Ce cours fait partie de la Spécialisation Informed Clinical Decision Making using Deep Learning

Fani Deligianni

Offert par

Spécialisation Informed Clinical Decision Making using Deep LearningUniversity of Glasgow

À propos de ce cours

3 526 consultations récentes

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. 
The schema and International Classification of Diseases coding is important to understand how to map research questions to data and how to extract key clinical outcomes in order to develop clinically useful machine learning algorithms.

Dates limites flexibles

Réinitialisez les dates limites selon votre disponibilité.

Certificat partageable

Obtenez un Certificat lorsque vous terminez

100 % en ligne

Commencez dès maintenant et apprenez aux horaires qui vous conviennent.

Cours 1 sur 5 dans le

Spécialisation Informed Clinical Decision Making using Deep Learning

Niveau intermédiaire

Basic background in sql/postgres queries is required along with knowledge in python programming and packages such as numpy, scipy and matplotlib.

Approx. 21 heures pour terminer

Anglais

Sous-titres : Anglais

Ce que vous allez apprendre

Understand the Schema of publicly available EHR databases (MIMIC-III)

Recognise the International Classification of Diseases (ICD) use

Extract and visualise descriptive statistics from clinical databases

Understand and extract key clinical outcomes such as mortality and stay of length

Compétences que vous acquerrez

International Classification of Diseases
mining clinical databases
Descriptive Statistics
Electronic Health Records
Ethics in EHR

Dates limites flexibles

Réinitialisez les dates limites selon votre disponibilité.

Certificat partageable

Obtenez un Certificat lorsque vous terminez

100 % en ligne

Commencez dès maintenant et apprenez aux horaires qui vous conviennent.

Cours 1 sur 5 dans le

Spécialisation Informed Clinical Decision Making using Deep Learning

Niveau intermédiaire

Basic background in sql/postgres queries is required along with knowledge in python programming and packages such as numpy, scipy and matplotlib.

Approx. 21 heures pour terminer

Anglais

Sous-titres : Anglais

Enseignant

Fani Deligianni

School of Computing Science

446 étudiants

5 cours

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.

We are a member of the prestigious Russell Group of leading UK Universities with annual research income of more than £179m. The University’s #TeamUofG community is truly international with over 8000 staff and 28,0000 students from from more than 140 countries. A 2019 Time Out survey placed Glasgow in the top ten cities in the world. Ranked between Berlin and Paris, Glasgow was voted number one for both friendliness and affordability. Right now our dedicated community of staff, students and alumni is working to address the challenges of Covid-19 and understand how we can make life safer for everyone.

Programme de cours : ce que vous apprendrez dans ce cours

Semaine

Semaine 1

5 heures pour terminer

Electronic Health Records and Public Databases

This module 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.

5 heures pour terminer

6 vidéos (Total 53 min), 9 lectures, 1 quiz

6 vidéos

Welcome to Informed Clinical Decision Making Specialisation1 min

Welcome to the course1 min

Big Data in Healthcare20 min

EHR System in the UK and USA12 min

MIMIC Critical Care Dataset: The Impact7 min

Data Usage Requirements9 min

9 lectures

Specialization and course structure10 min

Meet the team10 min

Standardized electronic health record data10 min

Migrating to electronic health record systems1h 30min

The Belmont Report1 h

Hardware requirements5 min

Obtaining access to the MIMIC-III Dataset10 min

Complete CITI course 10 min

MIMIC III - installation instructions5 min

1 exercice pour s'entraîner

Week 1 Summary Quiz30 min

Semaine

Semaine 2

6 heures pour terminer

MIMIC III as a relational database

This week includes a discussion of the basic structure of MIMIC III database and practical exercises on how to extract and visualise summary statistics. We will understand the difficulty in defining clinical outcomes and we are going to examine clinical variables related to a specific patient.

6 heures pour terminer

5 vidéos (Total 65 min), 7 lectures, 1 quiz

5 vidéos

MIMIC-III Data Linkage10 min

MIMIC-III as a Relational Database12 min

MIMIC-III - Descriptive Statistics16 min

Mortality and Length of Stay in MIMIC10 min

Vital Signs Extraction for a Single Patient15 min

7 lectures

MIMIC-III, a freely accessible critical care database1 h

Practical Exercise: Extract heart rate data using Postgres and Python30 min

Practical Exercise: Extract hospitalisation numbers using Postgres and Python30 min

Practical Exercise: Extract age and gender using Postgres and Python30 min

Practical Exercise: Extract mortality numbers using Postgres and Python30 min

Practical Exercise: Extract length of stay numbers using Postgres and Python30 min

Practical Exercise: Extract vital data from a single patient using Postgres and Python30 min

1 exercice pour s'entraîner

Week 2 Summary quiz30 min

Semaine

Semaine 3

5 heures pour terminer

International Classification of Disease System

This week discusses the history of the International Classification of Diseases (ICD) system, which has been developed collaboratively so that the medical terms and information in death certificates can be grouped together for statistical purposes. Practical examples shows how to extract ICD-9 codes from MIMIC III database and visualise them. Furthermore, we discuss differences between ICD-9, ICD-10 and ICD-11 systems.

5 heures pour terminer

5 vidéos (Total 53 min), 6 lectures, 1 quiz

5 vidéos

Introduction to International Classification of Disease System11 min

Evolution of the ICD System12 min

ICD-9 and MIMIC-III10 min

From ICD-9 to ICD-1012 min

Special Signs in ICD-106 min

6 lectures

WHO and Health Statistics40 min

History of the ICD10 min

Practical Exercise: Extract patients' height using Postgres and Python15 min

Practical Exercise: Extract table with days in ICU using Postgres and Python15 min

Practical Exercise: Extract Glasgow Coma Scale using Postgres and Python30 min

Practical Exercise: Extract ICD-9 related information using Postgres and Python1h 30min

1 exercice pour s'entraîner

Week 3 summary quiz30 min

Semaine

Semaine 4

5 heures pour terminer

Concepts in MIMIC-III and an example of patients inclusion flowchart

This week includes an overview of clinical concepts, which are statistical tools to provide illness scores. They are developed based on expert opinion and subsequently extended based on data-driven methods. These models are the precursor of machine learning models for precision medicine. Finally, the practical exercises of this week provides the opportunity to implement a complex flowchart of patients inclusion.

5 heures pour terminer

3 vidéos (Total 42 min), 11 lectures, 2 quiz

3 vidéos

Concepts in MIMIC III14 min

Relation of Catheterization to Mortality: An Example Study10 min

Data Extraction17 min

11 lectures

The MIMIC Code Repository: enabling reproducibility 10 min

The Association Between Indwelling Arterial Catheters and Mortality in Hemodynamically Stable30 min

Practical Exercise: Extract vital data of MIMIC-III using Postgres and Python20 min

Practical Exercise: Exclude ICU readmissions from the study using Postgres and Python20 min

Practical Exercise: Select patients requiring mechanical ventilation using Postgres and Python2 min

Practical Exercise: Exclude patients diagnosed with sepsis from the study using Postgres and Python20 min

Practical Exercise: Exclude patients requiring vasopressors from the study using Postgres and Python20 min

Practical Exercise: Exclude patients with a prior IAC placement from the study using Postgres and Python20 min

Practical Exercise: Exclude patients admitted to the CSRU or CCU care units from the study using Postgres and Python20 min

Practical Exercise: Combine all criteria and split the cohort in groups using Postgres and Python20 min

Practical Excercise: Visualise IAC groups10 min

2 exercices pour s'entraîner

Week 4 summary quiz30 min

End of course summative quiz30 min

À propos du Spécialisation Informed Clinical Decision Making using Deep Learning

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.

Informed Clinical Decision Making using Deep Learning

Foire Aux Questions

Quand aurai-je accès aux vidéos de cours et aux devoirs ?
L’accès à des vidéos de cours et des devoirs dépend de votre type d’inscription. Si vous suivez un cours en mode auditeur libre, vous pourrez voir la plupart des contenus de cours gratuitement. Pour accéder aux devoirs notés et obtenir un certificat, vous devrez acheter une expérience de certificat, pendant ou après avoir assister au cours en tant qu’auditeur libre. Si vous ne visualisez pas l’option auditeur libre :
Il est possible que le cours ne propose pas d’option auditeur libre. Vous pouvez en revanche accéder à un essai gratuit ou faire une demande d'aide financière.
Le cours propose peut-être « Cours complet, aucun certificat » à la place. Cette option vous permet de voir tous les contenus de cours, de soumettre les évaluations requises et d'obtenir une note finale. Cependant, vous ne pourrez pas acheter une expérience de certificat.
À quoi ai-je droit si je m'abonne à cette Spécialisation ?
Lorsque vous vous inscrivez au cours, vous bénéficiez d'un accès à tous les cours de la Spécialisation, et vous obtenez un Certificat lorsque vous avez réussi. Votre Certificat électronique est alors ajouté à votre page Accomplissements. À partir de cette page, vous pouvez imprimer votre Certificat ou l'ajouter à votre profil LinkedIn. Si vous souhaitez seulement lire et visualiser le contenu du cours, vous pouvez accéder gratuitement au cours en tant qu'auditeur libre.
Une aide financière est-elle possible ?
Oui. Dans certains programmes d’apprentissage, vous pouvez demander une aide financière ou une bourse d’études si vous ne pouvez pas payer les frais d’inscription. Si une aide financière ou une bourse d’études est disponible pour le programme d’apprentissage choisi, vous trouverez un lien pour faire une demande sur la page de description.

D'autres questions ? Visitez le Centre d'Aide pour les Étudiants.

Data mining of Clinical Databases - CDSS 1