Artificial intelligence for decision support in acute stroke - current roles and potential

Automated neuroradiological support systems for multiple cerebrovascular disease markers - A systematic review and meta-analysis

Cerebrovascular diseases (CVD) can lead to stroke and dementia. Stroke is the second leading cause of death world wide and dementia incidence is increasing by the year. There are several markers of CVD that are visible on brain imaging, including: white matter hyperintensities (WMH), acute and chronic ischaemic stroke lesions (ISL), lacunes, enlarged perivascular spaces (PVS), acute and chronic haemorrhagic lesions, and cerebral microbleeds (CMB). Brain atrophy also occurs in CVD. These markers are important for patient management and intervention, since they indicate elevated risk of future stroke and dementia. We systematically reviewed automated systems designed to support radiologists reporting on these CVD imaging findings. We considered commercially available software and research publications which identify at least two CVD markers. In total, we included 29 commercial products and 13 research publications. Two distinct types of commercial support system were available: those which identify acute stroke lesions (haemorrhagic and ischaemic) from computed tomography (CT) scans, mainly for the purpose of patient triage; and those which measure WMH and atrophy regionally and longitudinally. In research, WMH and ISL were the markers most frequently analysed together, from magnetic resonance imaging (MRI) scans; lacunes and PVS were each targeted only twice and CMB only once. For stroke, commercially available systems largely support the emergency setting, whilst research systems consider also follow-up and routine scans. The systems to quantify WMH and atrophy are focused on neurodegenerative disease support, where these CVD markers are also of significance. There are currently no openly validated systems, commercially, or in research, performing a comprehensive joint analysis of all CVD markers (WMH, ISL, lacunes, PVS, haemorrhagic lesions, CMB, and atrophy).

Postoperative self-care ability of continuous nursing based on artificial intelligence for stroke patients with neurological injury

According to the statistics of relevant data, stroke is a relatively common cerebrovascular disease, and its incidence rate is as high as 185/100,000 to 219/100,000. Continuous care can improve the quality of life of stroke patients and reduce the rate of hospital visits and hospitalizations. In this study, patients in a local hospital of third-grade class-A hospital were used as cases. Artificial intelligence was used to conduct continuous nursing intervention for the patients who were discharged from the stroke by using the WeChat platform, regular follow-up and home care. Afterwards, the collected data were given a post-processing, independent-samples t-test for two groups. After 3 months of extended care, the BI (Barthel Index) score of the intervention group has increased by 23.87 points, and the depression self-rating scale score has decreased by 9.12 points. Compared with the control group, the patients' self-care ability, depression state, compliance with health guidance and laboratory indicators were also better than those in the control group, and the differences were statistically significant (P < 0.05). Compared with the control group, the trend of increasing the scores of each index was more significant in the intervention group.

Generation of preoperative anaesthetic plans by ChatGPT-4.0: a mixed-method study

BACKGROUND

Recent advances in artificial intelligence (AI) have enabled development of natural language algorithms capable of generating coherent texts. We evaluated the quality, validity, and safety of this generative AI in preoperative anaesthetic planning.

METHODS

In this exploratory, single-centre, convergent mixed-method study, 10 clinical vignettes were randomly selected, and ChatGPT (OpenAI, 4.0) was prompted to create anaesthetic plans, including cardiopulmonary risk assessment, intraoperative anaesthesia technique, and postoperative management. A quantitative assessment compared these plans with those made by eight senior anaesthesia consultants. A qualitative assessment was performed by an adjudication committee through focus group discussion and thematic analysis. Agreement on cardiopulmonary risk assessment was calculated using weighted Kappa, with descriptive data representation for other outcomes.

RESULTS

ChatGPT anaesthetic plans showed variable agreement with consultants' plans. ChatGPT, the survey panel, and adjudication committee frequently disagreed on cardiopulmonary risk estimation. The ChatGPT answers were repetitive and lacked variety, evidenced by the strong preference for general anaesthesia and absence of locoregional techniques. It also showed inconsistent choices regarding airway management, postoperative analgesia, and medication use. While some differences were not deemed clinically significant, subpar postoperative pain management advice and failure to recommend tracheal intubation for patients at high risk for pulmonary aspiration were considered inappropriate recommendations.

CONCLUSIONS

Preoperative anaesthetic plans generated by ChatGPT did not consistently meet minimum clinical standards and were unlikely the result of clinical reasoning. Therefore, ChatGPT is currently not recommended for preoperative planning. Future large language models trained on anaesthesia-specific datasets might improve performance but should undergo vigorous evaluation before use in clinical practice.

Optimizing Stroke Risk Prediction: A Primary Dataset-Driven Ensemble Classifier With Explainable Artificial Intelligence

Background and Aims

Stroke remains a leading cause of mortality and long-term disability worldwide, presenting a significant global health challenge. Effective early prediction models are essential for reducing its impact. This study introduces a novel ensemble method for predicting stroke using two datasets: a primary dataset collected from a hospital, containing medical histories and clinical parameters, and a secondary dataset.

Methods

We applied several preprocessing techniques, including outlier detection, data normalization, k-means clustering, and missing value detection, to refine the datasets. A novel ensemble classifier was developed, combining AdaBoost, Gradient Boosting Machine (GBM), Multilayer Perceptron (MLP), and Random Forest (RF) algorithms to enhance predictive accuracy. Additionally, Explainable Artificial Intelligence (XAI) techniques such as SHAP and LIME were integrated to elucidate key features influencing stroke prediction.

Results

The proposed ensemble classifier achieved an accuracy of 95% for the secondary dataset and 80.36% for the primary dataset. Comparative analysis with other machine learning models highlighted the superior performance of the ensemble approach. The integration of XAI further provided insights into the critical indicators influencing stroke classification, improving model interpretability and decision-making.

Conclusion

Our study demonstrates that the novel ensemble classifier, supported by effective preprocessing and XAI techniques, is a powerful tool for stroke prediction. The high accuracy rates achieved validate its effectiveness and potential for practical clinical application. Future work will focus on incorporating deep learning techniques and medical imaging to further improve classification accuracy and model performance.

Artificial intelligence in stroke rehabilitation: From acute care to long-term recovery

Stroke is a leading cause of disability worldwide, driving the need for advanced rehabilitation strategies. The integration of Artificial Intelligence (AI) into stroke rehabilitation presents significant advancements across the continuum of care, from acute diagnosis to long-term recovery. This review explores AI's role in stroke rehabilitation, highlighting its impact on early diagnosis, motor recovery, and cognitive rehabilitation. AI-driven imaging techniques, such as deep learning applied to CT and MRI scans, improve early diagnosis and identify ischemic penumbra, enabling timely, personalized interventions. AI-assisted decision support systems optimize acute stroke treatment, including thrombolysis and endovascular therapy. In motor rehabilitation, AI-powered robotics and exoskeletons provide precise, adaptive assistance, while AI-augmented Virtual and Augmented Reality environments offer immersive, tailored recovery experiences. Brain-Computer Interfaces utilize AI for neurorehabilitation through neural signal processing, supporting motor recovery. Machine learning models predict functional recovery outcomes and dynamically adjust therapy intensities. Wearable technologies equipped with AI enable continuous monitoring and real-time feedback, facilitating home-based rehabilitation. AI-driven tele-rehabilitation platforms overcome geographic barriers by enabling remote assessment and intervention. The review also addresses the ethical, legal, and regulatory challenges associated with AI implementation, including data privacy and technical integration. Future research directions emphasize the transformative potential of AI in stroke rehabilitation, with case studies and clinical trials illustrating the practical benefits and efficacy of AI technologies in improving patient recovery.

Validation of a Machine-Learning Clinical Decision Aid for the Differential Diagnosis of Transient Loss of Consciousness

Background and Objectives

The aim of this study was to develop and validate a machine-learning classifier based on patient and witness questionnaires to support differential diagnosis of transient loss of consciousness (TLOC) at first presentation.

Methods

We prospectively recruited patients newly presenting with TLOC to an emergency department, an acute medical unit, and a first seizure or syncope clinic. We invited participants to complete an online questionnaire, either at home or at time of initial assessment. Two expert raters determined the cause of participants' TLOC after 6-month follow-up. We used independent development and validation samples to train a random forest classifier to predict diagnosis from participants' questionnaire responses and validate classifier performance. We compared classifier performance against penalized linear regression and referrer diagnosis.

Results

We included 178 participants in the final analysis, of whom 46 identified a witness able to complete an additional witness questionnaire. Given low witness recruitment, we developed a classifier based on patient answers only. A classifier trained on 9 items correctly identified 63 of 78 diagnoses (80.8%) (95% CI 70.0-88.5), an increase over the accuracy of initial assessing clinicians who were only able to diagnose 70.5% correctly. Within this, 96% (87.0%-99.4%) of those expertly rated as having syncope were correctly classified by the classifier (classifier sensitivity); 40% (20%-63.6%) of those expertly rated after follow-up as having either epilepsy or functional/dissociative seizures were similarly classified as being nonsyncope (classifier specificity).

Discussion

A machine-learning classifier for differential diagnosis of TLOC has comparable performance in differentiating between 3 main causes of primary TLOC as the current standard of care but is insufficiently accurate in its current form to warrant incorporation into routine care. A system including information from witnesses might improve classification performance.

Stroke Diagnosis and Prediction Tool Using ChatGLM: Development and Validation Study

BACKGROUND

Stroke is a globally prevalent disease that imposes a significant burden on health care systems and national economies. Accurate and rapid stroke diagnosis can substantially increase reperfusion rates, mitigate disability, and reduce mortality. However, there are considerable discrepancies in the diagnosis and treatment of acute stroke.

OBJECTIVE

The aim of this study is to develop and validate a stroke diagnosis and prediction tool using ChatGLM-6B, which uses free-text information from electronic health records in conjunction with noncontrast computed tomography (NCCT) reports to enhance stroke detection and treatment.

METHODS

A large language model (LLM) using ChatGLM-6B was proposed to facilitate stroke diagnosis by identifying optimal input combinations, using external tools, and applying instruction tuning and low-rank adaptation (LoRA) techniques. A dataset containing details of 1885 patients with and those without stroke from 2016 to 2024 was used for training and internal validation; another 335 patients from two hospitals were used as an external test set, including 230 patients from the training hospital but admitted at different periods, and 105 patients from another hospital.

RESULTS

The LLM, which is based on clinical notes and NCCT, demonstrates exceptionally high accuracy in stroke diagnosis, achieving 99% in the internal validation dataset and 95.5% and 79.1% in two external test cohorts. It effectively distinguishes between ischemia and hemorrhage, with an accuracy of 100% in the validation dataset and 99.1% and 97.1% in the other test cohorts. In addition, it identifies large vessel occlusions (LVO) with an accuracy of 80% in the validation dataset and 88.6% and 83.3% in the other test cohorts. Furthermore, it screens patients eligible for intravenous thrombolysis (IVT) with an accuracy of 89.4% in the validation dataset and 60% and 80% in the other test cohorts.

CONCLUSIONS

We developed an LLM that leverages clinical text and NCCT to identify strokes and guide recanalization therapy. While our results necessitate validation through widespread deployment, they hold the potential to enhance stroke identification and reduce reperfusion time.

External validation and performance analysis of a deep learning-based model for the detection of intracranial hemorrhage

PURPOSE

We aimed to investigate the external validation and performance of an FDA-approved deep learning model in labeling intracranial hemorrhage (ICH) cases on a real-world heterogeneous clinical dataset. Furthermore, we delved deeper into evaluating how patients' risk factors influenced the model's performance and gathered feedback on satisfaction from radiologists of varying ranks.

METHODS

This prospective IRB approved study included 5600 non-contrast CT scans of the head in various clinical settings, that is, emergency, inpatient, and outpatient units. The patients' risk factors were collected and tested for impacting the performance of DL model utilizing univariate and multivariate regression analyses. The performance of DL model was contrasted to the radiologists' interpretation to determine the presence or absence of ICH with subsequent classification into subcategories of ICH. Key metrics, including accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, were calculated. Receiver operating characteristics curve, along with the area under the curve, were determined. Additionally, a questionnaire was conducted with radiologists of varying ranks to assess their experience with the model.

RESULTS

The model exhibited outstanding performance, achieving a high sensitivity of 89% and specificity of 96%. Additional performance metrics, including positive predictive value (82%), negative predictive value (97%), and overall accuracy (94%), underscore its robust capabilities. The area under the ROC curve further demonstrated the model's efficacy, reaching 0.954. Multivariate logistic regression revealed statistical significance for age, sex, history of trauma, operative intervention, HTN, and smoking.

CONCLUSION

Our study highlights the satisfactory performance of the DL model on a diverse real-world dataset, garnering positive feedback from radiology trainees.

Bibliometric and visualized analysis of the application of artificial intelligence in stroke

Background

Stroke stands as a prominent cause of mortality and disability worldwide, posing a major public health concern. Recent years have witnessed rapid advancements in artificial intelligence (AI). Studies have explored the utilization of AI in imaging analysis, assistive rehabilitation, treatment, clinical decision-making, and outcome and risk prediction concerning stroke. However, there is still a lack of systematic bibliometric analysis to discern the current research status, hotspots, and possible future development trends of AI applications in stroke.

Methods

The publications on the application of AI in stroke were retrieved from the Web of Science Core Collection, spanning 2004-2024. Only articles or reviews published in English were included in this study. Subsequently, a manual screening process was employed to eliminate literature not pertinent to the topic. Visualization diagrams for comprehensive and in-depth analysis of the included literature were generated using CiteSpace, VOSviewer, and Charticulator.

Results

This bibliometric analysis included a total of 2,447 papers, and the annual publication volume shows a notable upward trajectory. The most prolific authors, countries, and institutions are Dukelow, Sean P., China, and the University of Calgary, respectively, making significant contributions to the advancement of this field. Notably, stable collaborative networks among authors and institutions have formed. Through clustering and citation burst analysis of keywords and references, the current research hotspots have been identified, including machine learning, deep learning, and AI applications in stroke rehabilitation and imaging for early diagnosis. Moreover, emerging research trends focus on machine learning as well as stroke outcomes and risk prediction.

Conclusion

This study provides a comprehensive and in-depth analysis of the literature regarding AI in stroke, facilitating a rapid comprehension of the development status, cooperative networks, and research priorities within the field. Furthermore, our analysis may provide a certain reference and guidance for future research endeavors.

A 25-Year Retrospective of the Use of AI for Diagnosing Acute Stroke: Systematic Review

BACKGROUND

Stroke is a leading cause of death and disability worldwide. Rapid and accurate diagnosis is crucial for minimizing brain damage and optimizing treatment plans.

OBJECTIVE

This review aims to summarize the methods of artificial intelligence (AI)-assisted stroke diagnosis over the past 25 years, providing an overview of performance metrics and algorithm development trends. It also delves into existing issues and future prospects, intending to offer a comprehensive reference for clinical practice.

METHODS

A total of 50 representative articles published between 1999 and 2024 on using AI technology for stroke prevention and diagnosis were systematically selected and analyzed in detail.

RESULTS

AI-assisted stroke diagnosis has made significant advances in stroke lesion segmentation and classification, stroke risk prediction, and stroke prognosis. Before 2012, research mainly focused on segmentation using traditional thresholding and heuristic techniques. From 2012 to 2016, the focus shifted to machine learning (ML)-based approaches. After 2016, the emphasis moved to deep learning (DL), which brought significant improvements in accuracy. In stroke lesion segmentation and classification as well as stroke risk prediction, DL has shown superiority over ML. In stroke prognosis, both DL and ML have shown good performance.

CONCLUSIONS

Over the past 25 years, AI technology has shown promising performance in stroke diagnosis.

Insights from ARCOS-V's Transition to Remote Data Collection during the COVID-19 Pandemic: A Descriptive Study

INTRODUCTION

The ARCOS-V study, an epidemiological study on stroke and transient ischaemic attack (TIA), faced the challenge of continuing data collection amidst the COVID-19 pandemic. This study aimed to describe the methodological changes and challenges encountered during the transition from paper-based methods to digital data collection for the ARCOS-V study and to provide insights into the potential of using digital tools to transform epidemiological research.

METHODS

The study adapted to remote data collection using REDCap and Zoom, involving daily health record reviews, direct data entry by trained researchers, and remote follow-up assessments. The process was secured with encryption and role-based access controls. The transition period was analysed to evaluate the effectiveness and challenges of the new approach.

RESULTS

The digital transition allowed for uninterrupted monitoring of stroke and TIA cases during lockdowns. Using REDCap and Zoom improved data reach, accuracy, and security. However, it also revealed issues such as the potential for systematic data entry errors and the need for robust security measures to protect sensitive health information.

CONCLUSION

The ARCOS-V study's digital transformation exemplifies the resilience of epidemiological research in the face of a global crisis. The successful adaptation to digital data collection methods highlights the potential benefits of such tools, particularly as we enter a new age of artificial intelligence (AI).

Progress and trends in neurological disorders research based on deep learning

In recent years, deep learning (DL) has emerged as a powerful tool in clinical imaging, offering unprecedented opportunities for the diagnosis and treatment of neurological disorders (NDs). This comprehensive review explores the multifaceted role of DL techniques in leveraging vast datasets to advance our understanding of NDs and improve clinical outcomes. Beginning with a systematic literature review, we delve into the utilization of DL, particularly focusing on multimodal neuroimaging data analysis-a domain that has witnessed rapid progress and garnered significant scientific interest. Our study categorizes and critically analyses numerous DL models, including Convolutional Neural Networks (CNNs), LSTM-CNN, GAN, and VGG, to understand their performance across different types of Neurology Diseases. Through particular analysis, we identify key benchmarks and datasets utilized in training and testing DL models, shedding light on the challenges and opportunities in clinical neuroimaging research. Moreover, we discuss the effectiveness of DL in real-world clinical scenarios, emphasizing its potential to revolutionize ND diagnosis and therapy. By synthesizing existing literature and describing future directions, this review not only provides insights into the current state of DL applications in ND analysis but also covers the way for the development of more efficient and accessible DL techniques. Finally, our findings underscore the transformative impact of DL in reshaping the landscape of clinical neuroimaging, offering hope for enhanced patient care and groundbreaking discoveries in the field of neurology. This review paper is beneficial for neuropathologists and new researchers in this field.

Unveiling the potential of machine learning approaches in predicting the emergence of stroke at its onset: a predicting framework

A stroke is a dangerous, life-threatening disease that mostly affects people over 65, but an unhealthy diet is also contributing to the development of strokes at younger ages. Strokes can be treated successfully if they are identified early enough, and suitable therapies are available. The purpose of this study is to develop a stroke prediction model that will improve stroke prediction effectiveness as well as accuracy. Predicting whether someone is suffering from a stroke or not can be accomplished with this proposed machine learning algorithm. In this research, various machine learning techniques are evaluated for predicting stroke on the healthcare stroke dataset. The feature selection algorithms used here are gradient boosting and random forest, and classifiers include the decision tree classifier, Support Vector Machine (SVM) classifier, logistic regression classifier, gradient boosting classifier, random forest classifier, K neighbors classifier, and Xtreme gradient boosting classifier. In this process, different machine-learning approaches are employed to test predictive methods on different data samples. As a result obtained from the different methods applied, and the comparison of different classification models, the random forest model offers an accuracy rate of 98%.

Artificial intelligence for MRI stroke detection: a systematic review and meta-analysis

OBJECTIVES

This systematic review and meta-analysis aimed to assess the stroke detection performance of artificial intelligence (AI) in magnetic resonance imaging (MRI), and additionally to identify reporting insufficiencies.

METHODS

PRISMA guidelines were followed. MEDLINE, Embase, Cochrane Central, and IEEE Xplore were searched for studies utilising MRI and AI for stroke detection. The protocol was prospectively registered with PROSPERO (CRD42021289748). Sensitivity, specificity, accuracy, and area under the receiver operating characteristic (ROC) curve were the primary outcomes. Only studies using MRI in adults were included. The intervention was AI for stroke detection with ischaemic and haemorrhagic stroke in separate categories. Any manual labelling was used as a comparator. A modified QUADAS-2 tool was used for bias assessment. The minimum information about clinical artificial intelligence modelling (MI-CLAIM) checklist was used to assess reporting insufficiencies. Meta-analyses were performed for sensitivity, specificity, and hierarchical summary ROC (HSROC) on low risk of bias studies.

RESULTS

Thirty-three studies were eligible for inclusion. Fifteen studies had a low risk of bias. Low-risk studies were better for reporting MI-CLAIM items. Only one study examined a CE-approved AI algorithm. Forest plots revealed detection sensitivity and specificity of 93% and 93% with identical performance in the HSROC analysis and positive and negative likelihood ratios of 12.6 and 0.079.

CONCLUSION

Current AI technology can detect ischaemic stroke in MRI. There is a need for further validation of haemorrhagic detection. The clinical usability of AI stroke detection in MRI is yet to be investigated.

CRITICAL RELEVANCE STATEMENT

This first meta-analysis concludes that AI, utilising diffusion-weighted MRI sequences, can accurately aid the detection of ischaemic brain lesions and its clinical utility is ready to be uncovered in clinical trials.

KEY POINTS

There is a growing interest in AI solutions for detection aid. The performance is unknown for MRI stroke assessment. AI detection sensitivity and specificity were 93% and 93% for ischaemic lesions. There is limited evidence for the detection of patients with haemorrhagic lesions. AI can accurately detect patients with ischaemic stroke in MRI.

Application of emerging technologies in ischemic stroke: from clinical study to basic research

Stroke is a primary cause of noncommunicable disease-related death and disability worldwide. The most common form, ischemic stroke, is increasing in incidence resulting in a significant burden on patients and society. Urgent action is thus needed to address preventable risk factors and improve treatment methods. This review examines emerging technologies used in the management of ischemic stroke, including neuroimaging, regenerative medicine, biology, and nanomedicine, highlighting their benefits, clinical applications, and limitations. Additionally, we suggest strategies for technological development for the prevention, diagnosis, and treatment of ischemic stroke.

Prediction and causal inference of cardiovascular and cerebrovascular diseases based on lifestyle questionnaires

Cardiovascular and cerebrovascular diseases (CCVD) are prominent mortality causes in Japan, necessitating effective preventative measures, early diagnosis, and treatment to mitigate their impact. A diagnostic model was developed to identify patients with ischemic heart disease (IHD), stroke, or both, using specific health examination data. Lifestyle habits affecting CCVD development were analyzed using five causal inference methods. This study included 473,734 patients aged ≥ 40 years who underwent specific health examinations in Kanazawa, Japan between 2009 and 2018 to collect data on basic physical information, lifestyle habits, and laboratory parameters such as diabetes, lipid metabolism, renal function, and liver function. Four machine learning algorithms were used: Random Forest, Logistic regression, Light Gradient Boosting Machine, and eXtreme-Gradient-Boosting (XGBoost). The XGBoost model exhibited superior area under the curve (AUC), with mean values of 0.770 (± 0.003), 0.758 (± 0.003), and 0.845 (± 0.005) for stroke, IHD, and CCVD, respectively. The results of the five causal inference analyses were summarized, and lifestyle behavior changes were observed after the onset of CCVD. A causal relationship from 'reduced mastication' to 'weight gain' was found for all causal species theory methods. This prediction algorithm can screen for asymptomatic myocardial ischemia and stroke. By selecting high-risk patients suspected of having CCVD, resources can be used more efficiently for secondary testing.

High-resolution magnetic resonance vessel wall imaging in ischemic stroke and carotid artery atherosclerotic stenosis: A review

Ischemic stroke is a significant burden on human health worldwide. Carotid Atherosclerosis stenosis plays an important role in the comprehensive assessment and prevention of ischemic stroke patients. High-resolution vessel wall magnetic resonance imaging has emerged as a successful technique for assessing carotid atherosclerosis stenosis. This advanced imaging modality has shown promise in effectively displaying a wide range of characteristics associated with the condition, leading to a comprehensive evaluation. High-resolution vessel wall magnetic resonance imaging not only enables a comprehensive evaluation of the instability of carotid atherosclerosis stenosis plaques but also provides valuable information for understanding the pathogenesis and predicting the prognosis of ischemic stroke patients. The purpose of this article is to review the application of high-resolution magnetic resonance imaging in ischemic stroke and carotid atherosclerotic stenosis.

Neuromonitoring in the ICU - what, how and why?

PURPOSE OF REVIEW

We selectively review emerging noninvasive neuromonitoring techniques and the evidence that supports their use in the ICU setting. The focus is on neuromonitoring research in patients with acute brain injury.

RECENT FINDINGS

Noninvasive intracranial pressure evaluation with optic nerve sheath diameter measurements, transcranial Doppler waveform analysis, or skull mechanical extensometer waveform recordings have potential safety and resource-intensity advantages when compared to standard invasive monitors, however each of these techniques has limitations. Quantitative electroencephalography can be applied for detection of cerebral ischemia and states of covert consciousness. Near-infrared spectroscopy may be leveraged for cerebral oxygenation and autoregulation computation. Automated quantitative pupillometry and heart rate variability analysis have been shown to have diagnostic and/or prognostic significance in selected subtypes of acute brain injury. Finally, artificial intelligence is likely to transform interpretation and deployment of neuromonitoring paradigms individually and when integrated in multimodal paradigms.

SUMMARY

The ability to detect brain dysfunction and injury in critically ill patients is being enriched thanks to remarkable advances in neuromonitoring data acquisition and analysis. Studies are needed to validate the accuracy and reliability of these new approaches, and their feasibility and implementation within existing intensive care workflows.

Novel artificial intelligence-based hypodensity detection tool improves clinician identification of hypodensity on non-contrast computed tomography in stroke patients

Introduction

In acute stroke, identifying early changes (parenchymal hypodensity) on non-contrast CT (NCCT) can be challenging. We aimed to identify whether the accuracy of clinicians in detecting acute hypodensity in ischaemic stroke patients on a non-contrast CT is improved with the use of an Artificial Intelligence (AI) based, automated hypodensity detection algorithm (HDT) using MRI-DWI as the gold standard.

Methods

The study employed a case-crossover within-clinician design, where 32 clinicians were tasked with identifying hypodensity lesions on NCCT scans for five a priori selected patient cases, before and after viewing the AI-based HDT. The DICE similarity coefficient (DICE score) was the primary measure of accuracy. Statistical analysis compared DICE scores with and without AI-based HDT using mixed-effects linear regression, with individual NCCT scans and clinicians as nested random effects.

Results

The AI-based HDT had a mean DICE score of 0.62 for detecting hypodensity across all NCCT scans. Clinicians' overall mean DICE score was 0.33 (SD 0.31) before AI-based HDT implementation and 0.40 (SD 0.27) after implementation. AI-based HDT use was associated with an increase of 0.07 (95% CI: 0.02-0.11, p = 0.003) in DICE score accounting for individual scan and clinician effects. For scans with small lesions, clinicians achieved a mean increase in DICE score of 0.08 (95% CI: 0.02, 0.13, p = 0.004) following AI-based HDT use. In a subgroup of 15 trainees, DICE score improved with AI-based HDT implementation [mean difference in DICE 0.09 (95% CI: 0.03, 0.14, p = 0.004)].

Discussion

AI-based automated hypodensity detection has potential to enhance clinician accuracy of detecting hypodensity in acute stroke diagnosis, especially for smaller lesions, and notably for less experienced clinicians.

Navigating the AI frontiers in cardiovascular research: a bibliometric exploration and topic modeling

Artificial intelligence (AI) has emerged as a promising field in cardiovascular disease (CVD) research, offering innovative approaches to enhance diagnosis, treatment, and patient outcomes. In this study, we conducted bibliometric analysis combined with topic modeling to provide a comprehensive overview of the AI research landscape in CVD. Our analysis included 23,846 studies from Web of Science and PubMed, capturing the latest advancements and trends in this rapidly evolving field. By employing LDA (Latent Dirichlet Allocation) we identified key research themes, trends, and collaborations within the AI-CVD domain. The findings revealed the exponential growth of AI-related research in CVD, underscoring its immense potential to revolutionize cardiovascular healthcare. The annual scientific publication of machine learning papers in CVD increases continuously and significantly since 2016, with an overall annual growth rate of 22.8%. Almost half (46.2%) of the growth happened in the last 5 years. USA, China, India, UK and Korea were the top five productive countries in number of publications. UK, Germany and Australia were the most collaborative countries with a multiple country publication (MCP) value of 42.8%, 40.3% and 40.0% respectively. We observed the emergence of twenty-two distinct research topics, including "stroke and robotic rehabilitation therapy," "robotic-assisted cardiac surgery," and "cardiac image analysis," which persisted as major topics throughout the years. Other topics, such as "retinal image analysis and CVD" and "biomarker and wearable signal analyses," have recently emerged as dominant areas of research in cardiovascular medicine. Convolutional neural network appears to be the most mentioned algorithm followed by LSTM (Long Short-Term Memory) and KNN (K-Nearest Neighbours). This indicates that the future direction of AI cardiovascular research is predominantly directing toward neural networks and image analysis. As AI continues to shape the landscape of CVD research, our study serves as a comprehensive guide for researchers, practitioners, and policymakers, providing valuable insights into the current state of AI in CVD research. This study offers a deep understanding of research trends and paves the way for future directions to maximiz the potential of AI to effectively combat cardiovascular diseases.

Mapping the Bibliometrics Landscape of AI in Medicine: Methodological Study

BACKGROUND

Artificial intelligence (AI), conceived in the 1950s, has permeated numerous industries, intensifying in tandem with advancements in computing power. Despite the widespread adoption of AI, its integration into medicine trails other sectors. However, medical AI research has experienced substantial growth, attracting considerable attention from researchers and practitioners.

OBJECTIVE

In the absence of an existing framework, this study aims to outline the current landscape of medical AI research and provide insights into its future developments by examining all AI-related studies within PubMed over the past 2 decades. We also propose potential data acquisition and analysis methods, developed using Python (version 3.11) and to be executed in Spyder IDE (version 5.4.3), for future analogous research.

METHODS

Our dual-pronged approach involved (1) retrieving publication metadata related to AI from PubMed (spanning 2000-2022) via Python, including titles, abstracts, authors, journals, country, and publishing years, followed by keyword frequency analysis and (2) classifying relevant topics using latent Dirichlet allocation, an unsupervised machine learning approach, and defining the research scope of AI in medicine. In the absence of a universal medical AI taxonomy, we used an AI dictionary based on the European Commission Joint Research Centre AI Watch report, which emphasizes 8 domains: reasoning, planning, learning, perception, communication, integration and interaction, service, and AI ethics and philosophy.

RESULTS

From 2000 to 2022, a comprehensive analysis of 307,701 AI-related publications from PubMed highlighted a 36-fold increase. The United States emerged as a clear frontrunner, producing 68,502 of these articles. Despite its substantial contribution in terms of volume, China lagged in terms of citation impact. Diving into specific AI domains, as the Joint Research Centre AI Watch report categorized, the learning domain emerged dominant. Our classification analysis meticulously traced the nuanced research trajectories across each domain, revealing the multifaceted and evolving nature of AI's application in the realm of medicine.

CONCLUSIONS

The research topics have evolved as the volume of AI studies increases annually. Machine learning remains central to medical AI research, with deep learning expected to maintain its fundamental role. Empowered by predictive algorithms, pattern recognition, and imaging analysis capabilities, the future of AI research in medicine is anticipated to concentrate on medical diagnosis, robotic intervention, and disease management. Our topic modeling outcomes provide a clear insight into the focus of AI research in medicine over the past decades and lay the groundwork for predicting future directions. The domains that have attracted considerable research attention, primarily the learning domain, will continue to shape the trajectory of AI in medicine. Given the observed growing interest, the domain of AI ethics and philosophy also stands out as a prospective area of increased focus.

Strokecopilot: a literature-based clinical decision support system for acute ischemic stroke treatment

BACKGROUND

Acute ischemic stroke (AIS) is an immediate emergency whose management is becoming more and more personalized while facing a limited number of neurologists with high expertise. Clinical decision support systems (CDSS) are digital tools leveraging information and artificial intelligence technologies. Here, we present the Strokecopilot project, a CDSS for the management of the acute phase of AIS. It has been designed to support the evidence-based medicine reasoning of neurologists regarding the indications of intravenous thrombolysis (IVT) and endovascular treatments (ET).

METHODS

Reference populations were manually extracted from the field's main guidelines and randomized clinical trials (RCT). Their characteristics were harmonized in a computerized reference database. We developed a web application whose algorithm identifies the reference populations matching the patient's characteristics. It returns the latter's outcomes in a graphical user interface (GUI), whose design has been driven by real-world practices.

RESULTS

Strokecopilot has been released at www.digitalneurology.net . The reference database includes 25 reference populations from 2 guidelines and 15 RCTs. After a request, the reference populations matching the patient characteristics are displayed with a summary and a meta-analysis of their results. The status regarding IVT and ET indications are presented as "in guidelines", "in literature", or "outside literature references". The GUI is updated to provide several levels of explanation. Strokecopilot may be updated as the literature evolves by loading a new version of the reference populations' database.

CONCLUSION

Strokecopilot is a literature-based CDSS, developed to support neurologists in the management of the acute phase of AIS.

Implementing Artificial Intelligence: Assessing the Cost and Benefits of Algorithmic Decision-Making in Critical Care

This article provides an overview of the most useful artificial intelligence algorithms developed in critical care, followed by a comprehensive outline of the benefits and limitations. We begin by describing how nurses and physicians might be aided by these new technologies. We then move to the possible changes in clinical guidelines with personalized medicine that will allow tailored therapies and probably will increase the quality of the care provided to patients. Finally, we describe how artificial intelligence models can unleash researchers' minds by proposing new strategies, by increasing the quality of clinical practice, and by questioning current knowledge and understanding.

Application and risk prediction of thrombolytic therapy in cardio-cerebrovascular diseases: a review

Cardiocerebrovascular diseases (CVDs) are the leading cause of death worldwide, consuming huge healthcare budget. For CVD patients, the prompt assessment and appropriate administration is the crux to save life and improve prognosis. Thrombolytic therapy, as a non-invasive approach to achieve recanalization, is the basic component of CVD treatment. Still, there are risks that limits its application. The objective of this review is to give an introduction on the utilization of thrombolytic therapy in cardiocerebrovascular blockage diseases, including coronary heart disease and ischemic stroke, and to review the development in risk assessment of thrombolytic therapy, comparing the performance of traditional scales and novel artificial intelligence-based risk assessment models.

A Decision Support System to Provide an Ongoing Prediction of Robot-Assisted Rehabilitation Outcome in Stroke Survivors

Clinicians often deal with complex robotic platform and serious games in stroke patients rehabilitation contexts, and they face two main problems: 1) the interpretation of either the performance in game or measures of a robotic system from the motor recovery point of view, and 2) the duration and complexity of clinical scales administration that makes repetitive assessments during the therapy unpractical. In this paper, a Random Tree Forest based system was trained and tested to provide a prediction of different clinical outcomes (i.e. FMA, ARAT, and MI) along the whole therapy duration, having non-clinical measures only as inputs, acting as a simulated decision support system. The dataset includes 30 post-stroke patients, that underwent a 30-session robot-assisted rehabilitation treatment. Results have shown that the system is able to produce very accurate and reliable predictions about the motor recovery of the patient at the end of the therapy, already in the first phases of the rehabilitation (i40% of therapy execution), just using robotic platform measures. Such a tool would provide a great benefit in terms of rehabilitation objectives planning, as a decision support tool for highly personalized rehabilitation treatments.

Functional MRI Assessment of Brain Activity During Hand Rehabilitation with an MR-Compatible Soft Glove in Chronic Stroke Patients: A Preliminary Study

Brain plasticity plays a significant role in functional recovery after stroke, but the specific benefits of hand rehabilitation robot therapy remain unclear. Evaluating the specific effects of hand rehabilitation robot therapy is crucial in understanding how it impacts brain activity and its relationship to rehabilitation outcomes. This study aimed to investigate the brain activity pattern during hand rehabilitation exercise using functional magnetic resonance imaging (fMRI), and to compare it before and after 3-week hand rehabilitation robot training. To evaluate it, an fMRI experimental environment was constructed to facilitate the same hand posture used in rehabilitation robot therapy. Two stroke survivors participated and the conjunction analysis results from fMRI scans showed that patient 1 exhibited a significant improvement in activation profile after hand rehabilitation robot training, indicative of improved motor function in the bilateral motor cortex. However, activation profile of patient 2 exhibited a slight decrease, potentially due to habituation to the rehabilitation task. Clinical results supported these findings, with patient 1 experiencing a greater increase in FMA score than patient 2. These results suggest that hand rehabilitation robot therapy can induce different brain activity patterns in stroke survivors, which may be linked to patient-specific training outcomes. Further studies with larger sample sizes are necessary to confirm these findings.

Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging

This comprehensive review unfolds a detailed narrative of Artificial Intelligence (AI) making its foray into radiology, a move that is catalysing transformational shifts in the healthcare landscape. It traces the evolution of radiology, from the initial discovery of X-rays to the application of machine learning and deep learning in modern medical image analysis. The primary focus of this review is to shed light on AI applications in radiology, elucidating their seminal roles in image segmentation, computer-aided diagnosis, predictive analytics, and workflow optimisation. A spotlight is cast on the profound impact of AI on diagnostic processes, personalised medicine, and clinical workflows, with empirical evidence derived from a series of case studies across multiple medical disciplines. However, the integration of AI in radiology is not devoid of challenges. The review ventures into the labyrinth of obstacles that are inherent to AI-driven radiology-data quality, the 'black box' enigma, infrastructural and technical complexities, as well as ethical implications. Peering into the future, the review contends that the road ahead for AI in radiology is paved with promising opportunities. It advocates for continuous research, embracing avant-garde imaging technologies, and fostering robust collaborations between radiologists and AI developers. The conclusion underlines the role of AI as a catalyst for change in radiology, a stance that is firmly rooted in sustained innovation, dynamic partnerships, and a steadfast commitment to ethical responsibility.

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

BACKGROUND

Established randomized trial-based parameters for acute ischemic stroke group patients into generic treatment groups, leading to attempts using various artificial intelligence (AI) methods to directly correlate patient characteristics to outcomes and thereby provide decision support to stroke clinicians. We review AI-based clinical decision support systems in the development stage, specifically regarding methodological robustness and constraints for clinical implementation.

METHODS

Our systematic review included full-text English language publications proposing a clinical decision support system using AI techniques for direct decision support in acute ischemic stroke cases in adult patients. We (1) describe data and outcomes used in those systems, (2) estimate the systems' benefits compared with traditional stroke diagnosis and treatment, and (3) reported concordance with reporting standards for AI in healthcare.

RESULTS

One hundred twenty-one studies met our inclusion criteria. Sixty-five were included for full extraction. In our sample, utilized data sources, methods, and reporting practices were highly heterogeneous.

CONCLUSIONS

Our results suggest significant validity threats, dissonance in reporting practices, and challenges to clinical translation. We outline practical recommendations for the successful implementation of AI research in acute ischemic stroke treatment and diagnosis.

Evaluation of Blood Biomarkers and Parameters for the Prediction of Stroke Survivors' Functional Outcome upon Discharge Utilizing Explainable Machine Learning

Despite therapeutic advancements, stroke remains a leading cause of death and long-term disability. The quality of current stroke prognostic models varies considerably, whereas prediction models of post-stroke disability and mortality are restricted by the sample size, the range of clinical and risk factors and the clinical applicability in general. Accurate prognostication can ease post-stroke discharge planning and help healthcare practitioners individualize aggressive treatment or palliative care, based on projected life expectancy and clinical course. In this study, we aimed to develop an explainable machine learning methodology to predict functional outcomes of stroke patients at discharge, using the Modified Rankin Scale (mRS) as a binary classification problem. We identified 35 parameters from the admission, the first 72 h, as well as the medical history of stroke patients, and used them to train the model. We divided the patients into two classes in two approaches: "Independent" vs. "Non-Independent" and "Non-Disability" vs. "Disability". Using various classifiers, we found that the best models in both approaches had an upward trend, with respect to the selected biomarkers, and achieved a maximum accuracy of 88.57% and 89.29%, respectively. The common features in both approaches included: age, hemispheric stroke localization, stroke localization based on blood supply, development of respiratory infection, National Institutes of Health Stroke Scale (NIHSS) upon admission and systolic blood pressure levels upon admission. Intubation and C-reactive protein (CRP) levels upon admission are additional features for the first approach and Erythrocyte Sedimentation Rate (ESR) levels upon admission for the second. Our results suggest that the said factors may be important predictors of functional outcomes in stroke patients.

Beyond high hopes: A scoping review of the 2019-2021 scientific discourse on machine learning in medical imaging

Machine learning has become a key driver of the digital health revolution. That comes with a fair share of high hopes and hype. We conducted a scoping review on machine learning in medical imaging, providing a comprehensive outlook of the field's potential, limitations, and future directions. Most reported strengths and promises included: improved (a) analytic power, (b) efficiency (c) decision making, and (d) equity. Most reported challenges included: (a) structural barriers and imaging heterogeneity, (b) scarcity of well-annotated, representative and interconnected imaging datasets (c) validity and performance limitations, including bias and equity issues, and (d) the still missing clinical integration. The boundaries between strengths and challenges, with cross-cutting ethical and regulatory implications, remain blurred. The literature emphasizes explainability and trustworthiness, with a largely missing discussion about the specific technical and regulatory challenges surrounding these concepts. Future trends are expected to shift towards multi-source models, combining imaging with an array of other data, in a more open access, and explainable manner.

Multi-layer perceptron classification & quantification of neuronal survival in hypoxic-ischemic brain image slices using a novel gradient direction, grey level co-occurrence matrix image training

Hypoxic ischemic encephalopathy (HIE) is a major global cause of neonatal death and lifelong disability. Large animal translational studies of hypoxic ischemic brain injury, such as those conducted in fetal sheep, have and continue to play a key role in furthering our understanding of the cellular and molecular mechanisms of injury and developing new treatment strategies for clinical translation. At present, the quantification of neurons in histological images consists of slow, manually intensive morphological assessment, requiring many repeats by an expert, which can prove to be time-consuming and prone to human error. Hence, there is an urgent need to automate the neuron classification and quantification process. In this article, we present a 'Gradient Direction, Grey level Co-occurrence Matrix' (GD-GLCM) image training method which outperforms and simplifies the standard training methodology using texture analysis to cell-classification. This is achieved by determining the Grey level Co-occurrence Matrix of the gradient direction of a cell image followed by direct passing to a classifier in the form of a Multilayer Perceptron (MLP). Hence, avoiding all texture feature computation steps. The proposed MLP is trained on both healthy and dying neurons that are manually identified by an expert and validated on unseen hypoxic-ischemic brain slice images from the fetal sheep in utero model. We compared the performance of our classifier using the gradient magnitude dataset as well as the gradient direction dataset. We also compare the performance of a perceptron, a 1-layer MLP, and a 2-layer MLP to each other. We demonstrate here a way of accurately identifying both healthy and dying cortical neurons obtained from brain slice images of the fetal sheep model under global hypoxia to high precision by identifying the most minimised MLP architecture, minimised input space (GLCM size) and minimised training data (GLCM representations) to achieve the highest performance over the standard methodology.

Automatic detection of stroke lesion from diffusion-weighted imaging via the improved YOLOv5

BACKGROUND AND OBJECTIVE

Stroke is the second most deadly disease globally and seriously endangers people's lives and health. The automatic detection of stroke lesions from diffusion-weighted imaging (DWI) can improve the diagnosis. Recently, automatic detection methods based on YOLOv5 have been utilized in medical images. However, most of them barely capture the stroke lesions because of their small size and fuzzy boundaries.

METHODS

To address this problem, a novel method for tracing the edge of the stroke lesion based on YOLOv5 (TE-YOLOv5) is proposed. Specifically, we constantly update the high-level features of the lesion using an aggregate pool (AP) module. Conversely, we feed the extracted feature into the reverse attention (RA) module to trace the edge relationship promptly. Overall, 1681 DWI images of 319 stroke patients have been collected, and experienced radiologists have marked the lesions. DWI images were randomly split into the training and test set at a ratio of 8:2. TE-YOLOv5 has been compared with the related models, and a detailed ablation analysis has been conducted to clarify the role of the RA and AP modules.

RESULTS

TE-YOLOv5 outperforms its counterparts and achieves competitive performance with a precision of 81.5%, a recall of 75.8%, and a mAP@0.5 of 80.7% (mean average precision while the intersection over union is 0.5) under the same backbone. At the patient level, the positive finding rate can reach 98.51%, while the confidence is set at 80.0%. After ablating RA, the mAP@0.5 decreases to 79.6%; after ablating RA and AP, the mAP@0.5 decreases to 78.1%.

CONCLUSIONS

The proposed TE-YOLOv5 can automatically and effectively detect stroke lesions from DWI images, especially for those with an extremely small size and blurred boundaries. AP and RA modules can aggregate multi-layer high-level features and concurrently track the edge relationship of stroke lesions. These detection methods might help radiologists improve stroke diagnosis and have great application potential in clinical practice.

An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data

Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients' class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.

Machine learning based analysis of stroke lesions on mouse tissue sections

An unbiased, automated and reliable method for analysis of brain lesions in tissue after ischemic stroke is missing. Manual infarct volumetry or by threshold-based semi-automated approaches is laborious, and biased to human error or biased by many false -positive and -negative data, respectively. Thereby, we developed a novel machine learning, atlas-based method for fully automated stroke analysis in mouse brain slices stained with 2% Triphenyltetrazolium-chloride (2% TTC), named "StrokeAnalyst", which runs on a user-friendly graphical interface. StrokeAnalyst registers subject images on a common spatial domain (a novel mouse TTC- brain atlas of 80 average mathematical images), calculates pixel-based, tissue-intensity statistics (z-scores), applies outlier-detection and machine learning (Random-Forest) models to increase accuracy of lesion detection, and produces volumetry data and detailed neuroanatomical information per lesion. We validated StrokeAnalyst in two separate experimental sets using the filament stroke model. StrokeAnalyst detects stroke lesions in a rater-independent and reproducible way, correctly detects hemispheric volumes even in presence of post-stroke edema and significantly minimizes false-positive errors compared to threshold-based approaches (false-positive rate 1.2-2.3%, p < 0.05). It can process scanner-acquired, and even smartphone-captured or pdf-retrieved images. Overall, StrokeAnalyst surpasses all previous TTC-volumetry approaches and increases quality, reproducibility and reliability of stroke detection in relevant preclinical models.

Quantification of hematoma and perihematomal edema volumes in intracerebral hemorrhage study: Design considerations in an artificial intelligence validation (QUANTUM) study

BACKGROUND

Hematoma and perihematomal edema volumes are important radiographic markers in spontaneous intracerebral hemorrhage. Accurate, reliable, and efficient quantification of these volumes will be paramount to their utility as measures of treatment effect in future clinical studies. Both manual and semi-automated quantification methods of hematoma and perihematomal edema volumetry are time-consuming and susceptible to inter-rater variability. Efforts are now underway to develop a fully automated algorithm that can replace them. A (QUANTUM) study to establish inter-quantification method measurement equivalency, which deviates from the traditional use of measures of agreement and a comparison hypothesis testing paradigm to indirectly infer quantification method measurement equivalence, is described in this article. The Quantification of Hematoma and Perihematomal Edema Volumes in Intracerebral Hemorrhage study aims to determine whether a fully automated quantification method and a semi-automated quantification method for quantification of hematoma and perihematomal edema volumes are equivalent to the hematoma and perihematomal edema volumes of the manual quantification method.

METHODS/DESIGN

Hematoma and perihematomal edema volumes of supratentorial intracerebral hemorrhage on 252 computed tomography scans will be prospectively quantified in random order by six raters using the fully automated, semi-automated, and manual quantification methods. Primary outcome measures for hematoma and perihematomal edema volumes will be quantified via computed tomography scan on admission (<24 h from symptom onset) and on day 3 (72 ± 12 h from symptom onset), respectively. Equivalence hypothesis testing will be conducted to determine if the hematoma and perihematomal edema volume measurements of the fully automated and semi-automated quantification methods are within 7.5% of the hematoma and perihematomal edema volume measurements of the manual quantification reference method.

DISCUSSION

By allowing direct equivalence hypothesis testing, the Quantification of Hematoma and Perihematomal Edema Volumes in Intracerebral Hemorrhage study offers advantages over radiology validation studies which utilize measures of agreement to indirectly infer measurement equivalence and studies which mistakenly try to infer measurement equivalence based on the failure of a comparison two-sided null hypothesis test to reach the significance level for rejection. The equivalence hypothesis testing paradigm applied to artificial intelligence application validation is relatively uncharted and warrants further investigation. The challenges encountered in the design of this study may influence future studies seeking to translate artificial intelligence medical technology into clinical practice.

Accuracy of Automated Computer-Aided Diagnosis for Stroke Imaging: A Critical Evaluation of Current Evidence

There is increasing interest in computer applications, using artificial intelligence methodologies, to perform health care tasks previously performed by humans, particularly in medical imaging for diagnosis. In stroke, there are now commercial artificial intelligence software for use with computed tomography or MR imaging to identify acute ischemic brain tissue pathology, arterial obstruction on computed tomography angiography or as hyperattenuated arteries on computed tomography, brain hemorrhage, or size of perfusion defects. A rapid, accurate diagnosis may aid treatment decisions for individual patients and could improve outcome if it leads to effective and safe treatment; or conversely, to disaster if a delayed or incorrect diagnosis results in inappropriate treatment. Despite this potential clinical impact, diagnostic tools including artificial intelligence methods are not subjected to the same clinical evaluation standards as are mandatory for drugs. Here, we provide an evidence-based review of the pros and cons of commercially available automated methods for medical imaging diagnosis, including those based on artificial intelligence, to diagnose acute brain pathology on computed tomography or magnetic resonance imaging in patients with stroke.

Deep Learning Applications for Acute Stroke Management

Brain imaging is essential to the clinical care of patients with stroke, a leading cause of disability and death worldwide. Whereas advanced neuroimaging techniques offer opportunities for aiding acute stroke management, several factors, including time delays, inter-clinician variability, and lack of systemic conglomeration of clinical information, hinder their maximal utility. Recent advances in deep machine learning (DL) offer new strategies for harnessing computational medical image analysis to inform decision making in acute stroke. We examine the current state of the field for DL models in stroke triage. First, we provide a brief, clinical practice-focused primer on DL. Next, we examine real-world examples of DL applications in pixel-wise labeling, volumetric lesion segmentation, stroke detection, and prediction of tissue fate postintervention. We evaluate recent deployments of deep neural networks and their ability to automatically select relevant clinical features for acute decision making, reduce inter-rater variability, and boost reliability in rapid neuroimaging assessments, and integrate neuroimaging with electronic medical record (EMR) data in order to support clinicians in routine and triage stroke management. Ultimately, we aim to provide a framework for critically evaluating existing automated approaches, thus equipping clinicians with the ability to understand and potentially apply DL approaches in order to address challenges in clinical practice. ANN NEUROL 2022.

Precision medicine in stroke: towards personalized outcome predictions using artificial intelligence

Stroke ranks among the leading causes for morbidity and mortality worldwide. New and continuously improving treatment options such as thrombolysis and thrombectomy have revolutionized acute stroke treatment in recent years. Following modern rhythms, the next revolution might well be the strategic use of the steadily increasing amounts of patient-related data for generating models enabling individualized outcome predictions. Milestones have already been achieved in several health care domains, as big data and artificial intelligence have entered everyday life. The aim of this review is to synoptically illustrate and discuss how artificial intelligence approaches may help to compute single-patient predictions in stroke outcome research in the acute, subacute and chronic stage. We will present approaches considering demographic, clinical and electrophysiological data, as well as data originating from various imaging modalities and combinations thereof. We will outline their advantages, disadvantages, their potential pitfalls and the promises they hold with a special focus on a clinical audience. Throughout the review we will highlight methodological aspects of novel machine-learning approaches as they are particularly crucial to realize precision medicine. We will finally provide an outlook on how artificial intelligence approaches might contribute to enhancing favourable outcomes after stroke.

A Review on Computer Aided Diagnosis of Acute Brain Stroke

Amongst the most common causes of death globally, stroke is one of top three affecting over 100 million people worldwide annually. There are two classes of stroke, namely ischemic stroke (due to impairment of blood supply, accounting for ~70% of all strokes) and hemorrhagic stroke (due to bleeding), both of which can result, if untreated, in permanently damaged brain tissue. The discovery that the affected brain tissue (i.e., 'ischemic penumbra') can be salvaged from permanent damage and the bourgeoning growth in computer aided diagnosis has led to major advances in stroke management. Abiding to the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines, we have surveyed a total of 177 research papers published between 2010 and 2021 to highlight the current status and challenges faced by computer aided diagnosis (CAD), machine learning (ML) and deep learning (DL) based techniques for CT and MRI as prime modalities for stroke detection and lesion region segmentation. This work concludes by showcasing the current requirement of this domain, the preferred modality, and prospective research areas.

Positive predictive value and stroke workflow outcomes using automated vessel density (RAPID-CTA) in stroke patients: One year experience

PURPOSE

Several new techniques have emerged for detecting anterior circulation large vessel occlusion by quantifying relative vessel density including RAPID-CTA, potentially allowing for faster triage and decreased time to mechanical thrombectomy. We present our one-year experience on positive predictive value of RAPID-CTA for the detection of large vessel occlusion in patients presenting with stroke symptoms and its effect on treatment time and clinical outcomes.

MATERIALS AND METHODS

Three hundred and ten patients presenting with stroke symptoms with relative vessel density <60% on RAPID-CTA were included (average age 70 years, 145 male, 165 female). Examinations were considered positive if there was evidence of large vessel occlusion or high grade stenosis. Computed tomography angiography to groin puncture time was calculated during one-year time intervals before and after RAPID-CTA installation. Ninety-day Modified Rankin Scale scores were obtained for patients in each cohort.

RESULTS

Of the 310 patients, 270 had large vessel occlusion or high grade stenosis (87% positive predictive value), with 161 having large vessel occlusion. Using 45% relative vessel density threshold, 129/161 large vessel occlusion were detected (80% sensitivity) and 163/172 examinations were positive (95% positive predictive value). Computed tomography angiography to groin puncture time was significantly lower after deployment of RAPID-CTA (93 min vs 68 min, p<0.05). Average 90 day modified Rankin Scale score was lower in the RAPID-CTA group with a higher percentage of patients with functional independence, although the data was not statistically significant.

CONCLUSION

RAPID-CTA had high positive predictive value for large vessel occlusion with a 45% relative vessel density threshold, which could facilitate active worklist reprioritization. Time to treatment was significantly lower and clinical outcomes were improved after deployment of RAPID-CTA.

CNN-Based Prognosis of BCI Rehabilitation Using EEG From First Session BCI Training

Stroke is a world-leading disease for causing disability. Brain-computer interaction (BCI) training has been proved to be a promising method in facilitating motor recovery. However, due to differences in each patient's neural-clinical profile, the potential of recovery for different patients can vary significantly by conducting BCI training, which remains a major problem in clinical rehabilitation practice. To address this issue, the objective of this study is to prognosticate the outcome of BCI training using motor state electroencephalographic (EEG) collected during the first session of BCI tasks, with the aim of prescribing BCI training accordingly. A Convolution Neural Network (CNN) based prognosis model was developed to predict the outcome of 11 stroke patients' recovery following a 2-week rehabilitation training with BCI. In our study, functional connectivity and power spectrum have been evaluated and applied as the inputs of CNN to regress patients' recovery rate. A saliency map was used to identify the correlation between EEG channels with the recovery outcome. The performance of our model was assessed using the leave-one-out cross-validation. Overall, the proposed model predicted patients' recovery with R² 0.98 and MSE 0.89. According to the saliency map, the highest functional connectivity occurred in Fp2/Fpz-AF8, Fp2/F4/F8-P3, P1/PO7-PO5 and AF3-AF4. Our results demonstrated that deep learning method has the potential to predict the recovery rate of BCI training, which contributes to guiding individualized prescription in the early stage of clinical rehabilitation.

From Three-Months to Five-Years: Sustaining Long-Term Benefits of Endovascular Therapy for Ischemic Stroke

Background and Purpose: During the months and years post-stroke, treatment benefits from endovascular therapy (EVT) may be magnified by disability-related differences in morbidity/mortality or may be eroded by recurrent strokes and non-stroke-related disability/mortality. Understanding the extent to which EVT benefits may be sustained at 5 years, and the factors influencing this outcome, may help us better promote the sustenance of EVT benefits until 5 years post-stroke and beyond.

Methods: In this review, undertaken 5 years after EVT became the standard of care, we searched PubMed and EMBASE to examine the current state of the literature on 5-year post-stroke outcomes, with particular attention to modifiable factors that influence outcomes between 3 months and 5 years post-EVT.

Results: Prospective cohorts and follow-up data from EVT trials indicate that 3-month EVT benefits will likely translate into lower 5-year disability, mortality, institutionalization, and care costs and higher quality of life. However, these group-level data by no means guarantee maintenance of 3-month benefits for individual patients. We identify factors and associated “action items” for stroke teams/systems at three specific levels (medical care, individual psychosocioeconomic, and larger societal/environmental levels) that influence the long-term EVT outcome of a patient. Medical action items include optimizing stroke rehabilitation, clinical follow-up, secondary stroke prevention, infection prevention/control, and post-stroke depression care. Psychosocioeconomic aspects include addressing access to primary care, specialist clinics, and rehabilitation; affordability of healthy lifestyle choices and preventative therapies; and optimization of family/social support and return-to-work options. High-level societal efforts include improving accessibility of public/private spaces and transportation, empowering/engaging persons with disability in society, and investing in treatments/technologies to mitigate consequences of post-stroke disability.

Conclusions: In the longtime horizon from 3 months to 5 years, several factors in the medical and societal spheres could negate EVT benefits. However, many factors can be leveraged to preserve or magnify treatment benefits, with opportunities to share responsibility with widening circles of care around the patient.

Emerging role of artificial intelligence in stroke imaging

Introduction: The recognition and therapy of patients with stroke is becoming progressively intricate as additional treatment choices become accessible and new associations between disease characteristics and treatment response are incessantly uncovered. Therefore, clinicians must regularly learn new skill, stay up to date with the literature and integrate advances into daily practice. The application of artificial intelligence (AI) to assist clinical decision making could diminish inter-rater variation in routine clinical practice and accelerate the mining of vital data that could expand recognition of patients with stroke, forecast of treatment responses and patient outcomes.Areas covered: In this review, the authors provide an up-to-date review of AI in stroke, analyzing the latest papers on this subject. These have been divided in two main groups: stroke diagnosis and outcome prediction.Expert opinion: The highest value of AI is its capability to merge, select and condense a large amount of clinical and imaging features of a single patient and to associate these with fitted models that have gone through robust assessment and optimization with large cohorts of data to support clinical decision making.

Review of deep learning algorithms for the automatic detection of intracranial hemorrhages on computed tomography head imaging

Artificial intelligence is a rapidly evolving field, with modern technological advances and the growth of electronic health data opening new possibilities in diagnostic radiology. In recent years, the performance of deep learning (DL) algorithms on various medical image tasks have continually improved. DL algorithms have been proposed as a tool to detect various forms of intracranial hemorrhage on non-contrast computed tomography (NCCT) of the head. In subtle, acute cases, the capacity for DL algorithm image interpretation support might improve the diagnostic yield of CT for detection of this time-critical condition, potentially expediting treatment where appropriate and improving patient outcomes. However, there are multiple challenges to DL algorithm implementation, such as the relative scarcity of labeled datasets, the difficulties in developing algorithms capable of volumetric medical image analysis, and the complex practicalities of deployment into clinical practice. This review examines the literature and the approaches taken in the development of DL algorithms for the detection of intracranial hemorrhage on NCCT head studies. Considerations in crafting such algorithms will be discussed, as well as challenges which must be overcome to ensure effective, dependable implementations as automated tools in a clinical setting.