MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets Article Swipe

PDF

Nassim Oufattole , Teya Bergamaschi , Aleksia Kolo , Hyewon Jeong , Hanna Gaggin , Collin M. Stultz , Matthew B. A. McDermott ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2411.00200

Effective, reliable, and scalable development of machine learning (ML) solutions for structured electronic health record (EHR) data requires the ability to reliably generate high-quality baseline models for diverse supervised learning tasks in an efficient and performant manner. Historically, producing such baseline models has been a largely manual effort--individual researchers would need to decide on the particular featurization and tabularization processes to apply to their individual raw, longitudinal data; and then train a supervised model over those data to produce a baseline result to compare novel methods against, all for just one task and one dataset. In this work, powered by complementary advances in core data standardization through the MEDS framework, we dramatically simplify and accelerate this process of tabularizing irregularly sampled time-series data, providing researchers the ability to automatically and scalably featurize and tabularize their longitudinal EHR data across tens of thousands of individual features, hundreds of millions of clinical events, and diverse windowing horizons and aggregation strategies, all before ultimately leveraging these tabular data to automatically produce high-caliber XGBoost baselines in a highly computationally efficient manner. This system scales to dramatically larger datasets than tabularization tools currently available to the community and enables researchers with any MEDS format dataset to immediately begin producing reliable and performant baseline prediction results on various tasks, with minimal human effort required. This system will greatly enhance the reliability, reproducibility, and ease of development of powerful ML solutions for health problems across diverse datasets and clinical settings.

Related Topics

Computer Science

Law

Concepts

Baseline (sea) Computer science Political science Law

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2411.00200
PDF: https://arxiv.org/pdf/2411.00200
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4404344739

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4404344739

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2411.00200

Digital Object Identifier
Title: MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-10-31

Full publication date if available
Authors: Nassim Oufattole, Teya Bergamaschi, Aleksia Kolo, Hyewon Jeong, Hanna Gaggin, Collin M. Stultz, Matthew B. A. McDermott

List of authors in order
Landing page: https://arxiv.org/abs/2411.00200

Publisher landing page
PDF URL: https://arxiv.org/pdf/2411.00200

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/2411.00200

Direct OA link when available
Concepts: Baseline (sea), Computer science, Political science, Law

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2025: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4404344739
doi	https://doi.org/10.48550/arxiv.2411.00200
ids.doi	https://doi.org/10.48550/arxiv.2411.00200
ids.openalex	https://openalex.org/W4404344739
fwci
type	preprint
title	MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12535
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.2630999982357025
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Machine Learning and Data Classification
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C12725497
concepts[0].level	2
concepts[0].score	0.757630467414856
concepts[0].wikidata	https://www.wikidata.org/wiki/Q810247
concepts[0].display_name	Baseline (sea)
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.43440529704093933
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C17744445
concepts[2].level	0
concepts[2].score	0.1845722198486328
concepts[2].wikidata	https://www.wikidata.org/wiki/Q36442
concepts[2].display_name	Political science
concepts[3].id	https://openalex.org/C199539241
concepts[3].level	1
concepts[3].score	0.0
concepts[3].wikidata	https://www.wikidata.org/wiki/Q7748
concepts[3].display_name	Law
keywords[0].id	https://openalex.org/keywords/baseline
keywords[0].score	0.757630467414856
keywords[0].display_name	Baseline (sea)
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.43440529704093933
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/political-science
keywords[2].score	0.1845722198486328
keywords[2].display_name	Political science
language	en
locations[0].id	pmh:oai:arXiv.org:2411.00200
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/2411.00200
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/2411.00200
locations[1].id	doi:10.48550/arxiv.2411.00200
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.2411.00200
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5059929364
authorships[0].author.orcid
authorships[0].author.display_name	Nassim Oufattole
authorships[0].author_position	first
authorships[0].raw_author_name	Oufattole, Nassim
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5114634775
authorships[1].author.orcid
authorships[1].author.display_name	Teya Bergamaschi
authorships[1].author_position	middle
authorships[1].raw_author_name	Bergamaschi, Teya
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5028540249
authorships[2].author.orcid
authorships[2].author.display_name	Aleksia Kolo
authorships[2].author_position	middle
authorships[2].raw_author_name	Kolo, Aleksia
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5101998939
authorships[3].author.orcid	https://orcid.org/0000-0003-1230-870X
authorships[3].author.display_name	Hyewon Jeong
authorships[3].author_position	middle
authorships[3].raw_author_name	Jeong, Hyewon
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5114634776
authorships[4].author.orcid
authorships[4].author.display_name	Hanna Gaggin
authorships[4].author_position	middle
authorships[4].raw_author_name	Gaggin, Hanna
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5024941370
authorships[5].author.orcid	https://orcid.org/0000-0002-3415-242X
authorships[5].author.display_name	Collin M. Stultz
authorships[5].author_position	middle
authorships[5].raw_author_name	Stultz, Collin M.
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5083993242
authorships[6].author.orcid	https://orcid.org/0000-0001-6048-9707
authorships[6].author.display_name	Matthew B. A. McDermott
authorships[6].author_position	last
authorships[6].raw_author_name	McDermott, Matthew B. A.
authorships[6].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/2411.00200
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-11-14T00:00:00
display_name	MEDS-Tab: Automated tabularization and baseline methods for MEDS datasets
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12535
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.2630999982357025
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Machine Learning and Data Classification
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2383111961, https://openalex.org/W2365952365, https://openalex.org/W2352448290, https://openalex.org/W2380820513, https://openalex.org/W2913146933, https://openalex.org/W2372385138, https://openalex.org/W4296359239
cited_by_count	1
counts_by_year[0].year	2025
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2411.00200
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/2411.00200
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/2411.00200
primary_location.id	pmh:oai:arXiv.org:2411.00200
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/2411.00200
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/2411.00200
publication_date	2024-10-31
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	44, 71, 79, 172
abstract_inverted_index.In	95
abstract_inverted_index.ML	232
abstract_inverted_index.an	32
abstract_inverted_index.by	99
abstract_inverted_index.in	31, 102, 171
abstract_inverted_index.of	5, 117, 140, 142, 146, 148, 228, 230
abstract_inverted_index.on	53, 210
abstract_inverted_index.to	20, 51, 60, 62, 77, 82, 127, 165, 180, 189, 200
abstract_inverted_index.we	110
abstract_inverted_index.EHR	136
abstract_inverted_index.all	87, 158
abstract_inverted_index.and	2, 34, 57, 68, 92, 113, 129, 132, 151, 155, 192, 205, 226, 240
abstract_inverted_index.any	196
abstract_inverted_index.for	10, 26, 88, 234
abstract_inverted_index.has	42
abstract_inverted_index.one	90, 93
abstract_inverted_index.the	18, 54, 107, 125, 190, 223
abstract_inverted_index.(ML)	8
abstract_inverted_index.MEDS	108, 197
abstract_inverted_index.This	177, 218
abstract_inverted_index.been	43
abstract_inverted_index.core	103
abstract_inverted_index.data	16, 76, 104, 137, 164
abstract_inverted_index.ease	227
abstract_inverted_index.just	89
abstract_inverted_index.need	50
abstract_inverted_index.over	74
abstract_inverted_index.raw,	65
abstract_inverted_index.such	39
abstract_inverted_index.task	91
abstract_inverted_index.tens	139
abstract_inverted_index.than	184
abstract_inverted_index.then	69
abstract_inverted_index.this	96, 115
abstract_inverted_index.will	220
abstract_inverted_index.with	195, 213
abstract_inverted_index.(EHR)	15
abstract_inverted_index.apply	61
abstract_inverted_index.begin	202
abstract_inverted_index.data,	122
abstract_inverted_index.data;	67
abstract_inverted_index.human	215
abstract_inverted_index.model	73
abstract_inverted_index.novel	84
abstract_inverted_index.tasks	30
abstract_inverted_index.their	63, 134
abstract_inverted_index.these	162
abstract_inverted_index.those	75
abstract_inverted_index.tools	186
abstract_inverted_index.train	70
abstract_inverted_index.work,	97
abstract_inverted_index.would	49
abstract_inverted_index.across	138, 237
abstract_inverted_index.before	159
abstract_inverted_index.decide	52
abstract_inverted_index.effort	216
abstract_inverted_index.format	198
abstract_inverted_index.health	13, 235
abstract_inverted_index.highly	173
abstract_inverted_index.larger	182
abstract_inverted_index.manual	46
abstract_inverted_index.models	25, 41
abstract_inverted_index.record	14
abstract_inverted_index.result	81
abstract_inverted_index.scales	179
abstract_inverted_index.system	178, 219
abstract_inverted_index.tasks,	212
abstract_inverted_index.XGBoost	169
abstract_inverted_index.ability	19, 126
abstract_inverted_index.compare	83
abstract_inverted_index.dataset	199
abstract_inverted_index.diverse	27, 152, 238
abstract_inverted_index.enables	193
abstract_inverted_index.enhance	222
abstract_inverted_index.events,	150
abstract_inverted_index.greatly	221
abstract_inverted_index.largely	45
abstract_inverted_index.machine	6
abstract_inverted_index.manner.	36, 176
abstract_inverted_index.methods	85
abstract_inverted_index.minimal	214
abstract_inverted_index.powered	98
abstract_inverted_index.process	116
abstract_inverted_index.produce	78, 167
abstract_inverted_index.results	209
abstract_inverted_index.sampled	120
abstract_inverted_index.tabular	163
abstract_inverted_index.through	106
abstract_inverted_index.various	211
abstract_inverted_index.advances	101
abstract_inverted_index.against,	86
abstract_inverted_index.baseline	24, 40, 80, 207
abstract_inverted_index.clinical	149, 241
abstract_inverted_index.dataset.	94
abstract_inverted_index.datasets	183, 239
abstract_inverted_index.generate	22
abstract_inverted_index.horizons	154
abstract_inverted_index.hundreds	145
abstract_inverted_index.learning	7, 29
abstract_inverted_index.millions	147
abstract_inverted_index.powerful	231
abstract_inverted_index.problems	236
abstract_inverted_index.reliable	204
abstract_inverted_index.reliably	21
abstract_inverted_index.requires	17
abstract_inverted_index.scalable	3
abstract_inverted_index.scalably	130
abstract_inverted_index.simplify	112
abstract_inverted_index.available	188
abstract_inverted_index.baselines	170
abstract_inverted_index.community	191
abstract_inverted_index.currently	187
abstract_inverted_index.efficient	33, 175
abstract_inverted_index.features,	144
abstract_inverted_index.featurize	131
abstract_inverted_index.processes	59
abstract_inverted_index.producing	38, 203
abstract_inverted_index.providing	123
abstract_inverted_index.reliable,	1
abstract_inverted_index.required.	217
abstract_inverted_index.settings.	242
abstract_inverted_index.solutions	9, 233
abstract_inverted_index.thousands	141
abstract_inverted_index.windowing	153
abstract_inverted_index.Effective,	0
abstract_inverted_index.accelerate	114
abstract_inverted_index.electronic	12
abstract_inverted_index.framework,	109
abstract_inverted_index.individual	64, 143
abstract_inverted_index.leveraging	161
abstract_inverted_index.particular	55
abstract_inverted_index.performant	35, 206
abstract_inverted_index.prediction	208
abstract_inverted_index.structured	11
abstract_inverted_index.supervised	28, 72
abstract_inverted_index.tabularize	133
abstract_inverted_index.ultimately	160
abstract_inverted_index.aggregation	156
abstract_inverted_index.development	4, 229
abstract_inverted_index.immediately	201
abstract_inverted_index.irregularly	119
abstract_inverted_index.researchers	48, 124, 194
abstract_inverted_index.strategies,	157
abstract_inverted_index.time-series	121
abstract_inverted_index.dramatically	111, 181
abstract_inverted_index.high-caliber	168
abstract_inverted_index.high-quality	23
abstract_inverted_index.longitudinal	66, 135
abstract_inverted_index.reliability,	224
abstract_inverted_index.tabularizing	118
abstract_inverted_index.Historically,	37
abstract_inverted_index.automatically	128, 166
abstract_inverted_index.complementary	100
abstract_inverted_index.featurization	56
abstract_inverted_index.tabularization	58, 185
abstract_inverted_index.computationally	174
abstract_inverted_index.standardization	105
abstract_inverted_index.reproducibility,	225
abstract_inverted_index.effort--individual	47
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	7
citation_normalized_percentile