Department of Biomedical Engineering, California State University, Long Beach, CA.
Department of Computer Engineering and Computer Science, California State University, Long Beach, CA.
Crit Care Med. 2019 Nov;47(11):e880-e885. doi: 10.1097/CCM.0000000000003966.
Continuous assessment of physiology after traumatic brain injury is essential to prevent secondary brain insults. The present work aims at the development of a method for detecting physiologic states associated with the outcome from time-series physiologic measurements using a hidden Markov model.
Unsupervised clustering of hourly values of intracranial pressure/cerebral perfusion pressure, the compensatory reserve index, and autoregulation status was attempted using a hidden Markov model. A ternary state variable was learned to classify the patient's physiologic state at any point in time into three categories ("good," "intermediate," or "poor") and determined the physiologic parameters associated with each state.
The proposed hidden Markov model was trained and applied on a large dataset (28,939 hr of data) using a stratified 20-fold cross-validation.
The data were collected from 379 traumatic brain injury patients admitted to Addenbrooke's Hospital, Cambridge between 2002 and 2016.
Retrospective observational analysis.
Unsupervised training of the hidden Markov model yielded states characterized by intracranial pressure, cerebral perfusion pressure, compensatory reserve index, and autoregulation status that were physiologically plausible. The resulting classifier retained a dose-dependent prognostic ability. Dynamic analysis suggested that the hidden Markov model was stable over short periods of time consistent with typical timescales for traumatic brain injury pathogenesis.
To our knowledge, this is the first application of unsupervised learning to multidimensional time-series traumatic brain injury physiology. We demonstrated that clustering using a hidden Markov model can reduce a complex set of physiologic variables to a simple sequence of clinically plausible time-sensitive physiologic states while retaining prognostic information in a dose-dependent manner. Such states may provide a more natural and parsimonious basis for triggering intervention decisions.
创伤性脑损伤后持续评估生理学对于预防继发性脑损伤至关重要。本研究旨在开发一种使用隐马尔可夫模型从时间序列生理学测量中检测与结果相关的生理状态的方法。
使用隐马尔可夫模型尝试对颅内压/脑灌注压、代偿储备指数和自动调节状态的每小时值进行无监督聚类。学习一个三态变量将患者的生理状态在任何时间点分类为三个类别（“良好”、“中等”或“差”），并确定与每个状态相关的生理参数。
使用分层 20 折交叉验证，在一个大型数据集（28939 小时的数据）上对提出的隐马尔可夫模型进行了训练和应用。
数据来自于 2002 年至 2016 年期间在剑桥 Addenbrooke 医院收治的 379 名创伤性脑损伤患者。
回顾性观察性分析。
隐马尔可夫模型的无监督训练产生了具有颅内压、脑灌注压、代偿储备指数和自动调节状态特征的状态，这些状态在生理学上是合理的。所得分类器保留了剂量依赖性的预后能力。动态分析表明，隐马尔可夫模型在短时间内是稳定的，与创伤性脑损伤发病机制的典型时间尺度一致。
据我们所知，这是首次将无监督学习应用于多维时间序列创伤性脑损伤生理学。我们证明，使用隐马尔可夫模型进行聚类可以将一组复杂的生理变量简化为一组简单的临床合理的时间敏感生理状态，同时以剂量依赖的方式保留预后信息。这些状态可能为触发干预决策提供更自然和简约的基础。
