Department of Computer Science, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand.
Boyer College of Music and Dance, Music Education and Therapy, Temple University, Philadelphia, USA.
BMC Med Inform Decis Mak. 2023 Feb 28;23(1):41. doi: 10.1186/s12911-023-02128-0.
Prolonged Disorders of Consciousness (PDOC) resulting from severe acquired brain injury can lead to complex disabilities that make diagnosis challenging. The role of machine learning (ML) in diagnosing PDOC states and identifying intervention strategies is relatively under-explored, having focused on predicting mortality and poor outcome. This study aims to: (a) apply ML techniques to predict PDOC diagnostic states from variables obtained from two non-invasive neurobehavior assessment tools; and (b) apply network analysis for guiding possible intervention strategies.
The Coma Recovery Scale-Revised (CRS-R) is a well-established tool for assessing patients with PDOC. More recently, music has been found to be a useful medium for assessment of coma patients, leading to the standardization of a music-based assessment of awareness: Music Therapy Assessment Tool for Awareness in Disorders of Consciousness (MATADOC). CRS-R and MATADOC data were collected from 74 PDOC patients aged 16-70 years at three specialist centers in the USA, UK and Ireland. The data were analyzed by three ML techniques (neural networks, decision trees and cluster analysis) as well as modelled through system-level network analysis.
PDOC diagnostic state can be predicted to a relatively high level of accuracy that sets a benchmark for future ML analysis using neurobehavioral data only. The outcomes of this study may also have implications for understanding the role of music therapy in interdisciplinary rehabilitation to help patients move from one coma state to another.
This study has shown how ML can derive rules for diagnosis of PDOC with data from two neurobehavioral tools without the need to harvest large clinical and imaging datasets. Network analysis using the measures obtained from these two non-invasive tools provides novel, system-level ways of interpreting possible transitions between PDOC states, leading to possible use in novel, next-generation decision-support systems for PDOC.
严重后天性脑损伤导致的持续性意识障碍（PDOC）可导致复杂残疾，使诊断变得具有挑战性。机器学习（ML）在诊断 PDOC 状态和确定干预策略方面的作用相对较少，主要集中在预测死亡率和不良预后上。本研究旨在：（a）应用 ML 技术从两种非侵入性神经行为评估工具中获取的变量来预测 PDOC 诊断状态；（b）应用网络分析来指导可能的干预策略。
修订后的昏迷恢复量表（CRS-R）是评估 PDOC 患者的一种成熟工具。最近，人们发现音乐是评估昏迷患者的一种有用手段，从而标准化了基于音乐的意识评估工具：意识障碍的音乐治疗评估工具（MATADOC）。CRS-R 和 MATADOC 数据是从美国、英国和爱尔兰的三个专科中心的 74 名年龄在 16-70 岁的 PDOC 患者中收集的。这些数据通过三种 ML 技术（神经网络、决策树和聚类分析）进行了分析，并通过系统级网络分析进行了建模。
PDOC 诊断状态可以预测到相对较高的准确性水平，为未来仅使用神经行为数据进行 ML 分析设定了基准。本研究的结果也可能对理解音乐治疗在跨学科康复中的作用具有启示意义，有助于患者从一种昏迷状态转变为另一种状态。
本研究表明，ML 如何从两种神经行为工具的数据中得出 PDOC 诊断规则，而无需采集大量的临床和影像学数据集。使用这两种非侵入性工具获得的测量值进行网络分析，提供了一种新的、系统级的方法来解释 PDOC 状态之间可能的转变，从而可能用于新型的、下一代 PDOC 决策支持系统。
