Artificial neural network-based analysis of the safetand efficacy of thrombolysis for ischemic stroke in older adults in Taiwan

研究成果: 雜誌貢獻文章同行評審

摘要

Background: The risk and benefit of tissue plasminogen activator (tPA) for aged>80 years with acute ischemic stroke (AIS) are controversial. In this study, we investigated the safety and efficacy of tPA in this population and utilized the artificial neural network (ANN) to established outcome predictive models. Methods: We retrospectively reviewed the stroke registry data of patients with AIS, aged >80 years who arrived at the hospital within 3 hours from the onset of symptoms. The characteristics and the outcomes, presented as modified Rankin Scale (mRS), and mortality rate at 3 months between the tPA-treated and non-tPA groups were analyzed. An ANN algorithm was applied to establish predictive models. Results: A total of 80 patients aged>80 years with AIS were identified, and 49 of them received tPA. After adequate training, our ANN models accurately predicted the outcomes with the area under the receiver operating characteristic curves of 0.974, and a low error to predict the mRS score at 3 months. After applying our prediction model to those in the non-tPA group, we demonstrated the potential benefits in those patients if they had undergone tPA therapy. Conclusions: Our results show that ANN can be a potentially useful tool for predicting the treatment outcomes of tPA. Such novel machine learning-based models may help with therapeutic decision making in clinical settings.

原文英語
頁(從 - 到)109-117
頁數9
期刊Neurology Asia
25
發行號2
出版狀態已發佈 - 六月 2020

ASJC Scopus subject areas

  • Neurology
  • Clinical Neurology

指紋 深入研究「Artificial neural network-based analysis of the safetand efficacy of thrombolysis for ischemic stroke in older adults in Taiwan」主題。共同形成了獨特的指紋。

引用此