Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
Establishment of a Suitability Prediction Model of N95 Respirator Based on Facial Images
17 Pages Posted: 28 Aug 2024
More...Abstract
Background: Currently, there is no rapid approach for fit test of N95 respirators.
Methods: Facial images and fitness factors 5 N95 respirators were gathered from 299 medical staffs in 10 hospitals in Beijing. Through matching training of facial image and fit factors, a prediction model has been established, enabling rapid recommendation of N95 respirators meeting the fitness standard via facial image recognition. Face geometry measurement was based on 3D face modelling, and the American TSI-8038 PortaCount Pro+ was used to conduct quantitative fit test. Multiple linear regression analysis was employed to identify facial dimensional features that significantly influenced the fit of N95 respirators.
Findings: Passing rate of the five N95 respirator fit tests was not uniform (P < 0.0001). Face width (Standardized Estimate = 0.13747) and nose length (Standardized Estimate = 0.20332) have positive influence on fit factor of 3M9132; face width (Standardized Estimate = -0.13977) has negative influence on that of NTPN95N, while chin length (Standardized Estimate = 0.25061) positive; face width (Standardized Estimate = 0.1069) and nose length (Standardized Estimate = 0.1722) were positive to fit factor of WN-95N folding; and face width (Standardized Estimate = 0.10605) and nose length (Standardized Estimate = 0.14938) were positive to that of WN-95N arch. The prediction accuracy of the respirator fitness prediction model based on facial image was as high as 96.06%.
Interpretation: It is practicable to employ the computer facial image recognition technology for rapid recommendation ofN95 respirators to medical staffs.
Funding: This study was funded by the Beijing Health Commission - Capital Health Development Research Project (No.: 2021-1G-2182).
Declaration of Interest: The authors declare no conflicts of interest with commercial products regarding the devices and materials used in this study.
Ethical Approval: This study was approved by the Academic Committee of Beijing You'an Hospital, Capital Medical University (approval number: 2021-069) and by the Ethics Committee of Beijing You'an Hospital, Capital Medical University (ethics committee archiving number: LL-2021-135-K).
Keywords: N95, Facial dimensions, Infection control, Respiratory protection
Suggested Citation: Suggested Citation