Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software

Kavitha C. Selvan; Angad Kalra; Joshua Reicher; Michael Muelly; Ayodeji Adegunsoye

doi:10.14740/jocmr5020

Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software

Kavitha C. Selvan^*, Angad Kalra, Joshua Reicher, Michael Muelly, Ayodeji Adegunsoye

^*Corresponding author for this work

Medicine, Pulmonary Division

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

Background: 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: 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: 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: 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.

Original language	English (US)
Pages (from-to)	423-429
Number of pages	7
Journal	Journal of Clinical Medicine Research
Volume	15
Issue number	8-9
DOIs	https://doi.org/10.14740/jocmr5020
State	Published - 2023

Funding

Dr. Selvan is supported by the National Institutes of Health (NIH)/National Heart, Lung, and Blood (NHLBI) grant T32HL007605. Dr. Adegunsoye is supported by the NIH grant K23HL146942. Foundations: CHEST Foundation, and Pulmonary Fibrosis Foundation. Thanks to Drs. Julia Seaman, PhD and Isabel Allen, PhD for biostatistical analysis, to Scott Gellert for guidance on the clinical study protocol, and to FGCL-3019-049 Trial, PRAISE Trial, Harvard COVID-19 Dataset, the National Institutes of Health (NIH), Medical Imaging and Data Resource Center (MIDRC), National Lung Cancer Screening Trial (NLST), Open Source Imaging Consortium (OSIC), and Babak-Tehran Dataset for data acquisition.

Keywords

Artificial intelligence
Early detection
Interstitial lung disease
Pulmonary fibrosis

ASJC Scopus subject areas

General Medicine

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.14740/jocmr5020

Cite this

@article{14322b48532f4d01a26eaad846e73a06,

title = "Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software",

abstract = "Background: 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{\texttrademark}, developed to improve detection of PF. Methods: ScreenDx-LungFibrosis{\texttrademark} 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: Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis{\texttrademark} 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: ScreenDx-LungFibrosis{\texttrademark} 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.",

keywords = "Artificial intelligence, Early detection, Interstitial lung disease, Pulmonary fibrosis",

author = "Selvan, {Kavitha C.} and Angad Kalra and Joshua Reicher and Michael Muelly and Ayodeji Adegunsoye",

note = "Publisher Copyright: {\textcopyright} The authors | Journal compilation",

year = "2023",

doi = "10.14740/jocmr5020",

language = "English (US)",

volume = "15",

pages = "423--429",

journal = "Journal of Clinical Medicine Research",

issn = "1918-3003",

publisher = "Elmer Press",

number = "8-9",

}

TY - JOUR

T1 - Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software

AU - Selvan, Kavitha C.

AU - Kalra, Angad

AU - Reicher, Joshua

AU - Muelly, Michael

AU - Adegunsoye, Ayodeji

N1 - Publisher Copyright: © The authors | Journal compilation

PY - 2023

Y1 - 2023

N2 - Background: 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: 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: 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: 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.

AB - Background: 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: 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: 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: 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.

KW - Artificial intelligence

KW - Early detection

KW - Interstitial lung disease

KW - Pulmonary fibrosis

UR - http://www.scopus.com/inward/record.url?scp=85174281163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85174281163&partnerID=8YFLogxK

U2 - 10.14740/jocmr5020

DO - 10.14740/jocmr5020

M3 - Article

C2 - 37822853

AN - SCOPUS:85174281163

SN - 1918-3003

VL - 15

SP - 423

EP - 429

JO - Journal of Clinical Medicine Research

JF - Journal of Clinical Medicine Research

IS - 8-9

ER -

Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software

Abstract

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this