计算精神病学:从神经科学到临床应用的桥梁
Computational psychiatry as a bridge from neuroscience to
clinical applications
Quentin
J M Huys1,2,5, Tiago V Maia3,5 & Michael J Frank4
1Translational Neuromodeling Unit, Institute for
Biomedical Engineering, University of Zürich and Swiss Federal
Institute of Technology (ETH) Zürich, Zürich, Switzerland.
2Centre for Addictive Disorders, Department of Psychiatry,
Psychotherapy and Psychosomatics, Hospital of Psychiatry,
University of Zürich, Zürich, Switzerland.
3School
of Medicine and Institute for Molecular Medicine, University of Lisbon, Lisbon,
Portugal.
4Computation in Brain and Mind, Brown Institute
for Brain Science, Psychiatry and Human Behavior,
Brown University, Providence,
USA.
5These authors contributed equally to this work.
Correspondence should be addressed to Q.J.M.H. (qhuys@cantab.net).
Accepted: 2015 by nature neuroscience
摘要:将神经科学的进步转化为精神疾病患者的利益面临巨大挑战,因为它涉及最复杂的器官,大脑及其与相似复杂环境的相互作用。处理这种复杂性需要强大的技术。计算精神病学将多种级别和类型的计算与多种类型的数据相结合,以提高对精神疾病的理解,预测和治疗。广义上讲,计算精神病学包含两种互补的方法:数据驱动和理论驱动。数据驱动的方法将机器学习方法应用于高维数据,以改善疾病分类,预测治疗结果或改善治疗选择。这些方法通常与基本机制无关。相比之下,理论驱动的方法使用的模型可以实例化此类机制的先验知识或明确的假设,可能会在多个层次的分析和抽象中进行实例化。我们回顾了这两种方法的最新进展,重点是临床应用,并强调了将它们组合起来的效用。
翻译稿件:计算精神病学:从神经科学到临床应用的桥梁
翻译原文:Computational psychiatry as a bridge from neuroscience to
clinical applications