David Sontag @david_sontag Twitter profile | Pikagi

Pikagi

David Sontag

@david_sontag

9,133

Followers

308

Following

39

Media

963

Statuses

CEO & Co-founder @layerhealth . Professor, MIT. Research on machine learning in health care. Part of @MIT_CSAIL , @MIT_IMES , @MITEECS , @AIHealthMIT

Massachusetts Institute of Technology

https://t.co/FXiIR7Z6tO

Joined February 2012

Don't wanna be here? Send us removal request.

Pinned Tweet

@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:

Tweet card media

MIT 6.S897 Machine Learning for Healthcare, Spring 2019

Instructors: David Sontag, Peter Szolovits View the complete course: https://ocw.mit.edu/6-S897S19 Introduces students to machine learning in healthcare, the...

www.youtube.com

23

828

3K

Last Seen Profiles

@oscar_g204

@EncoreAD_

@stw_pdg

@YuzukittyPH_

@stw_pdg

@stw_pdg

@anaaacpa

@IgnitionFBTC

@goblok251

@tyreekerobinson

@Alpha7_esports

@salbmmh69765376

@S0PHlEBECKETT

@Brandega

@KadynProctor1

@Osten_do

@Chavez_BC

@bokeplokalmalam

@Papuaviral1

@sugaarbullet

@bokeplokalmalam

@bokeplokalmalam

@stw_pdg

@OllyBausor

@shinjuku_sr

@junovercas

@lucyhale

@stw_pdg

@soranin81

@rabea204

@bokeplokalmalam

@TsuBunnii

@qbelite

@DYKWlTlA

@TEAMHENECIA

@aliyah_alb27685

@david_sontag

David Sontag

4 years

Just one week till the start of MIT's @edXOnline course on Machine Learning for Healthcare - open to the whole world and free to audit!

8

128

507

@david_sontag

David Sontag

11 months

We've launched Layer Health @layerhealth , a new AI startup solving healthcare's information problem, with large language models. I'm CEO, working with an amazing team and backed by $4 million from Google Ventures @GVteam @generalcatalyst & @inceptionhealth

Tweet card media

Introducing Layer Health — Layer Health

Introducing Layer Health - building the AI layer for healthcare, powered by large language models.

www.layerhealth.com

29

36

439

@david_sontag

David Sontag

3 years

In a first for ML virtual conferences, #UAI2021 early-bird registration is FREE for students🎓😎🎉. Conference will be July 27-30. Details here: @UncertaintyInAI

4

84

348

@david_sontag

David Sontag

2 years

Slides for MIT's Machine Learning for Healthcare '22 class w/ @DrMadhurNayan here: ! Featuring tons of new material including clinical NLP by @MonicaNAgrawal , imaging @YalaTweets , human-AI interaction @HsseinMzannar , fairness @irenetrampoline , &dataset shift

4

80

294

@david_sontag

David Sontag

3 years

New dataset & benchmark for clinical NLP and unsupervised learning! With a team of clinicians, we annotated 718 discharge summaries, 100K sentences, for patient instructions, appointments, medications, labs, procedures, & imaging:

@asapp

ASAPP

3 years

Can we improve patient and provider follow-up after a hospital discharge? Our #ACL2021NLP paper, led by @david_sontag , uses ML to extract action-items from clinical notes, and releases one of the largest annotated datasets for clinical NLP. (1/3)

3

22

57

3

50

284

@david_sontag

David Sontag

4 years

How to beat linear models for ML on health data? Pre-train using them! See our #AAAI2021 paper on Reverse Distillation & a new transformer-based model (). And... (drum roll) our new open-source code for ML on OMOP: @RBoiarsky @OHDSI

Tweet media one

4

41

269

@david_sontag

David Sontag

6 years

Big news from MIT today: a new College of Computing that will cut across the entire Institute, with a major focus on Artificial Intelligence.

2

93

249

@david_sontag

David Sontag

4 years

Applications NOW OPEN for MIT's undergraduate summer research program, which seeks to increase the # of underrepresented minorities and underserved (eg low socio-economic bg, 1st gen) students in graduate research. Come work with me on ML for health care!

2

107

221

@david_sontag

David Sontag

6 years

Our @NatureMedicine commentary, "Guidelines for reinforcement learning in healthcare", just published! Everyone interested in machine learning & healthcare should take a second to read these two pages. #AI @MIT_IMES @MIT_CSAIL @FinaleDoshi @frejohk

6

80

208

@david_sontag

David Sontag

3 years

Research in health care is often very personal. My lab's research on #MultipleMyeloma started when my mom was diagnosed with it in 2014. It is too late to help her, but I believe machine learning can help millions of other patients. Thanks to @TheMarkFdn for their support.

@TheMarkFdn

The Mark Foundation for Cancer Research

3 years

May is National Cancer Research Month. In honor of it, we are proud of highlight the work of our partner @david_sontag of @MIT_CSAIL / @MIT_IMES , a computer scientists who is tackling myeloma

4

15

43

1

21

206

@david_sontag

David Sontag

6 years

I've been increasingly worried about the fairness of machine learning in healthcare. ML is being used to prioritize care, and bias leads to disparities in who benefits. Here's my answer: "Why Is My Classifier Discriminatory?" w/ @irenetrampoline @frejohk

Tweet card media

Why Is My Classifier Discriminatory?

Recent attempts to achieve fairness in predictive models focus on the balance between fairness and accuracy. In sensitive applications such as healthcare or criminal justice, this trade-off is...

2

71

194

@david_sontag

David Sontag

6 years

MIT machine learning just got a whole lot stronger with new hires Pulkit Agrawal ( @pulkitology ), Jacob Andreas ( @jacobandreas ) and Cathy Wu ( @wucathy ). All starting in Fall 2019. All coming from my alma mater UC Berkeley :)

2

18

188

@david_sontag

David Sontag

6 years

Open health data = reproducible science = accelerated science.

@MIT_IMES

MIT IMES

6 years

A new database of images could pave a path for algorithmic models that ensure accurate diagnoses of conditions like pneumonia.

1

25

72

3

43

172

@david_sontag

David Sontag

10 months

Mike finished his Ph.D. with me at MIT a year ago, and is now recruiting students in CS @JohnsHopkins . Consider applying to work with him - he's a great mentor and top researcher.

@MichaelOberst

Michael Oberst

10 months

I'm recruiting PhD students for my lab at Johns Hopkins! Please apply if you're interested in reliable ML / causal inference for decision-making in healthcare. See my website () for more info. Deadline 12/15. Retweets welcome :)

Tweet media one

8

114

349

2

16

159

@david_sontag

David Sontag

3 years

Best paper award for #UAI2021 goes to @awnihannun , Chuan Guo, and Laurens van der Maaten for their paper Measuring Data Leakage in Machine-Learning Models with Fisher Information Congratulations!

1

21

145

@david_sontag

David Sontag

5 years

It *is* possible to get high-quality structured data from electronic medical records AND to save time; one just needs to re-think the user interface (and use machine learning). Here's a taste of the future: (w/ Steven Horng @bethisraellahey @BIDMCEM )

Tweet media one

3

36

141

@david_sontag

David Sontag

4 years

Attention all clinicians interested in machine learning & AI... work with MIT students! We are recruiting mentors for course projects in our Machine Learning for Healthcare Spring 2021 class. Details & sign up here: @willieboag @rayruizhiliao @ckbjimmy

Tweet card media

MIT ML4H Clinical Mentor Signup

MIT course 6.871 Machine Learning for Healthcare (https://mlhcmit.github.io/) introduces students to machine learning in healthcare, including the nature of clinical data and the use of machine...

docs.google.com

2

43

138

@david_sontag

David Sontag

6 years

Want to apply ML to real-world EHR data? This Partners Biobank challenge is a great opportunity to compare your algorithms to other researchers' algorithms on a common health care dataset:

0

76

139

@david_sontag

David Sontag

5 years

Jonas Peters and I are the program chairs for #UAI2020 . Paper deadline is Feb 20, 2020, and conference will be in Toronto, Aug 3-6, 2020. General chairs are @ryan_p_adams and @VibhavGogate . Consider submitting your best work!

Tweet card media

Uncertainty in Artificial Intelligence

2

34

133

@david_sontag

David Sontag

7 years

Large dataset of chest x-rays from 30K+ patients now available from the NIH!

Tweet card media

NIH Clinical Center provides one of the largest publicly available

The dataset of scans is from more than 30,000 patients, including many with advanced lung disease.

0

42

128

@david_sontag

David Sontag

3 years

We have at least 5 postdoctoral positions at MIT CSAIL for first-generation college students, individuals underrepresented in graduate education at MIT, and others overcoming significant challenges in path toward graduate school -- applications due June 24th

@MIT_CSAIL

MIT CSAIL

3 years

MIT CSAIL is excited to announce the Mentored Opportunity in Research Postdoctoral Fellowship (Meteor), to broaden participation in computing and artificial intelligence:

Tweet media one

2

48

182

0

51

112

@david_sontag

David Sontag

5 years

Wow! CHiQA: an experimental AI system for answering health-related questions for patients See paper & new (publicly available) datasets just published in JAMIA '19 by Demner-Fushman and colleagues @NLM_LHC

Tweet media one

1

29

109

@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 .

Tweet card media

Toward a smarter electronic health record

MedKnowts, a “smart” electronic health record system, can help doctors work more efficiently by presenting relevant information from a patient’s medical history, autocompleting medical terms as a...

3

23

108

@david_sontag

David Sontag

6 years

This is the future of probabilistic modeling.

@dustinvtran

Dustin Tran

6 years

"Simple, Distributed, and Accelerated Probabilistic Programming". The #NIPS2018 paper for Edward2. Scaling probabilistic programs to 512 TPUv2 cores and 100+ million parameter models.

Tweet media one

Tweet media two

8

214

739

1

25

102

@david_sontag

David Sontag

6 years

This is the most interesting & potentially impactful analysis of fairness in ML for healthcare that I've seen to date.

@sherrirose

Sherri Rose

6 years

Our new paper "Fair Regression for Health Care Spending" is out: We build fairness into the objective function for continuous outcomes & see large improvements in group undercompensation Coauthored w/PhD student Anna Zink Code:

Tweet media one

Tweet media two

Tweet media three

Tweet media four

1

50

146

1

24

106

@david_sontag

David Sontag

4 years

Virtual UAI conference website all ready to go! Conference starts Monday with tutorials. #uai2020

Uncertainty in Artificial Intelligence

0

24

105

@david_sontag

David Sontag

5 years

Overparameterization seems to be very helpful for supervised learning of deep neural networks -- but what about for unsupervised learning (e.g. using variational auto-encoders)? w/Rares Buhai, @risteski_a , and Yoni Halpern:

Tweet media one

1

28

107

@david_sontag

David Sontag

1 year

Congrats, @MonicaNAgrawal and @irenetrampoline !

Tweet media one

5

3

108

@david_sontag

David Sontag

3 years

The #UAI2021 program, with links to accepted papers, is now up! Highlights include live discussants for selected papers, keynote talks from thought leaders @SusanMurphylab1 , @erichorvitz , @zdeborova , @yudapearl , & Ankur Moitra, and 3 workshops.

Tweet media one

1

21

101

@david_sontag

David Sontag

4 years

Are you a medical student, resident or fellow with an interest in ML or NLP? MIT's clinical machine learning group needs your help with a user study on a new tool for rapid annotation of clinical notes! It'll take 15 hours and is paid. Details here:

Tweet card media

Participate in a user study to power the future of clinical machine learning! The MIT Clinical Machine Learning Group is seeking participants with medical training for a user study on a new tool for...

docs.google.com

2

38

94

@david_sontag

David Sontag

10 months

Monica finished her Ph.D. with me at MIT a year ago and is starting a research group at Duke in Sept 2024. As a leader both in industry @layerhealth and in academia, her LLM work is transforming healthcare. Consider applying to @dukecompsci and @DukeBiostats

@MonicaNAgrawal

Monica Agrawal

@MonicaNAgrawal

11 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

122

446

0

11

100

@david_sontag

David Sontag

6 years

Great tutorial on causal inference! I particularly like the sections on checking for violations of assumptions, natural experiments, and the framing of potential outcomes within the broader language of causal graphs.

@amt_shrma

Amit Sharma

6 years

at #KDD2018 ? Interested in estimating effects of algorithms or applying ML to societal domains like healthcare? Check out our tutorial on causal inference and counterfactual reasoning at 1pm today @emrek @kdd_news

1

52

145

0

23

98

@david_sontag

David Sontag

6 years

MIT's free Machine Learning for Healthcare consulting sessions begin March 5th at 5pm. All clinician researchers from the Boston area are welcome! Sign up here:

Tweet media one

3

39

90

@david_sontag

David Sontag

4 years

All of Us research platform opens up for beta testing, with data on 225,000 participants, enabled by cloud-based Jupyter notebooks and an OMOP common data model

2

30

90

@david_sontag

David Sontag

4 years

Need a break from the election? Check out my lab's latest work, just published today in Science Translational Medicine. Joint with @SanjatKanjilal , @MichaelOberst , @soorajb25 , and @helenz1235 . Paper:

@MIT_CSAIL

MIT CSAIL

4 years

New algorithm could help break antibiotic resistance in UTIs:

Tweet media one

0

21

113

2

13

88

@david_sontag

David Sontag

6 years

Congrats to my Ph.D. student, Yoni Halpern, for the AMIA Doctoral Dissertation Award second place prize, for his thesis "Semi-Supervised Learning for Electronic Phenotyping in Support of Precision Medicine"

@AMIAinformatics

AMIA

@AMIAinformatics

6 years

AMIA Doctoral Dissertation Award Winners announced! @blpercha and Yonatan Halpern will receive awards and present their doctoral work at #AMIA2018 . Read more about their winning dissertations, additional finalists, and the award program

Tweet media one

0

4

8

2

7

83

@david_sontag

David Sontag

6 years

Amazon web services just launched a product to extract medical concepts and perform de-identification in unstructured text in electronic medical records! This is incredibly exciting (1/3)

Tweet card media

Healthcare NLP - Amazon Comprehend Medical - AWS

Amazon Comprehend Medical is a a HIPAA-eligible service that uses machine learning to extract health data from medical text.

2

23

83

@david_sontag

David Sontag

6 years

Exactly the kind of academic-industry collaboration I like to see... and a reasonable data sharing agreement. Congrats NYU and FAIR!

@nyugrossman

NYU Grossman School of Medicine

6 years

We've released the largest-ever open-source dataset to speed up MRIs using #AI . Read how we've collaborated with @facebookai to provide researchers access to MR imaging and improve patient care worldwide

4

35

110

0

17

84

@david_sontag

David Sontag

5 years

Double/debiased machine learning Individual-level treatment Regulatory oversight From development to deployment Teaching yourself about structural racism

Tweet card media

Teaching yourself about structural racism will improve your machine learning

Summary. In this commentary, we put forth the following argument: Anyone conducting machine learning in a health-related domain should educate themselves a

academic.oup.com

@sherrirose

Sherri Rose

5 years

As the editors of @biostatistics , @drizopoulos and I are thrilled to share this free access multidisciplinary collection of commentaries on machine learning for causal inference. All 5 pieces are linked in our editorial about the series:

Tweet media one

6

206

487

0

30

84

@david_sontag

David Sontag

1 year

We used machine learning on EHR audit logs to learn to predict -- so that we can automatically surface -- patient notes that clinicians may want to read. Published today at #mlhc2023 , joint work between @MIT and @BIDMChealth . Paper: #NoMoreThousandClicks

@MonicaNAgrawal

Monica Agrawal

@MonicaNAgrawal

1 year

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

1

7

81

@david_sontag

David Sontag

2 years

Github Copilot is the most exciting large-scale, rapid, experiment of human-AI interaction that I've ever seen. We're going to learn so much from it. First up, this study by my student @HsseinMzannar from his work at @MSFTResearch w/ @bansalg_ , @adamfourney and @erichorvitz .

@HsseinMzannar

Hussein Mozannar

2 years

As Copilot becomes more popular, we need to understand how programmers interact with it. We built a model of interaction between Copilot and Programmers named 'CUPS' and predict programmer behavior in our latest paper

Tweet media one

6

29

138

0

15

80

@david_sontag

David Sontag

4 years

I'll be hosting a mentorship session Tues 4:30pm EST as part of @NeurIPSConf 's Mementor Beta. Hoping to chat with junior researchers working on machine learning in healthcare. May host more sessions later in the week depending on how it goes.

4

11

76

@david_sontag

David Sontag

5 years

The Broad Institute at MIT/Harvard has an opening for a Machine Learning Scientist working on applying ML to problems in medicine. Apply here:

www.broadinstitute.org

2

31

75

@david_sontag

David Sontag

4 years

New dataset alert! AMR-UTI: Antimicrobial Resistance in Urinary Tract Infections De-identified data derived from 80,000 patients with urinary tract infections (UTI) treated at Massachusetts General Hospital and Brigham & Women’s Hospital in Boston

AMR-UTI: Antimicrobial Resistance in Urinary Tract Infections Dataset | MIT Clinical ML

1

9

69

@david_sontag

David Sontag

6 years

New book on "Artificial Intelligence in Medical Imaging: Opportunities, Applications and Risks" with chapters by @DrHughHarvey and @DrLukeOR . Note: check your academic library, e.g. MIT has free access to PDF version of book.

@DrHughHarvey

Hugh Harvey

6 years

It arrived! Lovely to see the full print version @eranrad

Tweet media one

Tweet media two

Tweet media three

7

27

150

2

15

66

@david_sontag

David Sontag

5 years

Call for abstracts for NeurIPS 2019 causality workshop, "Do the right thing": machine learning and causal inference for improved decision making. Due Sept 9th. More details here:

0

23

66

@david_sontag

David Sontag

6 years

Our upcoming AISTATS 2019 papers: @frejohk 's "Support and Invertibility in Domain-Invariant Representations" & @apodosin 's "Overcomplete Independent Component Analysis via SDP" (both to be posted soon), & Hunter Lang's "Block Stability for MAP Inference" ()

Tweet card media

Block Stability for MAP Inference

To understand the empirical success of approximate MAP inference, recent work (Lang et al., 2018) has shown that some popular approximation algorithms perform very well when the input instance is...

0

8

65

@david_sontag

David Sontag

4 years

The 6 strategic areas MIT will be hiring in in the College of Computing (not all this year): social, economic, & ethical implications; natural intelligence; human health; *planetary* health; human experience; quantum computing

Tweet card media

Six strategic areas identified for shared faculty hiring in computing

The MIT Schwarzman College of Computing is creating 25 new faculty positions that will be shared between the college and an MIT department or school. Hiring will focus on six strategic areas of...

0

7

64

@david_sontag

David Sontag

8 years

Great article on interpretability in machine learning. Keep in mind: even linear models have some of these pitfalls!

0

42

60

@david_sontag

David Sontag

5 years

Working in the area of medical data science and want to be a tenure-track Assistant Professor at MIT? We've got a new opening joint between EECS and the Institute for Medical Engineering and Science. Apply by Feb 28th! @MIT_IMES @MITEECS @MIT_CSAIL

1

27

62

@david_sontag

David Sontag

6 years

ML faculty team “Punsupervised Learning” for scavenger hunt at Friday evening’s @MITEECS Ph.D. visit day, w/ Tamara Broderick, @jacobandreas , and Song Han

Tweet media one

1

3

61

@david_sontag

David Sontag

4 years

Paper deadline for #UAI2021 is Feb 19. Program chairs are Marloes Maathuis & @cassiopc , general chairs @david_sontag & Jonas Peters. Virtual conference will be July 27-30, single track, with assigned discussants for select papers

2

18

58

@david_sontag

David Sontag

5 years

@MichaelOberst and I tackle the following question in our upcoming ICML 2019 paper, motivated by our lab's research of ML in healthcare: How do you build trust in a new policy learned by reinforcement learning from observational data?

Tweet media one

1

14

58

@david_sontag

David Sontag

3 years

Runner-ups for best paper award #UAI2021 go to Batya Kenig Approximate Implication with d-Separation Francisco Ruiz, Michalis Titsias @TaylanCemgilML @ArnaudDoucet1 Unbiased Gradient Estim. for VAEs using Coupled Markov Chains

1

10

56

@david_sontag

David Sontag

6 years

@ShalitUri The title of Google's paper and the abstract's emphasis on deep learning is indeed misleading, given that a simple regression on a reasonable feature set gets similar performance (as I predicted back in February: ). /1

@david_sontag

David Sontag

7 years

@eigenhector @zacharylipton @Google @MarzyehGhassemi @davekale @JeffDean Where are the results reported for this l1-regularized linear model, using the same features? The title and abstract emphasize the term "deep". Academic papers shouldn't be marketing tools: we should avoid hype unless it is actually warranted by the results.

0

0

16

3

9

54

@david_sontag

David Sontag

5 years

Practical problem: you have a dataset and want to do causal inference. How to report the validity region, i.e. where the new policy should be used? Joint w/ @frejohk , Dennis Wei, @MichaelOberst , Tian Gao, @bratogram , @krvarshney (part of the @MITIBMLab ):

Tweet media one

0

16

57

@david_sontag

David Sontag

4 years

Registration now open for #UAI2020 , Aug 3-6, and all accepted papers are posted. Jonas, @VibhavGogate , @ryan_p_adams and I are so excited about the program!

Tweet media one

2

23

55

@david_sontag

David Sontag

6 years

Thoughtful article by Abraham Verghese @cuttingforstone : How Tech Can Turn Doctors Into Clerical Workers

3

12

52

@david_sontag

David Sontag

1 year

Exciting expert panel beginning @MITCSAIL as part of #chilconference

Tweet media one

2

4

57

@david_sontag

David Sontag

6 years

@ShalitUri I encourage folks to see slides 8-13 of my March talk at the AMIA summit "The (Current) Limits of Deep Learning in Health Care" () tl;dr: RNNs for risk stratification on longitudinal clinical data don't yet outperform simpler models, and for good reasons /2

2

7

53

@david_sontag

David Sontag

7 years

Machine learning of disease-symptom graph from medical records of 273,174 ER patients @MIT_IMES @MIT_CSAIL @BIDMCEM

0

22

53

@david_sontag

David Sontag

4 years

Pete Szolovits and I are looking for a TA for our MITx course Machine Learning for Healthcare, which will launch in early 2021 (~5 hr/week commitment). Please DM or email me if interested! Looking for PhD students or recent PhD graduates with research and/or industry experience.

2

8

53

@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

Tweet card media

B14 Fast, Structured Clinical Documentation via Contextual Autocomp...

www.youtube.com

0

8

50

@david_sontag

David Sontag

7 years

Still uncommon in unsupervised machine learning to have an algorithm that we both understand theoretically and which works well in practice -- our work on topic modeling is one example: Thanks to @blei_lab for perspective:

1

9

50

@david_sontag

David Sontag

5 years

Recommendations for a well-written causal inference from observational data paper on COVID-19 that I can cover in my MIT Machine Learning for Health Care class next week? @_MiguelHernan @barbradickerman @francescadomin8 @ShalitUri @suchisaria @SanjatKanjilal

7

4

51

@david_sontag

David Sontag

1 year

At MIT we are developing an AI-based tool to make doctors’ notes easier to read for patients. We are recruiting breast cancer patients for a user study with their notes. Participants will get $30 compensation. If interested, see . Please help advertise!

1

22

50

@david_sontag

David Sontag

5 years

Benchmarks for Bayesian deep learning. E.g., one can use this to quickly evaluate algorithms that "predict diabetic retinopathy, and use their uncertainty for prescreening (sending patients the model is uncertain about to an expert for further examination)"

@yaringal

Yarin

5 years

Really excited to release Bayesian Deep Learning Benchmarks - please share with others who you think might like this, and have a look at the blog/repo/colab: This work was done over a period of a year and a half by many collaborators @OATML_Oxford

Tweet media one

Tweet media two

9

405

1K

0

14

49

@david_sontag

David Sontag

3 years

Our #MLHC2021 paper, latest work in collaboration between @MIT and @sloan_kettering . We show we can reduce 80% of model errors with less than 15% of the manual annotation effort.

@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

0

6

47

@david_sontag

David Sontag

4 years

Reminiscing about what ICML and NeurIPS workshops used to be like in the early 2000's, when they were focused and had actual discussion & brainstorming about research in progress? Let's recreate that experience. Submit a workshop proposal for #UAI2021 !

@csilviavr

Silvia Chiappa

4 years

#UAI2021 will have a separate day for workshops! The call for workshop proposals is at Deadline: March 8 @UncertaintyInAI

1

6

23

0

3

48

@david_sontag

David Sontag

5 years

Best Treatment for the Coronavirus? Paid Sick Leave ("The government could defray the cost of emergency sick leave for employers, for example by allowing businesses to claim a one-time tax credit")

0

12

47

@david_sontag

David Sontag

2 years

I'm teaching a 3-day Machine Learning for Healthcare class (in person, at MIT) from June 27-29 through @MITProfessional incl. labs applying ML to health data, a sneak peak at the state-of-the-art research, and Q&As with health AI leaders in industry.

Machine Learning for Healthcare | Professional Education

professional.mit.edu

0

9

47

@david_sontag

David Sontag

4 years

So excited to see this first BIG step in the right direction. This is what can happen when we invest in health IT, informatics research, and common data models such as i2b2 and OMOP.

@hmkyale

Harlan Krumholz

4 years

Great by @zakkohane and colleagues: Consortium for Clinical Characterization of COVID-19 by EHR (4CE). Harmonized data sets analyzed locally and shared as aggregate data for rapid analysis and visualization. Great teamwork. Like @OHDSI . @medrxivpreprint

Tweet media one

0

17

53

1

17

47

@david_sontag

David Sontag

3 years

Looking for a postdoc and passionate about conducting research in foundational ML and disease biology? Come join the new Eric & Wendy Schmidt Center @broadinstitute ! I'm affiliate faculty and would be thrilled to collaborate - mention my name

www.broadinstitute.org

1

10

43

@david_sontag

David Sontag

8 years

Video of our ICML 2016 tutorial on causal inference for observational studies is now online:

3

15

44

@david_sontag

David Sontag

3 years

Excited about teaching the next generation of MIT undergrads about machine learning? We're hiring lecturer(s) and would love your application!

1

5

43

@david_sontag

David Sontag

3 years

We've had previous success with clinicians in Boston taking MIT's Machine Learning for Healthcare class - come join next year's cohort! Apply here: Some background in Python & machine learning needed, but we will help with resources to guide learning.

ADVANCED STUDY PROGRAM APPLICATION | Professional Education

professional.mit.edu

@DrMadhurNayan

Madhur Nayan

3 years

Attention clinicians interested in #MachineLearning : apply NOW (deadline Nov 1) to the Advanced Study Program @MIT to take 6.871 Machine Learning for Healthcare in Spring 2022. Check out last year's syllabus #AI #clinicianscientist #digitalhealth

1

2

15

0

10

43

@david_sontag

David Sontag

7 years

Our recent work on causal inference under hidden confounding.

@StatMLPapers

Stat.ML Papers

7 years

Causal Effect Inference with Deep Latent-Variable Models. (arXiv:1705.08821v1 [stat.ML])

1

11

25

0

19

39

@david_sontag

David Sontag

4 years

When deciding what treatment to prescribe, we don't always need exact counterfactual estimates - bounds might suffice. And we can estimate accurate bounds using less data! #ICML2020 paper with @Maggiemakar , @frejohk , and John Guttag

Tweet card media

[ICML 2020] Estimation of Bounds on Potential Outcomes For Decision...

ICML 2020 video presentation for "Estimation of Bounds on Potential Outcomes For Decision Making". Full paper arxiv link https://arxiv.org/abs/1910.04817

www.youtube.com

1

5

42

@david_sontag

David Sontag

2 years

Truly enjoyed today's @MITEECS Thriving Stars of AI highlighting the research of 4 stellar current and recent Ph.D. graduate women, @cen_sarah @irenetrampoline @DaniGetzen and @ShibaniSan + panel with our department's fearless leader Asu Ozdaglar. MC'd flawlessly by @AudeOliva

Tweet media one

0

2

42

@david_sontag

David Sontag

5 years

Slide from my sister @LauraBKleiman 's @CWR4C talk @kochinstitute @MIT yesterday on drug repurposing for cancer Real-world data + observational data -> real-world evidence ML, causal inference, health data sets This could have been one of my talks!

Tweet media one

2

2

42

@david_sontag

David Sontag

5 years

@overleaf Could you push your maintenance forward by a day? There's a major machine learning conference (ICML) paper deadline a few hours after your maintenance period, and many folks will be using Overleaf during that time.

1

7

40

@david_sontag

David Sontag

6 years

Boston-area postdocs, want to devote one day per week (funded) to participate in a new approach to biomedical research? Join the MIT Catalyst program! In past projects, 75% went on to receive follow-on funding; 44% transitioned to commercial development.

0

18

38

@david_sontag

David Sontag

7 years

@zacharylipton @Google @MarzyehGhassemi @davekale @JeffDean @JeffDean , while you are revising the paper, please consider adding a "simple" machine learning baseline of l1-regularized logistic regression using the same inputs as your deep models and backward time windows (see , "Enhanced model", for an example).

3

4

38

@david_sontag

David Sontag

4 years

Schedule for #UAI2020 (Aug 3-6) is now live, and is a great way to look through the accepted papers Register here:

Uncertainty in Artificial Intelligence

0

12

35

@david_sontag

David Sontag

4 years

@StanfordMed and @drnigam lead the way with institution-wide research access to de-identified data in OMOP common data model.

Tweet media one

1

14

38

@david_sontag

David Sontag

7 years

Looking forward to our AMIA-CRI panel Thursday morning on "Deep Learning for Healthcare - Hype or the real thing?"! Submit questions for the panel here: @nicktatonetti #TBICRI18 @AMIAinformatics @jimeng @MarzyehGhassemi

0

12

37

@david_sontag

David Sontag

5 years

I've recently starting using the phrase "target deployment" to characterize how ML in health care should be evaluated, in analogy to @_MiguelHernan 's "target trial"

@drnigam

Nigam Shah

5 years

Typically, we evaluate models, then quantify potential net-benefit, and realize some of it with real world operational constraints. I believe we can do a lot better in taking actions in response to a prediction. See our JAMA viewpoint @StanfordDeptMed

7

58

127

1

5

35

@david_sontag

David Sontag

3 years

Public service announcement for folks with links on their websites to previously recorded @icmlconf / @NeurIPSConf / @aclmeeting talks @TechTalksTV - you will want to remove the links. The website has been taken over by spammers.

1

8

34

@david_sontag

David Sontag

3 years

#UAI2021 is beginning now, with a keynote talk by @SusanMurphylab1 . Have a great conference everyone!

Tweet media one

1

3

34

@david_sontag

David Sontag

3 years

Day two of #UAI2021 begins with a keynote talk by @zdeborova

Tweet media one

0

4

31

@david_sontag

David Sontag

3 years

We then built machine learning algorithms to automatically extract or highlight these action items from hospital discharge notes. Too often things fall between the cracks during transitions in care. Time to change.

Tweet card media

CLIP: A Dataset for Extracting Action Items for Physicians from...

Continuity of care is crucial to ensuring positive health outcomes for patients discharged from an inpatient hospital setting, and improved information sharing can help. To share information,...

0

7

31

@david_sontag

David Sontag

10 months

Our NeurIPS '23 paper by @HsseinMzannar and colleagues at @MITIBMLab featured on MIT homepage today. Article here --

Tweet media one

0

1

33

@david_sontag

David Sontag

4 years

Our edX course on Machine Learning for Healthcare has launched, and starts March 15th! Sign up here:

2

12

29

@david_sontag

David Sontag

5 years

It was great to visit the ASAPP Argentina office for the first time!

@asapplatam

ASAPP Latam

5 years

Y con la oficina a full arrancamos la charla de David Sontag “How is Machine Learning going to change Healthcare”

Tweet media one

Tweet media two

0

9

29

0

2

31

@david_sontag

David Sontag

6 years

This is for my Machine Learning for Healthcare class this Spring at MIT @irenetrampoline @WilliamBoag @AndrewLBeam @oziadias @gbratmd @zakkohane @sherrirose

2

2

28

@david_sontag

David Sontag

7 years

@JeffDean @zacharylipton @Google @MarzyehGhassemi @davekale Agreed. However, please consider for v3. I often find that the gap is quite small between cleverly designed deep models and variants of the simple approach I suggested -- on precisely the same problems that you've looked at.

1

1

30

@david_sontag

David Sontag

5 years

Congratulations to my former student Helen Zhou for being awarded a PD Soros Fellowship!

Tweet card media

Helen Zhou – Paul & Daisy Soros Fellowships for New Americans

@helenz1235

Helen Zhou

5 years

Elated to share that I've been named a 2019 @PDSoros fellow! I'm very honored and blessed to be part of such an incredible community which highlights the immigrant experience and American dream. 🇺🇸🇺🇸

4

1

57

1

0

29

@david_sontag

David Sontag

6 years

Next MIT ML for Healthcare consulting session is this Weds. March 20th! Full list of dates/times for the semester here:

@david_sontag

David Sontag

6 years

MIT's free Machine Learning for Healthcare consulting sessions begin March 5th at 5pm. All clinician researchers from the Boston area are welcome! Sign up here:

Tweet media one

3

39

90

1

7

28

@david_sontag

David Sontag

8 years

@NandoDF massive computing will only be the start! combining causal models with deep learning (+ physics-based simulators) will be essential

3

4

28