AI assisted tool linked to improved stroke care and outcomes
Offers a more efficient and scalable method for improving stroke care and prognosis, say researchers
A clinical decision support tool that uses artificial intelligence (AI) to analyse scans after a stroke alongside treatment recommendations is associated with better quality care and long term outcomes for patients compared with usual care, finds a study from China published by The BMJ today.
The researchers say the tool “offers a more efficient and scalable method for improving stroke care and prognosis, with the added benefits of lower cost and greater sustainability.”
AI in healthcare has gained widespread attention, especially in assisting with disease diagnosis, treatment, prognosis, and enhancing clinical decision making. But most AI stroke tools have not been rigorously evaluated, so their use is currently limited.
To address this gap, researchers set out to test whether a stroke clinical decision support system (CDSS) that uses AI-assisted imaging analysis to classify stroke causes alongside evidence-based treatment recommendations could improve care quality and outcomes in routine clinical practice.
The trial findings are based on 21,603 patients (average age 67; 36% female) with acute ischaemic stroke admitted to one of 77 hospitals across China within seven days of symptom onset.
From January 2021 to June 2023, 11,054 patients at 38 hospitals received stroke CDSS support (intervention group) and 10,549 patients at 39 hospitals received usual medical care (control group).
Physicians assigned to intervention group patients received system training and factors such as hospital region and grade, patient age, medication history, and lifestyle, were taken into account.
Patients supported by the CDSS had fewer new vascular events (including stroke, heart attack, or related death) at three, six, and 12 months.
At three months, new vascular events occurred in 2.9% of the intervention group (320 of 11,054) compared with 3.9% of the control group (416 of 10,549), representing a 26% reduction.
This reduction was maintained at 12 months, with new vascular events occurring in 4% of the intervention group (440 of 11,054) versus 5.5% of the control group (576 of 10,549), a 27% reduction.
Patients receiving the intervention also showed higher stroke care quality performance measures than control patients (91.4% v 89.8%).
There were no significant differences between the two groups for disability and all-cause mortality at three, six, and 12 months. Similarly, there were no significant differences in moderate or severe bleeding, or all bleeding, between the groups at any of these time points.
The authors point out that the trial randomised hospitals rather than individual patients and that differences in care patterns and subsequent outpatient care might impact the findings.
But they note that the system was easy to use and integrated into all hospital information systems, so could serve as an AI based comprehensive management tool focusing on management in hospital and secondary prevention strategies.
As such, they conclude: “The stroke CDSS offers a promising approach to providing high quality care for patients with acute ischaemic stroke admitted to hospital, particularly for resource constrained regions with a heavy burden of cerebrovascular diseases like China.”
END
The researchers say the tool “offers a more efficient and scalable method for improving stroke care and prognosis, with the added benefits of lower cost and greater sustainability.”
AI in healthcare has gained widespread attention, especially in assisting with disease diagnosis, treatment, prognosis, and enhancing clinical decision making. But most AI stroke tools have not been rigorously evaluated, so their use is currently limited.
To address this gap, researchers set out to test whether a stroke clinical decision support system (CDSS) that uses AI-assisted imaging analysis to classify stroke causes alongside evidence-based treatment recommendations could improve care quality and outcomes in routine clinical practice.
The trial findings are based on 21,603 patients (average age 67; 36% female) with acute ischaemic stroke admitted to one of 77 hospitals across China within seven days of symptom onset.
From January 2021 to June 2023, 11,054 patients at 38 hospitals received stroke CDSS support (intervention group) and 10,549 patients at 39 hospitals received usual medical care (control group).
Physicians assigned to intervention group patients received system training and factors such as hospital region and grade, patient age, medication history, and lifestyle, were taken into account.
Patients supported by the CDSS had fewer new vascular events (including stroke, heart attack, or related death) at three, six, and 12 months.
At three months, new vascular events occurred in 2.9% of the intervention group (320 of 11,054) compared with 3.9% of the control group (416 of 10,549), representing a 26% reduction.
This reduction was maintained at 12 months, with new vascular events occurring in 4% of the intervention group (440 of 11,054) versus 5.5% of the control group (576 of 10,549), a 27% reduction.
Patients receiving the intervention also showed higher stroke care quality performance measures than control patients (91.4% v 89.8%).
There were no significant differences between the two groups for disability and all-cause mortality at three, six, and 12 months. Similarly, there were no significant differences in moderate or severe bleeding, or all bleeding, between the groups at any of these time points.
The authors point out that the trial randomised hospitals rather than individual patients and that differences in care patterns and subsequent outpatient care might impact the findings.
But they note that the system was easy to use and integrated into all hospital information systems, so could serve as an AI based comprehensive management tool focusing on management in hospital and secondary prevention strategies.
As such, they conclude: “The stroke CDSS offers a promising approach to providing high quality care for patients with acute ischaemic stroke admitted to hospital, particularly for resource constrained regions with a heavy burden of cerebrovascular diseases like China.”
END