Machine learning with generative mixture models for fetal monitoring

用于胎儿监测的生成混合模型的机器学习

• 批准号: 8816208
• 负责人: Petar M Djuric
• 金额: $ 23.46万
• 依托单位: STATE UNIVERSITY NEW YORK STONY BROOK
• 依托单位国家: 美国
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-03-01 至 2017-02-28
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8816208
• 关键词: Agreement; Algorithms; Apgar Score; Bayesian Method; Behavioral; Birth; Categories; Childbirth; Classification; Clinical; Communities; Consensus; Data; Data Set; Decision Support Systems; Delivery Rooms; Dependence; Dependency; Diagnosis; Diagnostic; Distress; Electrodes; Evolution; Feedback; Fetal Heart; Fetal Heart Rate; Fetal Monitoring; Fetus; Freedom; Gold; Individual; Intraobserver Variability; Joints; Knowledge; Label; Learning; Litigation; Machine Learning; Measurement; Methodology; Methods; Modeling; Monitor; Monte Carlo Method; Mothers; Motivation; Noise; Outcome; Outcome Measure; Output; Pattern; Performance; Phase; Physicians; Probability; Procedures; Process; Reading; Records; Research; Risk; Sampling; Scalp structure; Series; Signal Transduction; System; Testing; Time; Training; Umbilical cord structure; Uncertainty; Uterine Contraction; Validation; Work; base; cost; fetal; improved; interest; pressure; public health relevance; stem; theories; vector

DESCRIPTION (provided by applicant): For many years, there has been a concerted effort to automate the analysis of fetal heart rate (FHR) rhythms. However, despite significant advances in biomedical signal analysis, there has not been any significant improvement in automated decision support systems. FHR monitoring is now ubiquitous throughout delivery rooms, especially using the non-invasive Doppler monitor, but also using the fetal scalp electrode. Physician classification of fetal heart rate patterns is known to be a non-trivial problem because of significant inter and intra-observer variability of diagnosis. This has led to a marked increase in the number of caesarean deliveries, thereby increasing risk to the fetus and mother in many cases. This has further motivated the machine learning community to automate the classification procedure in the interest of accuracy and consistency as well as robustness with respect to noise. Usual approaches to this involve some type of supervised classification procedure, where the algorithm output on training data is compared with a "gold-standard" physician classification, followed by testing and validation on new datasets. However, since physician classification can be unreliable in the presence of the aforementioned diagnostic variability, as well as significant tracing noise, we propose the use of unsupervised algorithms to cluster FHR data records into clinically useful categories. We use nonparametric Bayes theory and Markov-time-dependence models for the evolution of feature sequences to propose methods that will achieve improved accuracy. The methods involve extraction of feature sequences from FHR time series data, which are modeled as samples from finite or infinite Dirichlet mixture models. We then use Gibbs sampling to obtain the cluster probabilities for each dataset. Clustering outcomes are compared against direct physician diagnosis and our current results are seen to be in broad agreement with them, while still giving new information on the character of different sub-groups of FHR records. With the proposed research, further gains in classification performance will be made.

描述（由申请人提供）：多年来，人们一直在努力实现胎儿心率（FHR）节律分析的自动化。然而，尽管生物医学信号分析取得了重大进展，但自动化决策支持系统却没有任何重大改进。胎心率监测现在在整个产房中无处不在，特别是使用非侵入性多普勒监测仪，但也使用胎儿头皮电极。众所周知，医生对胎儿心率模式的分类是一个不小的问题，因为观察者之间和观察者内部的诊断差异很大。这导致了显着增加 剖腹产的数量，从而在许多情况下增加了胎儿和母亲的风险。这进一步促使机器学习社区自动化分类过程，以提高准确性、一致性以及对噪声的鲁棒性。通常的方法涉及某种类型的监督分类程序，其中将训练数据的算法输出与“黄金标准”医生分类进行比较，然后对新数据集进行测试和验证。然而，由于在存在上述诊断变异性以及显着的跟踪噪声的情况下医生分类可能不可靠，因此我们建议使用无监督算法来 将 FHR 数据记录聚类为临床有用的类别。我们使用非参数贝叶斯理论和马尔可夫时间依赖性模型来进行特征序列的演化，以提出提高准确性的方法。这些方法涉及从胎心率时间序列数据中提取特征序列，这些数据被建模为来自有限或无限狄利克雷混合模型的样本。然后，我们使用吉布斯采样来获取每个数据集的聚类概率。将聚类结果与医生的直接诊断进行比较，我们目前的结果被认为与它们广泛一致，同时仍然提供了有关胎心率记录不同亚组特征的新信息。通过所提出的研究，分类性能将进一步提高。