring acceptable sensitivity for the class-imbalanced data. The performance evaluation demonstrated that the Bayesian network with selected features by wrapper-type feature selection can predict 3-month functional independence with an AUC of 0.889 using only 19 risk variables and 1-year mortality with an AUC of 0.893 using 24 variables. The Bayesian network with 50 features filtered by information gain can predict 3-month functional independence with an AUC of 0.875 and 1-year mortality with an AUC of 0.895. We also built an online prediction service, Yonsei Stroke Outcome Inference System, to substantialize the proposed solution for patients with stroke.

Machine Learning in Agriculture: A Review

Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems. The works analyzed were categorized in (a) crop management, including applications on yield prediction, disease detection, weed detection crop quality, and species recognition; (b) livestock management, including applications on animal welfare and livestock production; (c) water management; and (d) soil management. The filtering and classification of the presented articles demonstrate how agriculture will benefit from machine learning technologies. By applying machine learning to sensor data, farm management systems are evolving into real time artificial intelligence enabled programs that provide rich recommendations and insights for farmer decision support and action.