ETH Zürich, Department of Health Sciences and Technology (D-HEST), Zürich, Switzerland; Swiss Institute of Bioinformatics (SIB), Lausanne, Switzerland.
ETH Zürich, Department of Health Sciences and Technology (D-HEST), Zürich, Switzerland; Spinal Cord Injury Center, University Hospital Balgrist, University of Zürich, Switzerland.
Exp Neurol. 2024 Oct;380:114913. doi: 10.1016/j.expneurol.2024.114913. Epub 2024 Aug 2.
Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is a promising approach to enhance the prediction of recovery trajectories, but its integration into clinical practice requires a thorough understanding of its efficacy and applicability. We systematically reviewed the current literature on data-driven models of SCI recovery prediction. The included studies were evaluated based on a range of criteria assessing the approach, implementation, input data preferences, and the clinical outcomes aimed to forecast. We observe a tendency to utilize routinely acquired data, such as International Standards for Neurological Classification of SCI (ISNCSCI), imaging, and demographics, for the prediction of functional outcomes derived from the Spinal Cord Independence Measure (SCIM) III and Functional Independence Measure (FIM) scores with a focus on motor ability. Although there has been an increasing interest in data-driven studies over time, traditional machine learning architectures, such as linear regression and tree-based approaches, remained the overwhelmingly popular choices for implementation. This implies ample opportunities for exploring architectures addressing the challenges of predicting SCI recovery, including techniques for learning from limited longitudinal data, improving generalizability, and enhancing reproducibility. We conclude with a perspective, highlighting possible future directions for data-driven SCI recovery prediction and drawing parallels to other application fields in terms of diverse data types (imaging, tabular, sequential, multimodal), data challenges (limited, missing, longitudinal data), and algorithmic needs (causal inference, robustness).
脊髓损伤 (SCI) 是康复医学面临的重大挑战，个体之间的恢复结果差异很大。机器学习 (ML) 是增强恢复轨迹预测的一种很有前途的方法，但要将其整合到临床实践中，需要深入了解其功效和适用性。我们系统地回顾了关于 SCI 恢复预测数据驱动模型的现有文献。根据评估方法、实施、输入数据偏好以及旨在预测的临床结果的一系列标准，对纳入的研究进行了评估。我们观察到一种倾向，即倾向于使用常规采集的数据，例如国际 SCI 神经分类标准 (ISNCSCI)、影像学和人口统计学，来预测源自脊髓独立性测量 (SCIM) III 和功能独立性测量 (FIM) 评分的功能结果，重点是运动能力。尽管随着时间的推移，对数据驱动研究的兴趣有所增加，但线性回归和基于树的方法等传统机器学习架构仍然是实施的首选。这意味着有很多机会可以探索解决预测 SCI 恢复挑战的架构，包括用于从有限的纵向数据中学习、提高泛化能力和增强可重复性的技术。最后，我们从一个角度进行了总结，突出了数据驱动的 SCI 恢复预测的可能未来方向，并在不同数据类型（成像、表格、序列、多模态）、数据挑战（有限、缺失、纵向数据）和算法需求（因果推断、鲁棒性）方面与其他应用领域进行了比较。
