К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Deep Learning in Electronic Health Records · LearnSpace
Назад в каталог
courseraАнализ данных

Deep Learning in Electronic Health Records

Курс от University of Glasgow
Средний≈ 31.8 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

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.

Навыки, которые вы освоите

Data CleansingModel EvaluationAutoencodersDimensionality ReductionMedical RecordsElectocardiographyHealth InformaticsData PreprocessingDeep LearningPredictive ModelingModel OptimizationEmbeddingsApplied Machine LearningMachine Learning MethodsTime Series Analysis and ForecastingConvolutional Neural NetworksRecurrent Neural Networks (RNNs)Artificial Neural NetworksElectronic Medical Record

Программа курса

4 модулей · 71 учебных материалов

01Artificial Intelligence and Multi-Layer Perceptron19 материалов

Welcome

Welcome Video - Deep Learning in Electronic Health RecordsВидеоStay connected with UofG OnlineЧтение

Deep Learning and Artificial Intelligence

Deep Learning and Artificial IntelligenceВидеоArtificial IntelligenceЧтение

Учитесь у экспертов

Fani Deligianni

Dr

Deep Learning in Electronic Health Records
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 31.8 ч

4 модулей

Язык: Английский

Субтитры: Арабский, Французский, Итальянский, Бразильский португальский, Корейский, Немецкий, Испанский, Японский

Часть программы вашего университета

Training Multi-Layer Perceptron Networks

Multi-Layer PerceptronВидео
Training a Multi-Layer PerceptronВидео
Optimization of a Multi-Layer Perceptron (Part 1)Видео
Optimization of a Mutli-Layer Perceptrion (Part 2)Видео
Deep Learning for Health InformaticsЧтение

Multi-Layer Perceptron Networks for ECG Classification

Preprocessing of ECG SignalВидеоPractical Exercise: Pre-process ECG data for arrythmia detectionЧтениеPractical Exercise: Split and resample ECG dataЧтениеPractical Exercise: Classify beats using MLP and SVC models and the holdout beats validation protocolЧтение

End of Week 1

Week 1 summary quizЗаданиеWeek 1 - Your experienceОбсуждение

Week 1 - Interactive notebook examples

Pre-process ECG data for arrythmia detectionЛабораторнаяSplit and resample ECG dataЛабораторнаяClassification of beats using MLP and SVC models and beat holdout methodЛабораторнаяClassification of beats using MLP and SVC models and leave out patients methodЛабораторная
02Convolutional and Recurrent Neural Networks.16 материалов

Validation strategies of Machine Learning Models

Validation of Machine Learning ModelsВидеоEvaluating Learning Algorithms: AЧтениеPractical Exercise: Classify beats using MLP and SVC models and the leave out patients validation protocolЧтение

Convolutional Neural Networks in Time-Series Classification

Convolutional Neural NetworksВидеоPractical Exercise: Classify beats using a CNN and the beat holdout validation protocolЧтениеPractical Exercise: Classify beats using a CNN and the leave-out patients validation protocolЧтение

Recurrent Neural Networks in Time-Series Classification

Recurrent Neural NetworksВидеоPractical Exercise: Classify beats using an LSTM and the beat holdout validation protocolЧтениеPractical Exercise: Classify beats using an LSTM and the leave-out patients validation protocolЧтение

End of Week 2

End of week 2 quizЗаданиеWeek 2 - Your experienceОбсуждение

Week 2 - Interactive notebook examples

Classification of beats using a CNN model and the holdout beats validation protocolЛабораторнаяClassification of beats using a CNN model and the leave out patients validation protocolЛабораторнаяClassification of beats using an LSTM model and the holdout beats validation protocolЛабораторнаяClassification of beats using an LSTM model and the leave out patients validation protocolЛабораторнаяDimensionality reduction techniques to visualize ECG dataЛабораторная
03Preprocessing and imputation of MIMIC III data19 материалов

Data Extraction and Representation Pipeline

Benchmark Deep Learning Models with EHR - Part 1ВидеоA Data Extraction and Representation PipelineЧтениеPractical Exercise: Patients and time-series data extraction of MIMIC-IIIЧтение

In-hospital mortality prediction benchmark pipeline

Benchmark Deep Learning Models with EHR - Part 2ВидеоCreation of Benchmark data for DNNЧтениеPractical Exercise: Pre-processing of MIMIC-III datasetЧтениеPractical Exercise: One-hot encoding and in-hospital mortality predictionЧтениеPractical Exercise: in-hospital mortality prediction using one-hot encoding and undersamplingЧтение

Imputation Stategies

Imputation StrategiesВидеоPractical Exercise: Mean vs Joint modelling imputationЧтениеDeep Learning Imputation StrategiesВидеоImputation based on momentsЧтение

End of Week 3

End of week 3 quizЗаданиеWeek 3 - Your experienceОбсуждение

Week 3 - Interactive notebook examples

Study cohort selection and variable extractionЛабораторнаяImputation methods for in-hospital mortality predictionЛабораторнаяIn-hospital mortality prediction using one-hot encodingЛабораторнаяIn-hospital mortality prediction using one-hot encoding and undersamplingЛабораторнаяPre-processingЛабораторная
04EHR Encodings for machine learning models17 материалов

Target Encodings

Categorical and Continuous VariablesВидеоPractical Exercise: mean target encodingЧтениеPractical exercise: leave one out encodingЧтениеBayesian Target EncodingВидео

Natural Language Inspired Encodings

Encodings Inspired from NLPВидеоRepresentation Learning for Electronic Health RecordsЧтениеPractical Exercise: encoding using an autoencoderЧтение

Similarity Encodings

Other Types of EmbeddingsВидеоSimilarity EncodingsЧтение

End of Week 4

End of week 4 quizЗаданиеWeek 4 - Your experienceОбсуждение

Week 4 - Interactive notebook examples

In-hospital mortality prediction using an autoencoderЛабораторнаяIn-hospital mortality prediction using Bayesian target encodingЛабораторнаяIn-hospital mortality prediction using leave one out encodingЛабораторнаяIn-hospital mortality prediction using mean target encodingЛабораторная

Deep learning in Electronic Health Records - Summative Quiz

End of course summative quizЗаданиеKeeping Learning with UofG OnlineЧтение