University of Canberra, Human-Centred Technology Research Centre, ESTEM Faculty, Canberra, Australia.
Taipei Medical University Hospital, Department of Dentistry, Taipei, Taiwan.
J Biomed Opt. 2017 Oct;22(10):1-12. doi: 10.1117/1.JBO.22.10.106013.
Pain diagnosis for nonverbal patients represents a challenge in clinical settings. Neuroimaging methods, such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown promising results to assess neuronal function in response to nociception and pain. Recent studies suggest that neuroimaging in conjunction with machine learning models can be used to predict different cognitive tasks. The aim of this study is to expand previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. Toward this aim, we used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), mean age±standard deviation (31.9±5.5). The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest (RoI). The results showed that K-NN obtained slightly better results (92.08%) than SVM (91.25%) using the 24 channels; however, the performance slightly dropped using only channels from the RoI with K-NN (91.53%) and SVM (90.83%). These results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain.
非言语患者的疼痛诊断在临床环境中是一个挑战。神经影像学方法，如功能磁共振成像和功能性近红外光谱（fNIRS），已经显示出有希望的结果，可以评估神经元对伤害性刺激和疼痛的反应功能。最近的研究表明，神经影像学结合机器学习模型可以用于预测不同的认知任务。本研究的目的是通过探索使用机器学习模型根据温度水平（冷和热）和相应的疼痛强度（低和高）对 fNIRS 信号（氧合血红蛋白）进行分类，来扩展以前的研究。为此，我们使用定量感觉测试来确定 18 名健康受试者（3 名女性）的冷和热疼痛阈值和疼痛耐受度，平均值±标准差（31.9±5.5）。分类模型基于词袋方法，这是一种基于提取单词频率的文档分类直方图表示法，并适应于时间序列；分别使用了两种学习算法，K-最近邻（K-NN）和支持向量机（SVM）。在分类任务中，还比较了两组 fNIRS 通道，即全部 24 个通道和定义为我们感兴趣区域（RoI）的 8 个体感区域通道。结果表明，使用 24 个通道时，K-NN 获得的结果略优于 SVM（91.25%）（92.08%）；然而，仅使用 RoI 中的通道时，K-NN（91.53%）和 SVM（90.83%）的性能略有下降。这些结果表明，fNIRS 在开发基于生理学的人类疼痛诊断方面具有潜在的应用，这将有益于无法自我报告疼痛的脆弱患者。
