AI Stroke Triage: What the Research Actually Shows
Software that spots a likely stroke on a scan and pages the team. The clearest case anywhere in healthcare AI where minutes are the outcome.
Stroke care runs on a clock. Brain tissue dies while the process works, so every step that shaves minutes off the time from scan to treatment has a direct clinical payoff.
That is why stroke triage is the strongest test case for imaging AI. The claim is not that the software is a better neuroradiologist. It is that it notices the scan and alerts the team while the radiologist is still reading something else.
The research here tends to measure workflow timings rather than diagnostic accuracy, which is unusual and appropriate. Look for door-to-needle and scan-to-groin figures, and check whether the comparison period had the same staffing.
What Kind of Evidence This Is
Not every study carries the same weight. This is the mix behind the list below.
What to Measure in Your Own Setting
A published result is somebody else's hospital. These are the numbers worth tracking in yours.
- Time from scan completion to the specialist opening it, before and after. This is the step the software actually touches.
- Transfer time for patients moving between hospitals, which is where the biggest published gains have tended to appear.
- How many alerts turn out to be nothing, and whether the team still trusts the alert after six months.
- Whether the improvement held when the enthusiastic early adopters stopped watching it.
The Studies
Every entry links to the source record. Summaries are the study's own abstract, shortened but not reworded.
-
Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration.
Intracranial hemorrhage (ICH) requires prompt diagnosis to optimize patient outcomes. We hypothesized that machine learning algorithms could automatically analyze computed tomography (CT) of the head, prioritize radiology worklists and reduce time to diagnosis of ICH. 46,583 head CTs (~2 million images) acquired from 2007-2017 were collected from several facilities across Geisinger.
PMID 31304294 ... doi:10.1038/s41746-017-0015-z
-
Artificial intelligence to diagnose ischemic stroke and identify large vessel occlusions: a systematic review.
Background and purposeAcute stroke caused by large vessel occlusions (LVOs) requires emergent detection and treatment by endovascular thrombectomy. However, radiologic LVO detection and treatment is subject to variable delays and human expertise, resulting in morbidity. Imaging software using artificial intelligence (AI) and machine learning (ML), a branch of AI, may improve rapid frontline detection of LVO strokes.
PMID 31594798 ... doi:10.1136/neurintsurg-2019-015135
-
Artificial Intelligence and Acute Stroke Imaging.
Artificial intelligence technology is a rapidly expanding field with many applications in acute stroke imaging, including ischemic and hemorrhage subtypes. Early identification of acute stroke is critical for initiating prompt intervention to reduce morbidity and mortality.
PMID 33243898 ... doi:10.3174/ajnr.a6883
-
Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning.
Computed tomography (CT) of the head is used worldwide to diagnose neurologic emergencies. However, expertise is required to interpret these scans, and even highly trained experts may miss subtle life-threatening findings.
PMID 31636195 ... doi:10.1073/pnas.1908021116
-
Precise diagnosis of intracranial hemorrhage and subtypes using a three-dimensional joint convolutional and recurrent neural network.
ObjectivesTo evaluate the performance of a novel three-dimensional (3D) joint convolutional and recurrent neural network (CNN-RNN) for the detection of intracranial hemorrhage (ICH) and its five subtypes (cerebral parenchymal, intraventricular, subdural, epidural, and subarachnoid) in non-contrast head CT.MethodsA total of 2836 subjects (ICH/normal, 1836/1000) from three institutions were included in this ethically a...
PMID 31041565 ... doi:10.1007/s00330-019-06163-2
-
Microwave-based stroke diagnosis making global prehospital thrombolytic treatment possible.
Here, we present two different brain diagnostic devices based on microwave technology and the associated two first proof-of-principle measurements that show that the systems can differentiate hemorrhagic from ischemic stroke in acute stroke patients, as well as differentiate hemorrhagic patients from healthy volunteers.
PMID 24951677 ... doi:10.1109/tbme.2014.2330554
-
Evaluation of Artificial Intelligence-Powered Identification of Large-Vessel Occlusions in a Comprehensive Stroke Center.
Background and purposeArtificial intelligence algorithms have the potential to become an important diagnostic tool to optimize stroke workflow. Viz LVO is a medical product leveraging a convolutional neural network designed to detect large-vessel occlusions on CTA scans and notify the treatment team within minutes via a dedicated mobile application.
PMID 33384294 ... doi:10.3174/ajnr.a6923
-
Utilization of Artificial Intelligence-based Intracranial Hemorrhage Detection on Emergent Noncontrast CT Images in Clinical Workflow.
Authors implemented an artificial intelligence (AI)-based detection tool for intracranial hemorrhage (ICH) on noncontrast CT images into an emergent workflow, evaluated its diagnostic performance, and assessed clinical workflow metrics compared with pre-AI implementation.
PMID 35391777 ... doi:10.1148/ryai.210168
-
Analysis of head CT scans flagged by deep learning software for acute intracranial hemorrhage.
PurposeTo analyze the implementation of deep learning software for the detection and worklist prioritization of acute intracranial hemorrhage on non-contrast head CT (NCCT) in various clinical settings at an academic medical center.MethodsUrgent NCCT scans were reviewed by the Aidoc (Tel Aviv, Israel) neural network software.
PMID 31828361 ... doi:10.1007/s00234-019-02330-w
-
Automated Large Vessel Occlusion Detection Software and Thrombectomy Treatment Times: A Cluster Randomized Clinical Trial.
ImportanceThe benefit of endovascular stroke therapy (EVT) in large vessel occlusion (LVO) ischemic stroke is highly time dependent. Process improvements to accelerate in-hospital workflows are critical.ObjectiveTo determine whether automated computed tomography (CT) angiogram interpretation coupled with secure group messaging can improve in-hospital EVT workflows.Design, setting, and participantsThis cluster randomi...
PMID 37721738 ... doi:10.1001/jamaneurol.2023.3206
-
Active Reprioritization of the Reading Worklist Using Artificial Intelligence Has a Beneficial Effect on the Turnaround Time for Interpretation of Head CT with Intracranial Hemorrhage.
PurposeTo determine how to optimize the delivery of machine learning techniques in a clinical setting to detect intracranial hemorrhage (ICH) on non-contrast-enhanced CT images to radiologists to improve workflow.Materials and methodsIn this study, a commercially available machine learning algorithm that flags abnormal noncontrast CT examinations for ICH was implemented in a busy academic neuroradiology practice betw...
PMID 33937858 ... doi:10.1148/ryai.2020200024
-
Collateral Automation for Triage in Stroke: Evaluating Automated Scoring of Collaterals in Acute Stroke on Computed Tomography Scans.
Computed tomography angiography (CTA) collateral scoring can identify patients most likely to benefit from mechanical thrombectomy and those more likely to have good outcomes and ranges from 0 (no collaterals) to 3 (complete collaterals).
PMID 31216543 ... doi:10.1159/000500076
-
Detection of early infarction signs with machine learning-based diagnosis by means of the Alberta Stroke Program Early CT score (ASPECTS) in the clinical routine.
PurposeNew software solutions emerged to support radiologists in image interpretation in acute ischemic stroke. This study aimed to validate the performance of computer-aided assessment of the Alberta Stroke Program Early CT score (ASPECTS) for detecting signs of early infarction.MethodsASPECT scores were assessed in 119 CT scans of patients with acute middle cerebral artery ischemia.
PMID 30066278 ... doi:10.1007/s00234-018-2066-5
-
Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Intracranial Hemorrhage.
ObjectiveTo determine the institutional diagnostic accuracy of an artificial intelligence (AI) decision support systems (DSS), Aidoc, in diagnosing intracranial hemorrhage (ICH) on noncontrast head CTs and to assess the potential generalizability of an AI DSS.MethodsThis retrospective study included 3,605 consecutive, emergent, adult noncontrast head CT scans performed between July 1, 2019, and December 30, 2019, at ...
PMID 33819478 ... doi:10.1016/j.jacr.2021.03.005
-
Deep learning-based detection and segmentation of diffusion abnormalities in acute ischemic stroke.
BackgroundAccessible tools to efficiently detect and segment diffusion abnormalities in acute strokes are highly anticipated by the clinical and research communities.MethodsWe developed a tool with deep learning networks trained and tested on a large dataset of 2,348 clinical diffusion weighted MRIs of patients with acute and sub-acute ischemic strokes, and further tested for generalization on 280 MRIs of an external...
PMID 35602200 ... doi:10.1038/s43856-021-00062-8
-
Deep Learning Based Software to Identify Large Vessel Occlusion on Noncontrast Computed Tomography.
Background and purposeReliable recognition of large vessel occlusion (LVO) on noncontrast computed tomography (NCCT) may accelerate identification of endovascular treatment candidates. We aim to validate a machine learning algorithm (MethinksLVO) to identify LVO on NCCT.MethodsPatients with suspected acute stroke who underwent NCCT and computed tomography angiography (CTA) were included.
PMID 32842922 ... doi:10.1161/strokeaha.120.030326
-
Deep learning fully convolution network for lumen characterization in diabetic patients using carotid ultrasound: a tool for stroke risk.
Manual ultrasound (US)-based methods are adapted for lumen diameter (LD) measurement to estimate the risk of stroke but they are tedious, error prone, and subjective causing variability. We propose an automated deep learning (DL)-based system for lumen detection. The system consists of a combination of two DL systems: encoder and decoder for lumen segmentation.
PMID 30255236 ... doi:10.1007/s11517-018-1897-x
-
Detecting Large Vessel Occlusion at Multiphase CT Angiography by Using a Deep Convolutional Neural Network.
Background Large vessel occlusion (LVO) stroke is one of the most time-sensitive diagnoses in medicine and requires emergent endovascular therapy to reduce morbidity and mortality. Leveraging recent advances in deep learning may facilitate rapid detection and reduce time to treatment. Purpose To develop a convolutional neural network to detect LVOs at multiphase CT angiography.
PMID 32990513 ... doi:10.1148/radiol.2020200334
-
Improving Sensitivity on Identification and Delineation of Intracranial Hemorrhage Lesion Using Cascaded Deep Learning Models.
Highly accurate detection of the intracranial hemorrhage without delay is a critical clinical issue for the diagnostic decision and treatment in an emergency room. In the context of a study on diagnostic accuracy, there is a tradeoff between sensitivity and specificity.
PMID 30680471 ... doi:10.1007/s10278-018-00172-1
-
Artificial intelligence-enabled retinal vasculometry for prediction of circulatory mortality, myocardial infarction and stroke.
AimsWe examine whether inclusion of artificial intelligence (AI)-enabled retinal vasculometry (RV) improves existing risk algorithms for incident stroke, myocardial infarction (MI) and circulatory mortality.MethodsAI-enabled retinal vessel image analysis processed images from 88 052 UK Biobank (UKB) participants (aged 40-69 years at image capture) and 7411 European Prospective Investigation into Cancer (EPIC)-Norfolk...
PMID 36195457 ... doi:10.1136/bjo-2022-321842
-
Artificial Intelligence for Large-Vessel Occlusion Stroke: A Systematic Review.
BackgroundOptimal outcomes after large-vessel occlusion (LVO) stroke are highly dependent on prompt diagnosis, effective communication, and treatment, making LVO an attractive avenue for the application of artificial intelligence (AI), specifically machine learning (ML).
PMID 34896351 ... doi:10.1016/j.wneu.2021.12.004
-
Artificial intelligence in stroke imaging: Current and future perspectives.
Artificial intelligence (AI) is a fast-growing research area in computer science that aims to mimic cognitive processes through a number of techniques. Supervised machine learning, a subfield of AI, includes methods that can identify patterns in high-dimensional data using labeled 'ground truth' data and apply these learnt patterns to analyze, interpret, or make predictions on new datasets.
PMID 32980785 ... doi:10.1016/j.clinimag.2020.09.005
-
Utility of Artificial Intelligence Tool as a Prospective Radiology Peer Reviewer - Detection of Unreported Intracranial Hemorrhage.
Rationale and objectivesMisdiagnosis of intracranial hemorrhage (ICH) can adversely impact patient outcomes. The increasing workload on the radiologists may increase the chance of error and compromise the quality of care provided by the radiologists.Materials and methodsWe used an FDA approved artificial intelligence (AI) solution based on a convolutional neural network to assess the prevalence of ICH in scans, which...
PMID 32102747 ... doi:10.1016/j.acra.2020.01.035
-
Validation of a Deep Learning Tool in the Detection of Intracranial Hemorrhage and Large Vessel Occlusion.
Purpose: Recently developed machine-learning algorithms have demonstrated strong performance in the detection of intracranial hemorrhage (ICH) and large vessel occlusion (LVO). However, their generalizability is often limited by geographic bias of studies.
PMID 33995252 ... doi:10.3389/fneur.2021.656112
Study records come from Europe PMC, which indexes PubMed, MEDLINE, PMC and preprint servers. Titles, journals, years, identifiers, citation counts and abstracts are reproduced from the source record and are not rewritten here. Listing a study is not an endorsement of its conclusion, and citation count measures attention rather than quality. This page is a starting point for your own reading, not clinical guidance.