Jason Alan Fries

Assistant professor developing foundation models for longitudinal healthcare data.

Select Publications

Publications (grouped by year): 2026, 2025, 2024, 2023, 2022, 2021, 2020, 2019, 2017.

2026

Suhana Bedi, Jason Fries, Nigam Shah.How to interpret 'zero-shot' results from generative EHR models. Nature Medicine. 2026 Journal
[ Nature Medicine, BibTex ]

@article{bedi2026zeroshot,
  author = {suhana and jfries and nigam},
  title = { {How to interpret 'zero-shot' results from generative EHR models} },
  journal = {Nature Medicine},
  year = {2026}
}

2025

Monica Munnangi^✱, Akshay Swaminathan^✱, Jason Fries^✱, Jenelle Jindal, Sanjana Narayanan, Ivan Lopez, Lucia Tu, Philip Chung, Jesutofunmi A. Omiye, Mehr Kashyap, Nigam Shah.FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs. Machine Learning for Healthcare. 2025 Conference
[ PDF, ArXiv, Proceedings of Machine Learning Research (PMLR), BibTex ]

@inproceedings{munnangi2024:preprint,
  author = {Monica Munnangi and akshay and jfries and Jenelle Jindal and Sanjana Narayanan and Ivan Lopez and Lucia Tu and Philip Chung and Jesutofunmi A. Omiye and Mehr Kashyap and Nigam Shah},
  title = { {FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs} },
  booktitle = {Machine Learning for Healthcare},
  year = {2025}
}

Zepeng Huo^✱, Jason Fries^✱, Alejandro Lozano^✱, Jeya Maria Jose Valanarasu, Ethan Steinberg, Louis Blankemeier, Akshay S. Chaudhari, Curtis Langlotz, Nigam Shah.Time-to-Event Pretraining for 3D Medical Imaging. International Conference on Learning Representations (ICLR). 2025 Conference
[ PDF, ArXiV, BibTex ]

@inproceedings{huo2024:preprint,
  author = {zepeng and jfries and alozano and Jeya Maria Jose Valanarasu and Ethan Steinberg and Louis Blankemeier and Akshay S. Chaudhari and Curtis Langlotz and nigam},
  title = { {Time-to-Event Pretraining for 3D Medical Imaging} },
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025}
}

Michael Wornow^✱, Suhana Bedi^✱, Miguel Angel Fuentes Hernandez, Ethan Steinberg, Jason Alan Fries, Christopher Ré, Sanmi Koyejo, Nigam H Shah.Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs. International Conference on Learning Representations (ICLR). 2025 Conference
[ PDF, ArXiV, BibTex ]

@inproceedings{wornow2025:conference,
  author = {mwornow and suhana and Miguel Angel Fuentes Hernandez and Ethan Steinberg and Jason Alan Fries and Christopher Ré and Sanmi Koyejo and Nigam H Shah},
  title = { {Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHRs} },
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025}
}

Hejie Cui, Alyssa Unell, Bowen Chen, Jason Fries, Emily Alsentzer, Sanmi Koyejo, Nigam Shah.TIMER: temporal instruction modeling and evaluation for longitudinal clinical records. npj Digital Medicine. 2025 Journal
[ npj Digital Medicine, BibTex ]

@article{cui2025timer,
  author = {Hejie Cui and Alyssa Unell and Bowen Chen and jfries and Emily Alsentzer and Sanmi Koyejo and nigam},
  title = { {TIMER: temporal instruction modeling and evaluation for longitudinal clinical records} },
  journal = {npj Digital Medicine},
  year = {2025}
}

Suhana Bedi, Hejie Cui, Miguel Fuentes, Alyssa Unell, Michael Wornow, Juan M Banda, Nikesh Kotecha, Timothy Keyes, Yifan Mai, Mert Oez, Hao Qiu, Shrey Jain, Leonardo Schettini, Mehr Kashyap, Jason Fries, Akshay Swaminathan, Philip Chung, Fateme Nateghi, Asad Aali, Ashwin Nayak, Shivam Vedak, Sneha S Jain, Birju Patel, Oluseyi Fayanju, Shreya Shah, Ethan Goh, Dong-han Yao, Brian Soetikno, Eduardo Reis, Sergios Gatidis, Vasu Divi, Robson Capasso, Rachna Saralkar, Chia-Chun Chiang, Jenelle Jindal, Tho Pham, Faraz Ghoddusi, Steven Lin, Albert S Chiou, Christy Hong, Mohana Roy, Michael F Gensheimer, Hinesh Patel, Kevin Schulman, Dev Dash, Danton Char, Lance Downing, Francois Grolleau, Kameron Black, Bethel Mieso, Aydin Zahedivash, Wen-wai Yim, Harshita Sharma, Tony Lee, Hannah Kirsch, Jennifer Lee, Nerissa Ambers, Carlene Lugtu, Aditya Sharma, Bilal Mawji, Alex Alekseyev, Vicky Zhou, Vikas Kakkar, Jarrod Helzer, Anurang Revri, Yair Bannett, Roxana Daneshjou, Jonathan Chen, Emily Alsentzer, Keith Morse, Nirmal Ravi, Nima Aghaeepour, Vanessa Kennedy, Akshay Chaudhari, Thomas Wang, Sanmi Koyejo, Matthew P Lungren, Eric Horvitz, Percy Liang, Mike Pfeffer, Nigam Shah.MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks. arXiv preprint arXiv:2505.23802. 2025 Preprint
[ arXiv, BibTex ]

@misc{bedi2025medhelm,
  author = {suhana and Hejie Cui and Miguel Fuentes and Alyssa Unell and mwornow and Juan M Banda and Nikesh Kotecha and Timothy Keyes and Yifan Mai and Mert Oez and Hao Qiu and Shrey Jain and Leonardo Schettini and Mehr Kashyap and jfries and akshay and Philip Chung and Fateme Nateghi and Asad Aali and Ashwin Nayak and Shivam Vedak and Sneha S Jain and Birju Patel and Oluseyi Fayanju and Shreya Shah and Ethan Goh and Dong-han Yao and Brian Soetikno and Eduardo Reis and Sergios Gatidis and Vasu Divi and Robson Capasso and Rachna Saralkar and Chia-Chun Chiang and Jenelle Jindal and Tho Pham and Faraz Ghoddusi and Steven Lin and Albert S Chiou and Christy Hong and Mohana Roy and Michael F Gensheimer and Hinesh Patel and Kevin Schulman and Dev Dash and Danton Char and Lance Downing and Francois Grolleau and Kameron Black and Bethel Mieso and Aydin Zahedivash and Wen-wai Yim and Harshita Sharma and Tony Lee and Hannah Kirsch and Jennifer Lee and Nerissa Ambers and Carlene Lugtu and Aditya Sharma and Bilal Mawji and Alex Alekseyev and Vicky Zhou and Vikas Kakkar and Jarrod Helzer and Anurang Revri and Yair Bannett and Roxana Daneshjou and Jonathan Chen and Emily Alsentzer and Keith Morse and Nirmal Ravi and Nima Aghaeepour and Vanessa Kennedy and Akshay Chaudhari and Thomas Wang and Sanmi Koyejo and Matthew P Lungren and Eric Horvitz and Percy Liang and Mike Pfeffer and nigam},
  title = { {MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks} },
  series = {arXiv preprint arXiv:2505.23802},
  year = {2025}
}

2024

Scott L. Fleming^✱, Alejandro Lozano^✱, William J. Haberkorn^✱, Jenelle A. Jindal^✱, Eduardo P. Reis^✱, Rahul Thapa, Louis Blankemeier, Julian Z. Genkins, Ethan Steinberg, Ashwin Nayak, Birju S. Patel, Chia-Chun Chiang, Alison Callahan, Zepeng Huo, Sergios Gatidis, Scott J. Adams, Oluseyi Fayanju, Shreya J. Shah, Thomas Savage, Ethan Goh, Akshay S. Chaudhari, Nima Aghaeepour, Christopher Sharp, Michael A. Pfeffer, Percy Liang, Jonathan H. Chen, Keith E. Morse, Emma Brunskill^◆, Jason Fries^◆, Nigam Shah^◆.MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records. AAAI Conference on Artificial Intelligence (AAAI). 2024 Conference
Best Thematic Paper Award (ML4H Symposium)
[ PDF, ArXiv, AAAI Proceedings, Website, BibTex ]

@inproceedings{fleming2023:aaai,
  author = {Scott L. Fleming and alozano and William J. Haberkorn and Jenelle A. Jindal and Eduardo P. Reis and rahul and Louis Blankemeier and Julian Z. Genkins and Ethan Steinberg and Ashwin Nayak and Birju S. Patel and Chia-Chun Chiang and Alison Callahan and zepeng and Sergios Gatidis and Scott J. Adams and Oluseyi Fayanju and Shreya J. Shah and Thomas Savage and Ethan Goh and Akshay S. Chaudhari and Nima Aghaeepour and Christopher Sharp and Michael A. Pfeffer and percy and Jonathan H. Chen and Keith E. Morse and Emma Brunskill and jfries and nigam},
  title = { {MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records} },
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024}
}

Ethan Steinberg^✱, Jason Fries^✱, Yizhe Xu, Nigam Shah.MOTOR: A Time-to-Event Foundation Model For Structured Medical Records. International Conference on Learning Representations (ICLR). 2024 Conference
Spotlight (Top 5%)
[ PDF, OpenReview, BibTex ]

@inproceedings{steinberg2024:iclr,
  author = {Ethan Steinberg and jfries and yizhe and nigam},
  title = { {MOTOR: A Time-to-Event Foundation Model For Structured Medical Records} },
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024}
}

Lawrence Guo^✱, Jason Fries^✱, Ethan Steinberg, Scott L. Fleming, Keith E. Morse, C Aftandilian, Jose Posada, Nigam Shah^◆, Lillian Sung^◆.A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records. npj Digital Medicine. 2024 Journal
[ PMC, BibTex ]

@article{guo2024:journal,
  author = {Lawrence Guo and jfries and Ethan Steinberg and Scott L. Fleming and Keith E. Morse and C Aftandilian and Jose Posada and nigam and lillian},
  title = { {A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records} },
  journal = {npj Digital Medicine},
  year = {2024}
}

Suhana Bedi, Yutong Liu, Lucy Orr-Ewing, Dev Dash, Sanmi Koyejo, Alison Callahan, Jason Fries, Michael Wornow, Akshay Swaminathan, Lisa Soleymani Lehmann, Hyo Jung Hong, Mehr Kashyap, Akash R. Chaurasia, Nirav R. Shah, Karandeep Singh, Troy Tazbaz, Arnold Milstein, Michael A. Pfeffer, Nigam Shah.Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review. JAMA. 2024 Journal
[ PDF, DOI, BibTex ]

@article{bedi2024:journal,
  author = {suhana and Yutong Liu and Lucy Orr-Ewing and Dev Dash and Sanmi Koyejo and Alison Callahan and jfries and mwornow and akshay and Lisa Soleymani Lehmann and Hyo Jung Hong and Mehr Kashyap and Akash R. Chaurasia and Nirav R. Shah and Karandeep Singh and Troy Tazbaz and Arnold Milstein and Michael A. Pfeffer and nigam},
  title = { {Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review} },
  journal = {JAMA},
  year = {2024}
}

Ryan Smith^✱, Jason Fries^✱, Braden Hancock, Stephen Bach.Language Models in the Loop: Incorporating Prompting into Weak Supervision. ACM/IMS Journal of Data Science. 2024 Journal
[ Article, BibTex ]

@article{smith2022_language,
  author = {Ryan Smith and jfries and Braden Hancock and sbach},
  title = { {Language Models in the Loop: Incorporating Prompting into Weak Supervision} },
  journal = {ACM/IMS Journal of Data Science},
  year = {2024}
}

Ethan Steinberg^✱, Michael Wornow^✱, Suhana Bedi^✱, Jason Fries, Matthew McDermott, Nigam Shah.meds_reader: A fast and efficient EHR processing library. AHLI Machine Learning for Health (ML4H) Symposium. 2024 Workshop
[ GitHub, BibTex ]

@inproceedings{steinberg2024:conference,
  author = {Ethan Steinberg and mwornow and suhana and jfries and Matthew McDermott and nigam},
  title = { {meds_reader: A fast and efficient EHR processing library} },
  booktitle = {AHLI Machine Learning for Health (ML4H) Symposium},
  year = {2024}
}

2023

Shih-Cheng Huang^✱, Zepeng Huo^✱, Ethan Steinberg^✱, Chia-Chun Chiang, Matthew P. Lungren, Curtis Langlotz, Serena Yeung, Nigam Shah, Jason Fries.INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis. Neural Information Processing Systems (NeurIPS). 2023 Conference
[ PDF, OpenReview, BibTex ]

@inproceedings{huang2023:conference,
  author = {Shih-Cheng Huang and zepeng and Ethan Steinberg and Chia-Chun Chiang and Matthew P. Lungren and Curtis Langlotz and Serena Yeung and nigam and jfries},
  title = { {INSPECT: A Multimodal Dataset for Pulmonary Embolism Diagnosis and Prognosis} },
  booktitle = {Neural Information Processing Systems (NeurIPS)},
  year = {2023}
}

Michael Wornow^✱, Rahul Thapa^✱, Ethan Steinberg, Jason Fries^◆, Nigam Shah^◆.EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models. Neural Information Processing Systems (NeurIPS). 2023 Conference
Spotlight (Top 10%)
[ PDF, BibTex ]

@inproceedings{wornow2023:conference,
  author = {mwornow and rahul and Ethan Steinberg and jfries and nigam},
  title = { {EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models} },
  booktitle = {Neural Information Processing Systems (NeurIPS)},
  year = {2023}
}

Louis Blankemeier, Jason Fries, Robert Tinn, Joseph Preston, Nigam Shah, Akshay Chaudhari.Efficient Diagnosis Assignment Using Unstructured Clinical Notes. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023 Conference
[ ACL Anthology, DOI, Abstract, BibTex ]

Electronic phenotyping entails using electronic health records (EHRs) to identify patients with specific health outcomes and determine when those outcomes occurred. Unstructured clinical notes, which contain a vast amount of information, are a valuable resource for electronic phenotyping. However, traditional methods, such as rule-based labeling functions or neural networks, require significant manual effort to tune and may not generalize well to multiple indications. To address these challenges, we propose HyDE (hybrid diagnosis extractor). HyDE is a simple framework for electronic phenotyping that integrates labeling functions and a disease-agnostic neural network to assign diagnoses to patients. By training HyDE's model to correct predictions made by labeling functions, we are able to disambiguate hypertension true positives and false positives with a supervised area under the precision-recall curve (AUPRC) of 0.85. We extend this hypertension-trained model to zero-shot evaluation of four other diseases, generating AUPRC values ranging from 0.82–0.95 and outperforming a labeling function baseline by 44 points in F1 score and a Word2Vec baseline by 24 points in F1 score on average. Furthermore, we demonstrate a speedup of >4x by pruning the length of inputs into our language model to ~2.3% of the full clinical notes, with negligible impact to the AUPRC. HyDE has the potential to improve the efficiency and efficacy of interpreting large-scale unstructured clinical notes for accurate EHR phenotyping.
```
@inproceedings{blankemeier2023_efficient,
  author = {Louis Blankemeier and jfries and Robert Tinn and Joseph Preston and nigam and Akshay Chaudhari},
  title = { {Efficient Diagnosis Assignment Using Unstructured Clinical Notes} },
  booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2023}
}
```

Lin Lawrence Guo, Ethan Steinberg, Scott Lanyon Fleming, Jose Posada, Joshua Lemmon, Stephen R. Pfohl, Nigam Shah, Jason Fries^◆, Lillian Sung^◆.EHR foundation models improve robustness in the presence of temporal distribution shift. Scientific Reports. 2023 Journal
[ Nature, BibTex ]

@article{guo2023ehr,
  author = {Lin Lawrence Guo and Ethan Steinberg and Scott Lanyon Fleming and Jose Posada and Joshua Lemmon and Stephen R. Pfohl and nigam and jfries and lillian},
  title = { {EHR foundation models improve robustness in the presence of temporal distribution shift} },
  journal = {Scientific Reports},
  year = {2023}
}

Michael Wornow, Yizhe Xu, Rahul Thapa, Birju Patel, Ethan Steinberg, Scott Fleming, Michael A. Pfeffer, Jason Fries, Nigam Shah.The shaky foundations of large language models and foundation models for electronic health records. npj Digital Medicine. 2023 Journal
[ Nature, BibTex ]

@article{wornow2023shaky,
  author = {mwornow and yizhe and rahul and Birju Patel and Ethan Steinberg and Scott Fleming and Michael A. Pfeffer and jfries and nigam},
  title = { {The shaky foundations of large language models and foundation models for electronic health records} },
  journal = {npj Digital Medicine},
  year = {2023}
}

Joshua Lemmon, Lin Lawrence Guo, Ethan Steinberg, Keith E. Morse, Scott Lanyon Fleming, Catherine Aftandilian, Stephen R. Pfohl, Jose D. Posada, Nigam Shah, Jason Fries, Lillian Sung.Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks. Journal of the American Medical Informatics Association. 2023 Journal
[ JAMIA, BibTex ]

@article{lemmon2023self,
  author = {Joshua Lemmon and Lin Lawrence Guo and Ethan Steinberg and Keith E. Morse and Scott Lanyon Fleming and Catherine Aftandilian and Stephen R. Pfohl and Jose D. Posada and nigam and jfries and lillian},
  title = { {Self-supervised machine learning using adult inpatient data produces effective models for pediatric clinical prediction tasks} },
  journal = {Journal of the American Medical Informatics Association},
  year = {2023}
}

2022

Jason Fries^✱, Leon Weber^✱, Natasha Seelam^✱, Gabriel Altay^✱, Debajyoti Datta, Samuele Garda, Sunny Kang, Rosaline Su, Wojciech Kusa, Samuel Cahyawijaya, Fabio Barth, Simon Ott, Matthias Samwald, Stephen Bach, Stella Biderman, Mario Sänger, Bo Wang, Alison Callahan, Daniel León Periñán, Théo Gigant, Patrick Haller, Jenny Chim, Jose Posada, John Giorgi, Karthik Rangasai Sivaraman, Marc Pàmies, Marianna Nezhurina, Robert Martin, Michael Cullan, Moritz Freidank, Nathan Dahlberg, Shubhanshu Mishra, Shamik Bose, Nicholas Broad, Yanis Labrak, Shlok Deshmukh, Sid Kiblawi, Ayush Singh, Minh Chien Vu, Trishala Neeraj, Jonas Golde, Albert Villanova del Moral, Benjamin Beilharz.BigBio: A Framework for Data-Centric Biomedical Natural Language Processing. Advances in Neural Information Processing Systems. 2022 Conference
[ Proceedings, BibTex ]

@inproceedings{neurips2022_bigbio,
  author = {jfries and Leon Weber and Natasha Seelam and Gabriel Altay and Debajyoti Datta and Samuele Garda and Sunny Kang and Rosaline Su and Wojciech Kusa and Samuel Cahyawijaya and Fabio Barth and Simon Ott and Matthias Samwald and sbach and Stella Biderman and Mario Sänger and Bo Wang and Alison Callahan and Daniel León Periñán and Théo Gigant and Patrick Haller and Jenny Chim and Jose Posada and John Giorgi and Karthik Rangasai Sivaraman and Marc Pàmies and Marianna Nezhurina and Robert Martin and Michael Cullan and Moritz Freidank and Nathan Dahlberg and Shubhanshu Mishra and Shamik Bose and Nicholas Broad and Yanis Labrak and Shlok Deshmukh and Sid Kiblawi and Ayush Singh and Minh Chien Vu and Trishala Neeraj and Jonas Golde and Albert Villanova del Moral and Benjamin Beilharz},
  title = { {BigBio: A Framework for Data-Centric Biomedical Natural Language Processing} },
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2022}
}

Stephen Bach, Victor Sanh, Zheng Xin Yong, Albert Webson, Colin Raffel, Nihal V. Nayak, Abheesht Sharma, Taewoon Kim, M. Saiful Bari, Thibault Fevry, Zaid Alyafeai, Manan Dey, Andrea Santilli, Zhiqing Sun, Srulik Ben-david, Canwen Xu, Gunjan Chhablani, Han Wang, Jason Fries, Maged Al-shaibani, Shanya Sharma, Urmish Thakker, Khalid Almubarak, Xiangru Tang, Dragomir Radev, Mike Tian-jian Jiang, Alexander Rush.PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 2022 Conference
[ ACL Anthology, DOI, Abstract, BibTex ]

PromptSource is a system for creating, sharing, and using natural language prompts. Prompts are functions that map an example from a dataset to a natural language input and target output. Using prompts to train and query language models is an emerging area in NLP that requires new tools that let users develop and refine these prompts collaboratively. PromptSource addresses the emergent challenges in this new setting with (1) a templating language for defining data-linked prompts, (2) an interface that lets users quickly iterate on prompt development by observing outputs of their prompts on many examples, and (3) a community-driven set of guidelines for contributing new prompts to a common pool. Over 2,000 prompts for roughly 170 datasets are already available in PromptSource. PromptSource is available at https://github.com/bigscience-workshop/promptsource.
```
@inproceedings{bach2022_promptsource,
  author = {sbach and Victor Sanh and Zheng Xin Yong and Albert Webson and Colin Raffel and Nihal V. Nayak and Abheesht Sharma and Taewoon Kim and M. Saiful Bari and Thibault Fevry and Zaid Alyafeai and Manan Dey and Andrea Santilli and Zhiqing Sun and Srulik Ben-david and Canwen Xu and Gunjan Chhablani and Han Wang and jfries and Maged Al-shaibani and Shanya Sharma and Urmish Thakker and Khalid Almubarak and Xiangru Tang and Dragomir Radev and Mike Tian-jian Jiang and Alexander Rush},
  title = { {PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts} },
  booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations},
  pages = {93--104},
  year = {2022}
}
```

Victor Sanh^✱, Albert Webson^✱, Colin Raffel^✱, Stephen Bach^✱, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, M. Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal Nayak, Debajyoti Datta, Jonathan Chang, Mike Tian-Jian Jiang, Han Wang, Matteo Manica, Sheng Shen, Zheng Xin Yong, Harshit Pandey, Rachel Bawden, Thomas Wang, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Andrea Santilli, Thibault Fevry, Jason Fries, Ryan Teehan, Teven Le Scao, Stella Biderman, Leo Gao, Thomas Wolf, Alexander M. Rush.Multitask Prompted Training Enables Zero-Shot Task Generalization. International Conference on Learning Representations. 2022 Conference
Spotlight (Top 5%)
[ OpenReview, BibTex ]

@inproceedings{sanh2022_multitask,
  author = {Victor Sanh and Albert Webson and Colin Raffel and sbach and Lintang Sutawika and Zaid Alyafeai and Antoine Chaffin and Arnaud Stiegler and Arun Raja and Manan Dey and M. Saiful Bari and Canwen Xu and Urmish Thakker and Shanya Sharma and Eliza Szczechla and Taewoon Kim and Gunjan Chhablani and Nihal Nayak and Debajyoti Datta and Jonathan Chang and Mike Tian-Jian Jiang and Han Wang and Matteo Manica and Sheng Shen and Zheng Xin Yong and Harshit Pandey and Rachel Bawden and Thomas Wang and Trishala Neeraj and Jos Rozen and Abheesht Sharma and Andrea Santilli and Thibault Fevry and jfries and Ryan Teehan and Teven Le Scao and Stella Biderman and Leo Gao and Thomas Wolf and Alexander M. Rush},
  title = { {Multitask Prompted Training Enables Zero-Shot Task Generalization} },
  booktitle = {International Conference on Learning Representations},
  year = {2022}
}

Adam S. Miner^✱, Scott L. Fleming^✱, Albert Haque, Jason Fries, Tim Althoff, Denise E. Wilfley, W. Stewart Agras, Arnold Milstein, Jeff Hancock, Steven M. Asch.A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency. npj Mental Health Research. 2022 Journal
[ Nature, BibTex ]

@article{miner2022_computational,
  author = {Adam S. Miner and Scott L. Fleming and Albert Haque and jfries and Tim Althoff and Denise E. Wilfley and W. Stewart Agras and Arnold Milstein and Jeff Hancock and Steven M. Asch},
  title = { {A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency} },
  journal = {npj Mental Health Research},
  pages = {19},
  year = {2022}
}

Lin Lawrence Guo, Stephen R. Pfohl, Jason Fries, Alistair E.W. Johnson, Jose Posada, Catherine Aftandilian, Nigam Shah, Lillian Sung.Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine. Scientific Reports. 2022 Journal
[ Nature, DOI, BibTex ]

@article{guo2022_evaluation,
  author = {Lin Lawrence Guo and Stephen R. Pfohl and jfries and Alistair E.W. Johnson and Jose Posada and Catherine Aftandilian and nigam and lillian},
  title = { {Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine} },
  journal = {Scientific Reports},
  pages = {1--10},
  year = {2022}
}

Jason Fries^✱, Natasha Seelam^✱, Gabriel Altay^✱, Leon Weber^✱, Myungsun Kang^✱, Debajyoti Datta^✱, Ruisi Su^✱, Samuele Garda^✱, Bo Wang, Simon Ott, Matthias Samwald, Wojciech Kusa.Dataset Debt in Biomedical Language Modeling. Challenges & Perspectives in Creating Large Language Models. 2022 Workshop
[ OpenReview, BibTex ]

@inproceedings{fries2022_dataset,
  author = {jfries and Natasha Seelam and Gabriel Altay and Leon Weber and Myungsun Kang and Debajyoti Datta and Ruisi Su and Samuele Garda and Bo Wang and Simon Ott and Matthias Samwald and Wojciech Kusa},
  title = { {Dataset Debt in Biomedical Language Modeling} },
  booktitle = {Challenges & Perspectives in Creating Large Language Models},
  year = {2022}
}

2021

Lin Lawrence Guo, Stephen R. Pfohl, Jason Fries, Jose Posada, Scott Lanyon Fleming, Catherine Aftandilian, Nigam Shah, Lillian Sung.Systematic Review of Approaches to Preserve Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine. Applied Clinical Informatics. 2021 Journal
[ PubMed, BibTex ]

@article{guo2021_systematic,
  author = {Lin Lawrence Guo and Stephen R. Pfohl and jfries and Jose Posada and Scott Lanyon Fleming and Catherine Aftandilian and nigam and lillian},
  title = { {Systematic Review of Approaches to Preserve Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine} },
  journal = {Applied Clinical Informatics},
  pages = {808--815},
  year = {2021}
}

Jason Fries, Ethan Steinberg, Saelig Khattar, Scott L. Fleming, Jose Posada, Alison Callahan, Nigam Shah.Ontology-driven weak supervision for clinical entity classification in electronic health records. Nature Communications. 2021 Journal
[ Nature, DOI, BibTex ]

@article{fries2021_ontology,
  author = {jfries and Ethan Steinberg and Saelig Khattar and Scott L. Fleming and Jose Posada and Alison Callahan and nigam},
  title = { {Ontology-driven weak supervision for clinical entity classification in electronic health records} },
  journal = {Nature Communications},
  pages = {1--11},
  year = {2021}
}

Ethan Steinberg, Ken Jung, Jason Fries, Conor K. Corbin, Stephen R. Pfohl, Nigam Shah.Language models are an effective representation learning technique for electronic health record data. Journal of Biomedical Informatics. 2021 Journal
[ DOI, ScienceDirect, Abstract, BibTex ]

Widespread adoption of electronic health records (EHRs) has fueled the development of using machine learning to build prediction models for various clinical outcomes. However, this process is often constrained by having a relatively small number of patient records for training the model. We demonstrate that using patient representation schemes inspired from techniques in natural language processing can increase the accuracy of clinical prediction models by transferring information learned from the entire patient population to the task of training a specific model, where only a subset of the population is relevant. Such patient representation schemes enable a 3.5% mean improvement in AUROC on five prediction tasks compared to standard baselines, with the average improvement rising to 19% when only a small number of patient records are available for training the clinical prediction model.
```
@article{steinberg2021_language_models,
  author = {Ethan Steinberg and Ken Jung and jfries and Conor K. Corbin and Stephen R. Pfohl and nigam},
  title = { {Language models are an effective representation learning technique for electronic health record data} },
  journal = {Journal of Biomedical Informatics},
  pages = {103637},
  year = {2021}
}
```

Yuyin Zhou, Shih-Cheng Huang, Jason Fries, Alaa Youssef, Timothy J. Amrhein, Marcello Chang, Imon Banerjee, Daniel Rubin, Lei Xing, Nigam Shah.RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR. arXiv. 2021 Preprint
[ ArXiv, BibTex ]

@misc{zhou2021_radfusion,
  author = {yuyin and Shih-Cheng Huang and jfries and Alaa Youssef and Timothy J. Amrhein and Marcello Chang and Imon Banerjee and Daniel Rubin and Lei Xing and nigam},
  title = { {RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR} },
  series = {arXiv},
  year = {2021}
}

2020

Alison Callahan^✱, Ethan Steinberg^✱, Jason Fries, Saurabh Gombar, Birju Patel, Conor K. Corbin, Nigam Shah.Estimating the efficacy of symptom-based screening for COVID-19. NPJ Digital Medicine. 2020 Journal
[ Nature, DOI, BibTex ]

@article{callahan2020_estimating,
  author = {Alison Callahan and Ethan Steinberg and jfries and Saurabh Gombar and Birju Patel and Conor K. Corbin and nigam},
  title = { {Estimating the efficacy of symptom-based screening for COVID-19} },
  journal = {NPJ Digital Medicine},
  pages = {1--3},
  year = {2020}
}

Adam S. Miner^✱, Albert Haque^✱, Jason Fries, Scott L. Fleming, Denise E. Wilfley, G. Terence Wilson, Arnold Milstein, Dan Jurafsky, Bruce A. Arnow, W. Stewart Agras.Assessing the accuracy of automatic speech recognition for psychotherapy. NPJ Digital Medicine. 2020 Journal
[ Nature, DOI, BibTex ]

@article{miner2020_assessing,
  author = {Adam S. Miner and Albert Haque and jfries and Scott L. Fleming and Denise E. Wilfley and G. Terence Wilson and Arnold Milstein and Dan Jurafsky and Bruce A. Arnow and W. Stewart Agras},
  title = { {Assessing the accuracy of automatic speech recognition for psychotherapy} },
  journal = {NPJ Digital Medicine},
  pages = {1--8},
  year = {2020}
}

2019

Paroma Varma, Frederic Sala, Shiori Sagawa, Jason Fries, Daniel Y. Fu, Saelig Khattar, Ashwini Ramamoorthy, Ke Xiao, Kayvon Fatahalian, James Priest, Christopher Ré.Multi-Resolution Weak Supervision for Sequential Data. NeurIPS. 2019 Conference
[ Paper, BibTex ]

@inproceedings{varma2019_multiresolution,
  author = {Paroma Varma and Frederic Sala and Shiori Sagawa and jfries and Daniel Y. Fu and Saelig Khattar and Ashwini Ramamoorthy and Ke Xiao and Kayvon Fatahalian and James Priest and Christopher Ré},
  title = { {Multi-Resolution Weak Supervision for Sequential Data} },
  booktitle = {NeurIPS},
  pages = {192-203},
  year = {2019}
}

Alison Callahan^✱, Jason Fries^✱, Christopher Ré, James I. Huddleston, Nicholas J. Giori, Scott Delp, Nigam Shah.Medical device surveillance with electronic health records. NPJ Digital Medicine. 2019 Journal
[ Nature, DOI, BibTex ]

@article{callahan2019_medical,
  author = {Alison Callahan and jfries and Christopher Ré and James I. Huddleston and Nicholas J. Giori and Scott Delp and nigam},
  title = { {Medical device surveillance with electronic health records} },
  journal = {NPJ Digital Medicine},
  pages = {1--10},
  year = {2019}
}

Jason Fries, Paroma Varma, Vincent S. Chen, Ke Xiao, Heliodoro Tejeda, Priyanka Saha, Jared Dunnmon, Henry Chubb, Shiraz Maskatia, Madalina Fiterau.Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences. Nature Communications. 2019 Journal
[ Nature, DOI, BibTex ]

@article{fries2019_weakly,
  author = {jfries and Paroma Varma and Vincent S. Chen and Ke Xiao and Heliodoro Tejeda and Priyanka Saha and Jared Dunnmon and Henry Chubb and Shiraz Maskatia and Madalina Fiterau},
  title = { {Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences} },
  journal = {Nature Communications},
  pages = {1--10},
  year = {2019}
}

2017

Alexander Ratner, Stephen Bach, Henry Ehrenberg, Jason Fries, Sen Wu, Christopher Ré.Snorkel: Rapid training data creation with weak supervision. Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases. 2017 Conference
[ ACM, DOI, BibTex ]

@inproceedings{ratner2017_snorkel,
  author = {Alexander Ratner and sbach and Henry Ehrenberg and jfries and Sen Wu and Christopher Ré},
  title = { {Snorkel: Rapid training data creation with weak supervision} },
  booktitle = {Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases},
  pages = {269},
  year = {2017}
}