发表机构
University College Cork; INFANT Research Centre; University of Bonn Medical Centre; Helmholtz-Institute for Radiation and Nuclear Physics; Interdisciplinary Center for Complex Systems; Collège de France; University of Lisbon（科克大学学院; INFANT研究中心; 波恩大学医学中心; 亥姆霍兹辐射与核物理研究所; 复杂系统跨学科中心; 法兰西学院; 里斯本大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于临界转变的癫痫检测算法，通过ROC分析验证其性能，确定最优及通用参数，可接近专家水平，能辅助机器学习算法，适用于不同癫痫形态的啮齿类数据。
AI 中文摘要
现有大多数癫痫检测算法需要对数据进行大量预处理，且依赖启发式或目前无法解释的机器学习方法，这些方法在面对可变癫痫形态、发作间期癫痫样放电及伪迹时，往往难以平衡检测的灵敏度与特异度。本文提出一种替代方法：基于临界转变概念的癫痫检测算法，可克服上述局限。具体而言，通过受试者工作特征（ROC）分析，量化该算法与癫痫啮齿类动物不同癫痫形态发作电压记录中癫痫发作起始和终止时间的专家标注一致性；分析算法性能如何依赖参数及在不同啮齿类记录会话中的变化，为每个记录会话确定最优算法参数，多数情况下达到接近专家水平的性能；最终得到适用于所有记录会话的单一通用算法参数集，该算法在通用设置下仍保持高性能，展现出通用性、对不同癫痫形态的鲁棒性，以及补充机器学习算法的潜力。
英文摘要
Most existing seizure detection algorithms require extensive pre-processing of the data and rely on heuristic or currently unexplainable machine learning approaches. These approaches often struggle with balancing detection sensitivity and specificity in the presence of variable seizure morphologies, interictal epileptiform discharges, and artefacts. Here, we consider an alternative approach: our seizure detection algorithm, which is based on the concept of critical transitions and overcomes the aforementioned limitations. Specifically, we perform a receiver-operating-characteristic analysis to quantify the performance of our algorithm in terms of its agreement with expert annotations of seizure onset and offset times in the voltage recordings of seizure activity in epileptic rodents with different seizure morphologies. We demonstrate how performance depends on algorithm parameters and varies across different rodent recording sessions. We determine the optimal set of algorithm parameters for each recording session, with near expert-level performance achieved in most cases. Finally, we derive a single general set of algorithm parameters applicable across all recording sessions. The algorithm maintains its high performance in this general setting, demonstrating its versatility, robustness across varying seizure morphologies, and potential to complement machine learning algorithms.
