Geoff Tison
@geofftison
Excited to share our work on self-supervised learning for ECGs ๐ฉบ With small fraction of labeled data, #3KG outperforms previous self-supervised methods and is close to fully supervised performance. Bryan Gopal Ryan Han Gautham Raghupathi w/ Geoff Tison arxiv.org/abs/2106.04452
โ๏ธ November #CJC Editor's pick from Stanley Nattel Predicting Incident Heart Failure in Women With Machine Learning: The Womenโs Health Initiative Cohort. Corresponding author: Geoff Tison ๐ ow.ly/lAMz50GNP39
The pandemic winter is ending, so why are our pandemic habits sticking around? I needed some #Inspiration so I reached out to some smart people for tips to reboot npr.org/sections/healtโฆ Michael Honigberg, MD, MPP Katy Milkman Geoff Tison Greg Marcus Morning Edition
Reduced physical activity & weight gain are changes many have experienced since the #pandemic, but itโs โnot surprising,โ Dr. Geoff Tison says. โPeople are just less used to being active." Learn about #GoalSetting and other tips to get back on track. ucsfh.org/3hVh4FF
AI analysis of HCM ECGs correlates with longitudinal hemodynamic, cardiac structural and laboratory markers in obstructive HCM patients. bit.ly/3i1JkXf #JACC #cvHCM #ECG #EKG #CardioTwitter Geoff Tison Peter Noseworthy, MD
A study published in The Lancet Global Health by lead author Geoff Tison and UC San Francisco researchers shows that physical activity remains decreased worldwide 2 years since #COVID19 onset. doi.org/10.1016/S2214-โฆ
We present a new perspective in @cellrepmed on the present state and future outlook of AI and machine learning in cardiovascular medicine: bit.ly/3GduJ8k Geoff Tison A thread: #AI, #Cardiology
UCSF Center for Real World Evidence Collab w/ JanssenUS published in Journal of Cardiac Failure "Electrocardiogram Detection of Pulmonary Hypertension Using Deep Learning" sciencedirect.com/science/articlโฆ Atul Butte Geoff Tison RWE, signal processing, AND machine learning / deep learning!
I am so proud to be part of an amazing community at UC San Francisco pushing the boundaries of biomedical #AI, including UCSF Bakar Computational Health Sciences Institute arnaoutlab Geoff Tison Sharmila Majumdar Aaron Neinstein, MD Madhumita Sushil UCSF Center for Intelligent Imaging and so many others!
Geoff Tison UCSF Cardiology created an AI-powered algorithm that accurately predicts ๐myocardial injury using #ECG data. โ The algorithm's negative predictive value of 80% allows it to triage low-risk patients using a simple and cost-effective ECG. rdcu.be/c6tCu #AI
We analyze performance for ECGs over 4 datasets: PTB-XL, Chapman-Shaoxing, Georgia 12-lead ECG Challenge, and CPSC. Geoff Tison We show you how to visualize the normalized signal for each lead as well as train models with a 7-label task across datasets. arxiv.org/abs/2304.08486