The 5th Clinical Natural Language Processing Workshop
At ACL 2023. 14 Jul 2023, Toronto, Canada.
14 Jul 2023 (all times EDT) |
|
| 08:55–09:00 | Opening Remarks |
| 09:00–09:45 |
Keynote: Patient record summarization: tasks, approaches, evaluation, and open challenges
Speaker: Noemie Elhadad Abstract: The patient record contains an overwhelming large amount of information, too much for a clinician to make sense of it, and yet the information it contains may be critical for clinicians to care for their patients safely and effectively. In this talk, I will review two tasks to alleviate the information overload in clinical care: longitudinal patient record summarization and abstractive brief hospital course summarization. I will describe potential approaches, evaluation objectives, and current open questions. Finally, using the abstractive task of brief hospital course summarization as a grounding example, I will discuss LLMs in the context of clinical NLP. Biography: Noémie Elhadad is Chair of the department of Biomedical Informatics at Columbia University, affiliated with the department of Computer Science and the Data Science Institute. Elhadad’s research lies at the intersection of artificial intelligence, human-centered computing, and medicine. She creates novel methods and tools to support patients and clinicians in their information needs, with particular focus on ensuring that the AI systems of the future are robust, safe, fair, and just. |
| 09:45–10:30 | Oral Session I |
| 09:45–10:00 | Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning Brihat Sharma, Yanjun Gao, Timothy A Miller, Matthew Churpek, Majid Afshar, Dmitriy Dligach |
| 10:00–10:15 | Factors Affecting the Performance of Automated Speaker Verification in Alzheimer’s Disease Clinical Trials Malikeh Ehghaghi, Marija Stanojevic, Ali Akram, Jekaterina Novikova |
| 10:15–10:30 | Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts Sitong Zhou, Meliha Yetisgen, Mari Ostendorf |
| 10:30–11:00 | Break |
| 11:00–11:45 | Oral Session II |
| 11:00–11:15 | Multilingual Clinical NER: Translation or Cross-lingual Transfer? Félix Gaschi, Xavier Fontaine, Parisa Rastin, Yannick Toussaint |
| 11:15–11:30 | Method for Designing Semantic Annotation of Sepsis Signs in Clinical Text Melissa Y. Yan, Lise Tuset Gustad, Lise Husby Høvik, Øystein Nytrø |
| 11:30–11:45 | UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition Aidan Mannion, Didier Schwab, Lorraine Goeuriot |
| 11:45–12:30 |
Keynote: The evolution of representations for clinical text and a few more thoughts about generative clinical models
Speaker: Timothy Miller Abstract: Large language models have excited the broader public like no previous NLP advance. This has led to predictions from all corners about the future of LLM-enabled NLP for clinical data and tasks. In this talk, I review several recent projects from my lab that did not use LLMs, and re-imagine these projects in an LLM-enabled context. The talk then synthesizes the lessons from those projects to propose some guidelines for optimal use of LLMs in clinical NLP research, imagine future directions that are now enabled, and to make some predictions about the future of our field. Biography: Tim Miller is an Associate Professor in the Computational Health Informatics Program at Boston Children’s Hospital, Department of Pediatrics at Harvard Medical School, and at the Harvard-MIT Center for Regulatory Science. He is the PI of the Machine Learning for Medical Language Lab, home of several federally funded projects, including projects focused on basic biomedical NLP research, as well as projects that are driven by biomedical use cases. His research focuses on domain adaptation/generalizability of ML-based NLP methods, as well as methods for learning universal patient representations. |
| 12:30–14:00 | Lunch |
| 14:00–14:45 | Oral Session III |
| 14:00–14:15 | Uncovering the Potential for a Weakly Supervised End-to-End Model in Recognising Speech from Patient with Post-Stroke Aphasia Giulia Sanguedolce, Patrick Naylor, Fatemeh Geranmayeh |
| 14:15–14:30 | Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor Conversations Gagandeep Singh, Yue Pan, Jesus Andres-Ferrer, Miguel Del-Agua, Frank Diehl, Joel Pinto, Paul Vozila |
| 14:30–14:45 | Navigating Data Scarcity: Pretraining for Medical Utterance Classification Do June Min, Veronica Perez-Rosas, Rada Mihalcea |
| 14:45–15:30 | Oral Session IV |
| 14:45–15:00 | Overview of the MEDIQA-Chat 2023 Shared Tasks on the Summarization & Generation of Doctor-Patient Conversations Asma Ben Abacha, Wen-wai Yim, Griffin Thomas Adams, Neal Snider, Meliha Yetisgen |
| 15:00–15:15 | WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models John Michael Giorgi, Augustin Toma, Ronald Xie, Sondra Chen, Kevin R An, Grace Xiaoyu Zheng, BO WANG |
| 15:15–15:30 | Team Cadence at MEDIQA-Chat 2023: Generating, augmenting and summarizing clinical dialogue with large language models Ashwyn Sharma, David Ian Feldman, Aneesh Jain |
| 15:30–16:00 | Break |
| 16:00–17:30 | Poster Session |
| 16:00–17:30 | Clinical BERTScore: An Improved Measure of Automatic Speech Recognition Performance in Clinical Settings Joel Shor, Ruyue Agnes Bi, Subhashini Venugopalan, Steven Ibara, Roman Goldenberg, Ehud Rivlin |
| 16:00–17:30 | Medical Visual Textual Entailment for Numerical Understanding of Vision-and-Language Models Hitomi Yanaka, Yuta Nakamura, Yuki Chida, Tomoya Kurosawa |
| 16:00–17:30 | Privacy-Preserving Knowledge Transfer through Partial Parameter Sharing Paul Youssef, Jörg Schlötterer, Christin Seifert |
| 16:00–17:30 | Breaking Barriers: Exploring the Diagnostic Potential of Speech Narratives in Hindi for Alzheimer's Disease Kritesh Rauniyar, Shuvam Shiwakoti, Sweta Poudel, Surendrabikram Thapa, Usman Naseem, Mehwish Nasim |
| 16:00–17:30 | Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning Lifeng Han, Gleb Erofeev , Irina Sorokina, Serge Gladkoff, Goran Nenadic |
| 16:00–17:30 | Tracking the Evolution of Covid-19 Symptoms through Clinical Conversations Ticiana Linhares Coelho da Silva, José A. Fernandes de Macêdo, Régis Pires Magalhães |
| 16:00–17:30 | Aligning Factual Consistency for Clinical Studies Summarization through Reinforcement Learning Xiangru Tang, Arman Cohan, Mark Gerstein |
| 16:00–17:30 | Navigating Data Scarcity: Pretraining for Medical Utterance Classification Do June Min, Veronica Perez-Rosas, Rada Mihalcea |
| 16:00–17:30 | Hindi Chatbot for Supporting Maternal and Child Health Related Queries in Rural India Ritwik Mishra, Simranjeet Singh, Jasmeet Kaur, Pushpendra Singh, Rajiv Ratn Shah |
| 16:00–17:30 | Multi-Task Training with In-Domain Language Models for Diagnostic Reasoning Brihat Sharma, Yanjun Gao, Timothy A Miller, Matthew Churpek, Majid Afshar, Dmitriy Dligach |
| 16:00–17:30 | Context-aware Medication Event Extraction from Unstructured Text Noushin Salek Faramarzi, Meet Patel, Sai Harika Bandarupally, Ritwik Banerjee |
| 16:00–17:30 | Improving Automatic KCD Coding: Introducing the KoDAK and an Optimized Tokenization Method for Korean Clinical Documents Geunyeong Jeong, Juoh Sun, Seokwon Jeong, Hyunjin Shin, Harksoo Kim |
| 16:00–17:30 | Who needs context? Classical techniques for Alzheimer’s disease detection Behrad Taghibeyglou, Frank Rudzicz |
| 16:00–17:30 | Knowledge Injection for Disease Names in Logical Inference between Japanese Clinical Texts Natsuki Murakami, Mana Ishida, Yuta Takahashi, Hitomi Yanaka, Daisuke Bekki |
| 16:00–17:30 | Training Models on Oversampled Data and a Novel Multi-class Annotation Scheme for Dementia Detection Nadine Abdelhalim, Ingy Yasser Hassan Abdou Abdelhalim, Riza Batista-Navarro |
| 16:00–17:30 | Improving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles Weipeng Zhou, Majid Afshar, Dmitriy Dligach, Yanjun Gao, Timothy A Miller |
| 16:00–17:30 | Can Large Language Models Safely Address Patient Questions Following Cataract Surgery? Mohita Chowdhury, Ernest Lim, Aisling Higham, Rory McKinnon, Nikoletta Ventoura, Yajie Vera He, Nick de Pennington |
| 16:00–17:30 | Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor Conversations Gagandeep Singh, Yue Pan, Jesus Andres-Ferrer, Miguel Del-Agua, Frank Diehl, Joel Pinto, Paul Vozila |
| 16:00–17:30 | clulab at MEDIQA-Chat 2023: Summarization and classification of medical dialogues Kadir Bulut Ozler, Steven Bethard |
| 16:00–17:30 | Leveraging Natural Language Processing and Clinical Notes for Dementia Detection Ming Liu, Richard Beare, Taya Collyer, Nadine Andrew, Velandai Srikanth |
| 16:00–17:30 | Automated Orthodontic Diagnosis from a Summary of Medical Findings Takumi Ohtsuka, Tomoyuki Kajiwara, Chihiro Tanikawa, Yuujin Shimizu, Hajime Nagahara, Takashi Ninomiya |
| 16:00–17:30 | Harnessing the Power of BERT in the Turkish Clinical Domain: Pretraining Approaches for Limited Data Scenarios Hazal Türkmen, Oguz Dikenelli, Cenk Eraslan, Mehmet Cem Calli, Suha Sureyya Ozbek |
| 16:00–17:30 | A Meta-dataset of German Medical Corpora: Harmonization of Annotations and Cross-corpus NER Evaluation Ignacio Llorca, Florian Borchert, Matthieu-P. Schapranow |
| 16:00–17:30 | Uncovering the Potential for a Weakly Supervised End-to-End Model in Recognising Speech from Patient with Post-Stroke Aphasia Giulia Sanguedolce, Patrick Naylor, Fatemeh Geranmayeh |
| 16:00–17:30 | Textual Entailment for Temporal Dependency Graph Parsing Jiarui Yao, Steven Bethard, Kristin Wright-Bettner, Eli T Goldner, David A Harris, Guergana K Savova |
| 16:00–17:30 | Generating medically-accurate summaries of patient-provider dialogue: A multi-stage approach using large language models Varun Nair, Elliot Schumacher, Anitha Kannan |
| 16:00–17:30 | Factors Affecting the Performance of Automated Speaker Verification in Alzheimer’s Disease Clinical Trials Malikeh Ehghaghi, Marija Stanojevic, Ali Akram, Jekaterina Novikova |
| 16:00–17:30 | Team Cadence at MEDIQA-Chat 2023: Generating, augmenting and summarizing clinical dialogue with large language models Ashwyn Sharma, David Ian Feldman, Aneesh Jain |
| 16:00–17:30 | Method for Designing Semantic Annotation of Sepsis Signs in Clinical Text Melissa Y. Yan, Lise Tuset Gustad, Lise Husby Høvik, Øystein Nytrø |
| 16:00–17:30 | Prompt Discriminative Language Models for Domain Adaptation Keming Lu, Peter Potash, Xihui Lin, Yuwen Sun, Zihan Qian, Zheng Yuan, Tristan Naumann, Tianxi Cai, Junwei Lu |
| 16:00–17:30 | Cross-domain German Medical Named Entity Recognition using a Pre-Trained Language Model and Unified Medical Semantic Types Siting Liang, Mareike Hartmann, Daniel Sonntag |
| 16:00–17:30 | Reducing Knowledge Noise for Improved Semantic Analysis in Biomedical Natural Language Processing Applications Usman Naseem, Surendrabikram Thapa, Qi Zhang, Liang Hu, Anum Masood, Mehwish Nasim |
| 16:00–17:30 | Medical knowledge-enhanced prompt learning for diagnosis classification from clinical text Yuxing Lu, Xukai Zhao, Jinzhuo Wang |
| 16:00–17:30 | Multilingual Clinical NER: Translation or Cross-lingual Transfer? Félix Gaschi, Xavier Fontaine, Parisa Rastin, Yannick Toussaint |
| 16:00–17:30 | UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition Aidan Mannion, Didier Schwab, Lorraine Goeuriot |
| 16:00–17:30 | WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models John Michael Giorgi, Augustin Toma, Ronald Xie, Sondra Chen, Kevin R An, Grace Xiaoyu Zheng, BO WANG |
| 16:00–17:30 | Automatic Coding at Scale: Design and Deployment of a Nationwide System for Normalizing Referrals in the Chilean Public Healthcare System Fabián Villena, Matías Rojas, Felipe Arias, Jorge Pacheco, Paulina Vera, Jocelyn Dunstan |
| 16:00–17:30 | Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts Sitong Zhou, Meliha Yetisgen, Mari Ostendorf |
| 16:00–17:30 | Intersectionality and Testimonial Injustice in Medical Records Kenya S. Andrews, Bhuvni Shah, Lu Cheng |
| 16:00–17:30 | Interactive Span Recommendation for Biomedical Text Louis Blankemeier, Theodore Zhao, Robert Tinn, Sid Kiblawi, Yu Gu, Akshay S Chaudhari, Hoifung Poon, Sheng Zhang, Mu Wei, J. Samuel Preston |
| 16:00–17:30 | Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning Giridhar Kaushik Ramachandran, Yujuan Fu, Bin HAN, Kevin Lybarger, Nic J Dobbins, Ozlem Uzuner, Meliha Yetisgen |
| 16:00–17:30 | Teddysum at MEDIQA-Chat 2023: an analysis of fine-tuning strategy for long dialog summarization Yongbin Jeong, Ju-Hyuck Han, Kyung Min CHAE, Yousang Cho, Hyunbin Seo, KyungTae Lim, Key-Sun Choi, Younggyun Hahm |
| 16:00–17:30 | Rare Codes Count: Mining Inter-code Relations for Long-tail Clinical Text Classification Jiamin Chen, Xuhong Li, Junting Xi, Lei Yu, Haoyi Xiong |
| 16:00–17:30 | NewAgeHealthWarriors at MEDIQA-Chat 2023 Task A: Summarizing Short Medical Conversation with Transformers Prakhar Mishra, Ravi Theja Desetty |
| 16:00–17:30 | Storyline-Centric Detection of Aphasia and Dysarthria in Stroke Patient Transcripts Peiqi Sui, Kelvin Wong, Xiaohui Yu, JOHN JULIUS VOLPI, Stephen T. C. Wong |
| 16:00–17:30 | Pre-trained language models in Spanish for health insurance coverage Claudio Aracena, Nicolás Rodríguez, Victor Rocco, Jocelyn Dunstan |
| 16:00–17:30 | Utterance Classification with Logical Neural Network: Explainable AI for Mental Disorder Diagnosis Yeldar Toleubay, Don Joven Agravante, Daiki Kimura, Baihan Lin, Djallel Bouneffouf, Michiaki Tatsubori |
| 16:00–17:30 | A Survey of Evaluation Methods of Generated Medical Textual Reports Yongxin Zhou, Fabien Ringeval, François Portet |
| 16:00–17:30 | UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations? Junda Wang, Zonghai Yao, Avijit Mitra, Samuel Osebe, zhichao Yang, hong yu |
| 16:00–17:30 | HealthMavericks@MEDIQA-Chat 2023: Benchmarking different Transformer based models for Clinical Dialogue Summarization Kunal Suri, Saumajit Saha, Atul Singh |
| 16:00–17:30 | SummQA at MEDIQA-Chat 2023: In-Context Learning with GPT-4 for Medical Summarization Yash Mathur, Sanketh Rangreji, Raghav Kapoor, Medha Palavalli, Amanda Bertsch, Matthew R. Gormley |
| 16:00–17:30 | Overview of the MEDIQA-Chat 2023 Shared Tasks on the Summarization & Generation of Doctor-Patient Conversations Asma Ben Abacha, Wen-wai Yim, Griffin Thomas Adams, Neal Snider, Meliha Yetisgen |
| 16:00–17:30 | Transfer Learning for Low-Resource Clinical Named Entity Recognition Nevasini Sasikumar, Krishna Sri Ipsit Mantri |
| 16:00–17:30 | IUTEAM1 at MEDIQA-Chat 2023: Is simple fine tuning effective for multi layer summarization of clinical conversations? Dhananjay Srivastava |
| 16:00–17:30 | Care4Lang at MEDIQA-Chat 2023: Fine-tuning Language Models for Classifying and Summarizing Clinical Dialogues Amal Abdullah Alqahtani, Rana Salama, Mona T. Diab, Abdou Youssef |
| 16:00–17:30 | Calvados at MEDIQA-Chat 2023: Improving Clinical Note Generation with Multi-Task Instruction Finetuning Kirill Milintsevich, Navneet Agarwal |
| 16:00–17:30 | DS4DH at MEDIQA-Chat 2023: Leveraging SVM and GPT-3 Prompt Engineering for Medical Dialogue Classification and Summarization Boya Zhang, Rahul Mishra, Douglas Teodoro |
| 16:00–17:30 | GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning Xiangru Tang, Andrew Tran, Jeffrey Tan, Mark Gerstein |