A Deep Learning Approach to Predict Conductive Hearing Loss in Patients With Otitis Media With Effusion Using Otoscopic Images

Abstract

IMPORTANCEOtitis media with effusion (OME) is one of the most common causes of acquired conductive hearing loss (CHL). Persistent hearing loss is associated with poor childhood speech and language development and other adverse consequence. However, to obtain accurate and reliable hearing thresholds largely requires a high degree of cooperation from the patients. OBJECTIVE To predict CHL from otoscopic images using deep learning (DL) techniques and a logistic regression model based on tympanic membrane features. DESIGN, SETTING, AND PARTICIPANTSA retrospective diagnostic/prognostic study was conducted using 2790 otoscopic images obtained from multiple centers between January 2015 and November 2020. Participants were aged between 4 and 89 years. Of 1239 participants, there were 209 ears from children and adolescents (aged 4-18 years [16.87%]), 804 ears from adults (aged 18-60 years [64.89%]), and 226 ears from older people (aged >60 years, [18.24%]). Overall, 679 ears (54.8%) were from men. The 2790 otoscopic images were randomly assigned into a training set (2232 [80%]), and validation set (558 [20%]). The DL model was developed to predict an average air-bone gap greater than 10 dB. A logistic regression model was also developed based on otoscopic features. MAIN OUTCOMES AND MEASURESThe performance of the DL model in predicting CHL was measured using the area under the receiver operating curve (AUC), accuracy, and F1 score (a measure of the quality of a classifier, which is the harmonic mean of precision and recall; a higher F1 score means better performance). In addition, these evaluation parameters were compared to results obtained from the logistic regression model and predictions made by three otologists. RESULTSThe performance of the DL model in predicting CHL showed the AUC of 0.74, accuracy of 81%, and F1 score of 0.89. This was better than the results from the logistic regression model (ie, AUC of 0.60, accuracy of 76%, and F1 score of 0.82), and much improved on the performance of the 3 otologists; accuracy of 16%, 30%, 39%, and F1 scores of 0.09, 0.18, and 0.25, respectively. Furthermore, the DL model took 2.5 seconds to predict from 205 otoscopic images, whereas the 3 otologists spent 633 seconds, 645 seconds, and 692 seconds, respectively. CONCLUSIONS AND RELEVANCEThe model in this diagnostic/prognostic study provided greater accuracy in prediction of CHL in ears with OME than those obtained from the logistic regression model and otologists. This indicates great potential for the use of artificial intelligence tools to facilitate CHL evaluation when CHL is unable to be measured.

Advances in Image‐Based Artificial Intelligence in Otorhinolaryngology–Head and Neck Surgery: A Systematic Review

“…Several studies have directly compared AI against human physicians 24,26,31,32,36,42,52,71 . Some showed the superiority of AI over nonspecialist physicians 26 or otolaryngologists 71 in narrowly defined fields.…”

“…Some studies used a single AI algorithm, while others combined 2 or more algorithms to solve clinical problems 25,38,63,74,75,79 . The data sources were used to train, validate, and test AI models, including single‐ and multiple‐center databases, 52,81 and public databases 25,85 …”

“…Recent studies have applied AI to otological imaging in various clinical contexts (Supplemental File 3, available online). These studies combined AI with otoscopy, [22][23][24][25][26]31,32,38,48,52,57,68,[74][75][76]79,81,84,85,93,95 computed tomography (CT), 30,36,41,42,50,62,63,70,71,88 and magnetic resonance imaging (MRI). 43,73,78 Most studies have focused on the image-based otoscopic diagnosis and automated segmentation of temporal bone CT for classifying normal and abnormal mastoid air cells.…”

“…73,78 Several studies have directly compared AI against human physicians. 24,26,31,32,36,42,52,71 Some showed the superiority of AI over nonspecialist physicians 26 or otolaryngologists 71 in narrowly defined fields. Some studies used a single AI algorithm, while others combined 2 or more algorithms to solve clinical problems.…”

“…Some studies used a single AI algorithm, while others combined 2 or more algorithms to solve clinical problems. 25,38,63,74,75,79 The data sources were used to train, validate, and test AI models, including single-and multiple-center databases, 52,81 and public databases. 25,85 Viscaino et al 26 used 22,000 otoscopic images to train a model that classifies 4 middle and external ear conditions: normal, chronic otitis media, otitis media with effusion, and earwax plugs.…”