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

IF 1.6 Q2 MEDICINE, GENERAL & INTERNAL

Journal of clinical medicine research Pub Date : 2023-09-01 Epub Date: 2023-09-30 DOI:10.14740/jocmr5020

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

{"title":"Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software.","authors":"Kavitha C Selvan, Angad Kalra, Joshua Reicher, Michael Muelly, Ayodeji Adegunsoye","doi":"10.14740/jocmr5020","DOIUrl":null,"url":null,"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.","PeriodicalId":94329,"journal":{"name":"Journal of clinical medicine research","volume":"15 8-9","pages":"423-429"},"PeriodicalIF":1.6000,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/7f/92/jocmr-15-423.PMC10563821.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of clinical medicine research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14740/jocmr5020","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/9/30 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}

引用次数: 0

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.

Abstract Image

查看原文本刊更多论文

利用先进的人工智能分类和通知软件的计算机辅助肺纤维化检测。

背景：提高对肺纤维化（PF）的认识和转诊对改善间质性肺病患者的预后至关重要。我们确定了人工智能分诊和通知软件ScreenDx LungFibrosis的性能指标和处理时间™, 方法：ScreenDx LungFibrosis™ 应用于多源数据的胸部计算机断层扫描（CT）扫描。将设备输出（+/-PF）与临床诊断（+/-PF）进行比较，并评估诊断性能。主要终点包括装置灵敏度和特异性>80%，处理时间<4.5分钟。结果：在3018名患者中，PF占22.9%。ScreenDx肺纤维化™ 检测PF的敏感性和特异性分别为91.3%（95%置信区间：89.0-93.3%）和95.1%（95%置信度：94.2-96.0%）。平均处理时间为27.6秒（95%可信区间：26.0-29.1秒）。结论：ScreenDx肺纤维化™ 准确可靠地识别PF，每个病例的处理时间很快，强调了其在常规应用于胸部CT时对PF结果进行变革性改善的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of clinical medicine research

CiteScore

5.10

自引率

0.00%

发文量