DeepLearning.AI

AI for Medicine Specialization

up to 3 months
Intermediate

AI is transforming the practice of medicine. This Specialization provides practical experience in applying machine learning to medical problems, helping doctors diagnose patients more accurately, predict future health outcomes, and recommend better treatments.

Model interpretation
Image Segmentation
Natural Language Extraction
Machine Learning
Time-To-Event Modeling

Overview

In this Specialization, you will learn to diagnose diseases from x-rays and 3D MRI brain images, predict patient survival rates using tree-based models, estimate treatment effects using data from randomized trials, and automate the labeling of medical datasets using natural language processing. The course covers model interpretation, image segmentation, natural language extraction, and more.

Online
course location
English
course language
Professional Certification
upon course completion
Self-paced
course format
Live classes
delivered online

Who is this course for?

Medical Professionals

Doctors, nurses, and other healthcare providers looking to enhance their diagnostic and prognostic capabilities using AI.

Data Scientists

Individuals with a background in data science who want to apply their skills to the medical field.

Researchers

Academics and industry researchers interested in the latest AI techniques for medical applications.

This Specialization offers key benefits such as improved diagnostic accuracy, better health predictions, and enhanced treatment recommendations. It covers essential AI techniques like model interpretation, image segmentation, and natural language processing. Ideal for medical professionals, data scientists, and researchers, this course will help you advance your career by applying AI to real-world medical problems.

Pre-Requisites

1 / 3

Basic understanding of machine learning concepts
Familiarity with Python programming
Knowledge of medical terminology is helpful but not required

What will you learn?

Course 1: AI For Medical Diagnosis

Learn about the nuances of working with both 2D and 3D medical image data for multi-class classification and image segmentation. Apply these techniques to classify diseases in x-ray images and segment tumors in 3D MRI brain images.

Week 1

Introduction: A conversation with Andrew Ng, Diagnosis examples, Model training on chest x-rays, Training, prediction, and loss, Class imbalance, Binary cross entropy loss function, Resampling methods, Multi-task loss, Transfer learning and data augmentation, Model testing

Week 2

Introduction: A conversation with Andrew Ng, Evaluation metrics, Accuracy in terms of conditional probability, Sensitivity, specificity, and prevalence, Confusion matrix, ROC curve, Threshold (operating point), Confidence intervals, Width of confidence intervals and sample size, Using a sample to estimate the population

Week 3

Introduction: A conversation with Andrew Ng, Representing MRI data, Image registration, 2D and 3D segmentation, 3D U-Net, Data augmentation for segmentation, Loss function for image segmentation, Soft dice loss, External validation, Retrospective vs. prospective data, Working with cleaned vs. raw data, Measuring patient outcomes, Algorithmic bias, Model influence on medical decision-making

Course 2: AI For Medical Prognosis

Explore multiple examples of prognostic tasks and use decision trees to model non-linear relationships in medical data. Learn to handle missing data and apply these techniques to predict mortality rates more accurately.

Week 1

Introduction: A conversation with Andrew Ng, Examples of prognostic tasks, Patient profile to risk score, Risk score for atrial fibrillation, Liver disease mortality, Calculate 10-year risk of heart disease, Risk score computation, Evaluating prognostic models, Concordant pairs, Risk ties, Permissible pairs, C-index interpretation

Week 2

Decision trees for prognosis, Predicting mortality risk, Dividing the input space, Non-linear associations, Class boundaries of a decision tree, Random forest, Ensemble methods, Survival data, Problems with dropping incomplete rows, Dropping incomplete case changes the distribution, Imputation, Mean imputation, Regression imputation

Week 3

Survival function, Censoring, Collecting time data, Heart attack data, Estimating the survival function, Using censored data, Chain rule of conditional probability, Derivation, Calculating probabilities from the data, Comparing estimates, Kaplan Meier Estimate

Week 4

Hazard functions, Survival to hazard, Cumulative hazard, Individualized predictions, Individual vs. baseline hazard, Smoker vs. non-smoker, Effect of age on hazard, Factor risk increase or decrease, Survival trees, Nelson Aelen estimator, Mortality score, Evaluating survival models, Permissible pair examples, Harrell’s concordance index

Course 3: AI For Medical Treatment

Estimate treatment effects using data from randomized control trials and apply tree-based models. Learn machine learning interpretation methods and use natural language entity extraction to automate the labeling of medical datasets.

Week 1

Treatment effect estimation, Randomized control trials, Average risk reduction, Individualized treatment effect, T-Learner and S-Learner, C-for-benefit

Week 2

Information extraction from medical reports, Rules-based label extraction, Text matching, Negation detection, Dependency parsing, Question-Answering with BERT

Week 3

Machine Learning Interpretation, Interpret CNN models with GradCAM, Aggregate and Individual feature importance, Permutation Importance, Shapley Values, Interpret random forest models

Meet your instructors

Pranav Rajpurkar
Assistant Professor of Biomedical Informatics, Harvard University
Dr. Rajpurkar is an Assistant Professor at Harvard University, applying artificial intelligence to revolutionize healthcare. His work has been widely published, recognized, and featured in prominent media outlets.
Amirhossein Kiani
Product Manager, Google
Amirhossein Kiani is a formally named Product Manager at Google based in the San Francisco Bay Area. He currently works on the Gemini in Workspace project and has recently studied at DeepLearning.AI.
Bora Uyumazturk
Graphics Multimedia Editor, The New York Times
Bora Uyumazturk is an instructor at DeepLearning.AI and has previously worked as a Graphics Multimedia Editor at The New York Times. He has extensive experience in multimedia and graphics.
Eddy Shyu
Curriculum Product Manager, DeepLearning.AI
Eddy Shyu is a Curriculum Product Manager at DeepLearning.AI. He designed and led the creation of Andrew Ng’s Machine Learning Specialization and 14 other AI/ML courses, with over 500,000 unique learners enrolled.

Upcoming cohorts

Cost
Free
Duration
3 months
Dates
start now
Location
Online

Free