- Deep Learning
- Machine Learning
- Explainable Machine Learning
- processing electronic health records
- clinical decision support systems
- International Classification of Diseases
- mining clinical databases
- Descriptive Statistics
- Electronic Health Records
- Ethics in EHR
- preprocessing of EHR and imputation
- Convolutional Neural Network
Spécialisation Informed Clinical Decision Making using Deep Learning
Apply Deep Learning in Electronic Health Records. Understand the road path from data mining of clinical databases to clinical decision support systems
Offert par
Spécialisation Informed Clinical Decision Making using Deep LearningUniversity of Glasgow Ce que vous allez apprendre
Extract and preprocess data from complex clinical databases
Apply deep learning in Electronic Health Records
Imputation of Electronic Health Records and data encodings
Explainable, fair and privacy-preserved Clinical Decision Support Systems
Compétences que vous acquerrez
À propos de ce Spécialisation
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.
Projet d'apprentissage appliqué
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.
Certificat partageable
Obtenez un Certificat lorsque vous terminez
Cours en ligne à 100 %
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Planning flexible
Définissez et respectez des dates limites flexibles.
Niveau intermédiaire
Last year undergraduate or master students of computing science or engineering. Basic knowledge on SQL queries and python is required.
Approximativement 5 mois pour terminer
Rythme recommandé de 5 heures/semaine
Anglais
Sous-titres : Anglais
Certificat partageable
Obtenez un Certificat lorsque vous terminez
Cours en ligne à 100 %
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Planning flexible
Définissez et respectez des dates limites flexibles.
Niveau intermédiaire
Last year undergraduate or master students of computing science or engineering. Basic knowledge on SQL queries and python is required.
Approximativement 5 mois pour terminer
Rythme recommandé de 5 heures/semaine
Anglais
Sous-titres : Anglais
Comment fonctionne la Spécialisation
Suivez les cours
Une Spécialisation Coursera est une série de cours axés sur la maîtrise d'une compétence. Pour commencer, inscrivez-vous directement à la Spécialisation ou passez en revue ses cours et choisissez celui par lequel vous souhaitez commencer. Lorsque vous vous abonnez à un cours faisant partie d'une Spécialisation, vous êtes automatiquement abonné(e) à la Spécialisation complète. Il est possible de terminer seulement un cours : vous pouvez suspendre votre formation ou résilier votre abonnement à tout moment. Rendez-vous sur votre tableau de bord d'étudiant pour suivre vos inscriptions aux cours et vos progrès.
Projet pratique
Chaque Spécialisation inclut un projet pratique. Vous devez réussir le(s) projet(s) pour terminer la Spécialisation et obtenir votre Certificat. Si la Spécialisation inclut un cours dédié au projet pratique, vous devrez terminer tous les autres cours avant de pouvoir le commencer.
Obtenir un Certificat
Lorsque vous aurez terminé tous les cours et le projet pratique, vous obtiendrez un Certificat que vous pourrez partager avec des employeurs éventuels et votre réseau professionnel.
Cette Spécialisation compte 5 cours
Data mining of Clinical Databases - CDSS 1
This course will introduce MIMIC-III, which is the largest publicly Electronic Health Record (EHR) database available to benchmark machine learning algorithms. In particular, you will learn about the design of this relational database, what tools are available to query, extract and visualise descriptive analytics.
Deep learning in Electronic Health Records - CDSS 2
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.
Explainable deep learning models for healthcare - CDSS 3
This course will introduce the concepts of interpretability and explainability in machine learning applications. The learner will understand the difference between global, local, model-agnostic and model-specific explanations. State-of-the-art explainability methods such as Permutation Feature Importance (PFI), Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanation (SHAP) are explained and applied in time-series classification. Subsequently, model-specific explanations such as Class-Activation Mapping (CAM) and Gradient-Weighted CAM are explained and implemented. The learners will understand axiomatic attributions and why they are important. Finally, attention mechanisms are going to be incorporated after Recurrent Layers and the attention weights will be visualised to produce local explanations of the model.
Clinical Decision Support Systems - CDSS 4
Machine learning systems used in Clinical Decision Support Systems (CDSS) require further external validation, calibration analysis, assessment of bias and fairness. In this course, the main concepts of machine learning evaluation adopted in CDSS will be explained. Furthermore, decision curve analysis along with human-centred CDSS that need to be explainable will be discussed. Finally, privacy concerns of deep learning models and potential adversarial attacks will be presented along with the vision for a new generation of explainable and privacy-preserved CDSS.
Offert par
University of Glasgow
The University of Glasgow has been changing the world since 1451. It is a world top 100 university (THE, QS) with one of the largest research bases in the UK.
Foire Aux Questions
Quelle est la politique de remboursement ?
Puis-je m'inscrire à un seul cours ?
Une aide financière est-elle possible ?
Puis-je suivre le cours gratuitement ?
Ce cours est-il vraiment accessible en ligne à 100 % ? Dois-je assister à certaines activités en personne ?
Quelle est la durée nécessaire pour terminer la Spécialisation ?
What background knowledge is necessary?
Do I need to take the courses in a specific order?
Puis-je obtenir des crédits universitaires si je réussis la Spécialisation ?
What will I be able to do upon completing the Specialization?
D'autres questions ? Visitez le Centre d'Aide pour les Étudiants.
