Apply Deep Learning in Electronic Health Records. Understand the road path from data mining of clinical databases to clinical decision support systems
This specialisation is for learners with experience in programming that are interested in expanding their skills in applying deep learning in Electronic Health Records and with a focus on how to translate their models into Clinical Decision Support Systems.
The main areas that would explore are:
Data mining of Clinical Databases: Ethics, MIMIC III database, International Classification of Disease System and definition of common clinical outcomes.
Deep learning in Electronic Health Records: From descriptive analytics to predictive analytics
Explainable deep learning models for healthcare applications: What it is and why it is needed
Clinical Decision Support Systems: Generalisation, bias, ‘fairness’, clinical usefulness and privacy of artificial intelligence algorithms.
Applied Learning Project
Learners have the opportunity to choose and undertake an exercise based on MIMIC-III extracted datasets that combines knowledge from:
Data mining of Clinical Databases to query the MIMIC database
Deep learning in Electronic Health Records to pre-process EHR and build deep learning models
Explainable deep learning models for healthcare to explain the models decision
Learners can choose from:
1. Permutation feature importance on the MIMIC critical care database
The technique is applied both on logistic regression and on an LSTM model. The explanations derived are global explanations of the model.
2. LIME on the MIMIC critical care database
The technique is applied on both logistic regression and an LSTM model. The explanations derived are local explanations of the model.
3. Grad-CAM on the MIMIC critical care database
GradCam is implemented and applied on an LSTM model that predicts mortality. The explanations derived are local explanations of the model.