|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/cdss2
课程评论：没有评论
课程名称：电子健康记录中的深度学习 - CDSS 2 课程概述：本课程概述了深度学习的主要原理及常见架构，重点探讨了如何将问题表述为时间序列分类，并应用于如心电图（ECG）等生命体征。由于电子健康记录（EHR）中存在缺失值和异质性（包括连续、序数和类别变量），因此在应用这些方法时会面临挑战。课程还探讨了插补技术和不同的编码策略来解决这些问题，并应用这些方法来制定基于MIMIC-III数据库中可用信息的临床预测基准。 课程大纲： 第一部分：人工智能与多层感知器 本周将概述深度学习的历史及流行的平台，并讨论多层感知器（MLP）网络及其常见的激活函数、损失函数和优化算法。通过实践练习，学生将优化和评估用于心电图分类的MLP。 第二部分：卷积神经网络与递归神经网络 本周讨论卷积神经网络（CNNs）的优势以及其在图像处理中的革命性贡献，并实现CNN用于时间序列分类。同时介绍递归神经网络（RNNs），特别是长短期记忆网络（LSTM）和门控递归单元网络（GRU）。强调训练、验证和测试数据集的重要性，以避免过拟合并进行模型评估。 第三部分：MIMIC III数据的预处理与插补 基于MIMIC-III数据库开发DNN的基准数据集涉及多个步骤，包括队列选择、单位转换、异常值去除和时间窗口内的数据聚合。这些步骤将EHR表示为时间序列数据，但也容易出现缺失数据。因此，课程将介绍基于传统和深度学习技术的插补策略，学生将有机会预处理EHR并训练深度学习模型来预测院内死亡率。 第四部分：机器学习模型的EHR编码 EHR包括类别、序数和连续变量。适当的数据表示至关重要，因为编码会影响预测性能。本周将包括几种不同的数据编码策略，如目标编码、深度学习编码和相似性编码。特别将演示自编码器，这是一种深度学习架构，用于在低维空间中表示数据，并应用于院内死亡率的预测。
Part: 1
Title:Artificial Intelligence and Multi-Layer Perceptron
Description:This week includes an overview of deep learning history and popular deep learning platforms. Subsequently, Multi-Layer Perceptron (MLP) Networks are discussed along with common activation functions, loss functions and optimisation algorithms. Finally, the practical exercises will allow to optimise and evaluate MLP in ECG classification.
Part: 2
Title:Convolutional and Recurrent Neural Networks.
Description:Convolutional Neural Networks (CNNs) revolutionised the way we process images and they contributed significantly in deep learning success. This week we are going to discuss what advantages CNNs offer over MLP and we will implement CNNs for time-series classifications. Subsequently, we are going to present Recurrent Neural Networks (RNNs). In particular, we are going to discuss Long-Short Term Memory Networks and Gated Recurrent Unit Networks. Practical exercises will allow to design and train all these types of networks in ECG classification. The importance of training, validation and testing datasets will be emphasised for avoiding overfitting and model evaluation.
Part: 3
Title:Preprocessing and imputation of MIMIC III data
Description:Developing benchmark datasets for DNNs based on MIMIC-III database involves several steps that include cohort selection, unit conversion, outlier removal and aggregation of data within time windows. The later step allows to represent EHR as time-series data but it is also susceptible to missing data. For this reason imputation strategies both based on traditional and deep learning techniques are presented. The learner will have the opportunity to preprocess EHR and train deep learning models in predicting in-hospital mortality.
Part: 4
Title:EHR Encodings for machine learning models
Description:EHRs include categorical, ordinal and continuous variables. Appropriate data representation is important and encodings affect prediction performance. This week includes several different strategies to encode the data such as target encodings, deep learning encodings and similarity encodings. In particular, autoencoders which is a deep learning architecture to represent data in lower dimensional space will be demonstrated and applied in in-hospital mortality prediction.
Overview of the main principles of Deep Learning along with common architectures. Formulate the problem for time-series classification and apply it to vital signals such as ECG. Applying this methods in Electronic Health Records is challenging due to the missing values and the heterogeneity in EHR, which include both continuous, ordinal and categorical variables. Subsequently, explore imputation techniques and different encoding strategies to address these issues. Apply these approaches to formulate clinical prediction benchmarks derived from information available in MIMIC-III database.
