Sleep spindles are distinct electroencephalogram (EEG) patterns of brain activity that have been posited to play a critical role in development, learning, and neurological disorders. Manual scoring for sleep spindles is labor-intensive and tedious but could supplement automated algorithms to resolve challenges posed with either approaches alone. A Personalized Semi-Automatic Sleep Spindle Detection (PSASD) framework was developed to combine the strength of automated detection algorithms and visual expertise of human scorers. The underlying model in the PSASD framework assumes a generative model for EEG sleep spindles as oscillatory components, optimized to EEG amplitude, with remaining signals distributed into transient and low-frequency components. A single graphical user interface (GUI) allows both manual scoring of sleep spindles (model training data) and verification of automatically detected spindles. A grid search approach allows optimization of parameters to balance tradeoffs between precision and recall measures. PSASD outperformed DETOKS in F1-score by 19% and 4% on the DREAMS and P-DROWS-E datasets, respectively. It also outperformed YASA in F1-score by 25% in the P-DROWS-E dataset. Further benchmarking analysis showed that PSASD outperformed four additional widely used sleep spindle detectors in F1-score in the P-DROWS-E dataset. Titration analysis revealed that four 30-second epochs are sufficient to fine-tune the model parameters of PSASD. Associations of frequency, duration, and amplitude of detected sleep spindles matched those previously reported with automated approaches. Overall, PSASD improves detection of sleep spindles in EEG data acquired from both younger healthy and older adult patient populations.

中文翻译：

---

个性化半自动睡眠纺锤波检测（PSSD）框架

睡眠纺锤波是大脑活动的独特脑电图 (EEG) 模式，已被认为在发育、学习和神经系统疾病中发挥着关键作用。睡眠纺锤波的手动评分既费力又乏味，但可以补充自动化算法来解决单独使用这两种方法带来的挑战。开发了个性化半自动睡眠纺锤波检测 (PSSD) 框架，将自动检测算法的优势与人类评分员的视觉专业知识相结合。 PSASD 框架中的基础模型假设脑电图睡眠纺锤波的生成模型为振荡分量，并针对脑电图振幅进行了优化，其余信号分布为瞬态和低频分量。单个图形用户界面 (GUI) 允许对睡眠心轴（模型训练数据）进行手动评分并验证自动检测到的心轴。网格搜索方法允许优化参数以平衡精确度和召回率测量之间的权衡。在 DREAMS 和 P-DROWS-E 数据集上，PSASD 的 F1 分数比 DETOKS 分别高出 19% 和 4%。在 P-DROWS-E 数据集中，它的 F1 分数也比 YASA 高出 25%。进一步的基准分析表明，PSASD 在 P-DROWS-E 数据集中的 F1 分数方面优于另外四种广泛使用的睡眠纺锤波检测器。滴定分析表明，四个 30 秒的时期足以微调 PSASD 的模型参数。检测到的睡眠纺锤波的频率、持续时间和幅度的关联与之前用自动化方法报告的关联相匹配。总体而言，PSASD 改善了从年轻健康人群和老年患者群体中获取的脑电图数据中睡眠纺锤波的检测。