Pikagi
Monica Agrawal Profile Banner
Monica Agrawal Profile
Monica Agrawal

@MonicaNAgrawal

2,762
Followers
309
Following
15
Media
125
Statuses

Incoming asst prof at @DukeU (July 2024). Co-founder at @LayerHealth . ML and NLP for healthcare. PhD @mit_csail , BS/MS @stanford . She/her.

https://t.co/LOvBL6GKGN
Joined June 2019
Don't wanna be here? Send us removal request.
Pinned Tweet
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
7 months
I’m recruiting PhD students @Duke for fall 2024! Consider applying if you’re interested in reimagining healthcare by developing novel ML/NLP methodology. I can advise students through the CS dept and the Biostats & Bioinformatics dept. Info here:
Tweet media one
22
123
447
Last Seen Profiles
Space Cadet

@solspacecadet

Dployd; Again (Me/Myself/Eye)

@UnkleTwisted

AALIYAH LEGION ~ FAN ACCOUNT

@AaliyahLegion_

Johnny Depp

@JohnnyDepp39653

أخبار كلية العلوم الطبية المساعدة

@kuniv_ahs

جايز جزاء الحربي

@gaizal3arm

burP

@Iamkennethdrecz

Aine Derrick

@AineDasha

Neurodiverse Shiv

@limpyraven

Fundación Luzón

@FundacionLuzon

TY Ennie♉

@eni_ty

Asociación ALEPH-TEA

@aleph_tea

지메

@ikinarianime

Miu_Cosplayer

@smilecutty

Muirne Paap

@MuirneP

ً

@Iloolcool

Lucky Hens Rescue 🐔

@luckyhens

Ephie 🎀

@EphieX3

Sportsmans Speedway

@Sports_Speedway

Anahid Lara Lazaro

@AnahidLara

Parker Walsh

@ParkerWalsh21

Joe

@Joe86202059

Magali Guaresi

@MagaliGuaresi

ivaan⛈

@ivaangb__

Keenan Bailey

@CoachKee

Lane Yanda

@lane_yanda76047

Junior Firpo

@JuniorFirpo03

Dennise Keisel

@DenniseKei25308

Docent Sandokan

@DocentSandokan

Minajesty 👑

@officiallyminaj

Evangelina Dimalanta

@EvangeliDimalan

Awais Bhatti

@AwaisBhattiPMLN

Max Meyer

@mualphaxi

Bowers Futsal

@FutsalBowers

Dukkha

@Dukkhacs

🌻🟦Grace Hanks🟧🌱🖖

@GraceHanks5

@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
Absolutely thrilled to announce that I'll be joining @DukeU year next as an assistant professor, joint between Biostats/Bioinformatics and Computer Science!
Tweet media one
65
29
940
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
Defended my thesis today! Grateful for the most supportive committee, lab, friends, and family that a PhD student could ever hope for <3
Tweet media one
Tweet media two
Tweet media three
19
3
350
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
Releasing our flexible open-source clinical text annotation tool, built by our amazing undergraduate researcher Ariel Levy. It provides decision aid (recommendations, pre-filled annotations) to make annotation faster and less painful!
7
54
323
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
How can we pre-train good representations of longitudinal health data? Scramble a patient’s data (e.g radiology notes), and ask your model to unscramble! For chronic conditions, the model learns to attend to features corresponding to disease progression
4
25
223
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
Super excited to release this work bringing autocomplete to the EHR, deployed live! The goal is to make clinical notes faster and cleaner to write, all while creating structured data for downstream research. See the full video or the paper () for details!
@david_sontag
David Sontag
@david_sontag
4 years
Just out by my amazing @MIT team and @BIDMChealth - Fast, Structured Clinical Documentation via Contextual Autocomplete (), appearing in today's #MLHC2020 conference w @divya_gopinath , @MonicaNAgrawal , Luke Murray, @shorng , @karger
0
8
51
4
23
188
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
6 months
Excited to announce what we've been up to this year!
Tweet media one
@layerhealth
Layer Health
@layerhealth
6 months
Introducing Layer Health! We're thrilled to unveil our AI healthcare company spun out of @MIT , backed by $4M from @GVteam , @generalcatalyst , and @inceptionhealth . We’re on a mission to solve the information problem in healthcare. Want to learn more?
2
4
50
6
8
156
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
9 months
Clinicians have significant + shifting information needs over the course of a patient visit. In our new paper, we characterize + predict the notes relevant for clinicians to read, based on the current clinical context. Presenting this work, led by Sharon Jiang, today at #MLHC2023
Tweet media one
3
14
117
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
5 months
Excited to be spending the day at #ML4H2023 ! (I’m also recruiting PhD students this cycle at @DukeU , and prospective students should definitely feel free to grab me to chat!)
Tweet media one
2
12
113
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
Clinical notes are hard to understand: for people and computers. In our paper () presented at #MLHC2020 , we dive into the current performance of clinical entity extraction algorithms (hint: they could be better) and propose a path forward for clinical NLP.
2
25
104
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
Many variables needed to construct timelines for clinical research are trapped in notes 🗒️ Manual extraction can be expensive, and ML is still error-prone. In our #MLHC2021 paper, we explore a hybrid approach that can extract clinical events accurately with minimal oversight!
Tweet media one
2
13
92
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
Getting labeled data for clinical NLP can be prohibitively difficult. In work at #emnlp2022 , we find that GPT-3 models perform very well at clinical tasks in the few-shot setting, indicating a new paradigm for transforming EHR notes into actionable data
Tweet card media
Large language models help decipher clinical notes

Researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) used a GPT-3 large language style model to extract important data from electronic health records to decipher...

news.mit.edu
1
19
62
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
Tfw Georgia goes blue (by voting in the daughter of an Indian immigrant!) as a first in my lifetime :') growing up in GA, I constantly felt othered: by questions about my family’s “funny” clothing/food, by a mattress salesman who thought my family slept on coconuts (???) (1/2)
1
2
46
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
EHRs can be...suboptimal. Our new EHR tool proactively surfaces information (e.g. relevant notes + labs) in a side panel based on what's being typed in the note, so that clinicians can spend a little less of their day clicking. Work led by my HCI colleague @lukesmurray !
@david_sontag
David Sontag
@david_sontag
3 years
Presenting MedKnowts... a new way of writing clinical notes for electronic medical records, developed by AI and HCI researchers at @MIT and clinicians at @BIDMChealth .
3
23
108
1
8
45
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
Bopping around #ICML2022 this week! Excited to finally make the mythical “conference friends” I’ve heard about. DM me if you want to meet up to talk about NLP/ML for healthcare (or to help me find the best dessert in Baltimore)!
2
1
42
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
!!! Very excited for this course I TA'd in the spring to finally be publicly available 🩺💻 This graduate course covers topics particularly relevant to machine learning in healthcare like uncertainty, dataset shift, causal inference , and time-series data in the clinical context
@david_sontag
David Sontag
@david_sontag
4 years
MIT's class on Machine Learning in Healthcare is now available for free on MIT's OpenCourseWare! All videos, slides, and lecture notes can be found here:
23
833
3K
0
3
33
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
Our new #AISTATS2021 paper enables users to encode domain knowledge for flexible data cleaning of diverse errors. It was selfishly developed since I have spent approximately 90% of my PhD cleaning data (the other 10% has been spent making elaborate research gifs for Twitter).
@alexanderklew
Alex Lew
@alexanderklew
3 years
Excited to share PClean, our domain-specific PPL for scalable, Bayesian data cleaning! Short PClean programs can fix errors, impute missing values, & link duplicates in datasets w/ up to millions of rows. #AISTATS2021 w/ @MonicaNAgrawal , @david_sontag , @vmansinghka
2
31
145
0
3
35
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
7 months
In other news, I’m still trying to find a good lab name. My top contender is currently ML4ML4H (Monica’s Lab for Machine Learning for Healthcare), so please help me find better options.
10
1
28
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
What grad school feels like with my imposter syndrome
Tweet media one
0
0
28
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
Come hang out with me at ML4H — co-located with NeurIPS in New Orleans!
@SymposiumML4H
ML4H
@SymposiumML4H
2 years
Our workflow chair @MonicaNAgrawal spent a lot of time sifting through this years wonderful submissions. Now, she's talking about 5 reasons why she's excited to attend ML4H in person this year! Register for ML4H
0
4
17
0
1
24
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
Work at #AISTATS2022 , joint from MIT and MSK with @hunterjlang , @michael_offin , @lior_gazit , @david_sontag . Come hang at our poster session tomorrow 6:30AM-8 Eastern to learn more (or sleep in and DM me instead)!
Tweet card media
Leveraging Time Irreversibility with Order-Contrastive Pre-training

Label-scarce, high-dimensional domains such as healthcare present a challenge for modern machine learning techniques. To overcome the difficulties posed by a lack of labeled data, we explore an...

arxiv.org
1
1
23
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
Vividly I remember a summer camp where the class decided I shouldn’t have been born a citizen since my true loyalty could lie with India. I kept waiting for a defense that never came. So for today, I won’t stop smiling at the significance of Kamala Harris’s election (2/2)
1
0
23
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
After a whirlwind day organizing ML4H yesterday, excited to be spending the rest of the week at #NeurIPS2022 ! DM if you want to chat about NLP/ML for healthcare or sample French bakeries with me!
@SymposiumML4H
ML4H
@SymposiumML4H
1 year
We’re excited to meet you and check you in to the event!
Tweet media one
0
1
15
0
0
22
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
7 months
My research takes a human-centered approach to clinical NLP, smarter electronic health records, and the design and evaluation of human-in-the-loop systems. I’m incredibly excited by the avenues at Duke for thoughtful clinical translation and impact (e.g., @DukeAIHealth , @DIHI ).
1
1
19
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
However, we wanted to understand the interactions between domain experts, decision aid, and the resulting annotations. This became a #CHI2021 paper, presented today at 11AM EDT. Joint with @david_sontag and @arvindsatya1
1
2
19
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 months
Excited to be co-organizing the CHIL Doctoral Symposium — please consider applying!
@CHILconference
chilconference
@CHILconference
2 months
📢 Calling all PhD students! We're excited to announce that the Doctoral Symposium will be returning for CHIL 2024. Find more details at the link below and submit by March 15th! 📅 #CHIL2024
Tweet media one
0
8
25
0
1
16
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
5 years
Vanilla word vectors don’t naturally represent all relations (e.g. hierarchies). Andrew McCallum presenting interesting work on representing concepts as high-dimensional boxes in vector space #KR2ML
0
3
16
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
Excited to see this new Science Translational Medicine paper out from my lab (). It outlines a ML algorithm for smarter recommendation of antibiotics that can help reduce antibiotic resistance while simultaneously improving patient outcomes.
@MIT_CSAIL
MIT CSAIL
@MIT_CSAIL
4 years
New algorithm could help break antibiotic resistance in UTIs:
Tweet media one
0
21
116
0
0
16
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
An incredible new resource for clinical NLP!
@alistairewj
Alistair Johnson
@alistairewj
1 year
MIMIC-IV was published this week. The core dataset has been out for a while, but we've just published the deidentified free-text clinical notes: 300,000+ discharge summaries and 2.5 million radiology reports!
16
143
533
0
2
15
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
We investigate extraction of date of metastasis and medication start. Joint work with @j4sonzhao , Dr. Pedram Razavi, and @david_sontag . Video: Paper:
Tweet card media
19. Directing Human Attention in Event Localization for Clinical...
null
www.youtube.com
0
2
16
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
(And to clarify, by next year, I mean summer 2024, not the upcoming school year)
1
0
14
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
Joint work with @david_sontag and several wonderful Twitter-less coauthors at @MIT_CSAIL and @MGHMedicine . Learn more here (), and reach out if you're interested in helping create an open-sourced dataset!
Tweet card media
B18 Robust Benchmarking for Machine Learning of Clinical Entity...
null
www.youtube.com
0
2
11
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
5 years
Super excited to be in Long Beach for #icml2019 , my first ML conference! (And perhaps a little excited to be reunited with California beaches)
0
0
10
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
Empirically, we find that initializing models with `order-contrastive pre-training’ improves disease progression classification in both linear and deep settings. Theoretically in a simplified setting, we investigate why, proving a finite-sample guarantee for downstream error.
1
0
8
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
9 months
Work joint with Sharon Jiang, @shannonzshen , Barbara Lam, Nicholas Kurtzman, Steven Horng, @karger , @david_sontag
0
0
6
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
We benchmark 5 different tasks with diverse output spaces (e.g., disambiguation, clinical trial parsing, medication relation extraction). This involved the creation of new annotations, released here: . Paper:
1
0
3
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@mukulksachdeva My dissertation is now publicly available here!
0
0
3
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
@danofer Re: ICD codes, that would be interesting! We only tested on text data. Challenge with ICD codes is you need a technique for ignoring the shortcuts caused by global nonstationarities in ICD coding. Those make it easy to cheat on the self-supervised objective.
2
0
3
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
11 months
@david_sontag @irenetrampoline Thank you for melting in the heat to get graduation stage selfies with us! (and for the advising part too)
0
0
3
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
@danofer @david_sontag It’s a different self-supervised objective. We compare to masked language modeling (of clinical text) in our experiments. Intuitively, this objective focuses on time-irreversible features, which are useful for downstream tasks like classifying progression
0
0
2
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
@danofer Can’t share the pretrained model due to data-use agreement, unfortunately. Besides pre-processing, the code is p much out-of-the-box. For linear feature selector we used sklearn + L1 penalty to predict the order. For deep model, we used NextSentencePrediction from HuggingFace.
3
0
2
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
@patrickthealba thanks for trying it out! definitely let me know if you hit any snags in the process
0
0
2
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@jure @DukeU @dukecompsci @DukeBiostats Thank you so much! I wouldn’t be here without the crucial experience from the SNAP group!
0
0
2
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@harshaldev22 @mukulksachdeva Finally up!
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@mukulksachdeva My dissertation is now publicly available here!
0
0
3
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
7 months
@alexanderklew I just realized I have never mined you for food recs, so we should rectify that. Also thanks :)
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
@he_why_zhi_yanm @danofer Not a link, but for example, there was the conversion from ICD-9 to ICD-10 in the early 2010s, and there are new ICD codes introduced over time, e.g. for COVID
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@jocelyndunstane Thank you! Hopefully it wasn’t obvious I was running on 3 hours of sleep :)
1
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
@pranavrajpurkar Thanks, Pranav! Let's catch up once you're fully settled in the area!
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
11 months
@Sonali_Advani @DukeU @dukecompsci @DukeBiostats @DukeAdultID Thanks, and that sounds great! I’ll reach out closer to my start date!
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@NoClosedForm The full dissertation is still undergoing a few final finishing touches. Happy to send you the names of the papers that formed the backbone of the dissertation, if you'd like!
2
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@NoClosedForm If you're still interested in the dissertation:
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
@mukulksachdeva My dissertation is now publicly available here!
0
0
3
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
2 years
@_asubbaswamy Seems like the tastiest strategy for handling the weather this week 🍨
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
4 years
@jasonafries Thanks! Excited to see what we can collaborate on!
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
3 years
@_jennylai_ And we are so grateful to you all for participating :) It was so crucial for us to understand how decision aid affected clinical users, before we scaled up our efforts
0
0
1
@MonicaNAgrawal
Monica Agrawal
@MonicaNAgrawal
1 year
Joint work with @stefanhgm , @hunterjlang , Yoon Kim, and @david_sontag ….If you’d like to chat, catch us at the tail end of NeurIPS or me virtually at EMNLP
0
0
1