Noémie Elhadad Associate Professor in Biomedical Informatics Affiliated with Computer Science Data Science Institute Columbia University 622 W. 168th Street, PH-20 New York, NY 10032 noemie.elhadad @ columbia.edu

My research is at the intersection of machine learning, natural language processing, and medicine. I develop techniques that support clinicians, patients, and health researchers in their information workflow by deriving insights from large observational clinical data (e.g., the electronic patient record) and patient-generated data (e.g., online health communities and mobile health). My research relies on two types of methods: (1) I design novel computational approaches that infer models of health phenomena and account for the specific biases of large health data; (2) I translate the learned models into actionable knowledge and robust systems within the healthcare ecosystem (e.g., a patient record summarization system for clinicians at the point of care).

Besides doing research, I spend time with Anna, I listen to music on thisismyjam, and I make lists (see below).

Current projects include

• Citizen Endo, phenotyping endometriosis together with patients (@citizen_endo)
• HARVEST, a patient record summarization system
• Phenome, a large-scale probabilistic phenotyping model based on clinical records
• hNLP, methods and resources for natural language processing of health texts.

• (Sep 2018) Chris was awarded a Dean's Research Fellowship from the Columbia Vagelos College of Physicians & Surgeons.
• (Jul 2018) I am the new Graduate Program Director at DBMI.
• (Jun 2018) I gave a talk at the Friends of National Library of Medicine at the Data Science Innovation Symposium.
• (Jun 2018) Daniel joined the JAMIA Student Editorial Board.
• (Jun 2018) Ipek is one of the Data Science Institute Fellow.
• (May 2018) The lab had a one week OHDSI bootcamp together with the Janssen OHDSI folks (Patrick Ryan, Chris Knoll, Anthony Sena, and Jenna Reps).
• (Jan 2018) I will be teaching a new course at DBMI in Spring: Data Science for mHealth. Seminar style, with hands-on labs and a project. Datasets, sensors, and phones available. Register!
• (Nov 2017) The lab is getting ready to go to the ML4H workshop at NIPS. Come say hi!
• (Nov 2017) Rimma was awarded first prize for the AMIA Doctoral Dissertation Award.
• (Oct 2017) I gave a talk open to all on data science for endometriosis at the "Get a Clue" series organized by Clue.
• Old news
  

 
Teaching and Advising

• Starting July 2018, I am Graduate Program Director for the Department of Biomedical Informatics.
• Research Group: Oliver Bear Don't Walk IV, Chris Dambrosia, Ipek Ensari, Daniel Feller, Sharon Lipsky Gorman, Kai Jones, Karan Jani, Gal Levy-Fix, Mollie McKillop, Iñigo Urteaga.

 
Data and Code

• Biomedical scientific articles, press releases, and news stories dataset. See (Wallace et al. 2015) for more details.
• Redundancy removal and redundancy-aware topic modeling for longitudinal patient records. See (Cohen et al. 2013) and (Cohen et al. 2014) for more details.
• ICD9 coding of discharge summaries on PhysioNet. Need a PhysioNet account to access all MIMIC II data and code. See (Perotte et al. 2013) for more details.
• Unsupervised named-entity recognition for bio and clinical texts. See (Zhang and Elhadad 2013) for more details.
  
• Lexical simplification, code and test set. See (Biran, Brody, Elhadad 2011) for more details.
  
• Restaurant review corpus, annotated with topic and sentiment labels at the sentence level.
  
• Sentence ordering for text summarization.
  
• Sentence alignment for monolingual comparable corpora.

 
Publications (updated version at Google scholar)

• Gal Levy-Fix, Sharon Lipsky-Gorman, Jorge Sepulveda, Noémie Elhadad.
  When to Re-Order Laboratory Tests? Learning Laboratory Test Shelf-Life.
  2018. Journal of Biomedical Informatics. 85:21-29. [html]
   
• Xenia Miscouridou, Adler Perotte, Noémie Elhadad, Rajesh Ranganath.
  Deep Survival Analysis: Nonparametrics and Missingness.
  2018. Machine Learning for Healthcare. [pdf]
   
• Mollie McKillop, Lena Mamykina, Noémie Elhadad.
  Designing in the Dark: Eliciting Self-Tracking Dimensions for Understanding Enigmatic Diseases.
  2018. ACM SIGCHI conference on Human Factors in Computing Systems, CHI 2018. [pdf]
   
• Tal Baumel, Jamana Nassour-Kassis, Raphael Cohen, Michael Elhadad, Noémie Elhadad.
  Multi-Label Classification of Patient Notes: Case Study on ICD Code Assignment.
  2018. AAAI Workshop on Health Intelligence. arXiv.
   
• Daniel Feller, Jason Zucker, Michael Yin, Peter Gordon, Noémie Elhadad.
  Using clinical notes and natural language processing for automated HIV risk assessment.
  2018. Journal of Acquired Immune Deficiency Syndromes. 77(2):160-166.
   
• Shaodian Zhang, Tian Kang, Lin Qiu, Weinan Zhang, Yong Yu, Noémie Elhadad.
  Cataloguing treatments discussed and used in online autism communities.
  2017. World Wide Web (WWW'17). Perth, Australia. [pdf]
   
• Shaodian Zhang, Lin Qiu, Frank Chen, Weinan Zhang, Yong Yu, Noémie Elhadad.
  "We make choices we think are going to save us": Debate and stance identification for online breast cancer CAM discussions.
  2017. WWW Web Science Track. Perth, Australia. [pdf]
   
• Mollie McKillop, Natalie Voigt, Rebecca Schnall, Noémie Elhadad.
  Exploring Self-Tracking as a Participatory Research Activity Among Women with Endometriosis.
  2016. Journal of Participatory Medicine. 8:e17. [html]
   
• Rajesh Ranganath, Adler Perotte, Noémie Elhadad, David Blei.
  Deep Survival Analysis.
  2016. Machine Learning in Healthcare (MUCMD). Los Angeles, CA. [pdf]
   
• Rimma Pivovarov, Yael Coppleson, Sharon Lipsky Gorman, David Vawdrey, Noémie Elhadad.
  Can Patient Record Summarization Support Quality Metric Abstraction?
  2016. AMIA Fall Symposium. Chicago, IL. [pdf]
   
• Shaodian Zhang, Noémie Elhadad.
  Factors Contributing to Dropping-out in an Online Health Community: Static and Longitudinal Analyses.
  2016. AMIA Fall Symposium. Chicago, IL. [pdf]
   
• Shaodian Zhang, Erin O'Carroll Bantum, Jason Owen, Suzanne Bakken, Noémie Elhadad.
  Online cancer communities as informatics intervention for social support: Conceptualization, Characterization, and Impact.
  2016. Journal of the American Medical Informatics Association (JAMIA). [html]
   
• Shaodian Zhang, Edouard Grave, Elizabeth Sklar, Noémie Elhadad.
  Longitudinal analysis of discussion topics in an online breast cancer community using convolutional neural networks.
  2016. Journal of Biomedical Informatics. 69:1-9. arXiv.
   
• Dina Demner-Fushman, Noémie Elhadad.
  Aspiring to Unintended Consequences of Natural Language Processing: A Review of Recent Developments in Clinical and Consumer-Generated Text Processing.
  2016. IMIA Yearbook of Medical Informatics. [html]
   
• Ye Zhang, Erin Willis, Michael Paul, Noémie Elhadad, Byron Wallace.
  A Data-Driven Approach to Characterizing the (Perceived) Newsworthiness of Health Science Articles.
  2016. JMIR Medical Informatics. 4(3):e27;1-20. [html]
   
• Shaodian Zhang, Tian Kang, Xingting Zhang, Dong Wen, Noémie Elhadad, Jianbo Lei.
  Speculation Detection for Chinese Clinical Notes: Impacts of Word Segmentation and Embedding Models.
  2016. Journal of Biomedical Informatics (JBI). 60:334-341. [html]
   
• Lena Mamykina, Matthew Levine, Patricia Davidson, Arlene Smaldone, Noémie Elhadad, David Albers.
  Reasoning about Personally Generated Nutritional Data in Diabetes with Information Technology.
  2016. Journal of the American Medical Informatics Association (JAMIA). [html]
   
• Rimma Pivovarov, Adler Perotte, Edouard Grave, John Angiolillo, Chris Wiggins, Noémie Elhadad.
  Learning Probabilistic Phenotypes from Heterogeneous EHR Data.
  2015. Journal of Biomedical Informatics (JBI). 58:156-165. [html]
   
• Rajesh Ranganath, Adler Perotte, Noémie Elhadad, David Blei.
  The Survival Filter: Joint Survival Analysis with a Latent Time Series.
  2015. UAI. Amsterdam, Netherlands. [pdf]
   
• Edouard Grave, Noémie Elhadad.
  A Convex and Feature-rich Discriminative Approach to Dependency Grammar Induction.
  2015. ACL. pp 1375-1384. Beijing, China. [pdf]
   
• Rich Caruana, Yin Lou, Johannes Gehrke, Paul Koch, Marc Sturm, Noémie Elhadad.
  Intelligible Models for Healthcare: Predicting Pneumonia Risk and Hospital 30-day Readmission.
  2015. KDD. pp 1721-1730. Sidney, Australia. [pdf]
   
• Rimma Pivovarov, Noémie Elhadad.
  Automated Methods for the Summarization of Electronic Health Records.
  2015. Journal of the American Medical Informatics Association (JAMIA). 22(5):938-947. [html]
   
• Adler Perotte, Rajesh Ranganath, Jamie Hirsch, David Blei, Noémie Elhadad.
  Risk Prediction for Chronic Kidney Disease Progression Using Heterogeneous Electronic Health Record Data and Time Series Analysis.
  2015. Journal of the American Medical Informatics Association (JAMIA). 22(4):872-880. [html]
   
• Byron Wallace, Michael Paul, Noémie Elhadad.
  What Predicts Media Coverage of Health Science Articles?
  2015. AAAI W3PHI Workshop on the World Wide Web and Public Health Intelligence. [pdf]
   
• Lena Mamykina, Drashko Nakikj, Noémie Elhadad.
  Collective Sensemaking in Online Health Forums.
  2015. CHI. Seoul, Korea. pp. 3217-3226. [html]
   
• Jamie Hirsch, Jessica Tanenbaum, Sharon Lipsky Gorman, Connie Liu, Eric Schmitz, Dritan Hashorva, Artem Ervits, David Vawdrey, Marc Sturm, Noémie Elhadad.
  HARVEST, a Longitudinal Patient Record Summarizer.
  2015. Journal of the American Medical Informatics Association (JAMIA). 22(2):263-274. [html]
   
• Sameer Pradhan, Noémie Elhadad, Brett South, David Martinez, Lee Christensen, Amy Vogel, Hanna Suominen, Wendy Chapman, Guergana Savova.
  Evaluating the State of the Art in Disorder Recognition and Normalization of Clinical Narrative.
  2015. Journal of the American Medical Informatics Association (JAMIA). 22(1):143-154. [html]
   
• Noémie Elhadad, Sharon Lipsky Gorman, Jamie Hirsch, Connie Liu, David Vawdrey, Marc Sturm.
  HARVEST, a Holistic Patient Record Summarizer at the Point of Care.
  2014. AMIA Fall Symposium. [pdf]
   
• Noémie Elhadad, Luis Gravano, Daniel Hsu, Sharon Balter, Vasudha Reddy, HaeNa Waechter.
  Information Extraction from Social Media for Public Health.
  2014. KDD at Bloomberg Workshop. [pdf]
   
• Shaodian Zhang, Erin Bantum, Jason Owen, Noémie Elhadad.
  Does Sustained Participation in an Online Health Community Affect Sentiment?
  2014. AMIA Fall Symposium. pp. 1970-1979. Washington, DC. [pdf]
   
• Noémie Elhadad, Shaodian Zhang, Patricia Driscoll, and Samuel Brody.
  Characterizing the Sublanguage of Online Breast Cancer Forums for Medications, Symptoms, and Emotions.
  2014. AMIA Fall Symposium. pp. 516-525. Washington, DC. [pdf]
   
• Yolanda Hagar, David Albers, Rimma Pivovarov, Vanja Dukic, and Noémie Elhadad.
  Survival Analysis Adapted for Electronic Health Record Data: Experiments with Chronic Kidney Disease.
  2014. Statistical Analysis and Data Mining. 7(5):385-403. [html]
   
• Rimma Pivovarov, David Albers, Jorge Sepulveda, George Hripcsak, and Noémie Elhadad.
  Temporal Trends of Hemoglobin A1c Testing.
  2014. Journal of the American Medical Informatics Association (JAMIA). 21:1038-1044. [html]
   
• Rimma Pivovarov, David Albers, Jorge Sepulveda, and Noémie Elhadad.
  Identifying and Mitigating Biases in EHR Laboratory Tests.
  2014. Journal of Biomedical Informatics. 51:24-34. [html]
   
• Preethi Raghavan, Eric Fosler-Lussier, Noémie Elhadad, and Albert Lai.
  Cross-narrative Temporal Ordering of Medical Events.
  2014. ACL. pp. 998-1008. Baltimore, MD. [pdf]
   
• David Albers, Noémie Elhadad, Esteban Tabak, Adler Perotte, and George Hripcsak.
  Dynamical phenotyping: Using Temporal Analysis of Clinically Collected Physiologic Data to Stratify Populations.
  2014. PLoS ONE 9(6): e96443. [html]
   
• Raphael Cohen, Iddo Aviram, Michael Elhadad, and Noémie Elhadad.
  Redundancy-Aware Latent Dirichlet Allocation for Patient Record Notes.
  2014. PloS ONE 9(2): e87555. [html]
   
• Colin Walsh and Noémie Elhadad.
  Modeling Clinical Context: Rediscovering the Social History and Evaluating Language from the Clinic to the Wards.
  2014. AMIA Join Summits on Translational Science. [pdf]
   
• Adler Perotte, Rimma Pivovarov, Karthik Natarajan, Nicole Weiskopf, Frank Wood, and Noémie Elhadad.
  Diagnosis Code Assignment: Models and Evaluation Metrics.
  2014. Journal of the American Medical Informatics Association (JAMIA). 21(2):231-237. [html]
   
• Shaodian Zhang and Noémie Elhadad.
  Unsupervised Biomedical Named Entity Recognition: Experiments with Clinical and Biological Texts.
  2013. Journal of Biomedical Informatics. 46(6):1088-1098. [pdf]
   
• Samantha Kleinberg and Noémie Elhadad.
  Lessons Learned in Replicating Data-Driven Experiments in Mulitple Medical Systems and Patient Populations.
  2013. AMIA Annual Symposium. [pdf]
   
• Raphael Cohen, Michael Elhadad, and Noémie Elhadad.
  Redundancy in Electronic Health Record Corpora: Analysis, Impact on Text Mining Performance, and Mitigation Strategies.
  2013. BMC Bioinformatics. 14:10. [pdf]
   
• Patricia Driscoll, Sharon Lipsky Gorman, and Noémie Elhadad.
  Learning Attribution Labels for Disorder Mentions in Online Health Forums.
  2013. SIGIR Workshop on Health Search and Discovery, pp. 3-6. [pdf]
   
• Chaitanya Shivade, Preethi Raghavan, Eric Fosler-Lussier, Peter Embi, Noémie Elhadad, Stephen Johnson, Albert Lai.
  A review of approaches to identifying patient phenotype cohorts using electronic health records.
  2013. Journal of the American Medical Informatics Association (JAMIA). [in press]
   
• Sunmoo Yoon, Noémie Elhadad, Suzanne Bakken.
  A practical approach for content mining of tweets.
  2013. American Journal of Preventive Medicine. 45(1):122-129.
   
• Rimma Pivovarov and Noémie Elhadad.
  A Hybrid Knowledge-Based and Data-Driven Approach to Identifying Semantically Similar Concepts.
  2012. Journal of Biomedical Informatics. 45(3):471-81. [pdf]
   
• Hua Xu, Yonghui Wu, Noémie Elhadad, Peter Stetson, Carol Friedman.
  A New Clustering Method for Detecting Rare Senses of Abbreviations in Clinical Notes.
  2012. Journal of Biomedical Informatics. 45(6):1075-83.
   
• Adler Perotte, Nicholas Bartlett, Noémie Elhadad, and Frank Wood.
  Hierarchically Supervised Latent Dirichlet Allocation.
  2011. NIPS, pp. 2609-2617. [pdf]
   
• Or Biran, Samuel Brody, and Noémie Elhadad.
  Putting it Simply: a Context-Aware Approach to Lexical Simplification.
  2011. ACL, pp. 496-501. Portland, OR. [pdf]
   
• Mukund Jha and Noémie Elhadad.
  Cancer Stage Prediction Based on Patient Online Discourse.
  2010. ACL BioNLP Workshop, pp. 64-71. Uppsala, Sweden. [pdf]
   
• Daniel Reichert, David Kaufman, Benjamin Bloxham, Herbert Chase, and Noémie Elhadad.
  Cognitive Analysis of the Summarization of Longitudinal Patient Records.
  2010. AMIA Annual Symposium, pp.667-671. Washington, DC. [pdf]
   
• Lijun Feng, Martin Jansche, Matt Huenerfauth, and Noémie Elhadad.
  A Comparison of Features for Automatic Readability Assessment.
  2010. COLING, pp. 276-284. Beijin, China. [pdf]
   
• Julia Hirschberg, Anna Hjalmarsson, and Noémie Elhadad.
  "You're as Sick as You Sound" Using Computational Approaches for Modeling Speaker State to Gauge Illness and Recovery.
  2010. in Speech in Mobile Environments, Call Centers and Clinic. Edited by Amy Neustein, Ph.D., Springer. [in press]
   
• Samuel Brody and Noémie Elhadad.
  An Unsupervised Aspect-Sentiment Model for Online Reviews.
  2010. NAACL, pp. 804-812. Los Angeles, CA. [pdf]
   
• Samuel Brody and Noémie Elhadad.
  Detecting Salient Aspects in Online Reviews of Health Providers.
  2010. AMIA Annual Symposium, pp. 202-206. Washington, DC. [pdf]
   
• Ying Li, Sharon Lipsky Gorman, and Noémie Elhadad.
  Section Classification in Clinical Notes Using a Supervised Hidden Markov Model.
  2010. ACM International Health Informatics Symposium (IHI), pp. 744-750. Washington, DC. [pdf]
   
• Karthik Natarajan, Daniel Stein, Samat Jain, and Noémie Elhadad.
  An Analysis of Clinical Queries in an Electronic Health Record Search Utility.
  International Journal of Medical Informatics (IJMI), 2010, 79:515-522. [pdf]
   
• Karthik Natarajan, Daniel Stein, Samat Jain, and Noémie Elhadad.
  CISearch: What do Clinicians Search for within the EHR?
  2009. AMIA Annual Symposium. San Francisco, CA. Best Student Paper Finalist.
   
• Lijun Feng, Noémie Elhadad, and Matt Huenerfauth.
  Cognitively Motivated Features for Readability Assessment.
  2009. EACL, pp. 229-237. Athens, Greece. [pdf]
   
• Matt Huenerfauth, Lijun Feng, and Noémie Elhadad.
  Comparing Evaluation Techniques for Text Readability Software for Adults with Intellectual Disabilities.
  2009. ASSETS, pp. 3-10. Pittsburgh, PA. [pdf]
   
• Gayatree Ganu, Noémie Elhadad, and Amélie Marian.
  Beyond the Stars: Improving Rating Predictions using Review Text Content.
  2009. WebDB. Providence, RI. [pdf]
   
• George Hripcsak, Noémie Elhadad, Cynthia Chen, Li Zhou, Frances P. Morrison.
  Using Empirical Semantic Correlation to Deduce Meaning in Temporal Assertions in Clinical Texts.
  Journal of the American Medical Informatics Association (JAMIA), 2009, 16:220-227. [html]
   
• Sigfried Gold, Noémie Elhadad, Xinxin Zhu, James Cimino, and George Hripcsak.
  Extracting Structured Medication Event Information from Discharge Summaries.
  2008. AMIA Annual Symposium, pp. 237-241. Washigton, DC. Distinguished Paper Award. [pdf]
   
• Patrick McCormick, Noémie Elhadad, and Peter Stetson.
  Use of Semantic Features to Classify Patient Smoking Status.
  2008. AMIA Annual Symposium, pp. 450-454. Washington, DC. Best Student Paper Finalist. [pdf]
   
• Tielman Van Vleck, Adam Wilcox, Peter Stetson, Stephen Johnson, and Noémie Elhadad.
  Content and Structure of Clinical Problem Lists: A Corpus Analysis.
  2008. AMIA Annual Symposium, pp. 753-757. Washington, DC. [pdf]
   
• Xiaoyan Wang, Amy Chused, Noémie Elhadad, Carol Friedman, and Marianthi Markatou.
  Automated Knowledge Acquisition from Clinical Narrative Reports.
  2008. AMIA Annual Symposium, pp. 783-787. Washington, DC. [pdf]
   
• Noémie Elhadad and Komal Sutaria.
  Mining a Lexicon of Technical Terms and Lay Equivalents.
  2007. ACL BioNLP Workshop, pp. 49-56. Prague, Czech Republic. [pdf]
   
• Noémie Elhadad.
  Comprehending Technical Texts: Predicting and Defining Unfamiliar Terms.
  2006. AMIA Annual Symposium, pp. 239-243. Washington, DC. [pdf]
   
• Noémie Elhadad.
  User-Sensitive Text Summarization: Application to the Medical Domain.
  Ph.D. Thesis, Columbia University, January 2006. [pdf]
   
• Noémie Elhadad, Kathleen McKeown, David Kaufman, and Desmond Jordan.
  Facilitating Physicians' Access to Information via Tailored Text Summarization.
  2005. AMIA Annual Symposium, pp. 226-230. Washington, DC. [pdf]
   
• Noémie Elhadad, Min-Yen Kan, Judith Klavans, and Kathleen McKeown.
  Customization in a Unified Framework for Summarizing Medical Literature.
  Journal of Artificial Intelligence in Medicine, 2005, 33(2):179-198. in press
   
• Noémie Elhadad.
  User-Sensitive Text Summarization.
  2004. AAAI Doctoral Consortium, pp. 987-988. San Jose, CA. [pdf]
   
• Regina Barzilay and Noémie Elhadad.
  Sentence Alignment for Monolingual Comparable Corpora.
  2003. EMNLP, pp. 25-32. Sapporo, Japan. [pdf]
   
• Kathleen McKeown, Noémie Elhadad and Vasileios Hatzivassiloglou.
  Leveraging a Common Representation for Personalized Search and Summarization in a Medical Digital Library,
  2003. JCDL, pp. 159-170. Houston, TX. [pdf]
   
• Regina Barzilay, Noémie Elhadad and Kathleen McKeown.
  Inferring Strategies for Sentence Ordering in Multidocument News Summarization.
  Journal of Artificial Intelligence Research, 2002, 17:35-55. [pdf]
   
• Simone Teufel and Noémie Elhadad.
  Collection and Linguistic Processing of a Large-scale Corpus of Medical Articles.
  2002. LREC, pp. 1214-1218. Canary Islands, Spain. [pdf]
   
• Noémie Elhadad and Kathleen McKeown.
  Towards Generating Patient Specific Summaries of Medical Articles.
  2001. NAACL Workshop on Automatic Summarization, pp. 31-39. Pittsburgh, PA. [pdf]
   
• Regina Barzilay, Noémie Elhadad and Kathleen McKeown.
  Sentence Ordering in Multidocument Summarization,
  2001. HLT, pp. 318-324. San Diego, CA. [pdf]