Identification of asthma control factor in clinical notes using a hybrid deep learning model

Abstract Background There are significant variabilities in guideline-concordant documentation in asthma care. However, assessing clinician’s documentation is not feasible using only structured data but requires labor-intensive chart review of electronic health records (EHRs). A certain guideline ele...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Bhavani Singh Agnikula Kshatriya, Elham Sagheb, Chung-Il Wi, Jungwon Yoon, Hee Yun Seol, Young Juhn, Sunghwan Sohn
Formato: article
Lenguaje:EN
Publicado: BMC 2021
Materias:
Acceso en línea:https://doaj.org/article/0fa102a58f5d4605b8d85b926966941f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:0fa102a58f5d4605b8d85b926966941f
record_format dspace
spelling oai:doaj.org-article:0fa102a58f5d4605b8d85b926966941f2021-11-14T12:29:07ZIdentification of asthma control factor in clinical notes using a hybrid deep learning model10.1186/s12911-021-01633-41472-6947https://doaj.org/article/0fa102a58f5d4605b8d85b926966941f2021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01633-4https://doaj.org/toc/1472-6947Abstract Background There are significant variabilities in guideline-concordant documentation in asthma care. However, assessing clinician’s documentation is not feasible using only structured data but requires labor-intensive chart review of electronic health records (EHRs). A certain guideline element in asthma control factors, such as review inhaler techniques, requires context understanding to correctly capture from EHR free text. Methods The study data consist of two sets: (1) manual chart reviewed data—1039 clinical notes of 300 patients with asthma diagnosis, and (2) weakly labeled data (distant supervision)—27,363 clinical notes from 800 patients with asthma diagnosis. A context-aware language model, Bidirectional Encoder Representations from Transformers (BERT) was developed to identify inhaler techniques in EHR free text. Both original BERT and clinical BioBERT (cBERT) were applied with a cost-sensitivity to deal with imbalanced data. The distant supervision using weak labels by rules was also incorporated to augment the training set and alleviate a costly manual labeling process in the development of a deep learning algorithm. A hybrid approach using post-hoc rules was also explored to fix BERT model errors. The performance of BERT with/without distant supervision, hybrid, and rule-based models were compared in precision, recall, F-score, and accuracy. Results The BERT models on the original data performed similar to a rule-based model in F1-score (0.837, 0.845, and 0.838 for rules, BERT, and cBERT, respectively). The BERT models with distant supervision produced higher performance (0.853 and 0.880 for BERT and cBERT, respectively) than without distant supervision and a rule-based model. The hybrid models performed best in F1-score of 0.877 and 0.904 over the distant supervision on BERT and cBERT. Conclusions The proposed BERT models with distant supervision demonstrated its capability to identify inhaler techniques in EHR free text, and outperformed both the rule-based model and BERT models trained on the original data. With a distant supervision approach, we may alleviate costly manual chart review to generate the large training data required in most deep learning-based models. A hybrid model was able to fix BERT model errors and further improve the performance.Bhavani Singh Agnikula KshatriyaElham SaghebChung-Il WiJungwon YoonHee Yun SeolYoung JuhnSunghwan SohnBMCarticleDeep learningContext-aware language modelNatural language processingDocumentation variationsAdherence to asthma guidelinesInhaler techniqueComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss S7, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Deep learning
Context-aware language model
Natural language processing
Documentation variations
Adherence to asthma guidelines
Inhaler technique
Computer applications to medicine. Medical informatics
R858-859.7
spellingShingle Deep learning
Context-aware language model
Natural language processing
Documentation variations
Adherence to asthma guidelines
Inhaler technique
Computer applications to medicine. Medical informatics
R858-859.7
Bhavani Singh Agnikula Kshatriya
Elham Sagheb
Chung-Il Wi
Jungwon Yoon
Hee Yun Seol
Young Juhn
Sunghwan Sohn
Identification of asthma control factor in clinical notes using a hybrid deep learning model
description Abstract Background There are significant variabilities in guideline-concordant documentation in asthma care. However, assessing clinician’s documentation is not feasible using only structured data but requires labor-intensive chart review of electronic health records (EHRs). A certain guideline element in asthma control factors, such as review inhaler techniques, requires context understanding to correctly capture from EHR free text. Methods The study data consist of two sets: (1) manual chart reviewed data—1039 clinical notes of 300 patients with asthma diagnosis, and (2) weakly labeled data (distant supervision)—27,363 clinical notes from 800 patients with asthma diagnosis. A context-aware language model, Bidirectional Encoder Representations from Transformers (BERT) was developed to identify inhaler techniques in EHR free text. Both original BERT and clinical BioBERT (cBERT) were applied with a cost-sensitivity to deal with imbalanced data. The distant supervision using weak labels by rules was also incorporated to augment the training set and alleviate a costly manual labeling process in the development of a deep learning algorithm. A hybrid approach using post-hoc rules was also explored to fix BERT model errors. The performance of BERT with/without distant supervision, hybrid, and rule-based models were compared in precision, recall, F-score, and accuracy. Results The BERT models on the original data performed similar to a rule-based model in F1-score (0.837, 0.845, and 0.838 for rules, BERT, and cBERT, respectively). The BERT models with distant supervision produced higher performance (0.853 and 0.880 for BERT and cBERT, respectively) than without distant supervision and a rule-based model. The hybrid models performed best in F1-score of 0.877 and 0.904 over the distant supervision on BERT and cBERT. Conclusions The proposed BERT models with distant supervision demonstrated its capability to identify inhaler techniques in EHR free text, and outperformed both the rule-based model and BERT models trained on the original data. With a distant supervision approach, we may alleviate costly manual chart review to generate the large training data required in most deep learning-based models. A hybrid model was able to fix BERT model errors and further improve the performance.
format article
author Bhavani Singh Agnikula Kshatriya
Elham Sagheb
Chung-Il Wi
Jungwon Yoon
Hee Yun Seol
Young Juhn
Sunghwan Sohn
author_facet Bhavani Singh Agnikula Kshatriya
Elham Sagheb
Chung-Il Wi
Jungwon Yoon
Hee Yun Seol
Young Juhn
Sunghwan Sohn
author_sort Bhavani Singh Agnikula Kshatriya
title Identification of asthma control factor in clinical notes using a hybrid deep learning model
title_short Identification of asthma control factor in clinical notes using a hybrid deep learning model
title_full Identification of asthma control factor in clinical notes using a hybrid deep learning model
title_fullStr Identification of asthma control factor in clinical notes using a hybrid deep learning model
title_full_unstemmed Identification of asthma control factor in clinical notes using a hybrid deep learning model
title_sort identification of asthma control factor in clinical notes using a hybrid deep learning model
publisher BMC
publishDate 2021
url https://doaj.org/article/0fa102a58f5d4605b8d85b926966941f
work_keys_str_mv AT bhavanisinghagnikulakshatriya identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
AT elhamsagheb identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
AT chungilwi identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
AT jungwonyoon identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
AT heeyunseol identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
AT youngjuhn identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
AT sunghwansohn identificationofasthmacontrolfactorinclinicalnotesusingahybriddeeplearningmodel
_version_ 1718429149701341184