Integrating structured and unstructured data for timely prediction of bloodstream infection among children.
Journal
Pediatric research
ISSN: 1530-0447
Titre abrégé: Pediatr Res
Pays: United States
ID NLM: 0100714
Informations de publication
Date de publication:
03 2023
03 2023
Historique:
received:
09
01
2022
accepted:
08
05
2022
revised:
08
04
2022
pubmed:
20
7
2022
medline:
25
3
2023
entrez:
19
7
2022
Statut:
ppublish
Résumé
Hospitalized children with central venous lines (CVLs) are at higher risk of hospital-acquired infections. Information in electronic health records (EHRs) can be employed in training deep learning models to predict the onset of these infections. We incorporated clinical notes in addition to structured EHR data to predict serious bloodstream infections, defined as positive blood culture followed by at least 4 days of new antimicrobial agent administration, among hospitalized children with CVLs. Structured EHR information and clinical notes were extracted for a retrospective cohort including all hospitalized patients with CVLs at a single tertiary care pediatric health system from 2013 to 2018. Deep learning models were trained to determine the added benefit of incorporating the information embedded in clinical notes in predicting serious bloodstream infection. A total of 24,351 patient encounters met inclusion criteria. The best-performing model restricted to structured EHR data had a specificity of 0.951 and positive predictive value (PPV) of 0.056 when the sensitivity was set to 0.85. The addition of contextualized word embeddings improved the specificity to 0.981 and PPV to 0.113. Integrating clinical notes with structured EHR data improved the prediction of serious bloodstream infections among pediatric patients with CVLs. Developed an advanced infection prediction model in pediatrics that integrates the structured and unstructured EHRs. Extracted information from clinical notes to do timely prediction in a clinical setting. Developed a deep learning model framework that can be employed in predicting rare events in a complex and dynamic environment.
Sections du résumé
BACKGROUND
Hospitalized children with central venous lines (CVLs) are at higher risk of hospital-acquired infections. Information in electronic health records (EHRs) can be employed in training deep learning models to predict the onset of these infections. We incorporated clinical notes in addition to structured EHR data to predict serious bloodstream infections, defined as positive blood culture followed by at least 4 days of new antimicrobial agent administration, among hospitalized children with CVLs.
METHODS
Structured EHR information and clinical notes were extracted for a retrospective cohort including all hospitalized patients with CVLs at a single tertiary care pediatric health system from 2013 to 2018. Deep learning models were trained to determine the added benefit of incorporating the information embedded in clinical notes in predicting serious bloodstream infection.
RESULTS
A total of 24,351 patient encounters met inclusion criteria. The best-performing model restricted to structured EHR data had a specificity of 0.951 and positive predictive value (PPV) of 0.056 when the sensitivity was set to 0.85. The addition of contextualized word embeddings improved the specificity to 0.981 and PPV to 0.113.
CONCLUSIONS
Integrating clinical notes with structured EHR data improved the prediction of serious bloodstream infections among pediatric patients with CVLs.
IMPACT
Developed an advanced infection prediction model in pediatrics that integrates the structured and unstructured EHRs. Extracted information from clinical notes to do timely prediction in a clinical setting. Developed a deep learning model framework that can be employed in predicting rare events in a complex and dynamic environment.
Identifiants
pubmed: 35854085
doi: 10.1038/s41390-022-02116-6
pii: 10.1038/s41390-022-02116-6
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
969-975Informations de copyright
© 2022. The Author(s), under exclusive licence to the International Pediatric Research Foundation, Inc.
Références
Rupp, M. E. & Majorant, D. Prevention of vascular catheter-related bloodstream infections. Infect. Dis. Clin. 30, 853–868 (2016).
doi: 10.1016/j.idc.2016.07.001
Centers for Disease Control and Prevention. Vital signs: central line–associated blood stream infections—United States, 2001, 2008, and 2009. Ann. Emerg. Med. 58, 447–450 (2011).
doi: 10.1016/j.annemergmed.2011.07.035
Walker, L. W., Nowalk, A. J. & Visweswaran, S. Predicting outcomes in central venous catheter salvage in pediatric central line–associated bloodstream infection. J. Am. Med. Inf. Assoc. 28, 862–867 (2021).
doi: 10.1093/jamia/ocaa328
Tabaie, A. et al. Predicting presumed serious infection among hospitalized children on central venous lines with machine learning. Comput. Biol. Med. 132, 104289 (2021).
doi: 10.1016/j.compbiomed.2021.104289
pubmed: 33667812
pmcid: 9207586
Le, S. et al. Pediatric severe sepsis prediction using machine learning. Front. Pediatr. 7, 413 (2019).
doi: 10.3389/fped.2019.00413
pubmed: 31681711
pmcid: 6798083
Masino, A. J. et al. Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data. PLoS ONE 14, e0212665 (2019).
doi: 10.1371/journal.pone.0212665
pubmed: 30794638
pmcid: 6386402
Reyna, M. A. et al. Early prediction of sepsis from clinical data: the PhysioNet/Computing in Cardiology Challenge 2019. In 2019 Computing in Cardiology (CinC). pp. 1 (IEEE, 2019).
Nemati, S. et al. An interpretable machine learning model for accurate prediction of sepsis in the ICU. Crit. Care Med. 46, 547 (2018).
doi: 10.1097/CCM.0000000000002936
pubmed: 29286945
pmcid: 5851825
Raita, Y. et al. Machine learning-based prediction of acute severity in infants hospitalized for bronchiolitis: a multicenter prospective study. Sci. Rep. 10, 10979 (2020).
doi: 10.1038/s41598-020-67629-8
pubmed: 32620819
pmcid: 7335203
Tabaie, A. et al. Deep learning model to predict serious infection among children with central venous lines. Front. Pediatr. 9, 726870 (2021).
Huang, K., Altosaar, J. & Ranganath, R. ClinicalBERT: modeling clinical notes and predicting hospital readmission. Preprint at arXiv https://arxiv.org/abs/1904.05342 (2019).
Alsentzer, E. et al. Publicly available clinical BERT embeddings. Preprint at arXiv https://arxiv.org/abs/1904.03323 (2019).
Zhang, D., Thadajarassiri, J., Sen, C. & Rundensteiner, E. Time-aware transformer-based network for clinical notes series prediction. In Machine Learning for Healthcare Conference 566–588 (PMLR, 2020).
Amrollahi, F., Shashikumar, S. P., Razmi, F. & Nemati, S. Contextual embeddings from clinical notes improves prediction of sepsis. AMIA Annu. Symp. Proc. 2020, 197–202 (2020).
Liang, H. et al. Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence. Nat. Med. 25, 433–438 (2019).
doi: 10.1038/s41591-018-0335-9
pubmed: 30742121
Hsu, H. E. et al. A national approach to pediatric sepsis surveillance. Pediatrics 144, e20191790 (2019).
Weiss, S. L. et al. Identification of pediatric sepsis for epidemiologic surveillance using electronic clinical data. Pediatr. Crit. Care Med. 21, 113–121 (2020).
doi: 10.1097/PCC.0000000000002170
pubmed: 32032262
pmcid: 7008717
Rhee, C., Dantes, R. B., Epstein, L. & Klompas, M. Using objective clinical data to track progress on preventing and treating sepsis: CDC’s new ‘Adult Sepsis Event’ surveillance strategy. BMJ Qual. Saf. 28, 305–309 (2019).
doi: 10.1136/bmjqs-2018-008331
pubmed: 30254095
Si, Y., Wang, J., Xu, H. & Roberts, K. Enhancing clinical concept extraction with contextual embeddings. J. Am. Med. Inf. Assoc. 26, 1297–1304 (2019).
doi: 10.1093/jamia/ocz096
Johnson, A. E. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3, 1–9 (2016).
doi: 10.1038/sdata.2016.35
Lin, T. Y., Goyal, P., Girshick, R., He, K. & Dollár, P. Focal loss for dense object detection. In Proc. IEEE International Conference on Computer Vision 2980–2988 (IEEE, 2017).
Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. Preprint at arXiv https://arxiv.org/abs/1409.0473 (2014).
Leisman, D. E. et al. Development and reporting of prediction models: guidance for authors from editors of respiratory, sleep, and critical care journals. Crit. Care Med. 48, 623 (2020).
doi: 10.1097/CCM.0000000000004246
pubmed: 32141923
pmcid: 7161722
Leteurtre, S. et al. PELOD-2: an update of the PEdiatric logistic organ dysfunction score. Crit. Care Med. 41, 1761–1773 (2013).
doi: 10.1097/CCM.0b013e31828a2bbd
pubmed: 23685639
Pollack, M. M., Patel, K. M. & Ruttimann, U. E. PRISM III: an updated Pediatric Risk of Mortality score. Crit. Care Med. 24, 743–752 (1996).
doi: 10.1097/00003246-199605000-00004
pubmed: 8706448
Beeler, C. et al. Assessing patient risk of central line-associated bacteremia via machine learning. Am. J. Infect. Control 46, 986–991 (2018).
doi: 10.1016/j.ajic.2018.02.021
pubmed: 29661634
Sung, L. et al. Development and utility assessment of a machine learning bloodstream infection classifier in pediatric patients receiving cancer treatments. BMC Cancer 20, 1–9 (2020).
doi: 10.1186/s12885-020-07618-2
Goh, K. H. et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat. Commun. 12, 711 (2021).
doi: 10.1038/s41467-021-20910-4
pubmed: 33514699
pmcid: 7846756
Horng, S. et al. Creating an automated trigger for sepsis clinical decision support at emergency department triage using machine learning. PLoS ONE 12, e0174708 (2017).
doi: 10.1371/journal.pone.0174708
pubmed: 28384212
pmcid: 5383046