Title: Artificial Intelligence for Medicine

Units: 6

Pre-requisites: None

Description:

This course introduces Artificial Intelligence (AI) and its recent applications in medicine to students with only a little or no background in computer science. It starts by motivating and defining AI, before folding over to a survey of some of its newest applications to medicine, including diagnosis, prognosis, drug discovery, and recommendations of individualized treatments, to mention just a few. Afterwards, it provides a bird’s-eye view of some of the major AI techniques, including machine learning, deep neural networks, recommendation systems, and ranked retrieval. Finally, it concludes with a discussion on some of the concerns related to AI, including ethical issues, job security, society, and healthcare institutions, among others.

The course comprises a balance of lectures, case studies, live demonstrations of some medical AI applications, problem-solving assignments, and research tasks. The students will be exposed to industry- and research-based perspectives on AI for medicine. In addition, they will learn through an optional programming project the nuances of applying some AI models to solve concrete problems in medicine.

Artificial Intelligence (AI) is transforming various sectors, including medicine. This course will teach you what AI is, take you through a journey of AI applications in medicine, and give you a practical experience in applying AI to solve real-world medical problems. It will demystify major AI concepts, including machine learning, neural networks, Bayesian networks, recommendation systems, data science, and ranked retrieval, among others. In addition, it will allow you to navigate several societal issues and ethical concerns that surround AI.

This course incorporates seven major learning outcomes. In particular, after finishing the course, each student will be able to:

1. Define AI and discuss what AI can and cannot do.
2. Identify various AI applications in medicine and explain how they are transforming healthcare.
3. Recognize the power of big data in enabling AI and describe the different types of data representations.
4. Recognize the power of AI algorithms in solving medical problems and discuss how they can be applied in the medical field.
5. Explain different AI concepts, including machine learning, deep learning, recommendation systems, and ranked retrievals, among others.
6. Apply some AI techniques to solve real-world medical problems.
7. Discuss several societal issues and ethical concerns surrounding AI.

There is no required textbook for this course. Lecture slides and notes will be provided by the instructor and posted on the course webpage as necessary.

The participation of students in the course will involve five forms of activities:

• Attending lectures
• Solving assignments (including writing and reading assignments)
• Solving a large programming project (only for students taking 15-282)
• Taking exams and quizzes
• Participating in class discussions

Each student will receive a numeric score with a corresponding letter grade, based on a weighted average of the following:

1. Homework Assignments:

There will be 6 homework assignments, which will account for 35% of the final score. The lowest one will be dropped.

2. Quizzes:

There will be 2 quizzes, which will account for 20% of the final score.

3. Exams:

There will be two exams, midterm and final, which will account for 15% and 25%, respectively of the final score.

4. Attendance and Participation:

Attendance of classes and participation in discussions will account for 5% of the final score.

4. Project (optional):

There will be one optional applied learning project that is worth 10% bonus on top of the final score.

The table below shows the breakdown of the forms of activities that the course involves, alongside the quantity and the overall weight of each activity.

Type	#	Weight
Homework Assignments	6	35%
Quizzes	2	20%
Exams	2	40%
Attendance and Participation	12	5%
Project (optional)	1	10% Bonus

To ensure consistency across semesters, we set our grading standards in such a way as to compensate for the relative difficulty of tasks.

What follows is a rough guide to how course grades will be established, not a precise formula — we will fine-tune cutoffs and other details as we see fit after the end of the course. This is meant to help you set expectations and take actions if your trajectory in the class does not take you to the grade you are hoping for. So, here is a rough, very rough heuristic about the correlation between final letter grades and total scores:

• A: 90% and above
• B: 80-89%
• C: 70-79%
• D: 60-69%
• R: Below 60%

For urgent communication with the professor and course assistants, it is best to send an email. If you want to talk to any of them in person, remember that their office hours are merely nominal times upon which they guarantee that they will be in their offices. You are always welcome to visit them outside of their office hours if you need help or want to talk about any issue that pertains to the course.

We ask that you follow a few simple guidelines. The professor normally works with his office door being open. Whenever the office door is open, he welcomes visits from students. However, if the office door is closed, this means that he is busy with work, meetings, or phone calls; hence, prefers not to be disturbed.

We will use the course webpage as the central repository for all the course material. In particular, on the course webpage you can always:

• Obtain copies of any homework assignment and lecture slides.
• View announcements that relate to the course.
• Find links to any reference or data you need for your studying and assignments.
• Read clarifications and changes made to any assignments, schedules, or policies.

In addition, we will use Piazza for course announcements and online discussions. Use it to ask questions and to share your experience! The course staff will be happy to answer your questions in a timely manner. However, sometimes we might wait to answer in order to let others answer or for you to think about it a little more. We encourage you to answer each others' questions!

Another important issue appears while asking questions on Piazza. Please do not send your source code to ask questions. Your questions can be related to specific parts of your programs, but while others read your code they will be affected from your solutions. We need to let others find their own solutions for a better learning.

Lastly, all communication on Piazza should not include any inappropriate content or any form of expression that will be unethical or rude. Please find our 15-182 Piazza page at: https://piazza.com/class/lcopdz0v2vl9g/

The value of your degree depends on the academic integrity of yourself and your peers in each of your classes. Please read the University Policy on Academic Integrity (https://www.cmu.edu/policies/) carefully to understand the penalties associated with academic dishonesty at Carnegie Mellon University.

Academic integrity means that any work you submit for this course is your own. This is critical to your learning. The policy's intention is that you never hand in something you do not understand. Your understanding must be deep enough that, if necessary, you could re-do the work completely on your own. In short, do your own work.

We want you to collaborate with other students only if the collaboration improves your understanding. Therefore, you can talk about the homework assignments, but no one may take notes or record the discussion. When you write your solution, it should be yours. Go to a separate area and write your own code or answers. Do this individually so that you do not end up copying someone else's work. Your own solution, even if it is incorrect, is much better than someone else's that you do not understand.

When working on programming assignments, do not look at other students' code or show them your own. If you need that kind of help, get it from the course staff. You may discuss your code at a conceptual level; for example, "do we need a loop for this purpose or just an if statement?". You may collaborate on code at a whiteboard, but you may not take notes or photographs; the purpose of the collaboration is to develop your understanding so that you can then solve the problem yourself, on your own.

If the course staff sees similarities between your work and that of another student, we will attempt to understand what happened. Usually this involves asking you to explain your work and how you did it, and to re-create the work or solve a related problem during our meeting.

For exams, your work must be your own with no communication between you and others (except course staff), and you may use only authorized materials.

If you cannot keep up with the workload due to personal issues, please see your professor. He will help you work toward a solution and will be always happy to assist.

In this class, cheating, copying, or plagiarism means copying all or part of a program or homework solution from another student or unauthorized source, or knowingly giving such information to another student, or handing in a copy of work that you and another student did together, or giving or receiving unauthorized information during an examination. If you use information from another authoritative resource, you must cite the source of this information (and receive permission if required).

Students who violate this policy will be charged with academic dishonesty that can result in failure in this course and possible expulsion from Carnegie Mellon University. Review the official University Code for more information.

Each project or assignment must be the sole work of the student turning it in. Projects and assignments will be closely monitored, and students may be asked to explain suspicious similarities with any write-up or piece of code available. The following are guidelines on what cheating is and is not:

What is cheating?

• Sharing code or other electronic files: either by copying, retyping, looking at, or supplying a copy of a file.
• Sharing written assignments: either by re-writing, looking at, or supplying a copy of an assignment.

What is NOT cheating?

• Clarifying ambiguities or vague points in class handouts.
• Helping others use the computer systems, networks, compilers, debuggers, profilers, or other system facilities.
• Helping others with high-level design issues.
• Helping others debug their codes.

Consequently, be aware of what constitutes cheating (and what does not) when interacting with your colleague students. Same rules of cheating as above apply when collaborating with other students. In short, you cannot share written assignments, code, and/or other electronic files with other students. If you are unsure, ask the teaching staff.

Finally, be sure to store your work in protected directories. The penalty for cheating is severe, and might jeopardize your whole career as a student - cheating is not worth the trouble. By cheating in the course, you are cheating yourself; the worst outcome of cheating is missing an opportunity to learn. Besides, you will be removed from the course and assigned a failing grade. We also place a record of the incident in your permanent university profile.

Learning Disabilities

Carnegie Mellon University is committed to providing reasonable accommodations for all persons with disabilities. To access accommodation services you are expected to initiate the request and submit a Voluntary Disclosure of Disability Form to the office of Health & Wellness or CaPS-Q. In order to receive services/accommodations, verification of a disability is required as recommended in writing by a doctor, licensed psychologist or psycho-educational specialist. The office of Health & Wellness, CaPS-Q and Office of Disability Resources in Pittsburgh will review the information you provide. All information will be considered confidential and only released to appropriate persons on a need to know basis.

Once the accommodations have been approved, you will be issued a Summary of Accommodations Memorandum documenting the disability and describing the accommodation. You are responsible for providing the Memorandum to your professors at the beginning of each semester.

For more information on policies and procedures, please visit this document.

Taking Care of Yourself

Do your best to maintain a healthy lifestyle this semester by eating well, exercising, getting enough sleep, and taking some time to relax. This will help you achieve your goals and cope with stress.

All of us benefit from support during times of struggle. You are not alone. There are many helpful resources available on campus and an important part of the college experience is learning how to ask for help. Asking for support sooner rather than later is often helpful.

If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support. Counseling and Psychological Services (CaPS-Q) is here to help: call 4454 8525 or make an appointment to see the counselor by emailing student-counselling@qatar.cmu.edu. Consider reaching out to a friend, faculty, or family member you trust for help.

If you or someone you know is feeling suicidal or in danger of self-harm, call someone immediately, day or night, at 5554-7913.

If the situation is life threatening, call 999.

Please refer to Schedule for the tentative schedule for the class. The schedule indicates the project and the assignment activities as well. Any changes will be always announced and reflected on this webpage.