From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature
(1) Burn injuries demand multidisciplinary, evidence-based care, yet the extensive literature complicates timely decision making. Retrieval-augmented generation (RAG) synthesizes research while addressing inaccuracies in pretrained models. However, citation bias in sourcing for RAG often prioritizes...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | European Burn Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-1991/6/2/28 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850156902473793536 |
|---|---|
| author | Ariana Genovese Srinivasagam Prabha Sahar Borna Cesar A. Gomez-Cabello Syed Ali Haider Maissa Trabilsy Cui Tao Antonio Jorge Forte |
| author_facet | Ariana Genovese Srinivasagam Prabha Sahar Borna Cesar A. Gomez-Cabello Syed Ali Haider Maissa Trabilsy Cui Tao Antonio Jorge Forte |
| author_sort | Ariana Genovese |
| collection | DOAJ |
| description | (1) Burn injuries demand multidisciplinary, evidence-based care, yet the extensive literature complicates timely decision making. Retrieval-augmented generation (RAG) synthesizes research while addressing inaccuracies in pretrained models. However, citation bias in sourcing for RAG often prioritizes highly cited studies, overlooking less-cited but valuable research. This study examines RAG’s performance in burn management, comparing citation levels to enhance evidence synthesis, reduce selection bias, and guide decisions. (2) Two burn management datasets were assembled: 30 highly cited (mean: 303) and 30 less-cited (mean: 21). The Gemini-1.0-Pro-002 RAG model addressed 30 questions, ranging from foundational principles to advanced surgical approaches. Responses were evaluated for accuracy (5-point scale), readability (Flesch–Kincaid metrics), and response time with Wilcoxon rank sum tests (<i>p</i> < 0.05). (3) RAG achieved comparable accuracy (4.6 vs. 4.2, <i>p</i> = 0.49), readability (Flesch Reading Ease: 42.8 vs. 46.5, <i>p</i> = 0.26; Grade Level: 9.9 vs. 9.5, <i>p</i> = 0.29), and response time (2.8 vs. 2.5 s, <i>p</i> = 0.39) for the highly and less-cited datasets. (4) Less-cited research performed similarly to highly cited sources. This equivalence broadens clinicians’ access to novel, diverse insights without sacrificing quality. As plastic surgery evolves, RAG’s inclusive approach fosters innovation, improves patient care, and reduces cognitive burden by integrating underutilized studies. Embracing RAG could propel the field toward dynamic, forward-thinking care. |
| format | Article |
| id | doaj-art-c9b3e342b1184a76b5d71c48a5b7e18d |
| institution | OA Journals |
| issn | 2673-1991 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | European Burn Journal |
| spelling | doaj-art-c9b3e342b1184a76b5d71c48a5b7e18d2025-08-20T02:24:21ZengMDPI AGEuropean Burn Journal2673-19912025-06-01622810.3390/ebj6020028From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management LiteratureAriana Genovese0Srinivasagam Prabha1Sahar Borna2Cesar A. Gomez-Cabello3Syed Ali Haider4Maissa Trabilsy5Cui Tao6Antonio Jorge Forte7Division of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USADivision of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USADivision of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USADivision of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USADivision of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USADivision of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USADepartment of Artificial Intelligence and Informatics, Mayo Clinic, Jacksonville, FL 32224, USADivision of Plastic Surgery, Mayo Clinic, Jacksonville, FL 32224, USA(1) Burn injuries demand multidisciplinary, evidence-based care, yet the extensive literature complicates timely decision making. Retrieval-augmented generation (RAG) synthesizes research while addressing inaccuracies in pretrained models. However, citation bias in sourcing for RAG often prioritizes highly cited studies, overlooking less-cited but valuable research. This study examines RAG’s performance in burn management, comparing citation levels to enhance evidence synthesis, reduce selection bias, and guide decisions. (2) Two burn management datasets were assembled: 30 highly cited (mean: 303) and 30 less-cited (mean: 21). The Gemini-1.0-Pro-002 RAG model addressed 30 questions, ranging from foundational principles to advanced surgical approaches. Responses were evaluated for accuracy (5-point scale), readability (Flesch–Kincaid metrics), and response time with Wilcoxon rank sum tests (<i>p</i> < 0.05). (3) RAG achieved comparable accuracy (4.6 vs. 4.2, <i>p</i> = 0.49), readability (Flesch Reading Ease: 42.8 vs. 46.5, <i>p</i> = 0.26; Grade Level: 9.9 vs. 9.5, <i>p</i> = 0.29), and response time (2.8 vs. 2.5 s, <i>p</i> = 0.39) for the highly and less-cited datasets. (4) Less-cited research performed similarly to highly cited sources. This equivalence broadens clinicians’ access to novel, diverse insights without sacrificing quality. As plastic surgery evolves, RAG’s inclusive approach fosters innovation, improves patient care, and reduces cognitive burden by integrating underutilized studies. Embracing RAG could propel the field toward dynamic, forward-thinking care.https://www.mdpi.com/2673-1991/6/2/28AI (artificial intelligence)large language modelRAG (retrieval-augmented generation)burnplastic surgeryclinical decision support |
| spellingShingle | Ariana Genovese Srinivasagam Prabha Sahar Borna Cesar A. Gomez-Cabello Syed Ali Haider Maissa Trabilsy Cui Tao Antonio Jorge Forte From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature European Burn Journal AI (artificial intelligence) large language model RAG (retrieval-augmented generation) burn plastic surgery clinical decision support |
| title | From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature |
| title_full | From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature |
| title_fullStr | From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature |
| title_full_unstemmed | From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature |
| title_short | From Data to Decisions: Leveraging Retrieval-Augmented Generation to Balance Citation Bias in Burn Management Literature |
| title_sort | from data to decisions leveraging retrieval augmented generation to balance citation bias in burn management literature |
| topic | AI (artificial intelligence) large language model RAG (retrieval-augmented generation) burn plastic surgery clinical decision support |
| url | https://www.mdpi.com/2673-1991/6/2/28 |
| work_keys_str_mv | AT arianagenovese fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT srinivasagamprabha fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT saharborna fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT cesaragomezcabello fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT syedalihaider fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT maissatrabilsy fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT cuitao fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature AT antoniojorgeforte fromdatatodecisionsleveragingretrievalaugmentedgenerationtobalancecitationbiasinburnmanagementliterature |