Ignoring the Mirage of Disposable Clinician for Deployment of AI in Medicine | AI FOR GOOD DISCOVERY

Channel:

AI for Good

Subscribers:

19,700

Published on June 22, 2021 12:00:00 AM ● Video Link: https://www.youtube.com/watch?v=H6plZMLg2WQ

Duration: 0:00

250 views

0

Medicine is driving many investigators from the machine learning community to the exciting opportunities presented by applying their methodological tool kits to improve patient care. They are inspired by the impressive successes in image analysis (e.g. in radiology, pathology and dermatology) to proceed to broad application to decision support across the time series of patient encounters with healthcare. I will describe the central role of the clinician in this process, and I will examine closely some of the under-appreciated assumptions in that research/engineering agenda. Lastly, I focus on how ignoring these will limit success in medical applications and conversely how these assumptions define a necessary and ambitious research program in shared human-ML decision making.

⏱ Shownotes:
00:00 Intro
04:58 Introduction by Maha Farhat
07:04 Introduction by Isaac Kohane
07:38 Keeping the doctor in the loop for ML
08:24 Disclosure
09:11 THE ML SPECTRUM
11:33 Translating Artificial Intelligence into clinical care
14:00 AI helps clinicians predict when COVID-19 patients might need to go to the Intensive Care
16:09 Survival 3 Years After a WBC Test
19:00 Predicting survival from ordering a lab test
20:00 Machine learning for patient risk stratification
24:28 Case-control studies (shape of 1000s of studies on medical ML studies)
25:50 Risk as a trajectory
26:17 Prediction implied a time dimension
27:15 Simulating prospective deployment
27:29 Poor leaders in machine learning community
29:33 Why doctors hate their computers
30:03 Machine Learning in medicine
31:30 Is this the future of medicine in 10 years?
33:11 When does medicine succumb to AlphaZero?
35:32 Where is the game now clearer?
36:49 Adversarial attacks
39:10 Who completes the loop?
43:20 Coronavirus update
44:01 Analysing remarks from Maha Farhat.
44:28 Start of the Q&A Session
46:50 Q: Do you think there is a role for computers and helping collect or label patient data?
48:34 Q:What do you think of smartwatches using ML to diagnose Heart conditions?
51:25 Q: Better design roles out of technology to ensure already marginalized groups, do you have something similar in your work?
55:58 Q: Can you provide a framework for a doctor to critique each prediction case by case using the model internal properties?
57:28 Closing of the Q&A session
57:40 Closing remarks

🔴 Watch the latest #AIforGood videos:  

Explore more #AIforGood content:
1️ ⃣    • Top Hits  
2️ ⃣    • AI for Good Webinars  
3️ ⃣    • AI for Good Keynotes  

📅 Discover what's next on our programhttps://aiforgood.itu.int/programme/mme/

Social Media:
Websihttps://aiforgood.itu.int/int/
Twitthttps://twitter.com/ITU_AIForGoodod  
LinkedIn Pahttps://www.linkedin.com/company/2651190707  
LinkedIn Grohttps://www.linkedin.com/groups/856774848  
Instagrhttps://www.instagram.com/aiforgoodod  
Facebohttps://www.facebook.com/AIforGoodod  

What is AI for Good?
The AI for Good series is the leading action-oriented, global & inclusive United Nations platform on AI. The Summit is organized all year, always online, in Geneva by the ITU with XPRIZE Foundation in partnership with over 35 sister United Nations agencies, Switzerland and ACM. The goal is to identify practical applications of AI and scale those solutions for global impact.

Disclaimer:
The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.

#AIforhealth #Discovery