Payal Chandak
@payal_chandak
ML for Health! • PhD Student in HST @MIT_CSAIL @HarvardDBMI • previously at Columbia CS + Neuro
ID: 2904996769
20-11-2014 09:17:00
76 Tweet
557 Takipçi
252 Takip Edilen
Most self-supervised learning (SSL) methods for clinical time series data only use one data type e.g. vital signs or ECGs. Aniruddh Raghu, Payal Chandak, Ridwan Alam, John Guttag & #JClinic PI Collin Stultz propose a new SSL method for multimodal data 🐙 proceedings.mlr.press/v202/raghu23a.…
So grateful to have a wonderful mentor and advisor in Isaac Kohane and so excited to share this work with DBMI at Harvard Med community! 🙏🏼
📢 Super excited to share our new study Nature Medicine on developing and validating an explainable graph-based foundation model for drug repurposing, designed specially for rare diseases, which collectively affect 300 million patients globally! 🧵1/10
Excellent, entertaining and educational Year in Review for Clinical AI NEJM AI ai.nejm.org/doi/full/10.10… Kudos Pierre Elias, MD Emily Alsentzer