Contact information
-
Instructor Frank Rudzicz Office TRI 12-175 Office phone 416 597 3422 x7971 (at Toronto Rehab) Email frank@cs.toronto.[ude backwards] (fix the suffix) Twitter @SPOClab Piazza https://piazza.com/class#fall2016/csc4902600 Email policy For confidential course-related inquiries, consult the instructor. Emails sent with appropriate subject headings and from University of Toronto email addresses are most likely not to be redirected towards junk email folders, for example.
Course outline
-
This is an intensive introduction to AI applied to issues in medical diagnosis, therapy selection, monitoring, and learning from health data. It will briefly cover the healthcare industry in Canada, electronic medical records, and ethical/security concerns. It will go into more depth into language and video processing, and machine learning. The course will be project-based and students have considerable flexibility in defining their projects.
Prerequisites: Please see http://www.cdf.toronto.edu/~clarke/ugn/20111/prereq.html for information on prerequisites. For advice, contact the Undergraduate Office, in rooms 4252-4 of the Bahen Centre.
The course information sheet is available here.
Resources
-
Topic Title Notes Development Apple ResearchKit (free) and HealthKit (requires subscription). Development NLP tools Textbook Neustein, A. (2014) Text Mining of Web-Based Medical Content. Walter de Gruyter GmbH & Co KG. Textbook Merali, Z., Woodfine, J.D. eds. (2016) Toronto Notes. Data UpToDate (requires subscription). Data Texas Inpatient Public Use Data. Data National (Nationwide) Inpatient Sample (NIS). Data Classifying Clinical Text. Data MIDAS. Data HealthData.gov. Data/tools/community i2b2: informatics for integrating biology and the bedside. Cognitive Cloud IBM BlueMix. Open-source EMR Oscar EMR. Assesment Hamilton depression scale. Assesment The Neuropsychiatric Inventory Questionnaire. Vocabulary Unified Medical Language System (UMLS). Healthcare statistics CIHI statistics.
References
- Arnold, M. (2016). Digital health news update: Machine learning meets health search. Decision Resources Group
- Blenner, S. R., Köllmer, M., Rouse, A. J., Daneshvar, N., Williams, C., Andrews, L. B. (2016) Privacy Policies of Android Diabetes Apps and Sharing of Health Information. JAMA, 315(10), 1051.
- Brown, S. J., Lieberman, D. A., Gemeny, B. A., Fan, Y. C., Wilson, D. M., & Pasta, D. J. (1997). Educational video game for juvenile diabetes: Results of a controlled trial. Informatics for Health and Social Care, 22(1), 77-89.
- Bunescu, R., Ge, R., Kate, R. J., Marcotte, E. M., Mooney, R. J., Ramani, A. K., & Wong, Y. W. (2005).Comparative experiments on learning information extractors for proteins and their interactions. Artificial Intelligence in Medicine, 33(2), 139–155.
- Harpaz, R., DuMouchel, W., Shah, N. H., Madigan, D., Ryan, P., & Friedman, C. (2012). Novel Data Mining Methodologies for Adverse Drug Event Discovery and Analysis. Clinical Pharmacology and Therapeutics, 91(6), 1010–1021.
- Jensen, P. B., Jensen, L. J., & Brunak, S. (2012). Mining electronic health records: towards better research applications and clinical care. Nature Reviews Genetics, 13(6), 395-405.
- Liu, X., & Chen, H. (2015). Identifying adverse drug events from patient social media: A case study for diabetes. IEEE Intelligent Systems, 30(3):44–51.
- Luo, D., Wang, F., Sun, J., & Markatou, M. (2012). SOR: Scalable Orthogonal Regression for Non-Redundant Feature Selection and its Healthcare Applications. SIAM Data Mining …, 950–961.
- Reis, B. Y., Kohane, I. S., & Mandl, K. D. (2009). Longitudinal histories as predictors of future diagnoses of domestic abuse: modelling study. BMJ (Clinical Research Ed.), 339, b3677.
- Tu, K., Klein-Geltink, J., Mitiku, T. F., Mihai, C., & Martin, J. (2010). De-identification of primary care electronic medical records free-text data in Ontario, Canada. BMC Medical Informatics and Decision Making, 10(35).
- Weiss, J. C., Natarajan, S., Peissig, P. L., McCarty, C. a., & Page, D. (2012). Machine Learning for Personalized Medicine: Predicting Primary Myocardial Infarction from Electronic Health Records. AI Magazine, 33(Ldl), 33.
Other links
- Verily Is Building A Google For Medical Information (3 March 2016)
- The Next Big Tech Revolution Will Be In Your Ear (7 March 2016)
- How to prod along gamification in healthcare (8 March 2016)
- What I Learned Using An App To Design A House For Alzheimer's Patients (12 May 2016)
- A Profound Example of Digital Health Getting it So Right
- Why gamification is serious business
- Robotic Nurses
Evaluation policies
- General
- You will be graded on two in-class quizzes, participation, and a team project. The relative proportions of these grades are as follows:
Two quizzes (individual, 5% each) 10% Participation (individual) 5% Project (team) 85% Oral presentation: 10% Written report: 90% - Collaboration and plagiarism
- No unauthorized collaboration on the projects is permitted. The work you submit must be your team's own. 'Collaboration' in this context includes but is not limited to sharing of source code and correction of another's source code. Reporting fraudulent experimental results is, as should be obvious, also unaccept- able. Failure to observe this policy is an academic offence, carrying a penalty ranging from a zero on the project to suspension from the University. See Academic integrity at the University of Toronto.
Syllabus
-
The following is an estimate of the topics to be covered in the course and is subject to change.
- The healthcare industry
- Electronic medical records
- Clinical decision support systems
- Machine learning for natural language
- Machine learning for vision
- Human-computer interaction
- Bioethics and challenges to deployment
Calendar
-
16 September First lecture 25 September Last day to add CSC490 26 September Last day to add CSC2600 30 September Quiz 1 10 October Thanksgiving (no classes) 14 October Quiz 2 31 October Last day to drop 2600 7 November Last day to drop 490 9 December Last lecture and final report due
Lecture materials
-
Week Subjects Lecture slides Assigned reading 1
(16 Sep)- Introduction
1
(26 Sep)- Sound and vision
1
(21 Nov)- Ethics