NLP modeling recommendations for restricted data availability in clinical settings

Simple item page
dc.article.number116
dc.catalogadorpva
dc.contributor.authorVillena, Fabián
dc.contributor.authorBravo-Marquez, Felipe
dc.contributor.authorDunstan Escudero, Jocelyn Mariel
dc.date.accessioned2025-03-24T20:26:55Z
dc.date.available2025-03-24T20:26:55Z
dc.date.issued2025
dc.date.updated2025-03-09T01:03:32Z
dc.description.abstractBackground Clinical decision-making in healthcare often relies on unstructured text data, which can be challenging to analyze using traditional methods. Natural Language Processing (NLP) has emerged as a promising solution, but its application in clinical settings is hindered by restricted data availability and the need for domain-specific knowledge. Methods We conducted an experimental analysis to evaluate the performance of various NLP modeling paradigms on multiple clinical NLP tasks in Spanish. These tasks included referral prioritization and referral specialty classification. We simulated three clinical settings with varying levels of data availability and evaluated the performance of four foundation models. Results Clinical-specific pre-trained language models (PLMs) achieved the highest performance across tasks. For referral prioritization, Clinical PLMs attained an 88.85 % macro F1 score when fine-tuned. In referral specialty classification, the same models achieved a 53.79 % macro F1 score, surpassing domain-agnostic models. Continuing pre-training with environment-specific data improved model performance, but the gains were marginal compared to the computational resources required. Few-shot learning with large language models (LLMs) demonstrated lower performance but showed potential in data-scarce scenarios. Conclusions Our study provides evidence-based recommendations for clinical NLP practitioners on selecting modeling paradigms based on data availability. We highlight the importance of considering data availability, task complexity, and institutional maturity when designing and training clinical NLP models. Our findings can inform the development of effective clinical NLP solutions in real-world settings.
dc.fechaingreso.objetodigital2025-03-09
dc.format.extent13 páginas
dc.fuente.origenBiomed Central
dc.identifier.citationBMC Medical Informatics and Decision Making. 2025 Mar 07;25(1):116
dc.identifier.doi10.1186/s12911-025-02948-2
dc.identifier.urihttps://doi.org/10.1186/s12911-025-02948-2
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/102972
dc.information.autorucEscuela de Ingeniería; Dunstan Escudero, Jocelyn Mariel; S/I; 1285723
dc.issue.numero1
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaBMC Medical Informatics and Decision Making
dc.rightsacceso abierto
dc.rights.holderThe Author(s)
dc.rights.licenseAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectArtificial intelligence
dc.subjectNatural language processing
dc.subjectData availability
dc.subject.ddc000
dc.subject.deweyCiencias de la computaciónes_ES
dc.titleNLP modeling recommendations for restricted data availability in clinical settings
dc.typeartículo
dc.volumen25
sipa.codpersvinculados1285723
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
12911_2025_Article_2948.pdf
Size:
1.43 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.98 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas