Department of Molecular Neurology, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
Machine Learning and Data Analytics Lab, Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany.
Eur J Neurol. 2024 Aug;31(8):e16367. doi: 10.1111/ene.16367. Epub 2024 Jun 10.
Hereditary spastic paraplegias (HSPs) comprise a group of inherited neurodegenerative disorders characterized by progressive spasticity and weakness. Botulinum toxin has been approved for lower limb spasticity following stroke and cerebral palsy, but its effects in HSPs remain underexplored. We aimed to characterize the effects of botulinum toxin on clinical, gait, and patient-reported outcomes in HSP patients and explore the potential of mobile digital gait analysis to monitor treatment effects and predict treatment response.
We conducted a prospective, observational, multicenter study involving ambulatory HSP patients treated with botulinum toxin tailored to individual goals. Comparing data at baseline, after 1 month, and after 3 months, treatment response was assessed using clinical parameters, goal attainment scaling, and mobile digital gait analysis. Machine learning algorithms were used for predicting individual goal attainment based on baseline parameters.
A total of 56 patients were enrolled. Despite the heterogeneity of treatment goals and targeted muscles, botulinum toxin led to a significant improvement in specific clinical parameters and an improvement in specific gait characteristics, peaking at the 1-month and declining by the 3-month follow-up. Significant correlations were identified between gait parameters and clinical scores. With a mean balanced accuracy of 66%, machine learning algorithms identified important denominators to predict treatment response.
Our study provides evidence supporting the beneficial effects of botulinum toxin in HSP when applied according to individual treatment goals. The use of mobile digital gait analysis and machine learning represents a novel approach for monitoring treatment effects and predicting treatment response.
遗传性痉挛性截瘫（HSP）是一组遗传性神经退行性疾病，其特征为进行性痉挛和无力。肉毒毒素已被批准用于治疗中风和脑瘫后的下肢痉挛，但在 HSP 中的作用仍未得到充分探索。我们旨在描述肉毒毒素对 HSP 患者的临床、步态和患者报告结果的影响，并探讨移动数字步态分析在监测治疗效果和预测治疗反应方面的潜力。
我们进行了一项前瞻性、观察性、多中心研究，纳入了接受个体化目标导向的肉毒毒素治疗的可活动 HSP 患者。通过临床参数、目标达成评分和移动数字步态分析，在基线、治疗后 1 个月和 3 个月时评估治疗反应。使用机器学习算法根据基线参数预测个体目标的达成情况。
共纳入 56 例患者。尽管治疗目标和靶向肌肉存在异质性，但肉毒毒素治疗可显著改善特定的临床参数和特定的步态特征，在治疗后 1 个月达到峰值，并在 3 个月随访时下降。步态参数与临床评分之间存在显著相关性。平均平衡准确率为 66%，机器学习算法确定了预测治疗反应的重要指标。
本研究为根据个体化治疗目标应用肉毒毒素治疗 HSP 提供了有益效果的证据。移动数字步态分析和机器学习的应用代表了监测治疗效果和预测治疗反应的新方法。
