README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP
Open accessAbstract
The advancement in healthcare has shifted focus toward patient-centric approaches, particularly in self-care and patient education, facilitated by access to Electronic Health Records (EHR). However, medical jargon in EHRs poses significant challenges in patient comprehension. To address this, we introduce a new task of automatically generating lay definitions, aiming to simplify complex medical terms into patient-friendly lay language. We first created the README dataset, an extensive collection of over 50,000 unique (medical term, lay definition) pairs and 300,000 mentions, each offering context-aware lay definitions manually annotated by domain experts. We have also engineered a data-centric Human-AI pipeline that synergizes data filtering, augmentation, and selection to improve data quality. We then used README as the training data for models and leveraged a Retrieval-Augmented Generation method to reduce hallucinations and improve the quality of model outputs. Our extensive automatic and human evaluations demonstrate that open-source mobile-friendly models, when fine-tuned with high-quality data, are capable of matching or even surpassing the performance of state-of-the-art closed-source large language models like ChatGPT. This research represents a significant stride in closing the knowledge gap in patient education and advancing patient-centric healthcare solutions .
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In medicine, LLM judges have shown some promise for diagnostic support, documentation, clinical conversation, medical question answering, medical reasoning, and patient education.
“In the medical field (Li et al., 2024c; Raju et al., 2024), LLMs-as-judges have demonstrated certain potential in areas such as diagnostic support (Yao et al., 2024), medical documentation (Brake and Schaaf, 2024,?), clinical conversation (Wang et al., 2023a; Li et al., 2024a), medical question answering (Wang et al., 2024b; Krolik et al., 2024), medical reasoning (Jeong et al., 2024), and patient”
From MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback (2025) · cites this paper as Yao et al., 2024
The Method section uses GPT-3.5-turbo as an examiner of medical definitions for patient education, not as a judge for diagnostic support. A References entry names a separate study on imaging diagnostic support, but the searched passages do not report the claimed use of LLM judges in diagnosis. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 15
- Aguinis Herman, Villamor Isabel, and Ramani Ravi S. 2021. Mturk research: Review and recommendations. Journal of Management, 47(4): 823– 837.
- Alambo Amanuel, Banerjee Tanvi, Thirunarayan Krishnaprasad, and Raymer Michael. 2022. Entity-driven fact-aware abstractive summarization of biomedical literature. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 613– 620. IEEE.
- Banerjee Satanjeev and Lavie Alon. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65– 72, Ann Arbor, Michigan. Association for Computational Linguistics.
- Doak Cecilia Conrath, Doak Leonard G, and Root Jane H. 1996. Teaching patients with low literacy skills. AJN The American Journal of Nursing, 96(12): 16M.
- Guo Yue, Qiu Wei, Wang Yizhong, and Cohen Trevor. 2021. Automated lay language summarization of biomedical scientific reviews. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 160– 168.
- Lewis Patrick, Perez Ethan, Piktus Aleksandra, Petroni Fabio, Karpukhin Vladimir, Goyal Naman, Heinrich Küttler Mike Lewis, Yih Wen-tau, Rocktäschel Tim, 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33: 9459– 9474.
- Lin Chin-Yew. 2004. ROUGE: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74– 81.
- Nanna Kevin M 2009. Health literacy: Challenges and strategies. Online Journal of Issues in Nursing, 14(3): E1.
- Nutbeam Don. 2023. Artificial intelligence and health literacy—proceed with caution. Health Literacy and Communication Open, 1(1): 2263355.
- Shafquat Afrah, Mezey Jason, Beigi Mandis, Sun Jimeng, and Aptekar Jacob W. 2022. A source data privacy framework for synthetic clinical trial data. In NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research.
- Solnyshkina Marina, Zamaletdinov Radif, Gorodetskaya Ludmila, and Gabitov Azat. 2017. Evaluating text complexity and flesch-kincaid grade level. Journal of social studies education research, 8(3): 238– 248.
- Spooner Amy J., Booth Natasha, Downer Tai-Rae, Gordon Louisa, Hudson Adrienne P., Bradford Natalie K., Chris O’Donnell Alanna Geary, Henderson Robyn, Franks Cherie, Conway Aaron, Yates Patsy, and Chan Raymond J.. 2019. Advanced practice profiles and work activities of nurse navigators: An early-stage evaluation. Collegian, 26(1): 103– 109.
- Steven Euijong Whang Yuji Roh, Song Hwanjun, and Lee Jae-Gil. 2023. Data collection and quality challenges in deep learning: A data-centric ai perspective. The VLDB Journal, 32(4): 791– 813.
- Yang Zhichao, Yao Zonghai, Tasmin Mahbuba, Vashisht Parth, Won Seok Jang Feiyun Ouyang, Wang Beining, Berlowitz Dan, and Yu Hong. 2023. Performance of multimodal gpt-4v on usmle with image: Potential for imaging diagnostic support with explanations. medRxiv, pages 2023– 10.
- Zeng Changchang, Li Shaobo, Li Qin, Hu Jie, and Hu Jianjun. 2020. A survey on machine reading comprehension—tasks, evaluation metrics and benchmark datasets. Applied Sciences, 10(21): 7640.
Cited by
Sorted by citations
Traylor, D., Kern, K. V., Anderson, E. E., & Henderson, R. (2025) · Cureus · doi:10.7759/cureus.76825 · Cited by 30 · see citing works
Yao, Z., Parashar, A., Zhou, H., Jang, W. S., Ouyang, F., Yang, Z., & Yu, H. (2025) · Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2025.naacl-long.538 · Cited by 12 · see citing works
Self-citationMedReadCtrl: Personalizing medical text generation with readability-controlled instruction learningPreprint
Tran, H., Yao, Z., Jang, W. S., Sultana, S., Chang, A., Zhang, Y., & Hong, Y. (2025) · medRxiv · doi:10.1101/2025.07.09.25331239 · Cited by 9 · see citing works
Self-citationReadCtrl: Personalizing text generation with readability-controlled instruction learning
Tran, H., Yao, Z., Li, L., & Yu, H. (2025) · Workshop on Intelligent and Interactive Writing Assistants (In2Writing) · doi:10.18653/v1/2025.in2writing-1.3 · Cited by 7 · see citing works
Self-citationBenchmark of small language models for plain-language simplification in Spanish clinical texts
Martı́nez, P., Sánchez-Gómez, J. M., & Moreno, L. D. L. R. (2026) · Scientific Reports · doi:10.1038/s41598-026-65740-w · Cited by 1 · see citing works
Jang, W. S., Sultana, S., Yao, Z., Tran, H., Yang, Z., Kwon, S., & Yu, H. (2026) · JMIR AI · doi:10.2196/75561 · Cited by 1 · see citing works
Self-citationLeveraging Foundation Models in Maternal and Child Health: A Systematic ReviewPreprint
Mai, X., Liu, Y., Chung, P., Reiss, J. D., Zhou, S., Wong, R. J., Lin, M., Marić, I., Sirota, M., Aghaeepour, N., et al. (2025) · medRxiv · doi:10.1101/2025.08.29.25333768 · Cited by 1 · see citing works
Jang, W. S., Sultana, S., Yao, Z., Tran, H., Yang, Z., Kwon, S., & Yu, H. (2025) · doi:10.2196/preprints.75561
Self-citationPetMed-Agent: A Multi-Agent Framework for Affective Symptom Classification in Pet Health
Ma, R. (2026) · International Conference on Digital Society and Artificial Intelligence (DSAI) · doi:10.1145/3833541.3833796
Two-Phase Framework for Clinical Question-Answering: Auto-correction for Guideline-Concordance
Tariq, A., Das, A., Nakach, F.-Z., Yu, N., Patel, B. N., & Banerjee, I. (2025) · Studies in computational intelligence · doi:10.1007/978-3-032-11999-5_13
Ashwith, S. P. M., Yuvan Kalyan, U., Hariharan, P., & Shiny, S. S. G. (2026) · International Conference on Computational Intelligence Systems and Devices (ICCISD) · doi:10.1109/iccisd69924.2026.11732006
- Authors
- Yao, Z., Kantu, N. S., Wei, G., Tran, H., Duan, Z., Kwon, S., Yang, Z., & Yu, H.
- Affiliations
- University of Massachusetts Amherst (US)
- University of Massachusetts Lowell (US)
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Published
- 2024
- Volume
- 2024
- Pages
- 12609-12629
- PMC
- PMC12912280
- OpenAlex
- W4404780997
- Cited by
- 8
- References
- 0
- Citations by year
- 2026: 3 · 2025: 5
- FWCI
- 14.44
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc)
- arXiv (Cornell University)
- Funders
- U.S. Department of Veterans Affairs (I01 HX003969)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Text Readability and Simplification
- Keywords
- medical jargon, lay language, patient education, medical terminology, electronic health records, retrieval-augmented generation, hallucination mitigation, patient-centric healthcare, open-source language models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
