About

Mohamed Abdalla is a Scientist at the AIDE Lab in the Institute for Better Health at Trillium Health Partners. He earned his PhD in Computer Science from the Natural Language Processing Group (Department of Computer Science) at the University of Toronto in 2022. He was also a Vanier scholar, and was advised by Professor Frank Rudzicz and Professor Graeme Hirst. He holds affiliations with: i) Vector Institute for Artificial Intelligence, ii) Centre for Ethics, iii) ICES (formerly known as the Institute for Clinical and Evaluative Sciences).

Education

• PhD, 2022; University of Toronto
• MSc, 2018; UofT
• BSc, 2016; UofT

All Publications

Journal Papers

• Hurdles to AI Deployment: Noise in Schemas and "Gold" Labels
  Radiology: Artificial Intelligence; (2023)
  Abdalla M, Fine B
  [Link] [PDF]

• Tracing the Path of 37,050 Studies into Practice Across 18 Specialties of the 2.4 million Published between 2011-2020
  eLife; (2023)
  Abdalla M, Abdalla S, Abdalla M
  [Link]

• U"AI" testing: User interface and usability testing of a chest x-ray AI tool in a simulated real-world workflow
  Canadian Association of Radiologists Journal; (2022)
  Cheung JLS, Ali A, Abdalla M, Fine B
  [Link]

• Through the Looking-Glass: Insights from the Journal of the American Medical Association and the New England Journal of Medicine
  eLife; (2022)
  Abdalla M, Abdalla M, Abdalla S, Saad M, Jones DS, Podolsky SH
  [Link] [Medical N-Gram Viewer]

• Predicting the target specialty of referral notes to estimate per-specialty wait times with machine learning
  PLoS ONE; (2022)
  Abdalla M, Lu H, Pinzaru B, Rudzicz F, Jaakkimainen L
  [Link]

• The Under-representation and Stagnation of Female, Black, and Hispanic Authorship in the Journal of the American Medical Association and the New England Journal of Medicine
  Journal of Racial and Ethnic Health Disparities; (2022)
  Abdalla M, Abdalla M, Abdalla S, Saad M, Jones DS, Podolsky SH
  [Link]
  Media Coverage: [STAT News Article]

• A general framework for predicting the transcriptomic consequences of non-coding variation and small molecules
  PLOS Computational Biology; (2022)
  Abdalla M, Abdalla M.
  [Link]

• Accuracy of algorithms to identify people with atopic dermatitis in Ontario routinely collected health databases
  Journal of Investigative Dermatology; (2021)
  Abdalla M, Chen B, Santiago R, Young J, Eder L, Chan AW, Pope E, Tu K, Jaakkimainen L, Drucker AM.
  [Link]

• Mobilizing the Masses: Measuring Resource Mobilization on Twitter
  Sociological Methods and Research; (2021)
  Abul Reda A, Sinanoglu S, Abdalla M.
  [Link]

• Exploring the privacy-preserving properties of word embeddings: Algorithmic Validation
  Journal of Medical Internet Research (JMIR); (2020)
  Abdalla M, Abdalla M, Hirst G, Rudzicz F.
  [Link]

• Using Word Embeddings to Improve the Privacy of Clinical Notes
  Journal of the American Medical Informatics Association (JAMIA); (2020)
  Abdalla M, Abdalla M, Rudzicz F, Hirst G.
  [Link]

• A common glomerular transcriptomic signature distinguishes diabetic kidney disease from other kidney diseases in humans and mice
  Current Research in Translational Medicine; (2020)
  Abdalla M, Abdalla M, Siddiqi F, Geldenhuys L, Batchu S, Tolosa M, Yuen D, dos Santos C, Advani A.
  [Link]

• Survey: Word Embeddings for Clinical Data
  Journal of Biomedical Informatics: X ; (2019)
  Khattak F, Jeblee S, Pou-Prom C, Meany C, Abdalla M, Rudzicz F.
  [Link]

• Rhetorical structure and Alzheimer's disease
  Aphasiology; (2017)
  Abdalla M, Rudzicz F, Hirst G.
  [Link]

• Mapping genomic and transcriptomic alterations spatially in epithelial cells adjacent to human breast carcinoma
  Nature Communications; (2017)
  Abdalla M, Tran-Thanh D, Moreno J, Iakovlev V, Nair R, Kanwar N, Abdalla M, Lee J, Kwan J, Cawthorn T, Warren K, Arneson N, Wang D, Fox N, Youngson B, Miller N, Easson A, McCready D, Leong W, Boutros P, Done S.
  [Link]

Refereed Conference Papers

• The Elephant in the Room: Analyzing the Presence of Big Tech in Natural Language Processing Research
  Association for Computational Linguistics (ACL); (2023)
  Abdalla M, Wahle JP, Ruas T, Névéol A, Ducel F, Mohammad SM, Fort K
  [ArXiv Link]

• What Makes Sentences Semantically Related? A Textual Relatedness Dataset and Empirical Study
  European Chapter of the Association for Computational Linguistics (EACL); (2023)
  Abdalla M, Vishnubhotla K, Mohamad S.M.
  [ArXiv Link][Data Set Link]

• The Grey Hoodie Project: Big Tobacco, Big Tech, and the threat on academic integrity
  In Proceedings, Artificial Intelligence, Ethics, and Society (AIES); (2021)
  Abdalla M, Abdalla M
  [Link] [PDF]
  Media Coverage: [WIRED Article] [VentureBeat Article] [FastCompany Article]
  Talks: [Centre for Ethics Talk] [Future of Life Podcast]

• Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
  ACM Conference on Health, Inference, and Learning (CHIL); (2020)
  Zhang H*, Lu A*, Abdalla M, McDermot M, Ghassemi M.
  [Link]

• NLP with Wearables in Healthcare: Opportunities, challenges, and considerations
  International Conference on eHealth, Telemedicine, and Social Medicine. (eTELEMED); (2020)
  Rudzicz F, Ng R, Wu R, Abdalla M, Ho K.
  [Link][Best Paper Award]

• WearBreathing: Monitoring Respiratory Rate in-the-wild using a Smartwatch
  ACM International Joint Conference on Pervasive and Ubiquitous Computing 2019; (2019)
  Liaqat D, Abdalla M , Abed-Esfahani P, Gabel M, Son T, Wu R, Gershon A, Alshaer H, Rudzicz F, De Lara E.
  [Link]

• Enriching Word Embeddings without Labeled Corpora
  In Proceedings, 33rd AAAI Conference on Artificial Intelligence (AAAI); (2019)
  Abdalla M, Sahlgren M, Hirst G.
  [Link]

• Cross-Lingual Sentiment Analysis Without (Good) Translation
  In Proceedings of the Eighth International Joint Conference on Natural Language Processing (IJCNLP); (2017)
  Abdalla M, Hirst G.
  [Link]

Refereed (Archival) Workshop Proceedings

• Examining the rhetorical capacities of neural language models
  In Proceedings of the EMNLP BlackboxNLP Workshop; (2020)
  Zhu Z, Pan C, Abdalla M, Rudzicz F.
  [Link]

Non-Archival Workshop Proceedings

• The Grey Hoodie Project: Big Tobacco, Big Tech, and the threat on academic integrity
  In Proceedings of Resistance AI Workshop at NeurIPS ; (2020)
  Abdalla M, Abdalla M.
  [Workshop Link]

• Quantifying Fairness in a Multi-Group Setting and its Impact in the Clinical Setting
  In Proceedings of the Fair Machine Learning for Health Workshop at NeurIPS ; (2019)
  Abdalla M, Lu A, Zhang H, Chen I, Ghassemi M.
  [Workshop Link]

• Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings
  In Proceedings of Machine Learning for Health (ML4H) Workshop at NeurIPS ; (2019)
  Lu A*, Zhang H*, Abdalla M, McDermot M, Ghassemi M.
  [Workshop Link]

CV

Available upon request.