Impactful work led by @emilyswlau to develop a high-fidelity EHR cohort of >56K pregnancies, demonstrating the urgency posed by ⬆️ rates of pregnancy-related CV complications. A call to action. @CircAHA @patrick_ellinor @broadinstitute @broad_ml4h

Attending #ESC2025 @escardio ? Be sure to check out the latest work out of @MACE_Lab_AI ! @ShinoKany @JHaimovichMD @Keisuk_Usuda @broadinstitute @broad_ml4h

NEW from our group @broadinstitute @MGHHeartHealth @patrick_ellinor led by @ShinoKany and @lucidtronix ECG2CAD: An AI model for detection of coronary artery disease using 12-lead ECGs @JACCJournals https://t.co/wUKbjRxURI

Is the ECG secretly a sphygmomanometer? We trained a neural net to predict hypertension from ECGs and found it associated with many cardiovascular outcomes.

I am excited to share our latest study published @JACCJournals Adv. We found that meeting guideline-recommended physical activity (PA) levels—whether as a “weekend warrior” or via regular activity—is linked to lower visceral and pericardial fat. https://t.co/5mpwVrF7Op

Just how many diseases can you identify with a good old 12-lead #ECG? NEW @npjDigitalMed, co-led w/ @lucidtronix, @RVpacing & @xwang, we use an autoencoder to map ECG to phenome, finding associations btwn ECG & >600 conditions @broadinstitute @broad_ml4h @MGHHeartHealth LINK⬇️

🚨 New #ESCCardioTalk episode alert! 🚨 This week, Shinwan Kany & @shaan_khurshid explore another piece in the atrial fibrillation puzzle! 🧩💡 From clinical insights to genetic risk and AI-powered ECG analysis, this episode covers it all! Don’t miss out on the latest in heart

Many congratulations to @patrick_ellinor! Excited for the future of cardiovascular care, research, and innovation under his visionary leadership!

Delighted to welcome @WiroNiessen back to Boston and to a seminar hosted by @MahnazMaddah & broad_ml4h team. Looking forward to the collaborative opportunities between @broadinstitute, @MassGenBrigham & @umcg

Can AI automate HF adjudication in global clinical trials? Our latest #AHA2024 SimPub @CircHF In the DELIVER trial, our AI model for HF hosp was -Accurate -Generated identical treatment estimate for dapa as human CEC -Extracts evidence of HF Paper: https://t.co/cYslPU1fzP

Does combining clinical, genetic and ECG-based AI risk scores improve AF risk prediction? Check out our commentary on an interesting study by Jabbour et al. where we describe current key concepts and challenges! with @shaan_khurshid & @patrick_ellinor https://t.co/QWi7y00k8x

Is registration of medical images helpful for deep learning Biological models? Yes! https://t.co/As3i2spWKM

Can ECG #AI predict who will develop #afib after stroke (eg, to prioritize for ILR)? Yes! New in @CirculationEP our @broad_ml4h ECG #AI #afib risk model discriminates cardioembolic stroke (>> clinical factors) & stratifies risk of new #afib after stroke: https://t.co/bfIiX9wXC5

More good news on the weekend warrior benefits (previously viewed as potential harm) https://t.co/yTbMDk11FR @CircAHA Among ~90,000 @UK_biobank participants assessed for over 760 conditions with extended follow-up: "Associations appear similar whether physical activity follows a

Exercise is beneficial for health. But many people have to cram their activity into 1-2 days/week. Do they still get the benefit? To find out, we looked at associations of "weekend warrior” (WW) physical activity) and >600 diseases, now @CircAHA ! A 🧵 https://t.co/lUQM0kjPHl

Great presentation by @ShinoKany on using an AI model to detect CAD from the 12 lead ECG at #ESCCongress @aklfahed @broad_ml4h @MGHHeartHealth

Does combining clinical, genetic & ECG-based #AI risk tools to predict incident atrial fibrillation lead to more bang for your buck? Find out in our new preprint where we developed the comprehensive Predict-AF3 model to estimate incident AF risk. A 🧵 https://t.co/2lqIXsldP4

Happy to share our latest work out now in @NatureMedicine: Led by the incredibly talented @nauffal_victor, @MarcusKlarqvist, our @broad_ml4h team @broadinstitute used T1 images from the @uk_biobank to assess fibrosis in multiple organs. https://t.co/WRETlCS67g

In our new @JACCJournals #Advances analysis, we found that 20% of primary care patients @MassGenBrigham had a conduction disorder at baseline and another 6% developed a new conduction disorder over 10 years! @MGHHeartHealth #EPeeps #CardioTwitter 📷 Link:

Does an automated interpretation of “Possible AF” on 1L ECG predict incident AF in patients without a diagnosis of AF in follow up? Our study out in @hrs_journal now! Huge thank you to @patrick_ellinor @shaan_khurshid @alalusim_md @steven_lubitz et al! #VITALAF