Comparison of pulmonary congestion severity using artificial intelligence-assisted scoring versus clinical experts: A secondary analysis of BLUSHED-AHF.
Acute heart failure
Lung ultrasound
Machine learning
Point-of-care ultrasound
Quantification
Journal
European journal of heart failure
ISSN: 1879-0844
Titre abrégé: Eur J Heart Fail
Pays: England
ID NLM: 100887595
Informations de publication
Date de publication:
07 2023
07 2023
Historique:
revised:
24
04
2023
received:
03
03
2023
accepted:
09
05
2023
medline:
9
8
2023
pubmed:
23
5
2023
entrez:
23
5
2023
Statut:
ppublish
Résumé
Acute decompensated heart failure (ADHF) is the leading cause of cardiovascular hospitalizations in the United States. Detecting B-lines through lung ultrasound (LUS) can enhance clinicians' prognostic and diagnostic capabilities. Artificial intelligence/machine learning (AI/ML)-based automated guidance systems may allow novice users to apply LUS to clinical care. We investigated whether an AI/ML automated LUS congestion score correlates with expert's interpretations of B-line quantification from an external patient dataset. This was a secondary analysis from the BLUSHED-AHF study which investigated the effect of LUS-guided therapy on patients with ADHF. In BLUSHED-AHF, LUS was performed and B-lines were quantified by ultrasound operators. Two experts then separately quantified the number of B-lines per ultrasound video clip recorded. Here, an AI/ML-based lung congestion score (LCS) was calculated for all LUS clips from BLUSHED-AHF. Spearman correlation was computed between LCS and counts from each of the original three raters. A total of 3858 LUS clips were analysed on 130 patients. The LCS demonstrated good agreement with the two experts' B-line quantification score (r = 0.894, 0.882). Both experts' B-line quantification scores had significantly better agreement with the LCS than they did with the ultrasound operator's score (p < 0.005, p < 0.001). Artificial intelligence/machine learning-based LCS correlated with expert-level B-line quantification. Future studies are needed to determine whether automated tools may assist novice users in LUS interpretation.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1166-1169Informations de copyright
© 2023 European Society of Cardiology.
Références
Virani SS, Alonso A, Aparicio HJ, Benjamin EJ, Bittencourt MS, Callaway CW, et al. Heart disease and stroke statistics - 2021 update. Circulation. 2021;143:e254-e743. https://doi.org/10.1161/CIR.0000000000000950
Pivetta E, Goffi A, Nazerian P, Castagno D, Tozzetti C, Tizzani P, et al.; Study Group on Lung Ultrasound from the Molinette and Careggi Hospitals. Lung ultrasound integrated with clinical assessment for the diagnosis of acute decompensated heart failure in the emergency department: A randomized controlled trial. Eur J Heart Fail. 2019;21:754-766. https://doi.org/10.1002/ejhf.1379
McDonagh TA, Metra M, Adamo M, Gardner RS, Baumbach A, Böhm M, et al. 2021 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: Developed by the Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC). With the special contribution of the Heart Failure Association (HFA) of the ESC. Eur J Heart Fail. 2022;24:4-131. https://doi.org/10.1002/ejhf.2333
Martindale JL, Wakai A, Collins SP, Levy PD, Diercks D, Hiestand BC, et al. Diagnosing acute heart failure in the emergency department: A systematic review and meta-analysis. Acad Emerg Med. 2016;23:223-242. https://doi.org/10.1111/acem.12878
Platz E, Lewis EF, Uno H, Peck J, Pivetta E, Merz AA, et al. Detection and prognostic value of pulmonary congestion by lung ultrasound in ambulatory heart failure patients. Eur Heart J. 2016;37:1244-1251. https://doi.org/10.1093/eurheartj/ehv745
Gargani L, Pang PS, Frassi F, Miglioranza MH, Dini FL, Landi P, et al. Persistent pulmonary congestion before discharge predicts rehospitalization in heart failure: A lung ultrasound study. Cardiovasc Ultrasound. 2015;13:40. https://doi.org/10.1186/s12947-015-0033-4
Russell FM, Ferre R, Ehrman RR, Noble V, Gargani L, Collins SP, et al. What are the minimum requirements to establish proficiency in lung ultrasound training for quantifying B-lines? ESC Heart Fail. 2020;7:2941-2947. https://doi.org/10.1002/ehf2.12907
Herraiz JL, Freijo C, Camacho J, Muñoz M, González R, Alonso-Roca R, et al. Inter-rater variability in the evaluation of lung ultrasound in videos acquired from COVID-19 patients. Appl Sci. 2023;13:1321. https://doi.org/10.3390/app13031321
Baloescu C, Toporek G, Kim S, McNamara K, Liu R, Shaw MM, et al. Automated lung ultrasound B-line assessment using a deep learning algorithm. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67:2312-2320. https://doi.org/10.1109/TUFFC.2020.3002249
Pang PS, Russell FM, Ehrman R, Ferre R, Gargani L, Levy PD, et al. Lung ultrasound-guided emergency department management of acute heart failure (BLUSHED-AHF): A randomized controlled pilot trial. JACC Heart Fail. 2021;9:638-648. https://doi.org/10.1016/j.jchf.2021.05.008
Russell FM, Ehrman RR, Ferre R, Gargani L, Noble V, Rupp J, et al. Design and rationale of the B-lines lung ultrasound guided emergency department management of acute heart failure (BLUSHED-AHF) pilot trial. Heart Lung. 2019;48:186-192. https://doi.org/10.1016/j.hrtlng.2018.10.027
Lucassen RT, Jafari MH, Duggan NM, Jowkar N, Mehrtash A, Fischetti C, et al. Deep learning for detection and localization of B-lines in lung ultrasound. IEEE J Biomed Health Inform. 2023;1-10. http://doi.org/10.1109/JBHI.2023.3282596
Harrison NE, Favot MJ, Gowland L, Lenning J, Henry S, Gupta S, et al. Point-of-care echocardiography of the right heart improves acute heart failure risk stratification for low-risk patients: The REED-AHF prospective study. Acad Emerg Med. 2022;29:1306-1319. https://doi.org/10.1111/acem.14589