GenAI Exceeds Clinical Experts in Predicting Acute Kidney Injury following Paediatric Cardiopulmonary Bypass Article Swipe
Alireza S. Mahani
,
Mansour Taghavi Azar Sharabiani
,
Alex Bottle
,
Yadav Sriniva
,
Richard Issitt
,
Șerban Stoica
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-5370136/v1
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.21203/rs.3.rs-5370136/v1
The emergence of large language models (LLMs) opens new horizons to leverage, often unused, information in clinical text. Our study aims to capitalise on this new potential. Specifically, we examine the utility of text embeddings generated by LLMs in predicting postoperative acute kidney injury (AKI) in paediatric cardiopulmonary bypass (CPB) patients using electronic health record (EHR) text, and propose methods for explaining their output. AKI could be a serious complication in paediatric CPB and its accurate prediction can significantly improve patient outcomes by enabling timely interventions. We evaluate various text embedding algorithms such as Doc2Vec, top-performing sentence transformers on Hugging Face, and commercial LLMs from Google and OpenAI. We benchmark the cross-validated performance of these 'AI models' against a 'baseline model' as well as an established clinically-defined 'expert model'. The baseline model includes structured features, i.e., patient gender, age, height, body mass index and length of operation. The majority of AI models surpass, not only the baseline model, but also the expert model. An ensemble of AI and clinical-expert models improves discriminative performance by 23% compared to the baseline model. Consistency of patient clusters formed from AI-generated embeddings with clinical-expert clusters - measured via the adjusted rand index and adjusted mutual information metrics - illustrates the medical validity of LLM embeddings. We create a reverse mapping from the numeric embedding space to the natural-language domain via the embedding-based clusters, generating medical labels for the clusters in the process. We also use text-generating LLMs to summarise the differences between AI and expert clusters. Such 'explainability' outputs can increase medical practitioners' trust in the AI applications, and help generate new hypotheses, e.g., by studying the association of cluster memberships and outcomes of interest.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.21203/rs.3.rs-5370136/v1
- https://www.researchsquare.com/article/rs-5370136/latest.pdf
- OA Status
- gold
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4409957622
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4409957622Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.21203/rs.3.rs-5370136/v1Digital Object Identifier
- Title
-
GenAI Exceeds Clinical Experts in Predicting Acute Kidney Injury following Paediatric Cardiopulmonary BypassWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-04-29Full publication date if available
- Authors
-
Alireza S. Mahani, Mansour Taghavi Azar Sharabiani, Alex Bottle, Yadav Sriniva, Richard Issitt, Șerban StoicaList of authors in order
- Landing page
-
https://doi.org/10.21203/rs.3.rs-5370136/v1Publisher landing page
- PDF URL
-
https://www.researchsquare.com/article/rs-5370136/latest.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://www.researchsquare.com/article/rs-5370136/latest.pdfDirect OA link when available
- Concepts
-
Cardiopulmonary bypass, Acute kidney injury, Medicine, Intensive care medicine, Cardiology, Internal medicineTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4409957622 |
|---|---|
| doi | https://doi.org/10.21203/rs.3.rs-5370136/v1 |
| ids.doi | https://doi.org/10.21203/rs.3.rs-5370136/v1 |
| ids.openalex | https://openalex.org/W4409957622 |
| fwci | 0.0 |
| type | preprint |
| title | GenAI Exceeds Clinical Experts in Predicting Acute Kidney Injury following Paediatric Cardiopulmonary Bypass |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10684 |
| topics[0].field.id | https://openalex.org/fields/27 |
| topics[0].field.display_name | Medicine |
| topics[0].score | 0.9426000118255615 |
| topics[0].domain.id | https://openalex.org/domains/4 |
| topics[0].domain.display_name | Health Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2727 |
| topics[0].subfield.display_name | Nephrology |
| topics[0].display_name | Acute Kidney Injury Research |
| topics[1].id | https://openalex.org/T11930 |
| topics[1].field.id | https://openalex.org/fields/27 |
| topics[1].field.display_name | Medicine |
| topics[1].score | 0.9236999750137329 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2705 |
| topics[1].subfield.display_name | Cardiology and Cardiovascular Medicine |
| topics[1].display_name | Cardiac, Anesthesia and Surgical Outcomes |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2778881276 |
| concepts[0].level | 2 |
| concepts[0].score | 0.9309852719306946 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q552304 |
| concepts[0].display_name | Cardiopulmonary bypass |
| concepts[1].id | https://openalex.org/C2780472472 |
| concepts[1].level | 2 |
| concepts[1].score | 0.803264856338501 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q424337 |
| concepts[1].display_name | Acute kidney injury |
| concepts[2].id | https://openalex.org/C71924100 |
| concepts[2].level | 0 |
| concepts[2].score | 0.619353711605072 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11190 |
| concepts[2].display_name | Medicine |
| concepts[3].id | https://openalex.org/C177713679 |
| concepts[3].level | 1 |
| concepts[3].score | 0.46467429399490356 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q679690 |
| concepts[3].display_name | Intensive care medicine |
| concepts[4].id | https://openalex.org/C164705383 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4632161259651184 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q10379 |
| concepts[4].display_name | Cardiology |
| concepts[5].id | https://openalex.org/C126322002 |
| concepts[5].level | 1 |
| concepts[5].score | 0.4015931487083435 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11180 |
| concepts[5].display_name | Internal medicine |
| keywords[0].id | https://openalex.org/keywords/cardiopulmonary-bypass |
| keywords[0].score | 0.9309852719306946 |
| keywords[0].display_name | Cardiopulmonary bypass |
| keywords[1].id | https://openalex.org/keywords/acute-kidney-injury |
| keywords[1].score | 0.803264856338501 |
| keywords[1].display_name | Acute kidney injury |
| keywords[2].id | https://openalex.org/keywords/medicine |
| keywords[2].score | 0.619353711605072 |
| keywords[2].display_name | Medicine |
| keywords[3].id | https://openalex.org/keywords/intensive-care-medicine |
| keywords[3].score | 0.46467429399490356 |
| keywords[3].display_name | Intensive care medicine |
| keywords[4].id | https://openalex.org/keywords/cardiology |
| keywords[4].score | 0.4632161259651184 |
| keywords[4].display_name | Cardiology |
| keywords[5].id | https://openalex.org/keywords/internal-medicine |
| keywords[5].score | 0.4015931487083435 |
| keywords[5].display_name | Internal medicine |
| language | en |
| locations[0].id | doi:10.21203/rs.3.rs-5370136/v1 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://www.researchsquare.com/article/rs-5370136/latest.pdf |
| locations[0].version | acceptedVersion |
| locations[0].raw_type | posted-content |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.21203/rs.3.rs-5370136/v1 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5071770980 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-7932-6681 |
| authorships[0].author.display_name | Alireza S. Mahani |
| authorships[0].affiliations[0].raw_affiliation_string | Statman Solution |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Alireza Mahani |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Statman Solution |
| authorships[1].author.id | https://openalex.org/A5074159692 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3808-277X |
| authorships[1].author.display_name | Mansour Taghavi Azar Sharabiani |
| authorships[1].countries | GB |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I47508984 |
| authorships[1].affiliations[0].raw_affiliation_string | Imperial College London, Department of Primary Care and Public Health |
| authorships[1].institutions[0].id | https://openalex.org/I47508984 |
| authorships[1].institutions[0].ror | https://ror.org/041kmwe10 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I47508984 |
| authorships[1].institutions[0].country_code | GB |
| authorships[1].institutions[0].display_name | Imperial College London |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Mansour Sharabiani |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Imperial College London, Department of Primary Care and Public Health |
| authorships[2].author.id | https://openalex.org/A5085417650 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-9978-2011 |
| authorships[2].author.display_name | Alex Bottle |
| authorships[2].countries | GB |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I47508984 |
| authorships[2].affiliations[0].raw_affiliation_string | Imperial College London, Department of Primary Care and Public Health |
| authorships[2].institutions[0].id | https://openalex.org/I47508984 |
| authorships[2].institutions[0].ror | https://ror.org/041kmwe10 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I47508984 |
| authorships[2].institutions[0].country_code | GB |
| authorships[2].institutions[0].display_name | Imperial College London |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Alex Bottle |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Imperial College London, Department of Primary Care and Public Health |
| authorships[3].author.id | https://openalex.org/A5117384115 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Yadav Sriniva |
| authorships[3].countries | GB |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I2800129641, https://openalex.org/I45129253 |
| authorships[3].affiliations[0].raw_affiliation_string | Great Ormond Street Hospital |
| authorships[3].institutions[0].id | https://openalex.org/I2800129641 |
| authorships[3].institutions[0].ror | https://ror.org/00zn2c847 |
| authorships[3].institutions[0].type | healthcare |
| authorships[3].institutions[0].lineage | https://openalex.org/I2800129641, https://openalex.org/I2800349819 |
| authorships[3].institutions[0].country_code | GB |
| authorships[3].institutions[0].display_name | Great Ormond Street Hospital |
| authorships[3].institutions[1].id | https://openalex.org/I45129253 |
| authorships[3].institutions[1].ror | https://ror.org/02jx3x895 |
| authorships[3].institutions[1].type | education |
| authorships[3].institutions[1].lineage | https://openalex.org/I124357947, https://openalex.org/I45129253 |
| authorships[3].institutions[1].country_code | GB |
| authorships[3].institutions[1].display_name | University College London |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yadav Sriniva |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Great Ormond Street Hospital |
| authorships[4].author.id | https://openalex.org/A5028327431 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-6299-2557 |
| authorships[4].author.display_name | Richard Issitt |
| authorships[4].countries | GB |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I2800129641, https://openalex.org/I45129253 |
| authorships[4].affiliations[0].raw_affiliation_string | Great Ormond Street Hospital |
| authorships[4].institutions[0].id | https://openalex.org/I2800129641 |
| authorships[4].institutions[0].ror | https://ror.org/00zn2c847 |
| authorships[4].institutions[0].type | healthcare |
| authorships[4].institutions[0].lineage | https://openalex.org/I2800129641, https://openalex.org/I2800349819 |
| authorships[4].institutions[0].country_code | GB |
| authorships[4].institutions[0].display_name | Great Ormond Street Hospital |
| authorships[4].institutions[1].id | https://openalex.org/I45129253 |
| authorships[4].institutions[1].ror | https://ror.org/02jx3x895 |
| authorships[4].institutions[1].type | education |
| authorships[4].institutions[1].lineage | https://openalex.org/I124357947, https://openalex.org/I45129253 |
| authorships[4].institutions[1].country_code | GB |
| authorships[4].institutions[1].display_name | University College London |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Richard Issitt |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Great Ormond Street Hospital |
| authorships[5].author.id | https://openalex.org/A5061420147 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-0456-1249 |
| authorships[5].author.display_name | Șerban Stoica |
| authorships[5].countries | GB |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I2801868026 |
| authorships[5].affiliations[0].raw_affiliation_string | Bristol Royal Hospital for Children |
| authorships[5].institutions[0].id | https://openalex.org/I2801868026 |
| authorships[5].institutions[0].ror | https://ror.org/01qgecw57 |
| authorships[5].institutions[0].type | healthcare |
| authorships[5].institutions[0].lineage | https://openalex.org/I2801868026 |
| authorships[5].institutions[0].country_code | GB |
| authorships[5].institutions[0].display_name | Bristol Royal Hospital for Children |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Serban Stoica |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | Bristol Royal Hospital for Children |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://www.researchsquare.com/article/rs-5370136/latest.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | GenAI Exceeds Clinical Experts in Predicting Acute Kidney Injury following Paediatric Cardiopulmonary Bypass |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10684 |
| primary_topic.field.id | https://openalex.org/fields/27 |
| primary_topic.field.display_name | Medicine |
| primary_topic.score | 0.9426000118255615 |
| primary_topic.domain.id | https://openalex.org/domains/4 |
| primary_topic.domain.display_name | Health Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2727 |
| primary_topic.subfield.display_name | Nephrology |
| primary_topic.display_name | Acute Kidney Injury Research |
| related_works | https://openalex.org/W4387497383, https://openalex.org/W3183948672, https://openalex.org/W3173606202, https://openalex.org/W3110381201, https://openalex.org/W2948807893, https://openalex.org/W2935909890, https://openalex.org/W2899084033, https://openalex.org/W2778153218, https://openalex.org/W2758277628, https://openalex.org/W1531601525 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.21203/rs.3.rs-5370136/v1 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://www.researchsquare.com/article/rs-5370136/latest.pdf |
| best_oa_location.version | acceptedVersion |
| best_oa_location.raw_type | posted-content |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-5370136/v1 |
| primary_location.id | doi:10.21203/rs.3.rs-5370136/v1 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://www.researchsquare.com/article/rs-5370136/latest.pdf |
| primary_location.version | acceptedVersion |
| primary_location.raw_type | posted-content |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.21203/rs.3.rs-5370136/v1 |
| publication_date | 2025-04-29 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.- | 192, 204 |
| abstract_inverted_index.a | 68, 119, 214 |
| abstract_inverted_index.AI | 151, 167, 249, 263 |
| abstract_inverted_index.An | 164 |
| abstract_inverted_index.We | 87, 109, 212, 239 |
| abstract_inverted_index.an | 125 |
| abstract_inverted_index.as | 94, 122, 124 |
| abstract_inverted_index.be | 67 |
| abstract_inverted_index.by | 37, 83, 174, 271 |
| abstract_inverted_index.in | 16, 39, 46, 71, 236, 261 |
| abstract_inverted_index.of | 3, 33, 114, 146, 150, 166, 182, 209, 275, 280 |
| abstract_inverted_index.on | 24, 99 |
| abstract_inverted_index.to | 11, 22, 177, 222, 244 |
| abstract_inverted_index.we | 29 |
| abstract_inverted_index.'AI | 116 |
| abstract_inverted_index.23% | 175 |
| abstract_inverted_index.AKI | 65 |
| abstract_inverted_index.CPB | 73 |
| abstract_inverted_index.LLM | 210 |
| abstract_inverted_index.Our | 19 |
| abstract_inverted_index.The | 1, 130, 148 |
| abstract_inverted_index.and | 58, 74, 102, 107, 144, 168, 199, 250, 265, 278 |
| abstract_inverted_index.but | 159 |
| abstract_inverted_index.can | 78, 256 |
| abstract_inverted_index.for | 61, 233 |
| abstract_inverted_index.its | 75 |
| abstract_inverted_index.new | 9, 26, 268 |
| abstract_inverted_index.not | 154 |
| abstract_inverted_index.the | 31, 111, 156, 161, 178, 195, 206, 218, 223, 227, 234, 237, 246, 262, 273 |
| abstract_inverted_index.use | 241 |
| abstract_inverted_index.via | 194, 226 |
| abstract_inverted_index.LLMs | 38, 104, 243 |
| abstract_inverted_index.Such | 253 |
| abstract_inverted_index.age, | 139 |
| abstract_inverted_index.aims | 21 |
| abstract_inverted_index.also | 160, 240 |
| abstract_inverted_index.body | 141 |
| abstract_inverted_index.from | 105, 186, 217 |
| abstract_inverted_index.help | 266 |
| abstract_inverted_index.mass | 142 |
| abstract_inverted_index.only | 155 |
| abstract_inverted_index.rand | 197 |
| abstract_inverted_index.such | 93 |
| abstract_inverted_index.text | 34, 90 |
| abstract_inverted_index.this | 25 |
| abstract_inverted_index.well | 123 |
| abstract_inverted_index.with | 189 |
| abstract_inverted_index.(AKI) | 45 |
| abstract_inverted_index.(CPB) | 50 |
| abstract_inverted_index.(EHR) | 56 |
| abstract_inverted_index.Face, | 101 |
| abstract_inverted_index.acute | 42 |
| abstract_inverted_index.could | 66 |
| abstract_inverted_index.e.g., | 270 |
| abstract_inverted_index.i.e., | 136 |
| abstract_inverted_index.index | 143, 198 |
| abstract_inverted_index.large | 4 |
| abstract_inverted_index.model | 132 |
| abstract_inverted_index.often | 13 |
| abstract_inverted_index.opens | 8 |
| abstract_inverted_index.space | 221 |
| abstract_inverted_index.study | 20 |
| abstract_inverted_index.text, | 57 |
| abstract_inverted_index.text. | 18 |
| abstract_inverted_index.their | 63 |
| abstract_inverted_index.these | 115 |
| abstract_inverted_index.trust | 260 |
| abstract_inverted_index.using | 52 |
| abstract_inverted_index.(LLMs) | 7 |
| abstract_inverted_index.Google | 106 |
| abstract_inverted_index.bypass | 49 |
| abstract_inverted_index.create | 213 |
| abstract_inverted_index.domain | 225 |
| abstract_inverted_index.expert | 162, 251 |
| abstract_inverted_index.formed | 185 |
| abstract_inverted_index.health | 54 |
| abstract_inverted_index.injury | 44 |
| abstract_inverted_index.kidney | 43 |
| abstract_inverted_index.labels | 232 |
| abstract_inverted_index.length | 145 |
| abstract_inverted_index.model' | 121 |
| abstract_inverted_index.model, | 158 |
| abstract_inverted_index.model. | 163, 180 |
| abstract_inverted_index.models | 6, 152, 170 |
| abstract_inverted_index.mutual | 201 |
| abstract_inverted_index.record | 55 |
| abstract_inverted_index.timely | 85 |
| abstract_inverted_index.'expert | 128 |
| abstract_inverted_index.Hugging | 100 |
| abstract_inverted_index.OpenAI. | 108 |
| abstract_inverted_index.against | 118 |
| abstract_inverted_index.between | 248 |
| abstract_inverted_index.cluster | 276 |
| abstract_inverted_index.examine | 30 |
| abstract_inverted_index.gender, | 138 |
| abstract_inverted_index.height, | 140 |
| abstract_inverted_index.improve | 80 |
| abstract_inverted_index.mapping | 216 |
| abstract_inverted_index.medical | 207, 231, 258 |
| abstract_inverted_index.methods | 60 |
| abstract_inverted_index.metrics | 203 |
| abstract_inverted_index.model'. | 129 |
| abstract_inverted_index.models' | 117 |
| abstract_inverted_index.numeric | 219 |
| abstract_inverted_index.output. | 64 |
| abstract_inverted_index.outputs | 255 |
| abstract_inverted_index.patient | 81, 137, 183 |
| abstract_inverted_index.propose | 59 |
| abstract_inverted_index.reverse | 215 |
| abstract_inverted_index.serious | 69 |
| abstract_inverted_index.unused, | 14 |
| abstract_inverted_index.utility | 32 |
| abstract_inverted_index.various | 89 |
| abstract_inverted_index.Doc2Vec, | 95 |
| abstract_inverted_index.accurate | 76 |
| abstract_inverted_index.adjusted | 196, 200 |
| abstract_inverted_index.baseline | 131, 157, 179 |
| abstract_inverted_index.clinical | 17 |
| abstract_inverted_index.clusters | 184, 191, 235 |
| abstract_inverted_index.compared | 176 |
| abstract_inverted_index.enabling | 84 |
| abstract_inverted_index.ensemble | 165 |
| abstract_inverted_index.evaluate | 88 |
| abstract_inverted_index.generate | 267 |
| abstract_inverted_index.horizons | 10 |
| abstract_inverted_index.improves | 171 |
| abstract_inverted_index.includes | 133 |
| abstract_inverted_index.increase | 257 |
| abstract_inverted_index.language | 5 |
| abstract_inverted_index.majority | 149 |
| abstract_inverted_index.measured | 193 |
| abstract_inverted_index.outcomes | 82, 279 |
| abstract_inverted_index.patients | 51 |
| abstract_inverted_index.process. | 238 |
| abstract_inverted_index.sentence | 97 |
| abstract_inverted_index.studying | 272 |
| abstract_inverted_index.surpass, | 153 |
| abstract_inverted_index.validity | 208 |
| abstract_inverted_index.'baseline | 120 |
| abstract_inverted_index.benchmark | 110 |
| abstract_inverted_index.clusters, | 229 |
| abstract_inverted_index.clusters. | 252 |
| abstract_inverted_index.embedding | 91, 220 |
| abstract_inverted_index.emergence | 2 |
| abstract_inverted_index.features, | 135 |
| abstract_inverted_index.generated | 36 |
| abstract_inverted_index.interest. | 281 |
| abstract_inverted_index.leverage, | 12 |
| abstract_inverted_index.summarise | 245 |
| abstract_inverted_index.algorithms | 92 |
| abstract_inverted_index.capitalise | 23 |
| abstract_inverted_index.commercial | 103 |
| abstract_inverted_index.electronic | 53 |
| abstract_inverted_index.embeddings | 35, 188 |
| abstract_inverted_index.explaining | 62 |
| abstract_inverted_index.generating | 230 |
| abstract_inverted_index.operation. | 147 |
| abstract_inverted_index.paediatric | 47, 72 |
| abstract_inverted_index.potential. | 27 |
| abstract_inverted_index.predicting | 40 |
| abstract_inverted_index.prediction | 77 |
| abstract_inverted_index.structured | 134 |
| abstract_inverted_index.Consistency | 181 |
| abstract_inverted_index.association | 274 |
| abstract_inverted_index.differences | 247 |
| abstract_inverted_index.embeddings. | 211 |
| abstract_inverted_index.established | 126 |
| abstract_inverted_index.hypotheses, | 269 |
| abstract_inverted_index.illustrates | 205 |
| abstract_inverted_index.information | 15, 202 |
| abstract_inverted_index.memberships | 277 |
| abstract_inverted_index.performance | 113, 173 |
| abstract_inverted_index.AI-generated | 187 |
| abstract_inverted_index.complication | 70 |
| abstract_inverted_index.transformers | 98 |
| abstract_inverted_index.Specifically, | 28 |
| abstract_inverted_index.applications, | 264 |
| abstract_inverted_index.postoperative | 41 |
| abstract_inverted_index.significantly | 79 |
| abstract_inverted_index.discriminative | 172 |
| abstract_inverted_index.interventions. | 86 |
| abstract_inverted_index.practitioners' | 259 |
| abstract_inverted_index.top-performing | 96 |
| abstract_inverted_index.cardiopulmonary | 48 |
| abstract_inverted_index.clinical-expert | 169, 190 |
| abstract_inverted_index.cross-validated | 112 |
| abstract_inverted_index.embedding-based | 228 |
| abstract_inverted_index.text-generating | 242 |
| abstract_inverted_index.'explainability' | 254 |
| abstract_inverted_index.natural-language | 224 |
| abstract_inverted_index.clinically-defined | 127 |
| abstract_inverted_index.<title>Abstract</title> | 0 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile.value | 0.1845567 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |