Integrating speculation detection and deep learning to extract lung cancer diagnosis from clinical notes
Entity
UAM. Departamento de MedicinaPublisher
MDPIDate
2021-01-19Citation
10.3390/app11020865
Appl. Sci.11.2 (2021): 865
ISSN
2076-3417DOI
10.3390/app11020865Funded by
This work is supported by the EU Horizon 2020 innovation program under grant agreement No. 780495, project BigMedilytics (Big Data for Medical Analytics). It has been also supported by Fundación AECC and Instituto de Salud Carlos III (grant AC19/00034), under the frame of ERA-NET PerMedProject
eu-repo/grantAgreement/EC/H2020/780495/EU//BIGMEDEILYTICSEditor's Version
https://doi.org/10.3390/app11020865Subjects
Deep learning; Diagnosis extraction; Information extraction; Lung cancer; Natural Language Processing (NLP); Negation detection; Speculation detection; MedicinaRights
© 2021 by the authorsAbstract
Despite efforts to develop models for extracting medical concepts from clinical notes, there are still some challenges in particular to be able to relate concepts to dates. The high number of clinical notes written for each single patient, the use of negation, speculation, and different date formats cause ambiguity that has to be solved to reconstruct the patient’s natural history. In this paper, we concentrate on extracting from clinical narratives the cancer diagnosis and relating it to the diagnosis date. To address this challenge, a hybrid approach that combines deep learning-based and rule-based methods is proposed. The approach integrates three steps: (i) lung cancer named entity recognition, (ii) negation and speculation detection, and (iii) relating the cancer diagnosis to a valid date. In particular, we apply the proposed approach to extract the lung cancer diagnosis and its diagnosis date from clinical narratives written in Spanish. Results obtained show an F-score of 90% in the named entity recognition task, and a 89% F-score in the task of relating the cancer diagnosis to the diagnosis date. Our findings suggest that speculation detection is together with negation detection a key component to properly extract cancer diagnosis from clinical notes
Files in this item
Google Scholar:Pabón, Oswaldo Solarte
-
Torrente, Maria
-
Provencio Pulla, Mariano
-
Rodríguez-Gonzalez, Alejandro
-
Menasalvas, Ernestina
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.
-
Concordance between circulating tumor cells and clinical status during follow-up in anaplastic lymphoma kinase (ALK) non-small-cell lung cancer patients
Provencio Pulla, Mariano; Pérez-Callejo, David; Torrente, María; Martín, Paloma; Calvo de Juan, Virginia; Gutiérrez, Lourdes; Franco, Fernando; Coronado, María José; Cruz-Bermúdez, Juan Luis; Martín Ruiz-Valdepeñas, Asunción; Cruz-Bermúdez, Alberto; Sánchez-Beato, Margarita; Romero, Atocha; García-Grande, Aránzazu
2017-07-31 -
Dynamic circulating tumor DNA quantificaton for the individualization of non-small-cell lung cancer patients treatment
Provencio Pulla, Mariano; Torrente, María; Calvo de Juan, Virginia; Gutiérrez, Lourdes; Pérez-Callejo, David; Pérez-Barrios, Clara; Barquín, Miguel; Royuela Vicente, Ana; Rodríguez-Alfonso, Begoña; Sotelo, Miguel; Cruz-Bermúdez, Juan Luis; Mendez, Miriam; Cruz-Bermúdez, Alberto; Romero, Atocha
2017-08-07