期刊
INTERNATIONAL JOURNAL OF STROKE
卷 17, 期 7, 页码 785-792出版社
SAGE PUBLICATIONS LTD
DOI: 10.1177/17474930211051531
关键词
Artificial intelligence; intracerebral hemorrhage; unclear onset time; stroke; deep learning; non-contrast CT
资金
- CAMS Sciences Innovation Fund for Medical Science [2020-I2MCT-B-031]
- CAMS/PUMC Postgraduate Teaching Innovation Fund [10023201900107]
- National Key RAMP
- D Program of China [2018YFA0108600]
An artificial intelligence model utilizing weakly supervised multitask learning structure was able to identify onset time for spontaneous intracerebral hemorrhage patients with unclear onset, potentially benefiting from time-dependent treatments. The model showed good performance and generalizability, demonstrating potential for integration into clinical practice.
Background Approximately one-third of spontaneous intracerebral hemorrhage patients did not know the onset time and were excluded from studies about time-dependent treatments for hyperacute spontaneous intracerebral hemorrhage. Aims To help clinicians explore the benefit of time-dependent treatments for unclear-onset patients, we presented artificial intelligence models to identify onset time using non-contrast computed tomography (NCCT) based on weakly supervised multitask learning (WS-MTL) structure. Methods The patients with reliable symptom onset time (strong label) or repeat CT (weak label) were included and split into training set and test set (internal and external). The WS-MTL structure utilized strong and weak labels simultaneously to improve performance. The models included three binary classification models for classifying whether NCCT acquired within 6, 8 or 12 h for different treatments measured by area under curve, and a regression model for determining the exact onset time measured by mean absolute error. The generalizability of models was also explored in comprehensive analysis. Results A total of 4004 patients with 10,780 NCCT scans were included. The performance of WS-MTL classification model showed high accuracy, and that of regression model was satisfactory in <= 6 h subgroup. In comprehensive analysis, the WS-MTL showed better performance for larger hematomas and thinner scans. And the performance improved effectively as training amounts increasing and could be improved steadily through retraining. Conclusions The WS-MTL models showed good performance and generalizability. Considering the large number of unclear-onset spontaneous intracerebral hemorrhage patients, it may be worth to integrate the WS-MTL model into clinical practice to identify the onset time.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据