Beginning in late 2018, the Upstream Lab is investigating the potential of novel AI methods, particularly machine learning and natural language processing to advance proactive “upstream” care. However, we are also critical of these applications and share the concerns of many about the potential to worsen inequities. Several of our ongoing AI initiatives and projects are below.
AI is rapidly emerging as a technology that will impact numerous sectors. Within primary care, the future of AI is where the power, and opportunities may be realized in the broadest and most ambitious scale. It has the potential to improve care, lower costs, and reduce physician burnout. However, in order for this field to advance in a meaningful way, we need to have interdisciplinary teams inclusive of patients, providers, researchers, and system leaders to join in a collaborative effort to create positive impact toward health-related AI initiatives.
The big Data to Enhance and Evolve Primary care (DEEP Network) brings together patients, health providers, system leaders and academics across Canada to help set the direction of AI in primary care, and to catalyze patient-oriented research in this area.
Join us, as we host regular opportunities to share work in progress on AI integration in primary care, spark new ideas and collaborations, and work toward setting priorities for research in this rapidly evolving field.
JOIN OUR GROWING NETWORK!
To sign up, email: firstname.lastname@example.org
The Future is Now: Artificial Intelligence (AI) in Family Medicine
How will AI affect the work of Canada’s family doctors?
MARK YOUR CALENDAR TO JOIN US for this six-part Monthly Webinar Series
December 2020 to June 2021
The webinars include an amazing line-up of family medicine leaders who will enhance your understanding of AI, how it’s being used in family practice, and the potential of AI and other technologies to change how we learn, work and care for our patients.
This one-credit-per hour Group Learning activity has been certified by the CFPC for up to one Mainpro+® credit for each webinar session.
Select readings and resources from our AI Webinar Speakers
Introduction to AI and Applications in Primary Care
Paprica, A., McCradden M. What the public hopes and fears about the use of AI in health care. The Conversation. 2020; Nov 2.
Kueper JK, Terry AL, Zwarenstein M, Lizotte DJ. Artificial Intelligence and Primary Care Research: A Scoping Review. 2020; 18(3):250-258.
Doshi-Velez F, Perlis RH. Evaluating machine learning articles. JAMA. 2019; 322(180): 1777.
Liaw W, Kakadiaris IA. Primary care artificial intelligence: A branch hiding in plain sight. The Annals of Family Medicine. 2020; 18(3): 194-195.
Liu Y, Chen P-HC, Krause J, Peng L. How to read articles that use machine learning: users’ guides to the medical literature. JAMA. 2019; 322(18):1806.
Upshur, R (2019). Artificial Intelligence, Machine Learning and the potential impacts on the practice of Family Medicine: A briefing document. Toronto, ON, AMS Healthcare.
The Topol Review: Preparing the healthcare workforce to deliver the digital future.
The Task Force Report on AI and Emerging Digital Technologies from the Royal College of Physicians and Surgeons of Canada (until there are more primary care specific resources).
Machine Learning to Solve Primary Care Challenges
A YouTube video by 3Blue1Brown: But what is a Neural Network – Deep learning
Liyanage, Harshana et al. “Artificial Intelligence in Primary Health Care: Perceptions, Issues, and Challenges.” Yearbook of medical informatics vol. 28,1 (2019): 41-46. doi:10.1055/s-0039-1677901
Lin, Steven Y et al. “Ten Ways Artificial Intelligence Will Transform Primary Care.” Journal of general internal medicine vol. 34,8 (2019): 1626-1630. doi:10.1007/s11606-019-05035-1
Morley, Jessica et al. “The ethics of AI in health care: A mapping review.” Social science & medicine (1982) vol. 260 (2020): 113172. doi:10.1016/j.socscimed.2020.113172
Vollmer, Sebastian et al. “Machine Learning and Artificial Intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. BMJ 2020; 368:I6927. doi:10.1136/bmj.I6927.
Machine Learning Applied to Primary Care EMR Data for Classification
Garies S et al. Achieving quality primary care data: a description of the Canadian Primary Care Sentinel Surveillance Network data capture, extraction and processing in Alberta. Int J Popul Data Sci, 2019; 4:2.
Garies, Stephanie et al. “Data Resources Profile: National electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN).” International Journal of Epidemiology 2017, 1091-1092f. doi: 10.1093/ije/dyw248.
Gentil et al. “Factors influencing the development of primary care data collection projects from electronic health records: a systematic review of the literature.” BMC Med Inform Dec Mak (2017) 17:139
Hodge, Trevor. “EMR, EHR, and PHR – Why All the Confusion?”. Canada Health Infoway 2011; April 7.
Natural Language Processing and its Role in Primary Care
Royal College of Canada. “Task Force Report on Artificial Intelligence and Emerging Digital Technologies” 2020; April.
Machine Learning for Human resource management and to predict health service use
Liu Y et al. How to Read Articles that Use Machine Learning: User’s Guides to the Medical Literature. 2019; 332, 1806-1816.
Social and Ethical Implications of AI and Primary Care
Faes L et al. A Clinician’s Guide to Artificial Intelligence: How to Critically Appraise Machine Learning Studies. 2020; 9(2):7. doi: 10.1167/tvst.9.2.7
McCradden M et al. Ethical limitations of Algorithmic Fairness Solutions in Health Care Machine Learning. 2020; 2(5), E221-E223.
Fabulous talk on opacity in medicine – Opacity in Medicine AI – Juliette Ferry-Danini
McCradden M et al. Clinical Research underlies Ethical Integration of Healthcare Artificial Intelligence. 2020; 26, 1318-1330.
Shaw J et al. Beyond “Implementation”: Digital health Innovation and Service Design. 2018; 1:48
Steele Gray C. Seeking Meaningful Innovation: Lessons Learned Developing, Evaluating, and Implementing the Electronic Patient-Reported Outcome Tool. 2020; 22 (7):e17987.
Digital Implementation Investment Guide (DIIG): Integrating Digital Interventions into Health Programmes. Geneva: World Health Organization; 2020. License: CC BY-NC-SA 3.0 IGO