Seizure forecasting using machine learning models trained by seizure diaries.
Seizure forecasting using machine learning models trained by seizure diaries.
复制标题
DOI：
10.1088/1361-6579/aca6ca
复制
发表时间：
2022-12-14
影响因子：
3.2
通讯作者：
中科院分区：
文献类型：
--
作者：
难治性癫痫患者被下一次癫痫发作的不确定性所淹没。对未来癫痫发作的准确预测可以极大地提高这些患者的生活质量。新的证据表明，某些患者的癫痫发作可能具有周期性模式。尽管这些周期性不是直观的，但它们可以通过机器学习(ML)来识别，以识别具有可预测和不可预测癫痫模式的患者。使用人类癫痫项目153例患者的自我报告癫痫发作记录，其中超过3次报告发作(总计8337次发作)，以获得发作间隔时间序列，用于训练和评估预测模型。研究了两类预测方法：1)基于贝叶斯融合总体和个体发作模式的统计方法；2)基于最小二乘、最小绝对收缩和选择算子、支持向量机回归和长短期记忆回归的最大似然算法。训练和评价采用一人出局交叉验证，方法是对除一名受试者外的所有受试者的癫痫日记进行培训，并对遗漏的受试者进行测试。主要的预测模型是支持向量机回归和一种统计模型，该模型结合了总体癫痫发作时间间隔的中位数和受试者先前的癫痫发作间隔。支持向量机能够在0、1、2、3~4天的平均绝对预测误差内分别预测50%、70%、81%、84%和87%的未见对象癫痫发作。受试者的表现表明，癫痫发作频率越高的患者通常预测得越好。ML模型可以利用自我报告的癫痫日记中的非随机模式来预测未来的癫痫发作。虽然仅基于日记的癫痫发作预测只是癫痫患者临床护理的许多方面之一，但研究癫痫发作和患者的可预测性水平有助于更好地了解个性化和按人群分类的可预测癫痫发作和不可预测癫痫发作。
People with refractory epilepsy are overwhelmed by the uncertainty of their next seizures. Accurate prediction of future seizures could greatly improve the quality of life for these patients. New evidence suggests that seizure occurrences can have cyclical patterns for some patients. Even though these cyclicalities are not intuitive, they can be identified by machine learning (ML), to identify patients with predictable vs unpredictable seizure patterns. Self-reported seizure logs of 153 patients from the Human Epilepsy Project with more than three reported seizures (totaling 8,337 seizures) were used to obtain inter-seizure interval time-series for training and evaluation of the forecasting models. Two classes of prediction methods were studied: 1) statistical approaches using Bayesian fusion of population-wise and individual-wise seizure patterns; and 2) ML-based algorithms including least squares, least absolute shrinkage and selection operator, support vector machine (SVM) regression, and long short-term memory regression. Leave-one-person-out cross-validation was used for training and evaluation, by training on seizure diaries of all except one subject and testing on the left-out subject. The leading forecasting models were the SVM regression and a statistical model that combined the median of population-wise seizure time-intervals with a test subject’s prior seizure intervals. SVM was able to forecast 50%, 70%, 81%, 84%, and 87% of seizures of unseen subjects within 0, 1, 2, 3 to 4 days of mean absolute forecasting error, respectively. The subject-wise performances show that patients with more frequent seizures were generally better predicted. ML models can leverage non-random patterns within self-reported seizure diaries to forecast future seizures. While diary-based seizure forecasting alone is only one of many aspects of clinical care of patients with epilepsy, studying the level of predictability across seizures and patients paves the path towards a better understanding of predictable vs unpredictable seizures on individualized and population-wise bases.
登录
查看更多内容
影响因子：
5.6
作者：
Karoly, Philippa J.;Cook, Mark J.;Freestone, Dean R.
通讯作者：
Freestone, Dean R.
影响因子：
2.6
作者：
Pavlova, MK;Shea, SA;Bromfield, EB
通讯作者：
Bromfield, EB
影响因子：
2.6
作者：
Schulze-Bonhage, Andreas;Sales, Francisco;Ihle, Matthias
通讯作者：
Ihle, Matthias
影响因子：
5.3
作者：
Goldenholz, Daniel M.;Goldenholz, Shira R.;Theodore, William H.
通讯作者：
Theodore, William H.
影响因子：
14.5
作者：
Karoly, Philippa J.;Freestone, Dean R.;Cook, Mark J.
通讯作者：
Cook, Mark J.