Digital Otoscopy Videos Versus Composite Images: A Reader Study to Compare the Accuracy of ENT Physicians

Abstract

Objectives/Hypothesis With the increasing emphasis on developing effective telemedicine approaches in Otolaryngology, this study explored whether a single composite image stitched from a digital otoscopy video provides acceptable diagnostic information to make an accurate diagnosis, as compared with that provided by the full video. Study Design Diagnostic survey analysis. Methods Five Ear, Nose, and Throat (ENT) physicians reviewed the same set of 78 digital otoscope eardrum videos from four eardrum conditions: normal, effusion, retraction, and tympanosclerosis, along with the composite images generated by a SelectStitch method that selectively uses video frames with computer‐assisted selection, as well as a Stitch method that incorporates all the video frames. Participants provided a diagnosis for each item along with a rating of diagnostic confidence. Diagnostic accuracy for each pathology of SelectStitch was compared with accuracy when reviewing the entire video clip and when reviewing the Stitch image. Results There were no significant differences in diagnostic accuracy for physicians reviewing SelectStitch images and full video clips, but both provided better diagnostic accuracy than Stitch images. The inter‐reader agreement was moderate. Conclusions Equal to using full video clips, composite images of eardrums generated by SelectStitch provided sufficient information for ENTs to make the correct diagnoses for most pathologies. These findings suggest that use of a composite eardrum image may be sufficient for telemedicine approaches to ear diagnosis, eliminating the need for storage and transmission of large video files, along with future applications for improved documentation in electronic medical record systems, patient/family counseling, and clinical training. Level of Evidence 3 Laryngoscope, 131:E1668–E1676, 2021

Clinician-rated quality of video otoscopy recordings and still images for the asynchronous assessment of middle-ear disease

“…11 Similar to still images, identifying TM retraction was challenging using those composite images. 12 Previous studies have compared the quality and reliability of video otoscopy still images or recordings with the results of different gold standards including conventional onsite otoscopy 1,7,10 or otomicroscopy. 2,3,8,13,14 Another study has compared the diagnostic accuracy and confidence using video otoscopy the enhanced composite images stitched from video otoscopy recordings collected by experienced clinicians to the original recordings.…”

“…2,3,8,13,14 Another study has compared the diagnostic accuracy and confidence using video otoscopy the enhanced composite images stitched from video otoscopy recordings collected by experienced clinicians to the original recordings. 12 However, no study has compared the quality and ability to view the TM using still images to those of video recordings. It is still unknown whether video otoscopy still images or recordings can improve clinician-rated quality of otoscopy for asynchronous telehealth assessments and enable a more accurate diagnosis.…”

Telemedicine and Telementoring in Rhinology, Otology, and Laryngology: A Scoping Review

“… 26 In contrast, usefulness of endoscopic videos taken by health care personnel can be limited. 25 , 118 , 148 , 149 …”

“… 81 , 109 , 118 Most studies demonstrated moderate (κ = 0.41-0.60) to substantial (κ = 0.61-0.80) diagnostic agreement between VE and FTF evaluations. 25 , 82 , 84 , 87 , 88 , 91 , 92 , 114 - 117 , 121 , 124 , 148 - 150 , 160 A major issue is the quality of the physical examination being conducted remotely, which obviously has a lot of limitations. 6 , 8 , 17 , 25 , 28 , 29 , 89 , 96 , 121 , 124 , 156 However, VE has been found to expand health coverage, prevent unnecessary visits, and save travel costs.…”

Shortwave infrared otoscopy for diagnosis of middle ear effusions: a machine-learning-based approach

“…Another machine learning system using OCT found agreement with physician diagnosis in 91.5% of cases 25 . Manual annotations can also be automated with a machine learning frame selection tool 65 .…”