Meera Krishnamoorthy

AI Research Engineer @kira_learning
Previously Ph.D. @michigan_AI, B.S. @Caltech

[Meera Krishnamoorthy @MeeraKrishnamo1]

@max_spero_ I'm curious what you think the value add of Pangram is if all LLM companies embed watermarks in their text and image outputs. Is it to detect mixed authorship, or the degree to which the authorship is mixed?

[Meera Krishnamoorthy @MeeraKrishnamo1]

@mlforhc 😂

[Meera Krishnamoorthy @MeeraKrishnamo1]

Excited to present this work at MLHC next week!

[Machine Learning for Healthcare @mlforhc]

Spotlight: We propose a survival analysis method for settings where censoring is driven by interventions whose prevalence shifts over time. By @MeeraKrishnamo1, Donna Tjandra, & Jenna Wiens from @Michigan_AI; Amanda Kowalski from @umichECON; and @dmshanmugam from @cornell_tech.

[Meera Krishnamoorthy @MeeraKrishnamo1]

@KelseyTuoc i'm curious -- was this ChatGPT thinking?

[Meera Krishnamoorthy @MeeraKrishnamo1]

🗣️ My oral presentation: Tues 1–3 PM in Room 801B
📌 My poster presentation: Tues 5:30–8:30 PM
📄 Link to our paper: https://t.co/fyb4MuW0lX
Excited to chat with others working on robust ML!

[Meera Krishnamoorthy @MeeraKrishnamo1]

Excited to be at #KDD25 this week sharing our work on robust ML! This work was inspired by a real challenge my collaborators, Michael Sjoding and Jenna Wiens, faced when building a model for Michigan Medicine during the height of the COVID-19 pandemic. 🧵

[Meera Krishnamoorthy @MeeraKrishnamo1]

We propose a new CV-based method that more reliably selects models that rely on stable, as opposed to unstable correlations—leading to more reliable model performance over time.

[MichiganAI @michigan_AI]

How can #AI help stop hospital-acquired infections?

This cross-disciplinary effort, including Prof. Jenna Wiens, brings together computer science, clinical care, & data science to reduce C. diff spread w/ a real-world deployed AI tool. @UMengineering

📰 https://t.co/hKvZTZcNXS

[Meera Krishnamoorthy @MeeraKrishnamo1]

@eotles Thank you Erkin!!!!

[trenton c @chang_trenton]

(1/) Excited to announce our new publication on biases in lab testing and its implications for AI in healthcare! Read more from @UMengineering: https://t.co/KT65wb8vgu

[Meera Krishnamoorthy @MeeraKrishnamo1]

We propose an approach that allows us to get the best of both worlds!

[Meera Krishnamoorthy @MeeraKrishnamo1]

Many MIL tasks contain absolute position information, e.g., pathological findings in chest x-rays. Standard (non-transformer) MIL approaches are fast, but do not leverage this position information. Transformer-based MIL approaches leverage position information, but are slow.

[Meera Krishnamoorthy @MeeraKrishnamo1]

This is commonly used to classify large images. To avoid information loss that comes with down sampling these large images, one can instead divide large images into patches that maintain resolution, and then classify bag of patches

[Meera Krishnamoorthy @MeeraKrishnamo1]

We consider the multiple instance learning (MIL) setting. As opposed to standard supervised learning (mapping one input to one output), in MIL, a bag of inputs is mapped to a single output.

[Meera Krishnamoorthy @MeeraKrishnamo1]

Excited to present this work at #CHIL2024 in a few weeks!

[chilconference @CHILconference]

Read about "Multiple Instance Learning with Absolute Position Information" by @MeeraKrishnamo1, @michigan_AI at #CHIL2024!

[Meera Krishnamoorthy @MeeraKrishnamo1]

Excited to share our new comment in which we define and discuss the "off-label use" of AI models in healthcare, akin to the off-label use of drugs!

[MichiganAI @michigan_AI]

In #healthcare, many #AI models can be used in settings other than those for which they were approved.

In this recent Nature Medicine article, @MeeraKrishnamo1, M. Sjoding & Jenna Wiens focus on such off-label use of #AI and ways to ensure patient safety:
https://t.co/LhebyAPYMT

[Meera Krishnamoorthy @MeeraKrishnamo1]

Very cool work from @SarahJabbour_ about the potential issue with mitigating AI bias via clinicians in the loop!

[Sarah Jabbour @SarahJabbour_]

1/ Can AI explanations help clinicians catch when AI is biased? We answer this in our new work published in JAMA @JAMA_current!

https://t.co/ataSuZ5Mkx