Home  >  Article  >  Technology peripherals  >  Study: Artificial intelligence shortens stroke treatment time and reduces mortality by 60%

Study: Artificial intelligence shortens stroke treatment time and reduces mortality by 60%

WBOY
WBOYforward
2023-09-23 22:57:12518browse

News on September 22: For stroke patients, timely endovascular thrombectomy surgery is crucial to improving the patient’s prognosis. The time it takes for a patient to arrive at the hospital and undergo endovascular thrombectomy surgery has become an important indicator for a hospital to achieve stroke center certification

The application of artificial intelligence in diagnosing various medical conditions using CT images has been extensively explored. Therefore, automated methods based on artificial intelligence can be utilized to screen CT angiograms in patients with possible AIS, thereby shortening the time between evaluation and internal vessel thrombectomy

In this study, researchers used a randomized assignment ladder-like clinical trial to determine the effectiveness of an automated artificial intelligence-based system in detecting LVO in patients with possible AIS and improving hospital arrival and endovascular thrombectomy. Efficiency of time between start of assessment and workflow. Implementing random assignment analyzes at the individual patient level may cause problems while retaining the robustness of the randomized assessment.

Study: Artificial intelligence shortens stroke treatment time and reduces mortality by 60%

Picture source note: The picture is generated by AI, and the picture is authorized by the service provider Midjourney

The trial was conducted at four comprehensive stroke centers in the Houston area from January 2021 to the end of February 2022. The phased rollout at the hospital level comes after receiving clearance from the U.S. Food and Drug Administration (FDA) for use of the AI ​​platform in clinical care and receiving significant financial support to implement the software.

Participants in the trial included patients who presented to the emergency departments of these four comprehensive stroke centers with symptoms of AIS and LVO and underwent CT angiography. All patients included in the study were those with AIS associated with LVO of the middle cerebral artery, internal carotid artery, anterior cerebral artery, posterior cerebral artery, basilar artery, or intracranial vertebral artery

Since these patients had already decided to undergo internal vessel thrombectomy in the hospital, the time between the initial CT scan and internal vessel thrombectomy was significantly different in the inpatient cases and were therefore excluded from the analysis. For patients referred from other medical centers, the decision has been made for endovascular thrombectomy and they will proceed directly to the procedure without further imaging, which will change the workflow time

The intervention includes activation of artificial intelligence-based LVO detection from CT angiography, which is integrated with a secure messaging system. The system was activated in a randomized fashion at four comprehensive stroke centers. The activated system alerts radiologists and clinicians via mobile phone within minutes of completion of CT imaging of a possible LVO.

Research results

Key research findings include the impact of an automated artificial intelligence-based LVO detection system on door-to-abdomen time, which was determined using a linear regression model. Secondary outcomes included the time between arrival at the hospital and intravenous tissue kinase activator injection, the time between starting a CT scan and starting endovascular thrombectomy, and length of hospital stay.

By implementing an automated artificial intelligence-based LVO detection system, combined with a safety application that uses mobile phones for communication, inpatient AIS workflow time has been significantly improved. During the trial, a total of about 250 patients attended the emergency departments of the four hospitals, and door-to-abdominal time was reduced by 11 minutes through the use of the AI-based automated system. Additionally, mortality was reduced by 60%, along with a reduction in the time between the initial CT scan and initiation of endovascular thrombectomy

in conclusion

By using an automated AI-based system to detect LVO in patients with possible AIS, combined with a secure communication application, we successfully reduced the workflow within the hospital and significantly reduced the number of endovascular thrombectomies performed clinically Treatment time

[Source: Webmaster’s Home]

The above is the detailed content of Study: Artificial intelligence shortens stroke treatment time and reduces mortality by 60%. For more information, please follow other related articles on the PHP Chinese website!

Statement:
This article is reproduced at:sohu.com. If there is any infringement, please contact admin@php.cn delete