Early Identification of High-Risk TIA or Minor Stroke Using Artificial Neural Network

Pitfalls in Developing Machine Learning Models for Predicting Cardiovascular Diseases: Challenge and Solutions

In recent years, there has been explosive development in artificial intelligence (AI), which has been widely applied in the health care field. As a typical AI technology, machine learning models have emerged with great potential in predicting cardiovascular diseases by leveraging large amounts of medical data for training and optimization, which are expected to play a crucial role in reducing the incidence and mortality rates of cardiovascular diseases. Although the field has become a research hot spot, there are still many pitfalls that researchers need to pay close attention to. These pitfalls may affect the predictive performance, credibility, reliability, and reproducibility of the studied models, ultimately reducing the value of the research and affecting the prospects for clinical application. Therefore, identifying and avoiding these pitfalls is a crucial task before implementing the research. However, there is currently a lack of a comprehensive summary on this topic. This viewpoint aims to analyze the existing problems in terms of data quality, data set characteristics, model design, and statistical methods, as well as clinical implications, and provide possible solutions to these problems, such as gathering objective data, improving training, repeating measurements, increasing sample size, preventing overfitting using statistical methods, using specific AI algorithms to address targeted issues, standardizing outcomes and evaluation criteria, and enhancing fairness and replicability, with the goal of offering reference and assistance to researchers, algorithm developers, policy makers, and clinical practitioners.

Using machine learning-based radiomics to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes

OBJECTIVE

To establish a machine learning-based radiomics model to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes, thereby achieving accurate preoperative classification.

MATERIALS AND METHODS

A retrospective analysis was conducted on MRI T1WI-enhanced images of 105 patients with glioma and 172 patients with solitary brain metastasis from lung cancer, which were confirmed pathologically. The patients were divided into the training group and validation group in an 8:2 ratio for image segmentation, extraction, and filtering; multiple layer perceptron (MLP), support vector machine (SVM), random forest (RF), and logistic regression (LR) were used for modeling; fivefold cross-validation was used to train the model; the validation group was used to evaluate and assess the predictive performance of the model, ROC curve was used to calculate the accuracy, sensitivity, and specificity of the model, and the area under curve (AUC) was used to assess the predictive performance of the model.

RESULTS

The accuracy and AUC of the MLP differentiation model for high-grade glioma and solitary brain metastasis in the validation group was 0.992, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.968, respectively. The accuracy and AUC for the MLP and SVM differentiation model for high-grade glioma and small cell lung cancer brain metastasis in the validation group was 0.966, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.929, respectively. The accuracy and AUC for the MLP differentiation model for high-grade glioma and non-small cell lung cancer brain metastasis in the validation group was 0.982, 0.999, respectively, while the sensitivity and specificity were 0.958, 1.000, respectively.

CONCLUSION

The application of machine learning-based radiomics has a certain clinical value in differentiating glioma from solitary brain metastasis from lung cancer and its subtypes. In the HGG/SBM and HGG/NSCLC SBM validation groups, the MLP model had the best diagnostic performance, while in the HGG/SCLC SBM validation group, the MLP and SVM models had the best diagnostic performance.

Perspective of artificial intelligence in healthcare data management: A journey towards precision medicine

Mounting evidence has highlighted the implementation of big data handling and management in the healthcare industry to improve the clinical services. Various private and public companies have generated, stored, and analyzed different types of big healthcare data, such as omics data, clinical data, electronic health records, personal health records, and sensing data with the aim to move in the direction of precision medicine. Additionally, with the advancement in technologies, researchers are curious to extract the potential involvement of artificial intelligence and machine learning on big healthcare data to enhance the quality of patient's lives. However, seeking solutions from big healthcare data requires proper management, storage, and analysis, which imposes hinderances associated with big data handling. Herein, we briefly discuss the implication of big data handling and the role of artificial intelligence in precision medicine. Further, we also highlighted the potential of artificial intelligence in integrating and analyzing the big data that offer personalized treatment. In addition, we briefly discuss the applications of artificial intelligence in personalized treatment, especially in neurological diseases. Lastly, we discuss the challenges and limitations imposed by artificial intelligence in big data management and analysis to hinder precision medicine.

Machine learning-based prediction of in-ICU mortality in pneumonia patients

Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models for mortality prediction in patients with severe pneumonia. This retrospective study evaluated patients admitted to the ICU for severe pneumonia between January 2016 and December 2021. The predictive performance was analyzed by comparing the area under the receiver operating characteristic curve (AU-ROC) of ML models to that of conventional severity-of-illness scoring systems. Three ML models were evaluated: (1) logistic regression with L2 regularization, (2) gradient-boosted decision tree (LightGBM), and (3) multilayer perceptron (MLP). Among the 816 pneumonia patients included, 223 (27.3%) patients died. All ML models significantly outperformed the Simplified Acute Physiology Score II (AU-ROC: 0.650 [0.584-0.716] vs 0.820 [0.771-0.869] for logistic regression vs 0.827 [0.777-0.876] for LightGBM 0.838 [0.791-0.884] for MLP; P < 0.001). In the analysis for NRI, the LightGBM and MLP models showed superior reclassification compared with the logistic regression model in predicting in-ICU mortality in all length of stay in the ICU subgroups; all age subgroups; all subgroups with any APACHE II score, PaO₂/FiO₂ ratio < 200; all subgroups with or without history of respiratory disease; with or without history of CVA or dementia; treatment with mechanical ventilation, and use of inotropic agents. In conclusion, the ML models have excellent performance in predicting in-ICU mortality in patients with severe pneumonia. Moreover, this study highlights the potential advantages of selecting individual ML models for predicting in-ICU mortality in different subgroups.

Prognostic prediction of thrombolytic therapy with rt-PA in acute ischemic stroke patients using an artificial intelligence model

OBJECTIVE

Through the comparison of different prediction models, we hope to find a promising statistical method to evaluate the prognosis of patients with acute ischemic stroke (AIS) after thrombolytic therapy.

METHODS

Data of 518 patients who received thrombolytic therapy were retrospectively collected in this study. Among them, 362 patients met the eligibility criteria, so their data such as age, sex, smoking history, previous medical history, clinical and laboratory indicators were analyzed. According to the 3 month follow-up results, 266 patients were included in a good prognosis group (modified Rankin Scale (mRS) score ≤2) and 96 in a poor prognosis group (3≤mRS≤6). All variables with P<0.05 in univariant and multivariant analyses were assigned in logistic regression model and artificial neural network (ANN) model to predict neurological prognosis, and the performance of the two models were compared.

RESULTS

Age, NIHSS scores, the serum concentration of immediate glucose, APTT and MBP at admission were found to be the predictive factors through ANN and logistic regression analysis. The binary logistic regression model revealed that the percentage correction, the precision, recall and F1 score of the regression model were 79%, 69.23%, 37.50% and 48.65%, respectively. While those of ANN were 79.98%, 69.70%, 37.25%, and 49.66%, correspondingly.

CONCLUSIONS

ANN model is as effective as a logistic regression model in predicting the prognosis of AIS after thrombolytic therapy with rt-PA. Moreover, ANN is slightly superior to logistic regression in accuracy, precision and F1 score.

Artificial Intelligence in Acute Ischemic Stroke Subtypes According to Toast Classification: A Comprehensive Narrative Review

The correct recognition of the etiology of ischemic stroke (IS) allows tempestive interventions in therapy with the aim of treating the cause and preventing a new cerebral ischemic event. Nevertheless, the identification of the cause is often challenging and is based on clinical features and data obtained by imaging techniques and other diagnostic exams. TOAST classification system describes the different etiologies of ischemic stroke and includes five subtypes: LAAS (large-artery atherosclerosis), CEI (cardio embolism), SVD (small vessel disease), ODE (stroke of other determined etiology), and UDE (stroke of undetermined etiology). AI models, providing computational methodologies for quantitative and objective evaluations, seem to increase the sensitivity of main IS causes, such as tomographic diagnosis of carotid stenosis, electrocardiographic recognition of atrial fibrillation, and identification of small vessel disease in magnetic resonance images. The aim of this review is to provide overall knowledge about the most effective AI models used in the differential diagnosis of ischemic stroke etiology according to the TOAST classification. According to our results, AI has proven to be a useful tool for identifying predictive factors capable of subtyping acute stroke patients in large heterogeneous populations and, in particular, clarifying the etiology of UDE IS especially detecting cardioembolic sources.

XGBoost-Based Simple Three-Item Model Accurately Predicts Outcomes of Acute Ischemic Stroke

An all-inclusive and accurate prediction of outcomes for patients with acute ischemic stroke (AIS) is crucial for clinical decision-making. This study developed extreme gradient boosting (XGBoost)-based models using three simple factors-age, fasting glucose, and National Institutes of Health Stroke Scale (NIHSS) scores-to predict the three-month functional outcomes after AIS. We retrieved the medical records of 1848 patients diagnosed with AIS and managed at a single medical center between 2016 and 2020. We developed and validated the predictions and ranked the importance of each variable. The XGBoost model achieved notable performance, with an area under the curve of 0.8595. As predicted by the model, the patients with initial NIHSS score > 5, aged over 64 years, and fasting blood glucose > 86 mg/dL were associated with unfavorable prognoses. For patients receiving endovascular therapy, fasting glucose was the most important predictor. The NIHSS score at admission was the most significant predictor for those who received other treatments. Our proposed XGBoost model showed a reliable predictive power of AIS outcomes using readily available and simple predictors and also demonstrated the validity of the model for application in patients receiving different AIS treatments, providing clinical evidence for future optimization of AIS treatment strategies.

Application of machine learning-based models to boost the predictive power of the SPAN index

BACKGROUND

This study re-explored the predictive validity of Stroke Prognostication using Age and National Institutes of Health Stroke Scale (SPAN) index in patients who received different treatments for acute ischemic stroke (AIS) and developed machine learning-boosted outcome prediction models.

METHODS

We evaluated the prognostic relevance of SPAN index in patients with AIS who received intravenous tissue-type plasminogen activator (IV-tPA), intra-arterial thrombolysis (IAT) or non-thrombolytic treatments (non-tPA), and applied machine learning algorithms to develop SPAN-based outcome prediction models in a cohort of 2145 hospitalized AIS patients. The performance of the models was assessed and compared using the area under the receiver operating characteristic curves (AUCs).

RESULTS

SPAN index ≥100 was associated with higher mortality rate and higher modified Rankin Scale at discharge in AIS patients who received the different treatments. Compared to the lower AUCs for the SPAN-alone model across all groups, the AUCs of the logistic regression-boosted model were 0.838, 0.857, 0.766 and 0.875 for the whole cohort, non-tPA, IV-tPA and IAT groups, respectively. Similarly, the AUCs of the generated artificial neural network were 0.846, 0.858, 0.785 and 0.859 for the whole cohort, non-tPA, IV-tPA and IAT groups, respectively, while for gradient boosting decision tree model, we computed 0.850, 0.863, 0.779 and 0.815.

CONCLUSIONS

SPAN index has prognostic relevance in patients with AIS who received different treatments. The generated machine learning-based models exhibit good performance for predicting the functional recovery of AIS; thus, their proposed clinical application to aid outcome prediction and decision-making for the patients with AIS.

Multilayer perceptron-based prediction of stroke mimics in prehospital triage

The identification of stroke mimics (SMs) in patients with stroke could lead to delayed diagnosis and waste of medical resources. Multilayer perceptron (MLP) was proved to be an accurate tool for clinical applications. However, MLP haven't been applied in patients with suspected stroke onset within 24 h. Here, we aimed to develop a MLP model to predict SM in patients. We retrospectively reviewed the data of patients with a prehospital diagnosis of suspected stroke between July 2017 and June 2021. SMs were confirmed during hospitalization. We included demographic information, clinical manifestations, medical history, and systolic and diastolic pressure on admission. First, the cohort was randomly divided into a training set (70%) and an external testing set (30%). Then, the least absolute shrinkage and selection operator (LASSO) method was used in feature selection and an MLP model was trained based on the selected items. Then, we evaluated the performance of the model using the ten-fold cross validation method. Finally, we used the external testing set to compare the MLP model with FABS scoring system (FABS) and TeleStroke Mimic Score (TM-Score) using a receiver operator characteristic (ROC) curve. In total, 402 patients were included. Of these, 82 (20.5%) were classified as SMs. During the ten-fold cross validation, the mean area under the ROC curve (AUC) of 10 training sets and 10 validation sets were 0.92 and 0.87, respectively. In the external testing set, the AUC of the MLP model was significantly higher than that of the FABS (0.855 vs. 0.715, P = 0.038) and TM-Score (0.855 vs. 0.646, P = 0.006). The MLP model had significantly better performance in predicting SMs than FABS and TM-Score.

FAST-IT: Find A Simple Test - In TIA (transient ischaemic attack): a prospective cohort study to develop a multivariable prediction model for diagnosis of TIA through proteomic discovery and candidate lipid mass spectrometry, neuroimaging and machine learning-study protocol

INTRODUCTION

Transient ischaemic attack (TIA) may be a warning sign of stroke and difficult to differentiate from minor stroke and TIA-mimics. Urgent evaluation and diagnosis is important as treating TIA early can prevent subsequent strokes. Recent improvements in mass spectrometer technology allow quantification of hundreds of plasma proteins and lipids, yielding large datasets that would benefit from different approaches including machine learning. Using plasma protein, lipid and radiological biomarkers, our study will develop predictive algorithms to distinguish TIA from minor stroke (positive control) and TIA-mimics (negative control). Analysis including machine learning employs more sophisticated modelling, allowing non-linear interactions, adapting to datasets and enabling development of multiple specialised test-panels for identification and differentiation.

METHODS AND ANALYSIS

Patients attending the Emergency Department, Stroke Ward or TIA Clinic at the Royal Adelaide Hospital with TIA, minor stroke or TIA-like symptoms will be recruited consecutively by staff-alert for this prospective cohort study. Advanced neuroimaging will be performed for each participant, with images assessed independently by up to three expert neurologists. Venous blood samples will be collected within 48 hours of symptom onset. Plasma proteomic and lipid analysis will use advanced mass spectrometry (MS) techniques. Principal component analysis and hierarchical cluster analysis will be performed using MS software. Output files will be analysed for relative biomarker quantitative differences between the three groups. Differences will be assessed by linear regression, one-way analysis of variance, Kruskal-Wallis H-test, χ² test or Fisher's exact test. Machine learning methods will also be applied including deep learning using neural networks.

ETHICS AND DISSEMINATION

Patients will provide written informed consent to participate in this grant-funded study. The Central Adelaide Local Health Network Human Research Ethics Committee approved this study (HREC/18/CALHN/384; R20180618). Findings will be disseminated through peer-reviewed publication and conferences; data will be managed according to our Data Management Plan (DMP2020-00062).

Prediction of Recurrent Ischemic Stroke Using Registry Data and Machine Learning Methods: The Erlangen Stroke Registry

BACKGROUND

There have been multiple efforts toward individual prediction of recurrent strokes based on structured clinical and imaging data using machine learning algorithms. Some of these efforts resulted in relatively accurate prediction models. However, acquiring clinical and imaging data is typically possible at provider sites only and is associated with additional costs. Therefore, we developed recurrent stroke prediction models based solely on data easily obtained from the patient at home.

METHODS

Data from 384 patients with ischemic stroke were obtained from the Erlangen Stroke Registry. Patients were followed at 3 and 12 months after first stroke and then annually, for about 2 years on average. Multiple machine learning algorithms were applied to train predictive models for estimating individual risk of recurrent stroke within 1 year. Double nested cross-validation was utilized for conservative performance estimation and models' learning capabilities were assessed by learning curves. Predicted probabilities were calibrated, and relative variable importance was assessed using explainable artificial intelligence techniques.

RESULTS

The best model achieved the area under the curve of 0.70 (95% CI, 0.64-0.76) and relatively good probability calibration. The most predictive factors included patient's family and housing circumstances, rehabilitative measures, age, high calorie diet, systolic and diastolic blood pressures, percutaneous endoscopic gastrotomy, number of family doctor's home visits, and patient's mental state.

CONCLUSIONS

Developing fairly accurate models for individual risk prediction of recurrent ischemic stroke within 1 year solely based on registry data is feasible. Such models could be applied in a home setting to provide an initial risk assessment and identify high-risk patients early.

Artificial Neural Network Detects Hip Muscle Forces as Determinant for Harmonic Walking in People after Stroke

Many recent studies have highlighted that the harmony of physiological walking is based on a specific proportion between the durations of the phases of the gait cycle. When this proportion is close to the so-called golden ratio (about 1.618), the gait cycle assumes an autosimilar fractal structure. In stroke patients this harmony is altered, but it is unclear which factor is associated with the ratios between gait phases because these relationships are probably not linear. We used an artificial neural network to determine the weights associable to each factor for determining the ratio between gait phases and hence the harmony of walking. As expected, the gait ratio obtained as the ratio between stride duration and stance duration was found to be associated with walking speed and stride length, but also with hip muscle forces. These muscles could be important for exploiting the recovery of energy typical of the pendular mechanism of walking. Our study also highlighted that the results of an artificial neural network should be associated with a reliability analysis, being a non-deterministic approach. A good level of reliability was found for the findings of our study.

The Predictive Value of Dynamic Intrinsic Local Metrics in Transient Ischemic Attack

Background

Transient ischemic attack (TIA) is known as “small stroke.” However, the diagnosis of TIA is currently difficult due to the transient symptoms. Therefore, objective and reliable biomarkers are urgently needed in clinical practice.

Objective

The purpose of this study was to investigate whether dynamic alterations in resting-state local metrics could differentiate patients with TIA from healthy controls (HCs) using the support-vector machine (SVM) classification method.

Methods

By analyzing resting-state functional MRI (rs-fMRI) data from 48 patients with and 41 demographically matched HCs, we compared the group differences in three dynamic local metrics: dynamic amplitude of low-frequency fluctuation (d-ALFF), dynamic fractional amplitude of low-frequency fluctuation (d-fALFF), and dynamic regional homogeneity (d-ReHo). Furthermore, we selected the observed alterations in three dynamic local metrics as classification features to distinguish patients with TIA from HCs through SVM classifier.

Results

We found that TIA was associated with disruptions in dynamic local intrinsic brain activities. Compared with HCs, the patients with TIA exhibited increased d-fALFF, d-fALFF, and d-ReHo in vermis, right calcarine, right middle temporal gyrus, opercular part of right inferior frontal gyrus, left calcarine, left occipital, and left temporal and cerebellum. These alternations in the dynamic local metrics exhibited an accuracy of 80.90%, sensitivity of 77.08%, specificity of 85.37%, precision of 86.05%, and area under curve of 0.8501 for distinguishing the patients from HCs.

Conclusion

Our findings may provide important evidence for understanding the neuropathology underlying TIA and strong support for the hypothesis that these local metrics have potential value in clinical diagnosis.

Artificial Intelligence: A Shifting Paradigm in Cardio-Cerebrovascular Medicine

The future of healthcare is an organic blend of technology, innovation, and human connection. As artificial intelligence (AI) is gradually becoming a go-to technology in healthcare to improve efficiency and outcomes, we must understand our limitations. We should realize that our goal is not only to provide faster and more efficient care, but also to deliver an integrated solution to ensure that the care is fair and not biased to a group of sub-population. In this context, the field of cardio-cerebrovascular diseases, which encompasses a wide range of conditions-from heart failure to stroke-has made some advances to provide assistive tools to care providers. This article aimed to provide an overall thematic review of recent development focusing on various AI applications in cardio-cerebrovascular diseases to identify gaps and potential areas of improvement. If well designed, technological engines have the potential to improve healthcare access and equitability while reducing overall costs, diagnostic errors, and disparity in a system that affects patients and providers and strives for efficiency.

Wearable inertial sensors for human movement analysis: a five-year update

INTRODUCTION

The aim of the present review is to track the evolution of wearable IMUs from their use in supervised laboratory- and ambulatory-based settings to their application for long-term monitoring of human movement in unsupervised naturalistic settings.

AREAS COVERED

Four main emerging areas of application were identified and synthesized, namely, mobile health solutions (specifically, for the assessment of frailty, risk of falls, chronic neurological diseases, and for the monitoring and promotion of active living), occupational ergonomics, rehabilitation and telerehabilitation, and cognitive assessment. Findings from recent scientific literature in each of these areas was synthesized from an applied and/or clinical perspective with the purpose of providing clinical researchers and practitioners with practical guidance on contemporary uses of inertial sensors in applied clinical settings.

EXPERT OPINION

IMU-based wearable devices have undergone a rapid transition from use in laboratory-based clinical practice to unsupervised, applied settings. Successful use of wearable inertial sensing for assessing mobility, motor performance and movement disorders in applied settings will rely also on machine learning algorithms for managing the vast amounts of data generated by these sensors for extracting information that is both clinically relevant and interpretable by practitioners.

An Artificial Neural Network Prediction Model for Posttraumatic Epilepsy: Retrospective Cohort Study

Background

Posttraumatic epilepsy (PTE) is a common sequela after traumatic brain injury (TBI), and identifying high-risk patients with PTE is necessary for their better treatment. Although artificial neural network (ANN) prediction models have been reported and are superior to traditional models, the ANN prediction model for PTE is lacking.

Objective

We aim to train and validate an ANN model to anticipate the risks of PTE.

Methods

The training cohort was TBI patients registered at West China Hospital. We used a 5-fold cross-validation approach to train and test the ANN model to avoid overfitting; 21 independent variables were used as input neurons in the ANN models, using a back-propagation algorithm to minimize the loss function. Finally, we obtained sensitivity, specificity, and accuracy of each ANN model from the 5 rounds of cross-validation and compared the accuracy with a nomogram prediction model built in our previous work based on the same population. In addition, we evaluated the performance of the model using patients registered at Chengdu Shang Jin Nan Fu Hospital (testing cohort 1) and Sichuan Provincial People’s Hospital (testing cohort 2) between January 1, 2013, and March 1, 2015.

Results

For the training cohort, we enrolled 1301 TBI patients from January 1, 2011, to December 31, 2017. The prevalence of PTE was 12.8% (166/1301, 95% CI 10.9%-14.6%). Of the TBI patients registered in testing cohort 1, PTE prevalence was 10.5% (44/421, 95% CI 7.5%-13.4%). Of the TBI patients registered in testing cohort 2, PTE prevalence was 6.1% (25/413, 95% CI 3.7%-8.4%). The results of the ANN model show that, the area under the receiver operating characteristic curve in the training cohort was 0.907 (95% CI 0.889-0.924), testing cohort 1 was 0.867 (95% CI 0.842-0.893), and testing cohort 2 was 0.859 (95% CI 0.826-0.890). Second, the average accuracy of the training cohort was 0.557 (95% CI 0.510-0.620), with 0.470 (95% CI 0.414-0.526) in testing cohort 1 and 0.344 (95% CI 0.287-0.401) in testing cohort 2. In addition, sensitivity, specificity, positive predictive values and negative predictors in the training cohort (testing cohort 1 and testing cohort 2) were 0.80 (0.83 and 0.80), 0.86 (0.80 and 0.84), 91% (85% and 78%), and 86% (80% and 83%), respectively. When calibrating this ANN model, Brier scored 0.121 in testing cohort 1 and 0.127 in testing cohort 2. Compared with the nomogram model, the ANN prediction model had a higher accuracy (P=.01).

Conclusions

This study shows that the ANN model can predict the risk of PTE and is superior to the risk estimated based on traditional statistical methods. However, the calibration of the model is a bit poor, and we need to calibrate it on a large sample size set and further improve the model.

Digital health in stroke medicine: what are the opportunities for stroke patients?

PURPOSE OF REVIEW

The European Stroke Organisation published a European Stroke Action Plan (SAP-E) for the years 2018-2030. The SAP-E addresses the entire chain of care from primary prevention through to life after stroke. Within this document digital health tools are suggested for their potential to facilitate greater access to stroke care. In this review, we searched for digital health solutions for every domain of the SAP-E.

RECENT FINDINGS

Currently available digital health solutions for the cerebrovascular disease have been designed to support professionals and patients in healthcare settings at all stages. Telemedicine in acute settings has notably increased the access to tissue plasminogen activator and thrombectomy whereas in poststroke settings it has improved access to rehabilitation. Moreover, numerous applications aim to monitor vital signs and prescribed treatment adherence.

SUMMARY

SAP-E with its seven domains covers the whole continuum of stroke care, where digital health solutions have been considered to provide utility at a low cost. These technologies are progressively being used in all phases of stroke care, allowing them to overcome geographical and organizational barriers. The commercially available applications may also be used by patients and their careers in various context to facilitate accessibility to health improvement strategies.

Artificial intelligence in clinical decision support and outcome prediction - applications in stroke

Artificial intelligence (AI) is making a profound impact in healthcare, with the number of AI applications in medicine increasing substantially over the past five years. In acute stroke, it is playing an increasingly important role in clinical decision-making. Contemporary advances have increased the amount of information - both clinical and radiological - which clinicians must consider when managing patients. In the time-critical setting of acute stroke, AI offers the tools to rapidly evaluate and consolidate available information, extracting specific predictions from rich, noisy data. It has been applied to the automatic detection of stroke lesions on imaging and can guide treatment decisions through the prediction of tissue outcomes and long-term functional outcomes. This review examines the current state of AI applications in stroke, exploring their potential to reform stroke care through clinical decision support, as well as the challenges and limitations which must be addressed to facilitate their acceptance and adoption for clinical use.

Artificial Neural Network Analyzing Wearable Device Gait Data for Identifying Patients With Stroke Unable to Return to Work

A potential dramatic effect of long-term disability due to stroke is the inability to return to work. An accurate prognosis and the identification of the parameters inflating the possibility of return to work after neurorehabilitation are crucial. Many factors may influence it, such as mobility and, in particular, walking ability. In this pilot study, two emerging technologies have been combined with the aim of developing a prognostic tool for identifying patients able to return to work: a wearable inertial measurement unit for gait analysis and an artificial neural network (ANN). Compared with more conventional statistics, the ANN showed a higher accuracy in identifying patients with respect to healthy subjects (90.9 vs. 75.8%) and also in identifying the subjects unable to return to work (93.9 vs. 81.8%). In this last analysis, the duration of double support phase resulted the most important input of the ANN. The potentiality of the ANN, developed also in other fields such as marketing on social networks, could allow a powerful support for clinicians that today should manage a large amount of instrumentally recorded parameters in patients with stroke.

Artificial neural network based prediction of postthrombolysis intracerebral hemorrhage and death

Despite the salient benefits of the intravenous tissue plasminogen activator (tPA), symptomatic intracerebral hemorrhage (sICH) remains a frequent complication and constitutes a major concern when treating acute ischemic stroke (AIS). This study explored the use of artificial neural network (ANN)-based models to predict sICH and 3-month mortality for patients with AIS receiving tPA. We developed ANN models based on evaluation of the predictive value of pre-treatment parameters associated with sICH and mortality in a cohort of 331 patients between 2009 and 2018. The ANN models were generated using eight clinical inputs and two outputs. The generalizability of the model was validated using fivefold cross-validation. The performance of each model was assessed according to the accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). After adequate training, the ANN predictive model AUC for sICH was 0.941, with accuracy, sensitivity, and specificity of 91.0%, 85.7%, and 92.5%, respectively. The predictive model AUC for 3-month mortality was 0.976, with accuracy, sensitivity, and specificity of 95.2%, 94.4%, and 95.5%, respectively. The generated ANN-based models exhibited high predictive performance and reliability for predicting sICH and 3-month mortality after thrombolysis; thus, its clinical application to assist decision-making when administering tPA is envisaged.

Corneal confocal microscopy identifies greater corneal nerve damage in patients with a recurrent compared to first ischemic stroke

Objectives

Corneal nerve damage may be a surrogate marker for the risk of ischemic stroke. This study was undertaken to determine if there is greater corneal nerve damage in patients with recurrent ischemic stroke.

Methods

Corneal confocal microscopy (CCM) was used to quantify corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), corneal nerve fiber length (CNFL) and corneal nerve fiber tortuosity (CNFT) in 31 patients with recurrent ischemic stroke, 165 patients with a first acute ischemic stroke and 23 healthy control subjects.

Results

Triglycerides (P = 0.004, P = 0.017), systolic BP (P = 0.000, P = 0.000), diastolic BP (P = 0.000, P = 0.000) and HbA_1c (P = 0.000, P = 0.000) were significantly higher in patients with first and recurrent stroke compared to controls. There was no difference in age, BMI, HbA_1c, total cholesterol, triglycerides, LDL, HDL, systolic and diastolic BP between patients with a first and recurrent ischemic stroke. However, CNFD was significantly lower (24.98±7.31 vs 29.07±7.58 vs 37.91±7.13, P<0.05) and CNFT was significantly higher (0.085±0.042 vs 0.064±0.037 vs 0.039±0.022, P<0.05) in patients with recurrent stroke compared to first stroke and healthy controls. CNBD (42.21±24.65 vs 50.46±27.68 vs 87.24±45.85, P<0.001) and CNFL (15.66±5.70, P<0.001 vs 17.38±5.06, P = 0.003) were equally reduced in patients with first and recurrent stroke compared to controls (22.72±5.14).

Conclusions

Corneal confocal microscopy identified greater corneal nerve fibre loss in patients with recurrent stroke compared to patients with first stroke, despite comparable risk factors. Longitudinal studies are required to determine the prognostic utility of corneal nerve fiber loss in identifying patients at risk of recurrent ischemic stroke.

Clinical Risk Score for Predicting Recurrence Following a Cerebral Ischemic Event

Introduction: Recurrent stroke has a higher rate of death and disability. A number of risk scores have been developed to predict short-term and long-term risk of stroke following an initial episode of stroke or transient ischemic attack (TIA) with limited clinical utilities. In this paper, we review different risk score models and discuss their validity and clinical utilities.

Methods: The PubMed bibliographic database was searched for original research articles on the various risk scores for risk of stroke following an initial episode of stroke or TIA. The validation of the models was evaluated by examining the internal and external validation process as well as statistical methodology, the study power, as well as the accuracy and metrics such as sensitivity and specificity.

Results: Different risk score models have been derived from different study populations. Validation studies for these risk scores have produced conflicting results. Currently, ABCD² score with diffusion weighted imaging (DWI) and Recurrence Risk Estimator at 90 days (RRE-90) are the two acceptable models for short-term risk prediction whereas Essen Stroke Risk Score (ESRS) and Stroke Prognosis Instrument-II (SPI-II) can be useful for prediction of long-term risk.

Conclusion: The clinical risk scores that currently exist for predicting short-term and long-term risk of recurrent cerebral ischemia are limited in their performance and clinical utilities. There is a need for a better predictive tool which can overcome the limitations of current predictive models. Application of machine learning methods in combination with electronic health records may provide platform for development of new-generation predictive tools.

Artificial intelligence as an emerging technology in the current care of neurological disorders

BACKGROUND

Artificial intelligence (AI) has influenced all aspects of human life and neurology is no exception to this growing trend. The aim of this paper is to guide medical practitioners on the relevant aspects of artificial intelligence, i.e., machine learning, and deep learning, to review the development of technological advancement equipped with AI, and to elucidate how machine learning can revolutionize the management of neurological diseases. This review focuses on unsupervised aspects of machine learning, and how these aspects could be applied to precision neurology to improve patient outcomes. We have mentioned various forms of available AI, prior research, outcomes, benefits and limitations of AI, effective accessibility and future of AI, keeping the current burden of neurological disorders in mind.

DISCUSSION

The smart device system to monitor tremors and to recognize its phenotypes for better outcomes of deep brain stimulation, applications evaluating fine motor functions, AI integrated electroencephalogram learning to diagnose epilepsy and psychological non-epileptic seizure, predict outcome of seizure surgeries, recognize patterns of autonomic instability to prevent sudden unexpected death in epilepsy (SUDEP), identify the pattern of complex algorithm in neuroimaging classifying cognitive impairment, differentiating and classifying concussion phenotypes, smartwatches monitoring atrial fibrillation to prevent strokes, and prediction of prognosis in dementia are unique examples of experimental utilizations of AI in the field of neurology. Though there are obvious limitations of AI, the general consensus among several nationwide studies is that this new technology has the ability to improve the prognosis of neurological disorders and as a result should become a staple in the medical community.

CONCLUSION

AI not only helps to analyze medical data in disease prevention, diagnosis, patient monitoring, and development of new protocols, but can also assist clinicians in dealing with voluminous data in a more accurate and efficient manner.