Chris McIntosh
@CmcintoshAi
Followers
227
Following
543
Media
2
Statuses
81
AI Scientist at TGHRI, PMCC, JDMI, UHN; Chair in AI Medical Imaging; Assistant Professor University of Toronto; Affiliate Faculty at Vector Institute
Toronto, Ontario
Joined December 2010
RT @UHN_Research: This year at Commercialization at UHN was full of #impact, #collaboration, and global reach. ✨ 🌎 . Check out some of thei….
0
2
0
RT @TransformHF: 🎁 Your TRANSFORM HF 2024 Wrapped is here. We made quite an impact this year, from funded research to new and award-winni….
0
2
0
New insights into arrhythmia risk in cardiomyopathy! Using ML, we found that narrow, low-amplitude QRS peaks in the terminal phase of lead V1 are strong predictors of ventricular arrhythmias—outperforming clinical data or pacing features. @PMunkCardiacCtr
2
0
4
I'm incredibly grateful for the opportunity to not only build cutting edge technology but to get it ever closer to widespread clinical impact through commercialization. Thank you @UHN_Research.
A new AI-driven patented technology by @UHN-founded Curait Medical, streamlines radiation treatment consultation, helping doctors make faster and more informed clinical decisions. Read more ➡️ #AI #CancerCare #AHealthierWorld
0
3
12
Thank you @EMJReviews for the great conversation!.
How is #AI set to transform healthcare and medicine? . In this episode of the EMJ Podcast, Jonathan sits down with @CmcintoshAi to explore AI’s potential to reduce bias, enhance transparency, drive breakthroughs in patient care, and more. Watch here:
0
0
1
RT @Anivgf1: Happy to share our latest work on #medRxiv! We develop an explainable algorithm, Decision Path Similarity Matching (DPSM), tha….
medrxiv.org
Many clinical questions in medicine cannot be answered through randomized controlled trials (RCTs) due to ethical or feasibility constraints. In such cases, observational data is often the only...
0
3
0
RT @PMunkCardiacCtr: What an incredible adventure and amazing display of strength and resilience from patients! . Excited to see where this….
0
5
0
Coolest news of the decade. Geoff once again inspires us all to think bigger by showing the Nobel Prize is indeed in reach of computer scientists!.
BREAKING NEWS.The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”
1
0
0
RT @dineshpmcc1: Congratulations to @drchrisyu for his fantastic work using AI Approach to cardiac MRI for predicting cardiotoxicity risk!….
0
9
0
Thank you for highlighting our work!.
Researchers @UHN’s @TGHRI_UHN investigated why AI models don’t work as well as predicted in new health care settings & developed a way to better evaluate these models. Read more >
0
0
2
Postdoc opening in my lab at @UHN & @UofT developing multimodal AI to transform patient care. Work with diverse health datasets, build digital interventions, and see real-world clinical impact. Apply now: Please share widely to help spread the word!.
jobs.smartrecruiters.com
0
4
6
Huge thank you to @TransformHF,@uoft_tiss, and @UofTDSI for the support! We're looking forward to sharing the results and getting these technologies ever closer to positively impacting lives.
Chris McIntosh & Dan Franklin met at a TRANSFORM HF event. Now, with trainees Will Gao & Matthew Kenyon Lee, they’re developing advanced wearables that use #AI to produce cleaner data & more reliable insights into #heart function. Read more:
0
1
5
And a huge thank you to our team for their tremendous efforts @hearthealthydoc @YasMoayedi and support from so many groups @drbarryrubin @UHN @mbp @uoftmedicine @UofTCompSci @NSERC_CRSNG @UofTMedIm @trogersresearch @CIFAR_News @RadMedPM.
0
0
2
See our open source code to quickly integrate our method into your model, or examine your dataset under an existing model:
github.com
Contribute to mcintoshML/Data-Bias-Analysis development by creating an account on GitHub.
0
0
0
Our research tackles a critical challenge in medical AI: understanding why model performance drops during deployment. Our method reveals the impact of previously undiscovered data biases and provides an easy way to better estimate model generalization in house. #AIstandards.
Studies of #AI in medicine may overestimate accuracy to new situations by 20%. Models learn hidden biases in X-rays, ECGs, clinical notes etc. instead of real disease markers. This study proposes a solution for inc. reliability in reporting of results.
2
1
5
RT @BoWang87: Swiss is leading the AI infrastructure with 10k H100! Hope Canada can catch up with science investments ✊@bradwouters @drbarr….
0
6
0
RT @TransformHF: Join us in cheering on our co-lead, Dr. Heather Ross, and the #TestYourLimits team as they climb to new heights (and win s….
0
5
0