We may earn an affiliate commission when you visit our partners.
Course image
Fani Deligianni

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.

Read more

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.

Enroll now

Two deals to help you save

What's inside

Syllabus

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. 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.
Read more
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.
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.
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.

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Taught by Fani Deligianni, who's recognized for their work in this topic
Suitable for researchers interested in benchmarking machine learning algorithms in healthcare
Examines the International Classification of Disease system, which is highly relevant in healthcare analytics
Teaches healthcare informatics, which is a growing field with many career opportunities
Provides practical exercises for implementing patient inclusion flowcharts, which is a valuable skill in clinical research
Emphasizes understanding clinical outcomes and their influence on developing machine learning algorithms, which is crucial for developing clinically useful AI solutions

Save this course

Save Data mining of Clinical Databases - CDSS 1 to your list so you can find it easily later:
Save

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Data mining of Clinical Databases - CDSS 1 with these activities:
Compile a list of resources on MIMIC-III
Create a comprehensive collection of resources on MIMIC-III, including documentation, tutorials, and research papers, to aid your learning and future reference.
Show steps
  • Search and gather relevant resources from online sources.
  • Organize the resources into categories or topics.
  • Create a document or spreadsheet to list and describe the resources.
Read 'Fundamentals of Clinical Data Science' by Mark van der Laan
Enhance your understanding of the theoretical foundations and practical applications of clinical data science, providing a strong basis for your work with MIMIC-III.
View Targeted Learning on Amazon
Show steps
  • Read and comprehend the key concepts and principles presented in the book.
  • Apply the knowledge gained to your analysis of MIMIC-III data.
Explore MIMIC-III dataset
Explore the MIMIC-III database using tools like the MIMIC Explorer to familiarize yourself with the data structure and content, which will enhance your understanding of the course material.
Show steps
  • Access MIMIC-III database using MIMIC Explorer
  • Explore different tables and variables within the database
  • Identify key clinical concepts and outcomes relevant to your research interests
Ten other activities
Expand to see all activities and additional details
Show all 13 activities
Discussion Forum Participation
Actively participate in the course discussion forum by asking questions, sharing insights, and engaging with peers. This will enhance your understanding of the course material and foster a sense of community.
Show steps
  • Review discussion topics and assigned readings
  • Post thoughtful questions and comments
  • Engage in respectful and constructive discussions with peers
Follow tutorials on using SQL with MIMIC-III
Gain hands-on experience in using SQL to query and manipulate data from MIMIC-III, empowering you to extract valuable insights efficiently.
Browse courses on SQL
Show steps
  • Find and access online tutorials or documentation on using SQL with MIMIC-III.
  • Follow the tutorials step-by-step, practicing the SQL queries and techniques.
  • Apply the acquired knowledge to your own data analysis tasks.
SQL Practice
Practice writing SQL queries to extract specific data from the MIMIC-III database. This will strengthen your understanding of the database structure and improve your ability to access and analyze the data effectively.
Show steps
  • Learn basic SQL commands for data selection, filtering, and aggregation
  • Write SQL queries to retrieve patient demographics, diagnoses, and outcomes
  • Utilize SQL functions to manipulate and analyze data
Review ICD coding
Sharpen your ICD coding skills to enhance your ability to extract clinical outcomes from the MIMIC-III database.
Show steps
  • Revisit the principles of ICD coding systems.
  • Practice assigning ICD codes to medical diagnoses and procedures.
  • Compare and contrast ICD-9, ICD-10, and ICD-11 coding systems.
Extract and visualize descriptive analytics
Gain proficiency in extracting and visualizing data from MIMIC-III to enhance your understanding of patient characteristics and outcomes.
Browse courses on Descriptive Analytics
Show steps
  • Identify relevant data fields and variables from the MIMIC-III database.
  • Use SQL or Python to extract the data into a structured format.
  • Create visualizations (e.g., charts, graphs) to represent the extracted data.
  • Interpret the visualizations to draw meaningful insights.
Data Visualization Project
Create data visualizations to explore and present insights from the MIMIC-III database. This will help you develop your analytical skills and communicate your findings effectively.
Browse courses on Data Visualization
Show steps
  • Identify a research question or hypothesis to investigate
  • Extract and analyze relevant data from MIMIC-III
  • Create data visualizations using tools like Tableau or Python
  • Interpret and present your findings in a clear and concise manner
Develop a patient inclusion flowchart
Create a flowchart to define specific criteria for patient inclusion in your research project, ensuring that the selected patients are relevant and representative.
Browse courses on Research Methodology
Show steps
  • Define the research question and objectives.
  • Identify the relevant patient population.
  • Establish inclusion and exclusion criteria.
  • Create a flowchart that visually represents the patient inclusion process.
  • Validate the flowchart with other researchers.
Kaggle Competition Participation
Participate in relevant Kaggle competitions to apply your knowledge and skills in a real-world setting. This will challenge you, foster collaboration, and provide opportunities for recognition.
Browse courses on Kaggle
Show steps
  • Identify Kaggle competitions aligned with course topics
  • Form a team or work individually
  • Develop and implement machine learning models
  • Submit your solutions and track your progress
Participate in a MIMIC-III challenge or competition
Put your MIMIC-III and machine learning skills to the test by participating in a challenge or competition, pushing your limits and showcasing your abilities.
Show steps
  • Identify and register for a relevant MIMIC-III challenge or competition.
  • Develop a strategy for solving the challenge.
  • Train and evaluate your machine learning model.
  • Submit your results and compete against other participants.
  • Analyze the results and learn from your experience.
Develop a machine learning model to predict patient outcomes
Apply your knowledge of MIMIC-III and machine learning to create a model that can predict patient outcomes, such as length of stay or risk of readmission.
Browse courses on Machine Learning
Show steps
  • Define the machine learning problem and identify the target variable.
  • Select and prepare the relevant data from MIMIC-III.
  • Choose and train a machine learning model.
  • Evaluate the model's performance and interpret the results.
  • Write a report or presentation summarizing your findings.

Career center

Learners who complete Data mining of Clinical Databases - CDSS 1 will develop knowledge and skills that may be useful to these careers:
Clinical Data Analyst
A Clinical Data Analyst uses data to improve patient care. This course's focus on extracting and visualizing descriptive analytics from large EHR databases would be extremely useful. Furthermore, this course can help a Clinical Data Analyst develop clinically useful machine learning algorithms.
Machine Learning Engineer
A Machine Learning Engineer designs, develops, and deploys machine learning models. This course introduces learners to the use of machine learning algorithms in the healthcare domain. Furthermore, this course can help a Machine Learning Engineer develop clinically useful machine learning algorithms.
Data Scientist
A Data Scientist uses scientific methods, processes, algorithms, and systems to extract knowledge and insights from data. This course introduces learners to the design and usage of the MIMIC-III database, a valuable resource for Data Scientists. Furthermore, this course can help a Data Scientist develop clinically useful machine learning algorithms.
Health Informatics Specialist
A Health Informatics Specialist uses information technology to improve healthcare. This course would be useful for a Health Informatics Specialist in understanding the design and usage of EHR databases. Furthermore, this course can help a Health Informatics Specialist develop clinically useful machine learning algorithms.
Principal Data Engineer
A Principal Data Engineer leads and manages a team of Data Engineers. This course would be of use to a Principal Data Engineer in understanding the design and usage of EHR databases, especially MIMIC-III. Furthermore, this course can help a Principal Data Engineer develop clinically useful machine learning algorithms.
Medical Informatics Specialist
A Medical Informatics Specialist uses information technology to improve healthcare. This course would be of use to a Medical Informatics Specialist in understanding the design and usage of EHR databases, especially MIMIC-III. Furthermore, this course can help a Medical Informatics Specialist develop clinically useful machine learning algorithms.
Principal Machine Learning Engineer
A Principal Machine Learning Engineer leads and manages a team of Machine Learning Engineers. This course would be of use to a Principal Machine Learning Engineer in understanding the design and usage of EHR databases, especially MIMIC-III. Furthermore, this course can help a Principal Machine Learning Engineer develop clinically useful machine learning algorithms.
Research Analyst
A Research Analyst conducts research to provide insights. This course introduces learners to the design and usage of EHR databases, especially MIMIC-III. This would be useful for a Research Analyst who wants to learn more about the healthcare domain.
Research Scientist
A Research Scientist conducts research in a specialized field. This course introduces learners to the design and usage of EHR databases, especially MIMIC-III. This would be useful for a Research Scientist who wants to learn more about the healthcare domain.
Database Administrator
A Database Administrator manages and maintains databases. This course would be useful for a Database Administrator who wants to learn more about the design of relational databases, specifically in the healthcare domain.
Statistician
A Statistician applies statistical methods to solve problems in various fields. This course introduces learners to the design and usage of EHR databases. This may be useful for a Statistician in understanding the data used in healthcare.
Quality Assurance Analyst
A Quality Assurance Analyst ensures that software meets quality standards. This course introduces learners to the design and usage of EHR databases. This may be useful for a Quality Assurance Analyst in understanding the data used in healthcare.
Biostatistician
A Biostatistician applies statistical methods to solve problems in biology, medicine, and other fields. This course would provide an introduction to analyzing Electronic Health Records' data to understand clinical outcomes. While this course focuses on machine learning, it would still be useful for a Biostatistician to handle large sets of EHR data.
Software Developer
A Software Developer designs, develops, and deploys software. This course introduces learners to the design and usage of EHR databases. This may be useful for a Software Developer in understanding the data used in healthcare.
Systems Analyst
A Systems Analyst analyzes and designs computer systems. This course introduces learners to the design and usage of EHR databases. This may be useful for a Systems Analyst in understanding the data used in healthcare.

Reading list

We've selected 14 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Data mining of Clinical Databases - CDSS 1.
Introduces fundamental machine learning concepts and techniques in Python, a popular programming language in the data science community.
This is the official guide for coding and reporting using the ICD-10-CM, which is used for coding and classifying diseases and procedures in the United States.
Covers a broad range of data mining topics, from data preparation to model evaluation, using practical examples and hands-on exercises.
Introduces Apache Spark, a unified analytics engine for large-scale data processing, and covers topics such as Spark SQL, Spark Streaming, and Spark MLlib.
This text serves as a reference for medical professionals, providing background on the theory and practice of clinical diagnosis. It would be most useful as a supplement or for additional reading.
Introduces the fundamental concepts of data science, including data mining, machine learning, and statistical modeling, with a focus on business applications.
Covers the fundamental algorithms and applications of computer vision, such as image segmentation, object detection, and face recognition.
Introduces the fundamental concepts of reinforcement learning, a machine learning paradigm inspired by animal learning.
Serves as a practical guide to deep learning, covering topics such as neural networks, convolutional neural networks, and recurrent neural networks.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Data mining of Clinical Databases - CDSS 1.
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser