Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software.
Artificial intelligence
Early detection
Interstitial lung disease
Pulmonary fibrosis
Journal
Journal of clinical medicine research
ISSN: 1918-3003
Titre abrégé: J Clin Med Res
Pays: Canada
ID NLM: 101538301
Informations de publication
Date de publication:
Sep 2023
Sep 2023
Historique:
received:
30
08
2023
accepted:
25
09
2023
medline:
12
10
2023
pubmed:
12
10
2023
entrez:
12
10
2023
Statut:
ppublish
Résumé
Improvement in recognition and referral of pulmonary fibrosis (PF) is vital to improving patient outcomes within interstitial lung disease. We determined the performance metrics and processing time of an artificial intelligence triage and notification software, ScreenDx-LungFibrosis™, developed to improve detection of PF. ScreenDx-LungFibrosis™ was applied to chest computed tomography (CT) scans from multisource data. Device output (+/- PF) was compared to clinical diagnosis (+/- PF), and diagnostic performance was evaluated. Primary endpoints included device sensitivity and specificity > 80% and processing time < 4.5 min. Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis™ detected PF with a sensitivity and specificity of 91.3% (95% confidence interval (CI): 89.0-93.3%) and 95.1% (95% CI: 94.2-96.0%), respectively. Mean processing time was 27.6 s (95% CI: 26.0 - 29.1 s). ScreenDx-LungFibrosis™ accurately and reliably identified PF with a rapid per-case processing time, underscoring its potential for transformative improvement in PF outcomes when routinely applied to chest CTs.
Sections du résumé
Background
UNASSIGNED
Improvement in recognition and referral of pulmonary fibrosis (PF) is vital to improving patient outcomes within interstitial lung disease. We determined the performance metrics and processing time of an artificial intelligence triage and notification software, ScreenDx-LungFibrosis™, developed to improve detection of PF.
Methods
UNASSIGNED
ScreenDx-LungFibrosis™ was applied to chest computed tomography (CT) scans from multisource data. Device output (+/- PF) was compared to clinical diagnosis (+/- PF), and diagnostic performance was evaluated. Primary endpoints included device sensitivity and specificity > 80% and processing time < 4.5 min.
Results
UNASSIGNED
Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis™ detected PF with a sensitivity and specificity of 91.3% (95% confidence interval (CI): 89.0-93.3%) and 95.1% (95% CI: 94.2-96.0%), respectively. Mean processing time was 27.6 s (95% CI: 26.0 - 29.1 s).
Conclusions
UNASSIGNED
ScreenDx-LungFibrosis™ accurately and reliably identified PF with a rapid per-case processing time, underscoring its potential for transformative improvement in PF outcomes when routinely applied to chest CTs.
Identifiants
pubmed: 37822853
doi: 10.14740/jocmr5020
pmc: PMC10563821
doi:
Types de publication
Journal Article
Langues
eng
Pagination
423-429Subventions
Organisme : NHLBI NIH HHS
ID : K23 HL146942
Pays : United States
Organisme : NHLBI NIH HHS
ID : T32 HL007605
Pays : United States
Informations de copyright
Copyright 2023, Selvan et al.
Déclaration de conflit d'intérêts
Dr. Reicher, Dr. Muelly, and Mr. Scott Gellert have a financial interest in IMVARIA Inc. Dr. Adegunsoye has relationships with Genentech Inc., Inogen Inc., Medscape LLC, PatientMpower, Abbvie, and Boehringer Ingelheim Corp USA.
Références
Phys Med Biol. 2009 Nov 21;54(22):6881-99
pubmed: 19864701
Respir Res. 2017 Mar 7;18(1):45
pubmed: 28264721
Ann Am Thorac Soc. 2019 Mar;16(3):393-396
pubmed: 30620617
Lancet Reg Health Am. 2023 Aug 02;25:100566
pubmed: 37564420
Nat Commun. 2023 Apr 20;14(1):2272
pubmed: 37080956
Invest Radiol. 2015 Apr;50(4):261-7
pubmed: 25551822
Acad Radiol. 2015 May;22(5):626-31
pubmed: 25728361
BMC Pulm Med. 2018 Jan 17;18(1):9
pubmed: 29343236
Lancet Respir Med. 2018 Nov;6(11):837-845
pubmed: 30232049
Am J Respir Crit Care Med. 2022 Oct 1;206(7):883-891
pubmed: 35696341
Sci Rep. 2020 Jan 15;10(1):338
pubmed: 31941918
Acta Biomed. 2020 Aug 27;91(3):e2020062
pubmed: 32921714
Respir Res. 2019 Nov 12;20(1):253
pubmed: 31718645
Eur Respir J. 2016 Nov;48(5):1442-1452
pubmed: 27471206