Assessing diagnostic accuracy and tympanocentesis skills in the management of otitis media

AI Model Versus Clinician Otoscopy in the Operative Setting for Otitis Media Diagnosis

Prior work has demonstrated improved accuracy in otitis media diagnosis based on otoscopy using artificial intelligence (AI)-based approaches compared to clinician evaluation. However, this difference in accuracy has not been shown in a setting resembling the point-of-care. In this study, we compare the diagnostic accuracy of a machine-learning model to that of pediatricians using standard handheld otoscopes. We find that the model is more accurate than clinicians (90.6% vs 59.4%, P = .01). This is a step towards validation of AI-based diagnosis under more real-world conditions. With further validation, for example on different patient populations and in deployment, this technology could be a useful addition to the clinician's toolbox in accurately diagnosing otitis media.

"Seeing inside out": revealing the effectiveness of otoscopy training in virtual reality enhanced practical exams - a randomized controlled trial

BACKGROUND

The study aimed to assess the impact of different training modalities on otoscopy performance during a practical exam using a high-fidelity simulator and to determine if objective evaluation of otoscopy is feasible using a simulator that records insertion depth and tympanic membrane coverage.

METHODS

Participants were assigned to one of four groups: control and three intervention groups with varying training approaches. Participants received otoscopy training and then were assessed through a practical exam on a high-fidelity simulator that uses virtual reality to visualize the ear canal and middle ear. Performance was evaluated using a modified Objective Structured Assessment of Technical Skills checklist and Integrated Procedural Performance Instrument checklist. Insertion depth, tympanic membrane coverage, and correct diagnosis were recorded. Data were tested for normal distribution using the Shapiro-Wilk test. One-way ANOVA and, for non-normally distributed data, Kruskal-Wallis test combined with Dunn's test for multiple comparisons were used. Interrater reliability was assessed using Cohen's κ and Intraclass correlation coefficient.

RESULTS

All groups rated their training sessions positively. Performance on the OSATS checklist was similar among groups. IPPI scores indicated comparable patient handling skills. The feedback group examined larger tympanic membrane areas and had higher rates of correct diagnosis. The correct insertion depth was rarely achieved by all participants. Interrater reliability for OSATS was strong. IPPI reliability showed good correlation.

CONCLUSION

Regardless of training modality, participants perceived learning improvement and skill acquisition. Feedback improved examination performance, indicating simulator-guided training enhances skills. High-fidelity simulator usage in exams provides an objective assessment of performance.

Development and Validation of an Automated Classifier to Diagnose Acute Otitis Media in Children

Importance

Acute otitis media (AOM) is a frequently diagnosed illness in children, yet the accuracy of diagnosis has been consistently low. Multiple neural networks have been developed to recognize the presence of AOM with limited clinical application.

Objective

To develop and internally validate an artificial intelligence decision-support tool to interpret videos of the tympanic membrane and enhance accuracy in the diagnosis of AOM.

Design, Setting, and Participants

This diagnostic study analyzed otoscopic videos of the tympanic membrane captured using a smartphone during outpatient clinic visits at 2 sites in Pennsylvania between 2018 and 2023. Eligible participants included children who presented for sick visits or wellness visits.

Exposure

Otoscopic examination.

Main Outcomes and Measures

Using the otoscopic videos that were annotated by validated otoscopists, a deep residual-recurrent neural network was trained to predict both features of the tympanic membrane and the diagnosis of AOM vs no AOM. The accuracy of this network was compared with a second network trained using a decision tree approach. A noise quality filter was also trained to prompt users that the video segment acquired may not be adequate for diagnostic purposes.

Results

Using 1151 videos from 635 children (majority younger than 3 years of age), the deep residual-recurrent neural network had almost identical diagnostic accuracy as the decision tree network. The finalized deep residual-recurrent neural network algorithm classified tympanic membrane videos into AOM vs no AOM categories with a sensitivity of 93.8% (95% CI, 92.6%-95.0%) and specificity of 93.5% (95% CI, 92.8%-94.3%) and the decision tree model had a sensitivity of 93.7% (95% CI, 92.4%-94.9%) and specificity of 93.3% (92.5%-94.1%). Of the tympanic membrane features outputted, bulging of the TM most closely aligned with the predicted diagnosis; bulging was present in 230 of 230 cases (100%) in which the diagnosis was predicted to be AOM in the test set.

Conclusions and Relevance

These findings suggest that given its high accuracy, the algorithm and medical-grade application that facilitates image acquisition and quality filtering could reasonably be used in primary care or acute care settings to aid with automated diagnosis of AOM and decisions regarding treatment.

Insight into Automatic Image Diagnosis of Ear Conditions Based on Optimized Deep Learning Approach

Examining otoscopic images for ear diseases is necessary when the clinical diagnosis of ear diseases extracted from the knowledge of otolaryngologists is limited. Improved diagnosis approaches based on otoscopic image processing are urgently needed. Recently, convolutional neural networks (CNNs) have been carried out for medical diagnosis to obtain higher accuracy than standard machine learning algorithms and specialists' expertise. Therefore, the proposed approach involves using the Bayesian hyperparameter optimization with the CNN architecture for automatic diagnosis of ear imagery database including four classes: normal, myringosclerosis, earwax plug, and chronic otitis media (COM). The suggested approach was trained using 616 otoscopic images, and the performance of this approach was assessed using 264 testing images. In this paper, the performance of ear disease classification was compared in terms of accuracy, sensitivity, specificity, and positive predictive value (PPV). The results produced a classification accuracy of 98.10%, a sensitivity of 98.11%, a specificity of 99.36%, and a PPV of 98.10%. Finally, the suggested approach demonstrates how to locate optimal CNN hyperparameters for accurate diagnosis of ear diseases while taking time into account. As a result, the usefulness and dependability of the suggested approach will lead to the establishment of an automated tool for better categorization and prediction of different ear diseases.

Deep Learning Techniques and Imaging in Otorhinolaryngology-A State-of-the-Art Review

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology.

Reliability of nasopharyngeal PCR for the detection of otopathogens in children with uncomplicated acute otitis media compared to culture

Otopathogens in acute otitis media (AOM) have implications for care because the likelihood of resolution without antibiotics and optimal antibiotic agent varies by microorganism. We aimed to determine the sensitivity, specificity, positive predictive value, and negative predictive value of nasopharyngeal (NP) qualitative polymerase chain reaction (PCR) for common bacterial otopathogens in children with AOM compared to NP culture. NP flocked swabs collected from enrolled children aged 6 to 35 months with uncomplicated AOM in Denver, CO were tested by culture and multiplex PCR. The sensitivity and negative predictive value of PCR using culture as a reference were high (H. influenzae 93.3%, 98.0%; S. pneumoniae 94.2%, 95.1%; M. catarrhalis 92.3%, 86.4%); whereas the specificity and positive predictive value were lower and varied by organism (54.2%-84.1%, 55.1%-69.2%, respectively). PCR detected 1.5 times more organisms than culture. NP PCR has a high predictive value for excluding otopathogens compared to culture and warrants exploration as a diagnostic tool.

Efficacy of Pneumococcal Vaccine on Otitis Media: A Systematic Review and Meta-Analysis

OBJECTIVE

To assess the effect of the pneumococcal vaccine (PCV) toward the surgical management and complications of otitis media.

DATA SOURCES

MEDLINE, EMBASE, PubMed, Scopus, and clinicaltrial.gov.

REVIEW METHODS

A systematic search was performed using a combination of keywords and standardized terms about PCV and surgical management or complications of otitis media. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, studies were screened by 3 independent reviewers. Risk of bias assessment, followed by meta-analysis in only randomized-controlled trials was conducted. Vaccine efficacy (VE) and 95% confidence interval (CI) were reported.

RESULTS

Of the 2649 abstracts reviewed, 27 studies were included in the qualitative analysis and were categorized into 6 outcomes: tympanostomy tube insertion, otitis media with effusion (OME), mastoiditis, spontaneous tympanic membrane (TM) perforation, recurrent acute otitis media (AOM), and severe AOM. Fifteen studies were included in the meta-analysis to evaluate the rate of tympanostomy tube insertion, OME, and recurrent AOM. PCV was significantly more effective in lowering the rate of tympanostomy tube insertion (VE, 22.2%; 95% CI, 14.6-29.8) and recurrent AOM (VE, 10.06%; 95% CI, 7.46-12.65) when compared with the control group, with no significant difference in reducing the incidence of OME. The qualitative analysis revealed that PCV had efficacy in preventing severe AOM and spontaneous TM perforation but the effect on mastoiditis remained unclear.

CONCLUSION

The PCV was effective in reducing the rate of tympanostomy tube insertion and the incidence of recurrent AOM with a nonsignificant effect in preventing OME in children.

Image-Based Artificial Intelligence Technology for Diagnosing Middle Ear Diseases: A Systematic Review

Otolaryngological diagnoses, such as otitis media, are traditionally performed using endoscopy, wherein diagnostic accuracy can be subjective and vary among clinicians. The integration of objective tools, like artificial intelligence (AI), could potentially improve the diagnostic process by minimizing the influence of subjective biases and variability. We systematically reviewed the AI techniques using medical imaging in otolaryngology. Relevant studies related to AI-assisted otitis media diagnosis were extracted from five databases: Google Scholar, PubMed, Medline, Embase, and IEEE Xplore, without date restrictions. Publications that did not relate to AI and otitis media diagnosis or did not utilize medical imaging were excluded. Of the 32identified studies, 26 used tympanic membrane images for classification, achieving an average diagnosis accuracy of 86% (range: 48.7-99.16%). Another three studies employed both segmentation and classification techniques, reporting an average diagnosis accuracy of 90.8% (range: 88.06-93.9%). These findings suggest that AI technologies hold promise for improving otitis media diagnosis, offering benefits for telemedicine and primary care settings due to their high diagnostic accuracy. However, to ensure patient safety and optimal outcomes, further improvements in diagnostic performance are necessary.

Augmenting Community Diagnosis of Safe Ear Disease Through Tele-Myringoscopy with Borescope Using AIML Tecniques

This study utilized AIML (artificial intelligence & machine learning) techniques to analyze 115 images of central perforation of tympanic membrane obtained from Telemyringoscopy through Borescope in order to establish a facilitation-model for the community ear diagnosis. The Modified VGG19 with batch normalization revealed the highest training accuracy of 85 as compared to other CNN techniques. The training accuracy started to saturate around mid-70% and the Test accuracy was around 50%. Although AIML did not reveal a high predictive value, its potential based on our observations cannot be underestimated considering many limitations (sample size, image-quality, associated pathologies, illumination-factor) in this study. Such limitations if resolved may revolutionize community ear care through a better cost effective tele-myringoscopy with innovations in AIML/ telemedicine.

Diagnosis, Treatment, and Management of Otitis Media with Artificial Intelligence

A common infectious disease, otitis media (OM) has a low rate of early diagnosis, which significantly increases the difficulty of treating the disease and the likelihood of serious complications developing including hearing loss, speech impairment, and even intracranial infection. Several areas of healthcare have shown great promise in the application of artificial intelligence (AI) systems, such as the accurate detection of diseases, the automated interpretation of images, and the prediction of patient outcomes. Several articles have reported some machine learning (ML) algorithms such as ResNet, InceptionV3 and Unet, were applied to the diagnosis of OM successfully. The use of these techniques in the OM is still in its infancy, but their potential is enormous. We present in this review important concepts related to ML and AI, describe how these technologies are currently being applied to diagnosing, treating, and managing OM, and discuss the challenges associated with developing AI-assisted OM technologies in the future.

New insights into the treatment of acute otitis media

INTRODUCTION

Acute otitis media (AOM) affects most (80%) children by 5 years of age and is the most common reason children are prescribed antibiotics. The epidemiology of AOM has changed considerably since the widespread use of pneumococcal conjugate vaccines, which has broad-reaching implications for management.

AREAS COVERED

In this narrative review, we cover the epidemiology of AOM, best practices for diagnosis and management, new diagnostic technology, effective stewardship interventions, and future directions of the field. Literature review was performed using PubMed and ClinicalTrials.gov.

EXPERT OPINION

Inaccurate diagnoses, unnecessary antibiotic use, and increasing antimicrobial resistance remain major challenges in AOM management. Fortunately, effective tools and interventions to improve diagnostic accuracy, de-implement unnecessary antibiotic use, and individualize care are on the horizon. Successful scaling of these tools and interventions will be critical to improving overall care for children.

A deep learning approach to the diagnosis of atelectasis and attic retraction pocket in otitis media with effusion using otoscopic images

BACKGROUND

This study aimed to develop and validate a deep learning (DL) model to identify atelectasis and attic retraction pocket in cases of otitis media with effusion (OME) using multi-center otoscopic images.

METHOD

A total of 6393 OME otoscopic images from three centers were used to develop and validate a DL model for detecting atelectasis and attic retraction pocket. A threefold random cross-validation procedure was adopted to divide the dataset into training validation sets on a patient level. A team of otologists was assigned to diagnose and characterize atelectasis and attic retraction pocket in otoscopic images. Receiver operating characteristic (ROC) curves, including area under the ROC curve (AUC), accuracy, sensitivity, and specificity were used to assess the performance of the DL model. Class Activation Mapping (CAM) illustrated the discriminative regions in the otoscopic images.

RESULTS

Among all OME otoscopic images, 3564 (55.74%) were identified with attic retraction pocket, and 2460 (38.48%) with atelectasis. The diagnostic DL model of attic retraction pocket and atelectasis achieved a threefold cross-validation accuracy of 89% and 79%, AUC of 0.89 and 0.87, a sensitivity of 0.93 and 0.71, and a specificity of 0.62 and 0.84, respectively. Larger and deeper cases of atelectasis and attic retraction pocket showed greater weight, based on the red color depicted in the heat map of CAM.

CONCLUSION

The DL algorithm could be employed to identify atelectasis and attic retraction pocket in otoscopic images of OME, and as a tool to assist in the accurate diagnosis of OME.

Deep Learning Techniques for Ear Diseases Based on Segmentation of the Normal Tympanic Membrane

OBJECTIVES

Otitis media is a common infection worldwide. Owing to the limited number of ear specialists and rapid development of telemedicine, several trials have been conducted to develop novel diagnostic strategies to improve the diagnostic accuracy and screening of patients with otologic diseases based on abnormal otoscopic findings. Although these strategies have demonstrated high diagnostic accuracy for the tympanic membrane (TM), the insufficient explainability of these techniques limits their deployment in clinical practice.

METHODS

We used a deep convolutional neural network (CNN) model based on the segmentation of a normal TM into five substructures (malleus, umbo, cone of light, pars flaccida, and annulus) to identify abnormalities in otoscopic ear images. The mask R-CNN algorithm learned the labeled images. Subsequently, we evaluated the diagnostic performance of combinations of the five substructures using a three-layer fully connected neural network to determine whether ear disease was present.

RESULTS

We obtained the receiver operating characteristic (ROC) curve of the optimal conditions for the presence or absence of eardrum diseases according to each substructure separately or combinations of substructures. The highest area under the curve (0.911) was found for a combination of the malleus, cone of light, and umbo, compared with the corresponding areas under the curve of 0.737-0.873 for each substructure. Thus, an algorithm using these five important normal anatomical structures could prove to be explainable and effective in screening abnormal TMs.

CONCLUSION

This automated algorithm can improve diagnostic accuracy by discriminating between normal and abnormal TMs and can facilitate appropriate and timely referral consultations to improve patients' quality of life in the context of primary care.

Use of artificial intelligence for the diagnosis of cholesteatoma

Objectives

Accurate diagnosis of cholesteatomas is crucial. However, cholesteatomas can easily be missed in routine otoscopic exams. Convolutional neural networks (CNNs) have performed well in medical image classification, so we evaluated their use for detecting cholesteatomas in otoscopic images.

Study Design

Design and evaluation of artificial intelligence driven workflow for cholesteatoma diagnosis.

Methods

Otoscopic images collected from the faculty practice of the senior author were deidentified and labeled by the senior author as cholesteatoma, abnormal non-cholesteatoma, or normal. An image classification workflow was developed to automatically differentiate cholesteatomas from other possible tympanic membrane appearances. Eight pretrained CNNs were trained on our otoscopic images, then tested on a withheld subset of images to evaluate their final performance. CNN intermediate activations were also extracted to visualize important image features.

Results

A total of 834 otoscopic images were collected, further categorized into 197 cholesteatoma, 457 abnormal non-cholesteatoma, and 180 normal. Final trained CNNs demonstrated strong performance, achieving accuracies of 83.8%-98.5% for differentiating cholesteatoma from normal, 75.6%-90.1% for differentiating cholesteatoma from abnormal non-cholesteatoma, and 87.0%-90.4% for differentiating cholesteatoma from non-cholesteatoma (abnormal non-cholesteatoma + normal). DenseNet201 (100% sensitivity, 97.1% specificity), NASNetLarge (100% sensitivity, 88.2% specificity), and MobileNetV2 (94.1% sensitivity, 100% specificity) were among the best performing CNNs in distinguishing cholesteatoma versus normal. Visualization of intermediate activations showed robust detection of relevant image features by the CNNs.

Conclusion

While further refinement and more training images are needed to improve performance, artificial intelligence-driven analysis of otoscopic images shows great promise as a diagnostic tool for detecting cholesteatomas.

Level of Evidence

3.

Evaluation of the Impact of Optical Coherence Tomography on Pediatrician Otologic Examination Judgment

Accurate diagnosis of otitis media is imperative to judicious antibiotic prescription. Visualization of the tympanic membrane and accurate identification of middle ear effusion with standard otoscopy is inherently challenging in pediatrics, especially in the youngest children who are most at risk for otitis media. With the average diagnostic accuracy among primary care physicians of 50% and accurate identification of normal tympanic membrane versus acute otitis media versus otitis media with effusion ranging from 30% to 84% among pediatricians, there is great opportunity for diagnostic improvement and decreasing unnecessary antibiotic use. In a 96-pediatrician-blinded otoscopy diagnosis quiz, addition of optical coherence tomography, a novel depth-imaging technology, resulted in a 32% improvement in fluid identification, and 21% increase in diagnostic accuracy. This study suggests that the clinical use of this technology promises to improve diagnostic accuracy and antibiotic stewardship in pediatrics.

Feasibility of the Machine Learning Network to Diagnose Tympanic Membrane Lesions without Coding Experience

A machine learning platform operated without coding knowledge (Teachable machine^®) has been introduced. The aims of the present study were to assess the performance of the Teachable machine^® for diagnosing tympanic membrane lesions. A total of 3024 tympanic membrane images were used to train and validate the diagnostic performance of the network. Tympanic membrane images were labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), and cholesteatoma. According to the complexity of the categorization, Level I refers to normal versus abnormal tympanic membrane; Level II was defined as normal, OME, or COM + cholesteatoma; and Level III distinguishes between all four pathologies. In addition, eighty representative test images were used to assess the performance. Teachable machine^® automatically creates a classification network and presents diagnostic performance when images are uploaded. The mean accuracy of the Teachable machine^® for classifying tympanic membranes as normal or abnormal (Level I) was 90.1%. For Level II, the mean accuracy was 89.0% and for Level III it was 86.2%. The overall accuracy of the classification of the 80 representative tympanic membrane images was 78.75%, and the hit rates for normal, OME, COM, and cholesteatoma were 95.0%, 70.0%, 90.0%, and 60.0%, respectively. Teachable machine^® could successfully generate the diagnostic network for classifying tympanic membrane.

Automated multi-class classification for prediction of tympanic membrane changes with deep learning models

BACKGROUNDS AND OBJECTIVE

Evaluating the tympanic membrane (TM) using an otoendoscope is the first and most important step in various clinical fields. Unfortunately, most lesions of TM have more than one diagnostic name. Therefore, we built a database of otoendoscopic images with multiple diseases and investigated the impact of concurrent diseases on the classification performance of deep learning networks.

STUDY DESIGN

This retrospective study investigated the impact of concurrent diseases in the tympanic membrane on diagnostic performance using multi-class classification. A customized architecture of EfficientNet-B4 was introduced to predict the primary class (otitis media with effusion (OME), chronic otitis media (COM), and 'None' without OME and COM) and secondary classes (attic cholesteatoma, myringitis, otomycosis, and ventilating tube).

RESULTS

Deep-learning classifications accurately predicted the primary class with dice similarity coefficient (DSC) of 95.19%, while misidentification between COM and OME rarely occurred. Among the secondary classes, the diagnosis of attic cholesteatoma and myringitis achieved a DSC of 88.37% and 88.28%, respectively. Although concurrent diseases hampered the prediction performance, there was only a 0.44% probability of inaccurately predicting two or more secondary classes (29/6,630). The inference time per image was 2.594 ms on average.

CONCLUSION

Deep-learning classification can be used to support clinical decision-making by accurately and reproducibly predicting tympanic membrane changes in real time, even in the presence of multiple concurrent diseases.

"Human vs Machine" Validation of a Deep Learning Algorithm for Pediatric Middle Ear Infection Diagnosis

OBJECTIVE

We compared the diagnostic performance of human clinicians with that of a neural network algorithm developed using a library of tympanic membrane images derived from children taken to the operating room with the intent of performing myringotomy and possible tube placement for recurrent acute otitis media (AOM) or otitis media with effusion (OME).

STUDY DESIGN

Retrospective cohort study.

SETTING

Tertiary academic medical center from 2018 to 2021.

METHODS

A training set of 639 images of tympanic membranes representing normal, OME, and AOM was used to train a neural network as well as a proprietary commercial image classifier from Google. Model diagnostic prediction performance in differentiating normal vs nonpurulent vs purulent effusion was scored based on classification accuracy. A web-based survey was developed to test human clinicians' diagnostic accuracy on a novel image set, and this was compared head to head against our model.

RESULTS

Our model achieved a mean prediction accuracy of 80.8% (95% CI, 77.0%-84.6%). The Google model achieved a prediction accuracy of 85.4%. In a validation survey of 39 clinicians analyzing a sample of 22 endoscopic ear images, the average diagnostic accuracy was 65.0%. On the same data set, our model achieved an accuracy of 95.5%.

CONCLUSION

Our model outperformed certain groups of human clinicians in assessing images of tympanic membranes for effusions in children. Reduced diagnostic error rates using machine learning models may have implications in reducing rates of misdiagnosis, potentially leading to fewer missed diagnoses, unnecessary antibiotic prescriptions, and surgical procedures.

Assessment of Pediatric Residents' Comfort Level With CellScope Oto to Examine Pediatric Ear Exams

Examining a child's tympanic membrane (TM) is challenging, but crucial for proper management of acute otitis media (AOM). CellScope Oto (CSO) is an attachment that turns a smartphone into an otoscope. We aimed to assess pediatric resident comfort level with ear exams using CSO to see whether comfort level and accuracy of diagnosis of AOM improved. A pre-post study of pediatric residents in a freestanding Pediatric Emergency Department was conducted to assess their comfort level of traditional otoscope and CSO via a Likert scale. Ear exams were recorded and rated by 2 faculty for accuracy of AOM diagnosis. A total of 18 pediatric residents participated, and 308 exams were collected, with 2% diagnosed as AOM. The median change in comfort level increased by +1.0 for interns and third years but remained unchanged for second years. There was substantial agreement by faculty raters of video ear exams. Overall, comfort level increased with accuracy of diagnosis of AOM.

A Machine Learning Approach to Screen for Otitis Media Using Digital Otoscope Images Labelled by an Expert Panel

Background: Otitis media includes several common inflammatory conditions of the middle ear that can have severe complications if left untreated. Correctly identifying otitis media can be difficult and a screening system supported by machine learning would be valuable for this prevalent disease. This study investigated the performance of a convolutional neural network in screening for otitis media using digital otoscopic images labelled by an expert panel. Methods: Five experienced otologists diagnosed 347 tympanic membrane images captured with a digital otoscope. Images with a majority expert diagnosis (n = 273) were categorized into three screening groups Normal, Pathological and Wax, and the same images were used for training and testing of the convolutional neural network. Expert panel diagnoses were compared to the convolutional neural network classification. Different approaches to the convolutional neural network were tested to identify the best performing model. Results: Overall accuracy of the convolutional neural network was above 0.9 in all except one approach. Sensitivity to finding ears with wax or pathology was above 93% in all cases and specificity was 100%. Adding more images to train the convolutional neural network had no positive impact on the results. Modifications such as normalization of datasets and image augmentation enhanced the performance in some instances. Conclusions: A machine learning approach could be used on digital otoscopic images to accurately screen for otitis media.

Classification of Ear Imagery Database using Bayesian Optimization based on CNN-LSTM Architecture

The external and middle ear conditions are diagnosed using a digital otoscope. The clinical diagnosis of ear conditions is suffered from restricted accuracy due to the increased dependency on otolaryngologist expertise, patient complaint, blurring of the otoscopic images, and complexity of lesions definition. There is a high requirement for improved diagnosis algorithms based on otoscopic image processing. This paper presented an ear diagnosis approach based on a convolutional neural network (CNN) as feature extraction and long short-term memory (LSTM) as a classifier algorithm. However, the suggested LSTM model accuracy may be decreased by the omission of a hyperparameter tuning process. Therefore, Bayesian optimization is used for selecting the hyperparameters to improve the results of the LSTM network to obtain a good classification. This study is based on an ear imagery database that consists of four categories: normal, myringosclerosis, earwax plug, and chronic otitis media (COM). This study used 880 otoscopic images divided into 792 training images and 88 testing images to evaluate the approach performance. In this paper, the evaluation metrics of ear condition classification are based on a percentage of accuracy, sensitivity, specificity, and positive predictive value (PPV). The findings yielded a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a PPV of 100% for the testing database. Finally, the proposed approach shows how to find the best hyperparameters concerning the Bayesian optimization for reliable diagnosis of ear conditions under the consideration of LSTM architecture. This approach demonstrates that CNN-LSTM has higher performance and lower training time than CNN, which has not been used in previous studies for classifying ear diseases. Consequently, the usefulness and reliability of the proposed approach will create an automatic tool for improving the classification and prediction of various ear pathologies.

A deep learning approach for detecting otitis media from wideband tympanometry measurements

OBJECTIVE

In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on wideband tympanometry measurements.

METHODS

We develop a convolutional neural network for classification of otitis media based on the analysis of the wideband tympanogram. Saliency maps are computed to gain insight into the decision process of the convolutional neural network. Finally, we attempt to distinguish between otitis media with effusion and acute otitis media, a clinical subclassification important for the choice of treatment.

RESULTS

The approach shows high performance on the overall otitis media detection with an accuracy of 92.6%. However, the approach is not able to distinguish between specific types of otitis media.

CONCLUSION

Out approach can detect otitis media with high accuracy and the wideband tympanogram holds more diagnostic information than the commonly used techniques wideband absorbance measurements and simple tympanograms.

SIGNIFICANCE

This study shows how advanced deep learning methods enable automatic diagnosis of otitis media based on wideband tympanometry measurements, which could become a valuable diagnostic tool.

Pediatric Otoscopy Video Screening With Shift Contrastive Anomaly Detection

Ear related concerns and symptoms represent the leading indication for seeking pediatric healthcare attention. Despite the high incidence of such encounters, the diagnostic process of commonly encountered diseases of the middle and external presents a significant challenge. Much of this challenge stems from the lack of cost effective diagnostic testing, which necessitates the presence or absence of ear pathology to be determined clinically. Research has, however, demonstrated considerable variation among clinicians in their ability to accurately diagnose and consequently manage ear pathology. With recent advances in computer vision and machine learning, there is an increasing interest in helping clinicians to accurately diagnose middle and external ear pathology with computer-aided systems. It has been shown that AI has the capacity to analyze a single clinical image captured during the examination of the ear canal and eardrum from which it can determine the likelihood of a pathognomonic pattern for a specific diagnosis being present. The capture of such an image can, however, be challenging especially to inexperienced clinicians. To help mitigate this technical challenge, we have developed and tested a method using video sequences. The videos were collected using a commercially available otoscope smartphone attachment in an urban, tertiary-care pediatric emergency department. We present a two stage method that first, identifies valid frames by detecting and extracting ear drum patches from the video sequence, and second, performs the proposed shift contrastive anomaly detection (SCAD) to flag the otoscopy video sequences as normal or abnormal. Our method achieves an AUROC of 88.0% on the patient level and also outperforms the average of a group of 25 clinicians in a comparative study, which is the largest of such published to date. We conclude that the presented method achieves a promising first step toward the automated analysis of otoscopy video.

Inter-rater reliability of the diagnosis of otitis media based on otoscopic images and wideband tympanometry measurements

OBJECTIVES

This study aims to investigate the inter-rater reliability and agreement of the diagnosis of otitis media with effusion, acute otitis media, and no effusion cases based on an otoscopy image and in some cases an additional wideband tympanometry measurement of the patient.

METHODS

1409 cases were examined and diagnosed by an otolaryngologist in the clinic, and otoscopy examination and wideband tympanometry (WBT) measurement were conducted. Afterwards, four otolaryngologists (Ear, Nose, and Throat doctors, ENTs), who did not perform the acute examination of the patients, evaluated the otoscopy images and WBT measurements results for diagnosis (acute otitis media, otitis media with effusion, or no effusion). They also specified their diagnostic certainty for each case, and reported whether they used the image, wideband tympanometry, or both, for diagnosis.

RESULTS

All four ENTs agreed on the diagnosis in 57% of the cases, with a pairwise agreement of 74%, and a Light's Kappa of 0.58. There are, however, large differences in agreement and certainty between the three diagnoses. Acute otitis media yields the highest agreement (77% between all four ENTs) and certainty (0.90), while no effusion shows much lower agreement and certainty (34% and 0.58, respectively). There is a positive correlation between certainty and agreement between the ENTs across all cases, and both certainty and agreement increase for cases where a WBT measurement is shown in addition to the otoscopy image.

CONCLUSIONS

The inter-rater reliability between four ENTs was high when diagnosing acute otitis media and lower when diagnosing otitis media with effusion. However, WBT can add valuable information to get closer to the ground-truth diagnosis without myringotomy. Furthermore, the diagnostic certainty increases when the WBT is examined together with the otoscopy image.

Multimodal Handheld Probe for Characterizing Otitis Media - Integrating Raman Spectroscopy and Optical Coherence Tomography

Otitis media (OM) is a common disease of the middle ear, affecting 80% of children before the age of three. The otoscope, a simple illuminated magnifier, is the standard clinical diagnostic tool to observe the middle ear. However, it has limited contrast to detect signs of infection, such as clearly identifying and characterizing middle ear fluid or biofilms that accumulate within the middle ear. Likewise, invasive sampling of every subject is not clinically indicated nor practical. Thus, collecting accurate noninvasive diagnostic factors is vital for clinicians to deliver a precise diagnosis and effective treatment regimen. To address this need, a combined benchtop Raman spectroscopy (RS) and optical coherence tomography (OCT) system was developed. Together, RS-OCT can non-invasively interrogate the structural and biochemical signatures of the middle ear under normal and infected conditions.In this paper, in vivo RS scans from pediatric clinical human subjects presenting with OM were evaluated in parallel with RS-OCT data of physiologically relevant in vitro ear models. Component-level characterization of a healthy tympanic membrane and malleus bone, as well as OM-related middle ear fluid, identified the optimal position within the ear for RS-OCT data collection. To address the design challenges in developing a system specific to clinical use, a prototype non-contact multimodal handheld probe was built and successfully tested in vitro. Design criteria have been developed to successfully address imaging constraints imposed by physiological characteristics of the ear and optical safety limits. Here, we present the pathway for translation of RS-OCT for non-invasive detection of OM.

New Approaches and Technologies to Improve Accuracy of Acute Otitis Media Diagnosis

Several studies have shown that in recent years incidence of acute otitis media (AOM) has declined worldwide. However, related medical, social, and economic problems for patients, their families, and society remain very high. Better knowledge of potential risk factors for AOM development and more effective preventive interventions, particularly in AOM-prone children, can further reduce disease incidence. However, a more accurate AOM diagnosis seems essential to achieve this goal. Diagnostic uncertainty is common, and to avoid risks related to a disease caused mainly by bacteria, several children without AOM are treated with antibiotics and followed as true AOM cases. The main objective of this manuscript is to discuss the most common difficulties that presently limit accurate AOM diagnosis and the new approaches and technologies that have been proposed to improve disease detection. We showed that misdiagnosis can be dangerous or lead to relevant therapeutic mistakes. The need to improve AOM diagnosis has allowed the identification of a long list of technologies to visualize and evaluate the tympanic membrane and to assess middle-ear effusion. Most of the new instruments, including light field otoscopy, optical coherence tomography, low-coherence interferometry, and Raman spectroscopy, are far from being introduced in clinical practice. Video-otoscopy can be effective, especially when it is used in association with telemedicine, parents' cooperation, and artificial intelligence. Introduction of otologic telemedicine and use of artificial intelligence among pediatricians and ENT specialists must be strongly promoted in order to reduce mistakes in AOM diagnosis.

Differential Biases and Variabilities of Deep Learning-Based Artificial Intelligence and Human Experts in Clinical Diagnosis: Retrospective Cohort and Survey Study

Background

Deep learning (DL)–based artificial intelligence may have different diagnostic characteristics than human experts in medical diagnosis. As a data-driven knowledge system, heterogeneous population incidence in the clinical world is considered to cause more bias to DL than clinicians. Conversely, by experiencing limited numbers of cases, human experts may exhibit large interindividual variability. Thus, understanding how the 2 groups classify given data differently is an essential step for the cooperative usage of DL in clinical application.

Objective

This study aimed to evaluate and compare the differential effects of clinical experience in otoendoscopic image diagnosis in both computers and physicians exemplified by the class imbalance problem and guide clinicians when utilizing decision support systems.

Methods

We used digital otoendoscopic images of patients who visited the outpatient clinic in the Department of Otorhinolaryngology at Severance Hospital, Seoul, South Korea, from January 2013 to June 2019, for a total of 22,707 otoendoscopic images. We excluded similar images, and 7500 otoendoscopic images were selected for labeling. We built a DL-based image classification model to classify the given image into 6 disease categories. Two test sets of 300 images were populated: balanced and imbalanced test sets. We included 14 clinicians (otolaryngologists and nonotolaryngology specialists including general practitioners) and 13 DL-based models. We used accuracy (overall and per-class) and kappa statistics to compare the results of individual physicians and the ML models.

Results

Our ML models had consistently high accuracies (balanced test set: mean 77.14%, SD 1.83%; imbalanced test set: mean 82.03%, SD 3.06%), equivalent to those of otolaryngologists (balanced: mean 71.17%, SD 3.37%; imbalanced: mean 72.84%, SD 6.41%) and far better than those of nonotolaryngologists (balanced: mean 45.63%, SD 7.89%; imbalanced: mean 44.08%, SD 15.83%). However, ML models suffered from class imbalance problems (balanced test set: mean 77.14%, SD 1.83%; imbalanced test set: mean 82.03%, SD 3.06%). This was mitigated by data augmentation, particularly for low incidence classes, but rare disease classes still had low per-class accuracies. Human physicians, despite being less affected by prevalence, showed high interphysician variability (ML models: kappa=0.83, SD 0.02; otolaryngologists: kappa=0.60, SD 0.07).

Conclusions

Even though ML models deliver excellent performance in classifying ear disease, physicians and ML models have their own strengths. ML models have consistent and high accuracy while considering only the given image and show bias toward prevalence, whereas human physicians have varying performance but do not show bias toward prevalence and may also consider extra information that is not images. To deliver the best patient care in the shortage of otolaryngologists, our ML model can serve a cooperative role for clinicians with diverse expertise, as long as it is kept in mind that models consider only images and could be biased toward prevalent diseases even after data augmentation.

A Web-Based Deep Learning Model for Automated Diagnosis of Otoscopic Images

OBJECTIVES

To develop a multiclass-classifier deep learning model and website for distinguishing tympanic membrane (TM) pathologies based on otoscopic images.

METHODS

An otoscopic image database developed by utilizing publicly available online images and open databases was assessed by convolutional neural network (CNN) models including ResNet-50, Inception-V3, Inception-Resnet-V2, and MobileNetV2. Training and testing were conducted with a 75:25 breakdown. Area under the curve of receiver operating characteristics (AUC-ROC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were used to compare different CNN models' performances in classifying TM images.

RESULTS

Our database included 400 images, organized into normal (n = 196) and abnormal classes (n = 204), including acute otitis media (n = 116), otitis externa (n = 44), chronic suppurative otitis media (n = 23), and cerumen impaction (n = 21). For binary classification between normal versus abnormal TM, the best performing model had average AUC-ROC of 0.902 (MobileNetV2), followed by 0.745 (Inception-Resnet-V2), 0.731 (ResNet-50), and 0.636 (Inception-V3). Accuracy ranged between 0.73-0.77, sensitivity 0.72-0.88, specificity 0.58-0.84, PPV 0.68-0.81, and NPV 0.73-0.83. Macro-AUC-ROC for MobileNetV2 based multiclass-classifier was 0.91, with accuracy of 66%. Binary and multiclass-classifier models based on MobileNetV2 were loaded onto a publicly accessible and user-friendly website (https://headneckml.com/tympanic). This allows the readership to upload TM images for real-time predictions using the developed algorithms.

CONCLUSIONS

Novel CNN algorithms were developed with high AUC-ROCs for differentiating between various TM pathologies. This was further deployed as a proof-of-concept publicly accessible website for real-time predictions.

Face, Content, and Construct Validity of a Virtual Reality Otoscopy Simulator and Applicability to Medical Training

Objective

Otologic diseases are common in all age groups and can significantly impair the function of this important sensory organ. To make a correct diagnosis, the correct handling of the otoscope and a correctly performed examination are essential. A virtual reality simulator could make it easier to teach this difficult-to-teach skill. The aim of this study was to assess the face, content, and construct validity of the novel virtual reality otoscopy simulator and the applicability to otologic training.

Study Design

Face and content validity was assessed with a questionnaire. Construct validity was assessed in a prospectively designed controlled trial.

Setting

Training for medical students at a tertiary referral center.

Method

The questionnaire used a 6-point Likert scale. The otoscopy was rated with a modified Objective Structured Assessment of Technical Skills. Time to complete the task and the percentage of the assessed eardrum surface were recorded.

Results

The realism of the simulator and the applicability to medical training were assessed across several items. The ratings suggested good face and content validity as well as usefulness and functionality of the simulator. The otolaryngologists significantly outperformed the student group in all categories measured (P < .0001), suggesting construct validity of the simulator.

Conclusion

In this study, we could demonstrate face, content, and construct validity for a novel high-fidelity virtual reality otoscopy simulator. The results encourage the use of the otoscopy simulator as a complementary tool to traditional teaching methods in a curriculum for medical students.

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

Otitis media, a common disease marked by the presence of fluid within the middle ear space, imparts a significant global health and economic burden. Identifying an effusion through the tympanic membrane is critical to diagnostic success but remains challenging due to the inherent limitations of visible light otoscopy and user interpretation. Here we describe a powerful diagnostic approach to otitis media utilizing advancements in otoscopy and machine learning. We developed an otoscope that visualizes middle ear structures and fluid in the shortwave infrared region, holding several advantages over traditional approaches. Images were captured in vivo and then processed by a novel machine learning based algorithm. The model predicts the presence of effusions with greater accuracy than current techniques, offering specificity and sensitivity over 90%. This platform has the potential to reduce costs and resources associated with otitis media, especially as improvements are made in shortwave imaging and machine learning.

Efficient and accurate identification of ear diseases using an ensemble deep learning model

Early detection and appropriate medical treatment are of great use for ear disease. However, a new diagnostic strategy is necessary for the absence of experts and relatively low diagnostic accuracy, in which deep learning plays an important role. This paper puts forward a mechanic learning model which uses abundant otoscope image data gained in clinical cases to achieve an automatic diagnosis of ear diseases in real time. A total of 20,542 endoscopic images were employed to train nine common deep convolution neural networks. According to the characteristics of the eardrum and external auditory canal, eight kinds of ear diseases were classified, involving the majority of ear diseases, such as normal, Cholestestoma of the middle ear, Chronic suppurative otitis media, External auditory cana bleeding, Impacted cerumen, Otomycosis external, Secretory otitis media, Tympanic membrane calcification. After we evaluate these optimization schemes, two best performance models are selected to combine the ensemble classifiers with real-time automatic classification. Based on accuracy and training time, we choose a transferring learning model based on DensNet-BC169 and DensNet-BC1615, getting a result that each model has obvious improvement by using these two ensemble classifiers, and has an average accuracy of 95.59%. Considering the dependence of classifier performance on data size in transfer learning, we evaluate the high accuracy of the current model that can be attributed to large databases. Current studies are unparalleled regarding disease diversity and diagnostic precision. The real-time classifier trains the data under different acquisition conditions, which is suitable for real cases. According to this study, in the clinical case, the deep learning model is of great use in the early detection and remedy of ear diseases.

Handheld Briefcase Optical Coherence Tomography with Real-Time Machine Learning Classifier for Middle Ear Infections

A middle ear infection is a prevalent inflammatory disease most common in the pediatric population, and its financial burden remains substantial. Current diagnostic methods are highly subjective, relying on visual cues gathered by an otoscope. To address this shortcoming, optical coherence tomography (OCT) has been integrated into a handheld imaging probe. This system can non-invasively and quantitatively assess middle ear effusions and identify the presence of bacterial biofilms in the middle ear cavity during ear infections. Furthermore, the complete OCT system is housed in a standard briefcase to maximize its portability as a diagnostic device. Nonetheless, interpreting OCT images of the middle ear more often requires expertise in OCT as well as middle ear infections, making it difficult for an untrained user to operate the system as an accurate stand-alone diagnostic tool in clinical settings. Here, we present a briefcase OCT system implemented with a real-time machine learning platform for middle ear infections. A random forest-based classifier can categorize images based on the presence of middle ear effusions and biofilms. This study demonstrates that our briefcase OCT system coupled with machine learning can provide user-invariant classification results of middle ear conditions, which may greatly improve the utility of this technology for the diagnosis and management of middle ear infections.

Evaluation of digital otoscopy in pediatric patients: A prospective randomized controlled clinical trial

BACKGROUND

Acute otitis media is often misdiagnosed. Pediatric trainees learn otoscopy from supervisors who cannot concurrently view the eardrum. Digital, smartphone otoscopes show promise to improve the visibility and learning due to a concurrent view by trainees and supervisors. We aimed to determine whether use of digital otoscopes improved accuracy of the ear exams between medical trainees and their supervisors, compared to using traditional otoscopes. Secondarily, we evaluated whether the use of digital otoscopes reduced the number of repeat ear examinations by supervisors, changed the trainee's confidence in their exam findings, and led to differences in the rate of antibiotics prescribed.

METHODS

This study was a randomized controlled trial comparing use of a digital otoscope to a traditional otoscope, in a pediatric emergency department and primary care clinic in an academic tertiary care children's center. We used a modified validated image-based grading scale to compare accuracy of the ear exam between trainees and supervisors. Surveys documented modified OMgrade scores, frequency of supervisor exams, trainee confidence on a 5-point Likert scale, and antibiotic prescriptions. Inter-rater agreement of trainees and supervisors, the number of supervisor confirmatory examinations performed, trainee confidence, and antibiotic prescription rates were evaluated.

RESULTS

Amongst 188 children, 375 ears were examined by 85 trainees and 22 supervisors. The digital otoscope was utilized in 92 (48.9%) exams and 96 (51.1%) used the traditional otoscope. Accuracy of ear exam findings between trainees and supervisors improved by 11.2% (95% CI: 1.5, 21.8%, p = 0.033) using the Cellscope Oto (74.8%, 95% CI: 67.3, 82.1%) compared to the traditional otoscope (63.5%, 95% CI: 56.7, 70.4%). Fewer repeat supervisor exams were performed in the digital otoscope group (27.2%) vs. the traditional otoscope group (97.9%) (p < 0.001). There was no difference in mean trainee confidence in their examination (p = 0.955) or antibiotic prescription rates when using digital versus traditional otoscopes (p = 0.071).

CONCLUSIONS

Utilization of a digital otoscope resulted in increased accuracy of the ear exam between trainees and supervisors, and fewer total number of examinations performed on a given child. Compared to a traditional otoscope, a digital otoscope may be a more efficient and effective diagnostic tool.

Machine Learning for Accurate Intraoperative Pediatric Middle Ear Effusion Diagnosis

OBJECTIVES

Misdiagnosis of acute and chronic otitis media in children can result in significant consequences from either undertreatment or overtreatment. Our objective was to develop and train an artificial intelligence algorithm to accurately predict the presence of middle ear effusion in pediatric patients presenting to the operating room for myringotomy and tube placement.

METHODS

We trained a neural network to classify images as " normal" (no effusion) or "abnormal" (effusion present) using tympanic membrane images from children taken to the operating room with the intent of performing myringotomy and possible tube placement for recurrent acute otitis media or otitis media with effusion. Model performance was tested on held-out cases and fivefold cross-validation.

RESULTS

The mean training time for the neural network model was 76.0 (SD ± 0.01) seconds. Our model approach achieved a mean image classification accuracy of 83.8% (95% confidence interval [CI]: 82.7-84.8). In support of this classification accuracy, the model produced an area under the receiver operating characteristic curve performance of 0.93 (95% CI: 0.91-0.94) and F1-score of 0.80 (95% CI: 0.77-0.82).

CONCLUSIONS

Artificial intelligence-assisted diagnosis of acute or chronic otitis media in children may generate value for patients, families, and the health care system by improving point-of-care diagnostic accuracy. With a small training data set composed of intraoperative images obtained at time of tympanostomy tube insertion, our neural network was accurate in predicting the presence of a middle ear effusion in pediatric ear cases. This diagnostic accuracy performance is considerably higher than human-expert otoscopy-based diagnostic performance reported in previous studies.

Deep metric learning for otitis media classification

In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on otoscopy images of the tympanic membrane. A total of 1336 images were assessed by a medical specialist into three diagnostic groups: acute otitis media, otitis media with effusion, and no effusion. To provide proper treatment and care and limit the use of unnecessary antibiotics, it is crucial to correctly detect tympanic membrane abnormalities, and to distinguish between acute otitis media and otitis media with effusion. The proposed approach for this classification task is based on deep metric learning, and this study compares the performance of different distance-based metric loss functions. Contrastive loss, triplet loss and multi-class N-pair loss are employed, and compared with the performance of standard cross-entropy and class-weighted cross-entropy classification networks. Triplet loss achieves high precision on a highly imbalanced data set, and the deep metric methods provide useful insight into the decision making of a neural network. The results are comparable to the best clinical experts and paves the way for more accurate and operator-independent diagnosis of otitis media.

Deep Learning for Classification of Pediatric Otitis Media

OBJECTIVES/HYPOTHESIS

To create a new strategy for monitoring pediatric otitis media (OM), we developed a brief, reliable, and objective method for automated classification using convolutional neural networks (CNNs) with images from otoscope.

STUDY DESIGN

Prospective study.

METHODS

An otoscopic image classifier for pediatric OM was built upon the idea of deep learning and transfer learning using the two most widely used CNN architectures named Xception and MobileNet-V2. Otoscopic images, including acute otitis media (AOM), otitis media with effusion (OME), and normal ears were obtained from our institution. Among qualified otoendoscopic images, 10,703 images were used for training, and 1,500 images were used for testing. In addition, 102 images captured by smartphone with WI-FI connected otoscope were used as a prospective test set to evaluate the model for home screening and monitoring.

RESULTS

For all diagnoses combined in the test set, the Xception model and the MobileNet-V2 model had similar overall accuracies of 97.45% (95% CI 96.81%-97.94%) and 95.72% (95% CI 95.12%-96.16%). The overall accuracies of two models with smartphone images were 90.66% (95% CI 90.21%-90.98%) and 88.56% (95% CI 87.86%-90.05%). The class activation map results showed that the extracted features of smartphone images were the same as those of otoendoscopic images.

CONCLUSIONS

We have developed deep learning algorithms for the successfully automated classification of pediatric AOM and OME with otoscopic images. With a smartphone-enabled wireless otoscope, artificial intelligence may assist parents in early detection and continuous monitoring at home to decrease the visit frequencies.

LEVEL OF EVIDENCE

NA Laryngoscope, 131:E2344-E2351, 2021.

Short-Wave Infrared Fluorescence Chemical Sensor for Detection of Otitis Media

Otitis media (OM) or middle ear infection is one of the most common diseases in young children around the world. The diagnosis of OM is currently performed using an otoscope to detect middle ear fluid and inflammatory changes manifested in the tympanic membrane. However, conventional otoscopy cannot visualize across the tympanic membrane or sample middle ear fluid. This can lead to low diagnostic certainty and overdiagnoses of OM. To improve the diagnosis of OM, we have developed a short-wave infrared (SWIR) otoscope in combination with a protease-cleavable biosensor, 6QC-ICG, which can facilitate the detection of inflammatory proteases in the middle ear with an increase in contrast. 6QC-ICG is a fluorescently quenched probe, which is activated in the presence of cysteine cathepsin proteases that are up-regulated in inflammatory immune cells. Using a preclinical model and custom-built SWIR otomicroscope in this proof-of-concept study, we successfully demonstrated the feasibility of robustly distinguishing inflamed ears from controls (p = 0.0006). The inflamed ears showed an overall signal-to-background ratio of 2.0 with a mean fluorescence of 81 ± 17 AU, while the control ear exhibited a mean fluorescence of 41 ± 11 AU. We envision that these fluorescently quenched probes in conjunction with SWIR imaging tools have the potential to be used as an alternate/adjunct tool for objective diagnosis of OM.

Otitis Media Module in the Pediatric Preclerkship Educational Exercises (PRECEDE) Curriculum

INTRODUCTION

The Johns Hopkins Pediatrics Clerkship developed the PRECEDE (preclerkship educational exercises) curriculum with the primary goal of offering students formative instruction in essential pediatric clinical skills to prepare them for their clerkship. PRECEDE sessions occur at the beginning of each basic clerkship for new clinical clerkship students. The otitis media module is one in a series of modules presented in the curriculum and consists of a lecture and four short skills-development stations, each with a faculty facilitator.

METHODS

This 2-hour module began with a 1-hour didactic overview of otitis media. Medical students were divided into three groups. One group learned about writing prescriptions via two otitis media clinical vignettes. Another group explored visualization and diagnosis of otitis media via video. The last student group was subdivided and learned proper techniques for positioning and restraining pediatric patients during otoscopic exams and the psychomotor skills for performing otoscopic examinations, including pneumatic otoscopy. Student groups rotated through all four activity stations. Students were guided through discussion to develop interpretation, diagnostic, and treatment skills for acute otitis media.

RESULTS

Between 2010 and 2012, 254 third- and fourth-year medical students participated in this module. When asked to evaluate overall quality, 86% of learners rated the module as excellent, and 14% rated it as good.

DISCUSSION

By establishing these important skills, students may be better equipped to develop appropriate otitis media assessments, diagnoses, and care plans for patients and to use otitis media as a platform for broad education in other essential pediatric skills.

Smartphone-based spectral imaging otoscope: System development and preliminary study for evaluation of its potential as a mobile diagnostic tool

We develop a novel smartphone-based spectral imaging otoscope for telemedicine and examine its capability for the mobile diagnosis of middle ear diseases. The device was applied to perform spectral imaging and analysis of an ear-mimicking phantom and a normal and abnormal tympanic membrane for evaluation of its potential for the mobile diagnosis. Spectral classified images were obtained via online spectral analysis in a remote server. The phantom experimental results showed that it allowed us to distinguish four different fluids located behind a semitransparent membrane. Also, in the spectral classified images of normal ears (n = 3) and an ear with chronic otitis media (n = 1), the normal and abnormal regions in each ear could be quantitatively distinguished with high contrast. These preliminary results thus suggested that it might have the potentials for providing quantitative information for the mobile diagnosis of various middle ear diseases.

Panel 3: Genomics, precision medicine and targeted therapies

OBJECTIVE

To review the most recent advances in human and bacterial genomics as applied to pathogenesis and clinical management of otitis media.

DATA SOURCES

PubMed articles published since the last meeting in June 2015 up to June 2019.

REVIEW METHODS

A panel of experts in human and bacterial genomics of otitis media was formed. Each panel member reviewed the literature in their respective fields and wrote draft reviews. The reviews were shared with all panel members, and a merged draft was created. The panel met at the 20th International Symposium on Recent Advances in Otitis Media in June 2019, discussed the review and refined the content. A final draft was made, circulated, and approved by the panel members.

CONCLUSION

Trans-disciplinary approaches applying pan-omic technologies to identify human susceptibility to otitis media and to understand microbial population dynamics, patho-adaptation and virulence mechanisms are crucial to the development of novel, personalized therapeutics and prevention strategies for otitis media.

IMPLICATIONS FOR PRACTICE

In the future otitis media prevention strategies may be augmented by mucosal immunization, combination vaccines targeting multiple pathogens, and modulation of the middle ear microbiome. Both treatment and vaccination may be tailored to an individual's otitis media phenotype as defined by molecular profiles obtained by using rapidly developing techniques in microbial and host genomics.

Panel 1: Biotechnology, biomedical engineering and new models of otitis media

OBJECTIVE

To summarize recently published key articles on the topics of biomedical engineering, biotechnology and new models in relation to otitis media (OM).

DATA SOURCES

Electronic databases: PubMed, Ovid Medline, Cochrane Library and Clinical Evidence (BMJ Publishing).

REVIEW METHODS

Articles on biomedical engineering, biotechnology, material science, mechanical and animal models in OM published between May 2015 and May 2019 were identified and subjected to review. A total of 132 articles were ultimately included.

RESULTS

New imaging technologies for the tympanic membrane (TM) and the middle ear cavity are being developed to assess TM thickness, identify biofilms and differentiate types of middle ear effusions. Artificial intelligence (AI) has been applied to train software programs to diagnose OM with a high degree of certainty. Genetically modified mice models for OM have further investigated what predisposes some individuals to OM and consequent hearing loss. New vaccine candidates protecting against major otopathogens are being explored and developed, especially combined vaccines, targeting more than one pathogen. Transcutaneous vaccination against non-typeable Haemophilus influenzae has been successfully tried in a chinchilla model. In terms of treatment, novel technologies for trans-tympanic drug delivery are entering the clinical domain. Various growth factors and grafting materials aimed at improving healing of TM perforations show promising results in animal models.

CONCLUSION

New technologies and AI applications to improve the diagnosis of OM have shown promise in pre-clinical models and are gradually entering the clinical domain. So are novel vaccines and drug delivery approaches that may allow local treatment of OM.

IMPLICATIONS FOR PRACTICE

New diagnostic methods, potential vaccine candidates and the novel trans-tympanic drug delivery show promising results, but are not yet adapted to clinical use.

Development and Validation of an Assessment Tool for Technical Skills in Handheld Otoscopy

Objective:

Handheld otoscopy requires both technical and diagnostic skills, and is often reported to be insufficient after medical training. We aimed to develop and gather validity evidence for an assessment tool for handheld otoscopy using contemporary medical educational standards.

Study Design:

Educational study.

Setting:

University/teaching hospital.

Subjects and Methods:

A structured Delphi methodology was used to develop the assessment tool: nine key opinion leaders (otologists) in undergraduate training of otoscopy iteratively achieved consensus on the content. Next, validity evidence was gathered by the videotaped assessment of two handheld otoscopy performances of 15 medical students (novices) and 11 specialists in otorhinolaryngology using two raters. Standard setting (pass/fail criteria) was explored using the contrasting groups and Angoff methods.

Results:

The developed Copenhagen Assessment Tool of Handheld Otoscopy Skills (CATHOS) consists 10 items rated using a 5-point Likert scale with descriptive anchors. Validity evidence was collected and structured according to Messick’s framework: for example the CATHOS had excellent discriminative validity (mean difference in performance between novices and experts 20.4 out of 50 points, P < .001); and high internal consistency (Cronbach’s alpha = 0.94). Finally, a pass/fail score was established at 30 points for medical students and 42 points for specialists in ORL.

Conclusion:

We have developed and gathered validity evidence for an assessment tool of technical skills of handheld otoscopy and set standards of performance. Standardized assessment allows for individualized learning to the level of proficiency and could be implemented in under- and postgraduate handheld otoscopy training curricula, and is also useful in evaluating training interventions.

Level of evidence:

NA

Otitis Media Middle Ear Effusion Identification and Characterization Using an Optical Coherence Tomography Otoscope

OBJECTIVE

To determine the feasibility of detecting and differentiating middle ear effusions (MEEs) using an optical coherence tomography (OCT) otoscope.

STUDY DESIGN

Cross-sectional study.

SETTING

US tertiary care children's hospital.

SUBJECTS AND METHODS

Seventy pediatric patients undergoing tympanostomy tube placement were preoperatively imaged using an OCT otoscope. A blinded reader quiz was conducted using 24 readers from 4 groups of tiered medical expertise. The primary outcome assessed was reader ability to detect presence/absence of MEE. A secondary outcome assessed was reader ability to differentiate serous vs nonserous MEE.

RESULTS

OCT image data sets were analyzed from 45 of 70 total subjects. Blinded reader analysis of an OCT data subset for detection of MEE resulted in 90.6% accuracy, 90.9% sensitivity, 90.2% specificity, and intra/interreader agreement of 92.9% and 87.1%, respectively. Differentiating MEE type, reader identification of nonserous MEE had 70.8% accuracy, 53.6% sensitivity, 80.1% specificity, and intra/interreader agreement of 82.9% and 75.1%, respectively. Multivariate analysis revealed that age was the strongest predictor of OCT quality. The mean age of subjects with quality OCT was 5.01 years (n = 45), compared to 2.54 years (n = 25) in the remaining subjects imaged (P = .0028). The ability to capture quality images improved over time, from 50% to 69.4% over the study period.

CONCLUSION

OCT otoscopy shows promise for facilitating accurate MEE detection. The imageability with the prototype device was affected by age, with older children being easier to image, similar to current ear diagnostic technologies.

Updated Guidelines for the Management of Acute Otitis Media in Children by the Italian Society of Pediatrics: Diagnosis

BACKGROUND

In recent years, new progress has been made regarding the diagnosis, treatment and prevention of acute otitis media (AOM). The Italian Pediatric Society therefore decided to issue an update to the previous guidelines published in 2010.

METHODS

Literature searches were conducted on MEDLINE by Pubmed, including studies in children, in English or Italian, published between January 1, 2010, and December 31, 2018. The quality of the included studies was assessed using the grading of recommendations, assessment, development and evaluations (GRADE) methodology. In particular, the quality of the systematic reviews was evaluated using the AMSTAR 2 appraisal tool. The guidelines were formulated using the GRADE methodology by a multidisciplinary panel of experts.

RESULTS

The diagnosis of AOM is based on acute clinical symptoms and otoscopic evidence; alternatively, the presence of otorrhea associated with spontaneous tympanic membrane perforation allows the AOM diagnosis. The diagnosis of AOM must be certain and the use of a pneumatic otoscope is of fundamental importance. As an alternative to the pneumatic otoscope, pediatricians can use a static otoscope and a tympanometer. To objectively establish the severity of the episode for the formulation of a correct treatment program, an AOM severity scoring system taking into account clinical signs and otoscopic findings was developed.

CONCLUSIONS

The diagnosis of AOM is clinical and requires the introduction of specific medical training programs. The use of pneumatic otoscopes must be promoted, as they are not sufficiently commonly used in routine practice in Italy.

Building an Otoscopic screening prototype tool using deep learning

Background

Otologic diseases are often difficult to diagnose accurately for primary care providers. Deep learning methods have been applied with great success in many areas of medicine, often outperforming well trained human observers. The aim of this work was to develop and evaluate an automatic software prototype to identify otologic abnormalities using a deep convolutional neural network.

Material and methods

A database of 734 unique otoscopic images of various ear pathologies, including 63 cerumen impactions, 120 tympanostomy tubes, and 346 normal tympanic membranes were acquired. 80% of the images were used for the training of a convolutional neural network and the remaining 20% were used for algorithm validation. Image augmentation was employed on the training dataset to increase the number of training images. The general network architecture consisted of three convolutional layers plus batch normalization and dropout layers to avoid over fitting.

Results

The validation based on 45 datasets not used for model training revealed that the proposed deep convolutional neural network is capable of identifying and differentiating between normal tympanic membranes, tympanostomy tubes, and cerumen impactions with an overall accuracy of 84.4%.

Conclusion

Our study shows that deep convolutional neural networks hold immense potential as a diagnostic adjunct for otologic disease management.