Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology Article Swipe

PDF

Shashi Kant Gupta , Aditya Basu , Bradley Taylor , Anai N. Kothari , Hrituraj Singh ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2404.06680

Retrieving information from EHR systems is essential for answering specific questions about patient journeys and improving the delivery of clinical care. Despite this fact, most EHR systems still rely on keyword-based searches. With the advent of generative large language models (LLMs), retrieving information can lead to better search and summarization capabilities. Such retrievers can also feed Retrieval-augmented generation (RAG) pipelines to answer any query. However, the task of retrieving information from EHR real-world clinical data contained within EHR systems in order to solve several downstream use cases is challenging due to the difficulty in creating query-document support pairs. We provide a blueprint for creating such datasets in an affordable manner using large language models. Our method results in a retriever that is 30-50 F-1 points better than propriety counterparts such as Ada and Mistral for oncology data elements. We further compare our model, called Onco-Retriever, against fine-tuned PubMedBERT model as well. We conduct an extensive manual evaluation on real-world EHR data along with latency analysis of the different models and provide a path forward for healthcare organizations to build domain-specific retrievers.

Related Topics

Mechanical Engineering

Concepts

Computer science Information retrieval Automatic summarization Blueprint Data science Engineering Mechanical engineering

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2404.06680
PDF: https://arxiv.org/pdf/2404.06680
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4394776991

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4394776991

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2404.06680

Digital Object Identifier
Title: Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-04-10

Full publication date if available
Authors: Shashi Kant Gupta, Aditya Basu, Bradley Taylor, Anai N. Kothari, Hrituraj Singh

List of authors in order
Landing page: https://arxiv.org/abs/2404.06680

Publisher landing page
PDF URL: https://arxiv.org/pdf/2404.06680

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2404.06680

Direct OA link when available
Concepts: Computer science, Information retrieval, Automatic summarization, Blueprint, Data science, Engineering, Mechanical engineering

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4394776991
doi	https://doi.org/10.48550/arxiv.2404.06680
ids.doi	https://doi.org/10.48550/arxiv.2404.06680
ids.openalex	https://openalex.org/W4394776991
fwci
type	preprint
title	Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11710
topics[0].field.id	https://openalex.org/fields/13
topics[0].field.display_name	Biochemistry, Genetics and Molecular Biology
topics[0].score	0.9961000084877014
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	Biomedical Text Mining and Ontologies
topics[1].id	https://openalex.org/T10028
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9957000017166138
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Topic Modeling
topics[2].id	https://openalex.org/T10181
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9779000282287598
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Natural Language Processing Techniques
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.7473637461662292
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C23123220
concepts[1].level	1
concepts[1].score	0.5860162377357483
concepts[1].wikidata	https://www.wikidata.org/wiki/Q816826
concepts[1].display_name	Information retrieval
concepts[2].id	https://openalex.org/C170858558
concepts[2].level	2
concepts[2].score	0.4666549861431122
concepts[2].wikidata	https://www.wikidata.org/wiki/Q1394144
concepts[2].display_name	Automatic summarization
concepts[3].id	https://openalex.org/C155911762
concepts[3].level	2
concepts[3].score	0.4419670104980469
concepts[3].wikidata	https://www.wikidata.org/wiki/Q422321
concepts[3].display_name	Blueprint
concepts[4].id	https://openalex.org/C2522767166
concepts[4].level	1
concepts[4].score	0.3431469798088074
concepts[4].wikidata	https://www.wikidata.org/wiki/Q2374463
concepts[4].display_name	Data science
concepts[5].id	https://openalex.org/C127413603
concepts[5].level	0
concepts[5].score	0.0
concepts[5].wikidata	https://www.wikidata.org/wiki/Q11023
concepts[5].display_name	Engineering
concepts[6].id	https://openalex.org/C78519656
concepts[6].level	1
concepts[6].score	0.0
concepts[6].wikidata	https://www.wikidata.org/wiki/Q101333
concepts[6].display_name	Mechanical engineering
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.7473637461662292
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/information-retrieval
keywords[1].score	0.5860162377357483
keywords[1].display_name	Information retrieval
keywords[2].id	https://openalex.org/keywords/automatic-summarization
keywords[2].score	0.4666549861431122
keywords[2].display_name	Automatic summarization
keywords[3].id	https://openalex.org/keywords/blueprint
keywords[3].score	0.4419670104980469
keywords[3].display_name	Blueprint
keywords[4].id	https://openalex.org/keywords/data-science
keywords[4].score	0.3431469798088074
keywords[4].display_name	Data science
language	en
locations[0].id	pmh:oai:arXiv.org:2404.06680
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/2404.06680
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/2404.06680
locations[1].id	doi:10.48550/arxiv.2404.06680
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	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
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.2404.06680
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5052263686
authorships[0].author.orcid	https://orcid.org/0000-0001-6587-5607
authorships[0].author.display_name	Shashi Kant Gupta
authorships[0].author_position	first
authorships[0].raw_author_name	Gupta, Shashi Kant
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100606669
authorships[1].author.orcid	https://orcid.org/0000-0002-9760-0912
authorships[1].author.display_name	Aditya Basu
authorships[1].author_position	middle
authorships[1].raw_author_name	Basu, Aditya
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5103502112
authorships[2].author.orcid
authorships[2].author.display_name	Bradley Taylor
authorships[2].author_position	middle
authorships[2].raw_author_name	Taylor, Bradley
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5077843932
authorships[3].author.orcid	https://orcid.org/0000-0001-6544-8832
authorships[3].author.display_name	Anai N. Kothari
authorships[3].author_position	middle
authorships[3].raw_author_name	Kothari, Anai
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5044442880
authorships[4].author.orcid	https://orcid.org/0000-0003-3705-120X
authorships[4].author.display_name	Hrituraj Singh
authorships[4].author_position	last
authorships[4].raw_author_name	Singh, Hrituraj
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2404.06680
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Onco-Retriever: Generative Classifier for Retrieval of EHR Records in Oncology
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11710
primary_topic.field.id	https://openalex.org/fields/13
primary_topic.field.display_name	Biochemistry, Genetics and Molecular Biology
primary_topic.score	0.9961000084877014
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	Biomedical Text Mining and Ontologies
related_works	https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2366403280, https://openalex.org/W1495108544, https://openalex.org/W4304620183, https://openalex.org/W2091301346, https://openalex.org/W3148229873, https://openalex.org/W4389760904, https://openalex.org/W2150160875, https://openalex.org/W2351187795
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2404.06680
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/2404.06680
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/2404.06680
primary_location.id	pmh:oai:arXiv.org:2404.06680
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/2404.06680
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/2404.06680
publication_date	2024-04-10
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	100, 118, 171
abstract_inverted_index.We	98, 138, 151
abstract_inverted_index.an	107, 153
abstract_inverted_index.as	130, 149
abstract_inverted_index.in	79, 93, 106, 117
abstract_inverted_index.is	5, 87, 121
abstract_inverted_index.of	18, 35, 67, 165
abstract_inverted_index.on	29, 157
abstract_inverted_index.to	45, 60, 81, 90, 177
abstract_inverted_index.Ada	131
abstract_inverted_index.EHR	3, 25, 71, 77, 159
abstract_inverted_index.F-1	123
abstract_inverted_index.Our	114
abstract_inverted_index.and	14, 48, 132, 169
abstract_inverted_index.any	62
abstract_inverted_index.can	43, 53
abstract_inverted_index.due	89
abstract_inverted_index.for	7, 102, 134, 174
abstract_inverted_index.our	141
abstract_inverted_index.the	16, 33, 65, 91, 166
abstract_inverted_index.use	85
abstract_inverted_index.Such	51
abstract_inverted_index.With	32
abstract_inverted_index.also	54
abstract_inverted_index.data	74, 136, 160
abstract_inverted_index.feed	55
abstract_inverted_index.from	2, 70
abstract_inverted_index.lead	44
abstract_inverted_index.most	24
abstract_inverted_index.path	172
abstract_inverted_index.rely	28
abstract_inverted_index.such	104, 129
abstract_inverted_index.task	66
abstract_inverted_index.than	126
abstract_inverted_index.that	120
abstract_inverted_index.this	22
abstract_inverted_index.with	162
abstract_inverted_index.(RAG)	58
abstract_inverted_index.30-50	122
abstract_inverted_index.about	11
abstract_inverted_index.along	161
abstract_inverted_index.build	178
abstract_inverted_index.care.	20
abstract_inverted_index.cases	86
abstract_inverted_index.fact,	23
abstract_inverted_index.large	37, 111
abstract_inverted_index.model	148
abstract_inverted_index.order	80
abstract_inverted_index.solve	82
abstract_inverted_index.still	27
abstract_inverted_index.using	110
abstract_inverted_index.well.	150
abstract_inverted_index.advent	34
abstract_inverted_index.answer	61
abstract_inverted_index.better	46, 125
abstract_inverted_index.called	143
abstract_inverted_index.manner	109
abstract_inverted_index.manual	155
abstract_inverted_index.method	115
abstract_inverted_index.model,	142
abstract_inverted_index.models	39, 168
abstract_inverted_index.pairs.	97
abstract_inverted_index.points	124
abstract_inverted_index.query.	63
abstract_inverted_index.search	47
abstract_inverted_index.within	76
abstract_inverted_index.(LLMs),	40
abstract_inverted_index.Despite	21
abstract_inverted_index.Mistral	133
abstract_inverted_index.against	145
abstract_inverted_index.compare	140
abstract_inverted_index.conduct	152
abstract_inverted_index.forward	173
abstract_inverted_index.further	139
abstract_inverted_index.latency	163
abstract_inverted_index.models.	113
abstract_inverted_index.patient	12
abstract_inverted_index.provide	99, 170
abstract_inverted_index.results	116
abstract_inverted_index.several	83
abstract_inverted_index.support	96
abstract_inverted_index.systems	4, 26, 78
abstract_inverted_index.However,	64
abstract_inverted_index.analysis	164
abstract_inverted_index.clinical	19, 73
abstract_inverted_index.creating	94, 103
abstract_inverted_index.datasets	105
abstract_inverted_index.delivery	17
abstract_inverted_index.journeys	13
abstract_inverted_index.language	38, 112
abstract_inverted_index.oncology	135
abstract_inverted_index.specific	9
abstract_inverted_index.answering	8
abstract_inverted_index.blueprint	101
abstract_inverted_index.contained	75
abstract_inverted_index.different	167
abstract_inverted_index.elements.	137
abstract_inverted_index.essential	6
abstract_inverted_index.extensive	154
abstract_inverted_index.improving	15
abstract_inverted_index.pipelines	59
abstract_inverted_index.propriety	127
abstract_inverted_index.questions	10
abstract_inverted_index.retriever	119
abstract_inverted_index.searches.	31
abstract_inverted_index.PubMedBERT	147
abstract_inverted_index.Retrieving	0
abstract_inverted_index.affordable	108
abstract_inverted_index.difficulty	92
abstract_inverted_index.downstream	84
abstract_inverted_index.evaluation	156
abstract_inverted_index.fine-tuned	146
abstract_inverted_index.generation	57
abstract_inverted_index.generative	36
abstract_inverted_index.healthcare	175
abstract_inverted_index.real-world	72, 158
abstract_inverted_index.retrievers	52
abstract_inverted_index.retrieving	41, 68
abstract_inverted_index.challenging	88
abstract_inverted_index.information	1, 42, 69
abstract_inverted_index.retrievers.	180
abstract_inverted_index.counterparts	128
abstract_inverted_index.capabilities.	50
abstract_inverted_index.keyword-based	30
abstract_inverted_index.organizations	176
abstract_inverted_index.summarization	49
abstract_inverted_index.query-document	95
abstract_inverted_index.Onco-Retriever,	144
abstract_inverted_index.domain-specific	179
abstract_inverted_index.Retrieval-augmented	56
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
sustainable_development_goals[0].id	https://metadata.un.org/sdg/4
sustainable_development_goals[0].score	0.4300000071525574
sustainable_development_goals[0].display_name	Quality Education
citation_normalized_percentile