arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.01949cs.LGq-bio.QMstat.APstat.ME
收藏

人工智能用于痴呆研究方法优化

Artificial Intelligence for Dementia Research Methods Optimization

Ulster University(阿尔斯特大学);University Hospitals Bristol and Weston NHS Foundation Trust(布里斯托尔大学医院与韦斯顿国民健康服务体系基金会信托);University of Bristol(布里斯托尔大学);Université de Montréal(蒙特利尔大学);University of Aberdeen(阿伯丁大学);University of Nottingham(诺丁汉大学);UK Dementia Research Institute(英国痴呆症研究所);Imperial College London(帝国理工学院);University College London(伦敦大学学院);University of Verona(维罗纳大学);University of Sheffield(谢菲尔德大学)
Magda Bucholc, Charlotte James, Ahmad Al Khleifat, AmanPreet Badhwar, Natasha Clarke, Amir Dehsarvi, Christopher R. Madan, Sarah J. Marzi, Cameron Shand, Brian … 展开作者

Magda Bucholc, Charlotte James, Ahmad Al Khleifat, AmanPreet Badhwar, Natasha Clarke, Amir Dehsarvi, Christopher R. Madan, Sarah J. Marzi, Cameron Shand, Brian M. Schilder, Stefano Tamburin, Hanz M. Tantiangco, Ilianna Lourida, David J. Llewellyn, Janice M. Ranson

摘要:

简介:机器学习(ML)在从高维数据集中识别关键特征以及以人类专家级别或更高的准确度执行复杂任务方面非常成功。方法:我们总结和批判性地评价了ML在痴呆研究中的当前应用,并强调了未来研究的方向。结果如下:我们概述了在痴呆症研究中最常用的ML算法,并强调了ML在临床实践、实验医学和临床试验中使用的未来机会。我们讨论了再现性,可复制性和可解释性的问题,以及这些如何影响痴呆症研究的临床适用性。最后,我们给出了最先进的方法,如迁移学习,多任务学习和强化学习,如何应用于克服这些问题,并帮助未来的研究转化为临床实践的例子。讨论:基于ML的模型具有很大的希望,以促进我们对痴呆症的根本原因和病理机制的理解。

英文摘要:

Introduction: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater. Methods: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research. Results: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future. Discussion: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑