A Multimodal Autonomic Sensing Framework for Objective Assessment of Patient Responses to Dental Pulp Stimulation
作者: Youngsun Kong, Yubin Choi, Dongjin Song, Dong-Guk Shin, I-Ping Chen, Ki Chon
分类: cs.LG, eess.SP
发布日期: 2026-09-28
备注: 14 pages, 9 figures
💡 一句话要点
提出多模态自主感知框架以客观评估牙髓刺激下患者反应
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 多模态感知 自主信号 牙髓测试 深度学习 客观评估 电皮肤活动 心电图 疼痛管理
📋 核心要点
- 现有牙髓测试方法依赖患者主观反馈,难以准确评估疼痛程度,存在个体差异和沟通障碍。
- 本文提出了一种多模态自主感知框架,结合心电图、皮肤电活动等信号,通过深度学习模型实现对患者反应的客观评估。
- 实验结果表明,该框架在二分类任务中取得了80.2%的平衡准确率,显示出较强的分类能力,尤其是EDA信号对模型性能的贡献显著。
📝 摘要(中文)
患者对牙髓测试的反应,从无感觉到剧烈疼痛,提供了重要的牙髓状态评估信息。然而,疼痛是一种主观的感官和情感体验,因个体差异而难以传达。本文研究了补充的自主信号是否可以支持在牙科检查中对反应的客观评估。研究中,49名患者接受了冷牙髓测试,框架整合了心电图导出的皮肤神经活动(SKNA)和R-R间期(RRI),以及电皮肤活动(EDA),使用基于时间卷积网络的编码器和注意力中层融合。结果显示,该框架在无反应与轻度或强烈反应的二分类中达到了80.2%的平衡准确率,75.2%的灵敏度和85.2%的特异性。对于三类分类,平衡准确率为60.0%。这些发现支持了多模态自主感知在牙髓刺激反应的客观、非侵入性评估中的可行性。
🔬 方法详解
问题定义:本文旨在解决牙髓测试中患者反应的主观性问题,现有方法难以准确评估疼痛程度,且个体差异显著。
核心思路:通过整合多种自主信号(如SKNA、RRI和EDA),构建一个深度学习框架,以实现对患者反应的客观评估,减少主观因素的影响。
技术框架:框架包括数据采集、信号处理、特征提取和分类四个主要模块。使用时间卷积网络进行特征提取,并通过注意力机制进行中层融合,以提高分类性能。
关键创新:本研究的创新在于首次将多种自主信号结合使用,并通过深度学习方法实现对牙髓刺激反应的客观评估,显著提升了评估的准确性和可靠性。
关键设计:采用了基于时间卷积网络的编码器,结合注意力机制进行特征融合,模型训练中使用了适当的损失函数以优化分类性能,并考虑了个体基线信号和主观变量(如焦虑评分和性别)。
🖼️ 关键图片
📊 实验亮点
实验结果显示,该框架在无反应与轻度或强烈反应的二分类任务中达到了80.2%的平衡准确率,75.2%的灵敏度和85.2%的特异性。对于三类分类,平衡准确率为60.0%,表明该方法在客观评估患者反应方面具有显著优势。
🎯 应用场景
该研究的潜在应用领域包括牙科诊断和疼痛管理,能够为牙科医生提供更为客观的患者反应评估工具,提升临床决策的科学性和准确性。未来,该框架还可扩展至其他医疗领域,帮助实现更广泛的非侵入性生理信号监测与评估。
📄 摘要(原文)
Patient responses to dental pulp testing, ranging from no sensation to intense pain, provide important information for assessing pulp status in endodontic diagnosis. However, pain is a subjective sensory and emotional experience that varies considerably across individuals and can be difficult to communicate. We investigated whether complementary autonomic signals could support objective assessment of responses during dental examination. Forty-nine patients underwent cold pulp testing, yielding no-response, mild-response, and intense-response conditions. The framework integrated ECG-derived skin nerve activity (SKNA) and R-R intervals (RRI), together with electrodermal activity (EDA), using temporal convolutional network encoders with attention-based mid-level fusion. Individual baseline signals and subject-level covariates, including anxiety scores and biological sex, were also incorporated. The framework achieved 80.2% balanced accuracy, 75.2% sensitivity, and 85.2% specificity for binary classification of no response versus mild or intense response. For three-class classification, it achieved 60.0% balanced accuracy and a 58.8% macro-averaged F1 score. Ablation and attention-weight analyses indicated that EDA contributed most strongly to model performance, followed by RRI, while SKNA improved balanced accuracy by approximately five percentage points. Age was significantly associated with model performance. These findings support the feasibility of multimodal autonomic sensing for objective, non-invasive assessment of responses to dental pulp stimulation.