Analysis of Potential for User Errors in Mobile Deployment of Radiology Deep Learning for Cardiac Rhythm Device Detection.
We examine how convolutional neural networks (CNNs) for cardiac rhythm device detection can exhibit failures in performance under suboptimal deployment scenarios and examine how medically adversarial image presentation can further impair neural network performance. We validated the publicly availabl...
| Publicado en: | Journal of Digital Imaging Vol. 34; no. 3; pp. 572 - 581 |
|---|---|
| Autores principales: | , , , , |
| Formato: | diagnostic images pictorial research tables/charts Journal Article |
| Publicado: |
Springer Nature
Jun2021
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=151702157&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 151702157 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Jun2021 vid: 34 iid: 3 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 151702157 149360199 151702157 151702157 10.1007/s10278-021-00443-4 151702157 ppf: 572 ppct: 9 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Analysis of Potential for User Errors in Mobile Deployment of Radiology Deep Learning for Cardiac Rhythm Device Detection. aug: au: Sabottke, Carl Breaux, Marc Lee, Rebecca Foreman, Adam Spieler, Bradley affil: Department of Medical Imaging, University of Arizona College of Medicine, Tucson, AZ, USA sug: subj: Neural Networks (Computer) Deep Learning Mobile Applications Diagnostic Errors Heart Conduction System Human Retrospective Design Record Review ROC Curve Radiography, Thoracic kappa Statistic ab: We examine how convolutional neural networks (CNNs) for cardiac rhythm device detection can exhibit failures in performance under suboptimal deployment scenarios and examine how medically adversarial image presentation can further impair neural network performance. We validated the publicly available Pacemaker-ID web server and mobile app on 43 local hospital emergency department (ED) cases of patients presenting with a cardiac rhythm device on anterior-posterior (AP) chest radiograph and assessed performance using Cohen's kappa coefficient for inter-rater reliability. To illustrate adversarial performance concerns, we then produced example CNN models using the 65,379 patient MIMIC-CXR chest radiograph retrospective database and evaluated performance with area under the receiver operating characteristic (AUROC). In retrospective review of 43 patients with cardiac rhythm devices on AP chest radiographs during our study period (January 1, 2020 to March 1, 2020), 74.4% (32/43) had device manufacturer information readily available within the electronic medical record. A total of 25.6% of patients (11/43) did not have this information documented in the patient chart and could ostensibly benefit from CNN-based identification of device manufacturer. For patients with known device manufacturer, the Pacemaker-ID prediction was accurate in 87.5% of cases (28/32). Mobile app accuracy varied from 62.5 to 93.75% depending on image capture settings and presentation. Cohen's kappa coefficient varied from 0.448 to 0.897 depending on mobile image capture conditions. For our additional analysis of medically adversarial performance failures with a DenseNet121 trained on MIMIC-CXR images, we showed that an AUROC of 0.9807 ± 0.0051 could be achieved on an example testing dataset while masking a 30% false positive rate in identification of cardiac rhythm devices versus clinically distinct entities such as vagal nerve stimulators. Despite the promise of CNN approaches for cardiac rhythm device analysis on chest radiographs, further study is warranted to assess potential for errors driven by user misuse when deploying these models to mobile devices as well as for cases when performance can be impaired by the presence of other support apparatuses. pubtype: Academic Journal doctype: diagnostic images pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|