CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection Article Swipe
Zhengyang Shen
,
Xuehao Zhai
,
Hua Tu
,
X. Shi
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2510.01558
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2510.01558
Chagas disease affects nearly 6 million people worldwide, with Chagas cardiomyopathy representing its most severe complication. In regions where serological testing capacity is limited, AI-enhanced electrocardiogram (ECG) screening provides a critical diagnostic alternative. However, existing machine learning approaches face challenges such as limited accuracy, reliance on large labeled datasets, and more importantly, weak integration with evidence-based clinical diagnostic indicators. We propose a retrieval-augmented generation framework, CardioRAG, integrating large language models with interpretable ECG-based clinical features, including right bundle branch block, left anterior fascicular block, and heart rate variability metrics. The framework uses variational autoencoder-learned representations for semantic case retrieval, providing contextual cases to guide clinical reasoning. Evaluation demonstrated high recall performance of 89.80%, with a maximum F1 score of 0.68 for effective identification of positive cases requiring prioritized serological testing. CardioRAG provides an interpretable, clinical evidence-based approach particularly valuable for resource-limited settings, demonstrating a pathway for embedding clinical indicators into trustworthy medical AI systems.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2510.01558
- https://arxiv.org/pdf/2510.01558
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414817611
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414817611Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2510.01558Digital Object Identifier
- Title
-
CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease DetectionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-10-02Full publication date if available
- Authors
-
Zhengyang Shen, Xuehao Zhai, Hua Tu, X. ShiList of authors in order
- Landing page
-
https://arxiv.org/abs/2510.01558Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2510.01558Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2510.01558Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414817611 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2510.01558 |
| ids.doi | https://doi.org/10.48550/arxiv.2510.01558 |
| ids.openalex | https://openalex.org/W4414817611 |
| fwci | |
| type | preprint |
| title | CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12254 |
| topics[0].field.id | https://openalex.org/fields/13 |
| topics[0].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[0].score | 0.9092000126838684 |
| topics[0].domain.id | https://openalex.org/domains/1 |
| topics[0].domain.display_name | Life Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1312 |
| topics[0].subfield.display_name | Molecular Biology |
| topics[0].display_name | Machine Learning in Bioinformatics |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2510.01558 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2510.01558 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2510.01558 |
| locations[1].id | doi:10.48550/arxiv.2510.01558 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2510.01558 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102848878 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3442-6344 |
| authorships[0].author.display_name | Zhengyang Shen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shen, Zhengyang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5090568200 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-6419-1462 |
| authorships[1].author.display_name | Xuehao Zhai |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhai, Xuehao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5065484457 |
| authorships[2].author.orcid | https://orcid.org/0009-0008-0975-0971 |
| authorships[2].author.display_name | Hua Tu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Tu, Hua |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5091299418 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-9910-9345 |
| authorships[3].author.display_name | X. Shi |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Shi, Mayue |
| authorships[3].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2510.01558 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12254 |
| primary_topic.field.id | https://openalex.org/fields/13 |
| primary_topic.field.display_name | Biochemistry, Genetics and Molecular Biology |
| primary_topic.score | 0.9092000126838684 |
| primary_topic.domain.id | https://openalex.org/domains/1 |
| primary_topic.domain.display_name | Life Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1312 |
| primary_topic.subfield.display_name | Molecular Biology |
| primary_topic.display_name | Machine Learning in Bioinformatics |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2510.01558 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2510.01558 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2510.01558 |
| primary_location.id | pmh:oai:arXiv.org:2510.01558 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2510.01558 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2510.01558 |
| publication_date | 2025-10-02 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.6 | 4 |
| abstract_inverted_index.a | 29, 61, 114, 143 |
| abstract_inverted_index.AI | 152 |
| abstract_inverted_index.F1 | 116 |
| abstract_inverted_index.In | 16 |
| abstract_inverted_index.We | 59 |
| abstract_inverted_index.an | 132 |
| abstract_inverted_index.as | 41 |
| abstract_inverted_index.is | 22 |
| abstract_inverted_index.of | 111, 118, 123 |
| abstract_inverted_index.on | 45 |
| abstract_inverted_index.to | 102 |
| abstract_inverted_index.The | 89 |
| abstract_inverted_index.and | 49, 84 |
| abstract_inverted_index.for | 95, 120, 139, 145 |
| abstract_inverted_index.its | 12 |
| abstract_inverted_index.0.68 | 119 |
| abstract_inverted_index.case | 97 |
| abstract_inverted_index.face | 38 |
| abstract_inverted_index.high | 108 |
| abstract_inverted_index.into | 149 |
| abstract_inverted_index.left | 80 |
| abstract_inverted_index.more | 50 |
| abstract_inverted_index.most | 13 |
| abstract_inverted_index.rate | 86 |
| abstract_inverted_index.such | 40 |
| abstract_inverted_index.uses | 91 |
| abstract_inverted_index.weak | 52 |
| abstract_inverted_index.with | 8, 54, 70, 113 |
| abstract_inverted_index.(ECG) | 26 |
| abstract_inverted_index.cases | 101, 125 |
| abstract_inverted_index.guide | 103 |
| abstract_inverted_index.heart | 85 |
| abstract_inverted_index.large | 46, 67 |
| abstract_inverted_index.right | 76 |
| abstract_inverted_index.score | 117 |
| abstract_inverted_index.where | 18 |
| abstract_inverted_index.Chagas | 0, 9 |
| abstract_inverted_index.block, | 79, 83 |
| abstract_inverted_index.branch | 78 |
| abstract_inverted_index.bundle | 77 |
| abstract_inverted_index.models | 69 |
| abstract_inverted_index.nearly | 3 |
| abstract_inverted_index.people | 6 |
| abstract_inverted_index.recall | 109 |
| abstract_inverted_index.severe | 14 |
| abstract_inverted_index.89.80%, | 112 |
| abstract_inverted_index.affects | 2 |
| abstract_inverted_index.disease | 1 |
| abstract_inverted_index.labeled | 47 |
| abstract_inverted_index.limited | 42 |
| abstract_inverted_index.machine | 35 |
| abstract_inverted_index.maximum | 115 |
| abstract_inverted_index.medical | 151 |
| abstract_inverted_index.million | 5 |
| abstract_inverted_index.pathway | 144 |
| abstract_inverted_index.propose | 60 |
| abstract_inverted_index.regions | 17 |
| abstract_inverted_index.testing | 20 |
| abstract_inverted_index.However, | 33 |
| abstract_inverted_index.anterior | 81 |
| abstract_inverted_index.approach | 136 |
| abstract_inverted_index.capacity | 21 |
| abstract_inverted_index.clinical | 56, 73, 104, 134, 147 |
| abstract_inverted_index.critical | 30 |
| abstract_inverted_index.existing | 34 |
| abstract_inverted_index.language | 68 |
| abstract_inverted_index.learning | 36 |
| abstract_inverted_index.limited, | 23 |
| abstract_inverted_index.metrics. | 88 |
| abstract_inverted_index.positive | 124 |
| abstract_inverted_index.provides | 28, 131 |
| abstract_inverted_index.reliance | 44 |
| abstract_inverted_index.semantic | 96 |
| abstract_inverted_index.systems. | 153 |
| abstract_inverted_index.testing. | 129 |
| abstract_inverted_index.valuable | 138 |
| abstract_inverted_index.CardioRAG | 130 |
| abstract_inverted_index.ECG-based | 72 |
| abstract_inverted_index.accuracy, | 43 |
| abstract_inverted_index.datasets, | 48 |
| abstract_inverted_index.effective | 121 |
| abstract_inverted_index.embedding | 146 |
| abstract_inverted_index.features, | 74 |
| abstract_inverted_index.framework | 90 |
| abstract_inverted_index.including | 75 |
| abstract_inverted_index.providing | 99 |
| abstract_inverted_index.requiring | 126 |
| abstract_inverted_index.screening | 27 |
| abstract_inverted_index.settings, | 141 |
| abstract_inverted_index.CardioRAG, | 65 |
| abstract_inverted_index.Evaluation | 106 |
| abstract_inverted_index.approaches | 37 |
| abstract_inverted_index.challenges | 39 |
| abstract_inverted_index.contextual | 100 |
| abstract_inverted_index.diagnostic | 31, 57 |
| abstract_inverted_index.fascicular | 82 |
| abstract_inverted_index.framework, | 64 |
| abstract_inverted_index.generation | 63 |
| abstract_inverted_index.indicators | 148 |
| abstract_inverted_index.reasoning. | 105 |
| abstract_inverted_index.retrieval, | 98 |
| abstract_inverted_index.worldwide, | 7 |
| abstract_inverted_index.AI-enhanced | 24 |
| abstract_inverted_index.indicators. | 58 |
| abstract_inverted_index.integrating | 66 |
| abstract_inverted_index.integration | 53 |
| abstract_inverted_index.performance | 110 |
| abstract_inverted_index.prioritized | 127 |
| abstract_inverted_index.serological | 19, 128 |
| abstract_inverted_index.trustworthy | 150 |
| abstract_inverted_index.variability | 87 |
| abstract_inverted_index.variational | 92 |
| abstract_inverted_index.alternative. | 32 |
| abstract_inverted_index.demonstrated | 107 |
| abstract_inverted_index.importantly, | 51 |
| abstract_inverted_index.particularly | 137 |
| abstract_inverted_index.representing | 11 |
| abstract_inverted_index.complication. | 15 |
| abstract_inverted_index.demonstrating | 142 |
| abstract_inverted_index.interpretable | 71 |
| abstract_inverted_index.cardiomyopathy | 10 |
| abstract_inverted_index.evidence-based | 55, 135 |
| abstract_inverted_index.identification | 122 |
| abstract_inverted_index.interpretable, | 133 |
| abstract_inverted_index.representations | 94 |
| abstract_inverted_index.resource-limited | 140 |
| abstract_inverted_index.electrocardiogram | 25 |
| abstract_inverted_index.autoencoder-learned | 93 |
| abstract_inverted_index.retrieval-augmented | 62 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |