AI for Medical Diagnosis
DeepLearning.AI · View on Coursera ↗
Taught by Pranav Rajpurkar, Bora Uyumazturk, Amirhossein Kiani, Eddy Shyu
Data ScienceComputer Science
About the course
AI is transforming the practice of medicine. It’s helping doctors diagnose patients more accurately, make predictions about patients’ future health, and recommend better treatments. As an AI practitioner, you have the opportunity to join in this transformation of modern medicine. If you're already familiar with some of the math and coding behind AI algorithms, and are eager to develop your skills further to tackle challenges in the healthcare industry, then this specialization is for you. No pri
The dissent
The most-upvoted critical review (52 votes, 2.0★).
“IMO this is the weakest course offered by deeplearning.ai. It feels something more our of a medium blog than a full course that someone should pay money for. The good news is that you can sign up for a 7 day free trial and finish it before 7 days are over, so you're not out of any money, just your time. What do you learn? Some new metrics that are specific to medicine (specificity, sensitivity) and the concept of class imbalance (prevalence). The code assignments are designed by someone who understands the concepts well but is unable to teach some of them well (I'm being super critical here, coming from the viewpoint of someone who might spend $49 for a month on this). At the end, I'm unsure what you can say you learned and if you can really demonstrate any concepts in a job interview at a healthcare (adjacent) job. There was some demonstration of segmentation, but a lot of it is really left up to the learner to experiment and learn from. You could talk about these things in a job interview, but a technical round would quickly discover that your knowledge is surface and not really in depth. My 2 cents (stars?). …”
Excerpt. Read the full review on Coursera ↗
Coursera's 4.7 comes from 2,078 ratings. Of those, 2.3% are 1–2★.
Starisk reads the reviews learners voted most helpful, and weights each by the square root of its votes: a review with 80 upvotes counts about five times one with 2. Unvoted reviews are not skipped out of laziness — by this model they carry no evidence that other students endorsed them.
That measures what the most-endorsed reviews say, not “true quality.” The rating distribution above is the whole population, so you can see the sample next to it.
Reviews read on 23 Oct 2026.Read them on Coursera ↗