Reasoning Artificial Intelligence Collaborate With Radiologists in Neurological Disease Interpretation and Diagnosis on CT and MRI
试验速览
- 阶段
- 不适用
- 状态
- Enrolling By Invitation
- 发起方
- 入组人数
- 30,000
- 试验地点
- 1
- 主要终点
- AI tools vs Radiologists from Clinical silence trial
研究概览
简要总结
This clinic trial aims to validate the working performance of radiologists with or without artificial intelligence (AI) diagnostic tool at neurological diseases diagnosis on brain CT/MRI. Routine diagnosis workflow in real clinical scenario including imaging reading, feature interpretation, differential diagnosis, writing initial report and optimizing revised version. And the gold standards of diagnosis are the histopathology references for brain tumors and the discharge diagnosis integrating all the examination results for the other neurological diseases. The performance of AI-assisted tools on diagnosing should be examined in a clinical process with multiple aspects identical to human radiologists' work before being transformed and putted to use. This study hypothesizes that AI models, trained with over 100,000 patient scans, are non-inferior to radiologists in neurological disease diagnosis on brain CT and MRI. For the secondary end-points, we investigate the performance of AI-radiologist collaboration of reasoning-enhanced AI-assisted systems. We hypothesize that, by visualizing the process of imaging interpretation and diagnosis, reasoning-enhanced AI can not only improve working performance of radiologists but also boost their trust in AI tools.
详细描述
Neurological diseases affect over 50% of the world population, which contribute to an increasingly needs of imaging examination for screening and diagnosis. The shortage of neuroradiologists led to the excessive workload, linked with increasing of error rates and decreasing of report quality. Inexperienced radiologists struggle to make accurate diagnoses for some neurological diseases, especially brain tumors, which may lead to additional delays and a potentially meaningless examination for patients.
Artificial intelligence (AI) has shown potential to be "a tireless resident", which can rival human performance in medical imaging interpretation and assist radiologists in multiple links of clinical diagnostic work. However, clinicians recognize that "Black-box" models lacking clinical utility and interpretability face significant barriers to real-world deployment. While the reasoning-enhanced AI model, trained by a hundred thousand data, can not only achieve accurate and efficient diagnosis but also but also address the lack of explainability, transparency, and trust.
Owing to the heterogeneity of multi-modal real clinical data and complexity of neurological diseases, whether the developed AI-assisted system can truly serve as an "AI resident" facing challenges and doubts. Clinical trial is the best approach to verify the performance of diagnosis and human-machine collaboration of AI model with a wide range of users and prospective data before being approved for clinical use. Key aspects of the study design have been established in conjunction with a multi-disciplinary scientific advisory board, consisting with experts in AI, radiology, neurology, and pathology, to ensure meaningful validation of reasoning-enhanced AI model towards clinical translation.
This clinic trial contains two sub-studies:
- Clinical silence trial study for AI tools only:
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Other
入排标准
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •For MRI: patients suspected of harboring brain tumors or detected with brain occupancy at initiating or other institution, who subsequently underwent brain MRI.
- •For CT: patients with or without neurological symptoms, suspected of harboring ischemic, hemorrhagic, space-occupiing, degenerative brain disease, or traumatic brain injury, who subsequently underwent brain CT.
排除标准
- •Patients who opted-out or did not give permission to reuse clinical data.
- •Patients with a history of prior brain surgery.
- •Patients whose brain CT or MRI exhibit severe artifacts (e.g. heavy warping due to air, metal artifacts, heavy motion artifacts), thereby impeding the usage of the data.
结局指标
主要结局
AI tools vs Radiologists from Clinical silence trial
时间窗: 6 months
Diagnostic performance of AI models and over 50 radiologists from the Clinical silence trial study, at neurological diseases on brain CT/MRI, with respect to histopathology and discharge diagnosis as reference, to assess the working performance of neuroimaging AI diagnostic tools.
AI-assisted diagnostic tool collaborates with Radiologists in clinical workflow
时间窗: 6 months
Working efficiency (time taking) and diagnostic confidence and accuracy of radiologists from AI-radiologist collaboration study, at neurological diseases on brain CT/MRI, to assess the clinical viability of AI-assisted diagnostic tool.
次要结局
- Present AI vs the other AI tools uploaded from Clinical silence trial(6 months)
- Reasoning-enhanced AI model collaborates with Radiologists in clinical workflow(6 months)
研究者
Yaou Liu
Director of the Radiology Department
Beijing Tiantan Hospital