Diagnosis Of Otitis Media Research Articles

Computerized otoscopy image-based artificial intelligence model utilizing deep features provided by vision transformer, grid search optimization, and support vector machine for otitis media diagnosis

Computerized otoscopy image-based artificial intelligence model utilizing deep features provided by vision transformer, grid search optimization, and support vector machine for otitis media diagnosis

Clinical value of wideband acoustic immittance in the diagnosis of otitis media with effusion under negative intratympanic pressure in adults

Background Normative clinical values for wideband acoustic immittance (WAI) are not well-established. Aims This study aims to define the normative contour plot characteristics of WAI and evaluate its diagnostic value in detecting tympanic effusion. Materials and methods Data were collected from subjects with normal hearing (76 ears) and type C tympanograms on 226-Hz tympanometry (130 ears). Matlab was used to process and analyze the data. The maximum absorbance of WAI was used as the primary indicator, and the receiver operating characteristic (ROC) curve was drawn to determine the optimal cut-off value. WAI contour plots were compared to 226-Hz tympanometry and otoendoscopy, the latter being the gold standard. Results Mean WAI plots in the normal group showed single peaks (absorbance, >70%) and a nearly symmetrical distribution of the peak area around the 0 daPa pressure line. The ROC curve indicated an AUC value of 0.910, with 78% as the optimal cut-off value of maximum absorbance for detecting effusion. WAI demonstrated better diagnostic performance (sensitivity: 82.26%, specificity: 86.76%, kappa: 0.691) than 226-Hz tympanometry (sensitivity: 61.29%, specificity: 61.76%, kappa: 0.230). Conclusions and significance Normative WAI values were established, and WAI proved more accurate than 226-Hz tympanometry for identifying tympanic effusion, offering valuable guidance for selecting treatment options.

Characteristics and diagnostic performance of nonechoplanar diffusion-weighted imaging in detecting canine tympanokeratoma (cholesteatoma).

Tympanokeratomas (cholesteatomas) are destructive keratinic masses of the middle ear that are often treated surgically. In humans, nonechoplanar (non-EP) diffusion-weighted (DW) MRI is efficient in diagnosing tympanokeratomas and differentiating recurrent tympanokeratomas from granulation or fibrous tissue after surgery. The objectives of this study were to (1) determine the characteristics of non-EP DWI of histologically or cytologically confirmed canine tympanokeratomas, (2) determine the performance of non-EP DW images, apparent diffusion coefficient (ADC) map and ADC values in discriminating between tympanokeratomas and other causes of otitis media in dogs, and (3) find an optimal ADC cut-off value. Medical records of dogs diagnosed on MRI with otitis media in two veterinary hospitals were retrospectively reviewed. Sixty-two ears with a cytological or pathological diagnosis of either tympanokeratoma (36/62) or nontympanokeratoma otitis media (26/62) were selected. Diffusion-weighted images had an accuracy of 77.4%, a sensitivity of 94.4%, and a specificity of 53.8% for the detection of tympanokeratoma. The ADC value of middle ear content ranged from 517 to 1355.10-6mm2/s in tympanokeratoma and from 454 to 2447×10-6mm2/s in nontympanokeratoma otitis media. An ADC value below 916×10-6mm2/s interpreted as a tympanokeratoma yielded an accuracy of 78.7%, a sensitivity of 92.6%, and a specificity of 60%. In the study population, combined qualitative analysis of DW images and ADC maps was the most effective method for diagnosing tympanokeratomas with an accuracy of 80.9%, a sensitivity of 92.6%, and a specificity of 65%.

Reimagining otitis media diagnosis: A fusion of nested U-Net segmentation with graph theory-inspired feature set

Otitis media (OM) is a common infection or inflammation of the middle ear causing conductive hearing loss that primarily affects children and may delay speech, language, and cognitive development. OM can manifest itself in different forms, and can be diagnosed using (video) otoscopy (visualizing the tympanic membrane) or (video) pneumatic otoscopy and tympanometry. Accurate diagnosis of OM is challenging due to subtle differences in otoscopic features. This research aims to develop an automated computer-aided design (CAD) system to assist clinicians in diagnosing OM using otoscopy images. The ground truths, generated manually and validated by otolaryngologists, are utilized to train the proposed nested U-Net++ model. Ten clinically relevant gray level co-occurrence matrix (GLCM) and morphological features were extracted from the segmented Region of Interest (ROI) and validated for OM classification based on a statistical significance test. These features serve as input for a Graph Neural Network (GNN) model, the base model in our research. An optimized GNN model is proposed after ablation study of the base model. Three datasets, one private dataset, and two public ones have been used, where the private dataset is utilized for both training and testing, and the public datasets are used to test the robustness of the proposed GNN model only. The proposed GNN model obtained the highest accuracy in diagnosing OM: 99.38 %, 93.51 %, and 91.38 % for the private dataset, public dataset1, and public dataset2, respectively. The proposed methodology and results of this research might enhance clinicians' effectiveness in diagnosing OM.

Comparison of endoscopic tympanoplasty, cartilage vs. temporalis fascia in chronic suppurative otitis media with inactive mucosal disease: A prospective randomised study.

The introduction of endoscopy into middle ear has open up new opportunities for minimal invasive temporal bone surgery. The present study was planned to compare anatomical and functional outcome in patients who underwent endoscope assisted tympanoplasty using cartilage and temporalis fascia graft. The present prospective observational randomized study was carried out in the Department of Otorhinolaryngology of a tertiary care teaching hospital of Rajasthan, India from September 2020 to July 2021. Fifty patients of age group 18-60 years, with diagnosis of chronic otitis media having inactive mucosal disease were enrolled in the study and divided into two groups viz. cartilage (group I) and temporalis fascia group (group II). Each patient postoperatively underwent otoscopic examination of ear and pure tone audiometery at 8 weeks and 3rd month. Local wound condition, graft uptake and healing and hearing were assessed and compared. Graft uptake was 92% in cartilage group and 84% in temporalis fascia group. Air conduction and air-bone gap of patients in both the groups showed significant improvement after 3 months of surgery. (p˂0.05) Regarding bone conduction, both groups had shown non-significant changes. (p > 0.05) Hearing gain was comparable on both groups which was 6.71dB in cartilage group vs. 5.9 dB in other group. The present study showed that graft placement time for temporalis fascia graft was less than cartilage graft, but the difference was insignificant. Hearing improvement, graft uptake and clinical improvement were found to be statistically insignificant between both groups.

Health technology assessment of video otoscopy for the diagnosis of otitis media in children in comparison to conventional otoscopy in primary healthcare settings in India

ObjectiveThis Health Technology Assessment (HTA) was undertaken to assess the clinical-effectiveness, cost-effectiveness, and operational feasibility of using otoscopes in primary healthcare settings in India, for diagnosing otitis media in children. MethodsWe undertook a three-step process sequentially determining (i) clinical effectiveness of video as well as conventional otoscopy (compared to otic microscope as the reference standard); (ii)cost-effectiveness analysis of the video otoscope; and (iii)operational feasibility and health equity considerations. The systematic review for clinical effectiveness involved literature search across five databases, screening and inclusion of relevant studies, and data synthesis. Cost-effectiveness analysis was performed using data from published literature, specialist interviews, and cost assumptions if neither was available. The Progress Plus tool was used to explore health equity and operational feasibility was taken into account. ResultsThe systematic review on clinical effectiveness include three relevant studies from a total of 1361 identified. The pooled sensitivity and specificity of video otoscope were 0.70 (95%CI 0.60, 0.84) and 0.92 (CI95% 0.89, 0.95) to be 0.88 (95% CI, 0.84 to 0.91). The cost-effectiveness analysis identified the incremental cost-effectiveness ratio (compared to conventional otoscope) as INR 1008.4 per QALY, with an overall gain of 413 QALYs per year. This was well below the willingness-to-pay threshold for India. There was potential of enhancing health equity and no insurmountable operational barriers, to the use of video otoscope in primary healthcare settings. ConclusionThis HTA concluded that video otoscope is clinically effective, cost-effective, and operationally feasible in Indian primary health settings, for diagnosing otitis media in children.

Racial and Ethnic Disparities in Otolaryngology Office Visit and Tympanostomy Tube Placement in Children with Otitis Media.

Racial disparities are pervasive in access to pediatric surgery. The goal of this study was to test the hypotheses that, compared with White children, non-White and Hispanic children: (1) were less likely to attend evaluations by otolaryngologists after a diagnosis of otitis media (OM) eligible for surgical referral, and (2) these children were less likely to receive tympanostomy tube (TT) after surgical consultation. The OptumLabs Data Warehouse is a de-identified claims database of privately insured enrollees. Guidelines on the management of OMs suggest that children should be evaluated for surgery if they have recurrent acute OM or chronic OM with effusion. A cohort of children who were diagnosed with OM were constructed. For Hypothesis 1, the primary outcome was otolaryngology office visit within 6 months of a diagnosis of recurrent or chronic OM. For Hypothesis 2, the outcome was TT placement within 6 months following the otolaryngology office visit. Cox regression models were used to determine the relationship between race/ethnicity and the primary outcomes. Among 187,776 children with OMs, 72,774 (38.8%) had otolaryngology visits. In a multivariate Cox model, the hazard ratios of attending otolaryngology visit for Black, Hispanic, and Asian children were 0.93 (95% CI,0.90, 0.96), 0.86 (0.83, 0.88), and 0.74 (0.71, 0.77), compared with White children. Among the children evaluated by otolaryngologists, 46,554 (63.97%) received TT. Black, Hispanic, and Asian children with recurrent acute OM had lower likelihood of receiving TT. Racial disparities in attending otolaryngology office visit contributed to the disparities in receiving TT. Level 3 Laryngoscope, 134:3846-3852, 2024.

Summary of the clinical characteristics of tuberculous otitis media

Objective:The purpose of this study was to analyze and summarize the clinical characteristics and diagnostic methods of tuberculous otitis media（TOM）, to enrich clinical experience in diagnosis and treatment of tuberculous otitis media, so as to reduce missed diagnosis and misdiagnosis, and facilitate timely and effective therapy for better prognosis. Methods:This study retrospectively analyzed the clinical data of patients with tuberculous otitis media who were hospitalized in the Ear ward of our hospital and received surgical treatment from 2008 to 2022. The data of patients' clinical characteristics, radiological examination, intraoperative findings and therapeutic strategies were recorded and summarized. Results:A total of 23 cases （26 ears） of tuberculous otitis media were included in this retrospective study. The most common clinical symptoms were otorrhea（thin odorless fluid）（100%） and conductive hearing loss（100%）, with a high incidence of facial paralysis（23.1%）. It was not sensitive to traditional antibiotic treatment, eg. Levofloxacin （50% effective rate only）, and relapsed soon after drug withdrawal. It was revealed that all the surgical views had gray and white tough granulation tissue hyperplasia（100%）, and 23.1% with caseous necrosis. The purpose of surgery was to clear the lesion, reduce the recurrence rate of suppurative infection, and repair the function （hearing reconstruction or facial nerve decompression） as appropriate. The paraffin pathology of granulation tissue were reported as typical granulomatous inflammation and caseous necrosis with positive acid-fast staining, which was consistent with tuberculosis. Conclusion:It was easily confused by the clinical manifestations of tuberculous otitis media and common chronic suppurative otitis media. When met with the following conditions, we should pay highly attention to suspect tuberculous otitis media: The severity of local manifestations did not match with the length of the disease; with poor tympanic membrane at the early stage with no obvious cholesteatomas, with facial paralysis or hearing loss early onset; insensitive to traditional antibiotic treatment; with extensive granulation appeared in the tympanum and or mastoid cavity, with or without caseous necrosis or dead bone in the early days. The diagnosis should be confirmed based on the acid-fast staining of the histopathological section to detect positive acid-fast bacilli. Meanwhile, multiple laboratory examination methods（such as T-spot and PCR） should be integrated synchronously to help support the diagnosis.

Multi-modal deep learning for joint prediction of otitis media and diagnostic difficulty.

In this study, we propose a diagnostic model for automatic detection of otitis media based on combined input of otoscopy images and wideband tympanometry measurements. We present a neural network-based model for the joint prediction of otitis media and diagnostic difficulty. We use the subclassifications acute otitis media and otitis media with effusion. The proposed approach is based on deep metric learning, and we compare this with the performance of a standard multi-task network. The proposed deep metric approach shows good performance on both tasks, and we show that the multi-modal input increases the performance for both classification and difficulty estimation compared to the models trained on the modalities separately. An accuracy of 86.5% is achieved for the classification task, and a Kendall rank correlation coefficient of 0.45 is achieved for difficulty estimation, corresponding to a correct ranking of 72.6% of the cases. This study demonstrates the strengths of a multi-modal diagnostic tool using both otoscopy images and wideband tympanometry measurements for the diagnosis of otitis media. Furthermore, we show that deep metric learning improves the performance of the models.

Acute otitis media diagnosis in childhood: still a problem in 2023?

BackgroundDiagnosis of acute otitis media (AOM) in children can be challenging, given that symptoms are often non-specific or absent, and that the direct observation of the tympanic membrane in its entirety through otoscopy can sometimes be difficult. The aim of this study is to assess the diagnostic concordance in detection of AOM episodes between primary care paediatricians and physicians especially trained in paediatric otoscopy, and to characterize the most misleading elements in diagnostic failure.MethodsConsecutive clinical charts of children regularly followed for recurrent AOM (RAOM, i.e.: >3 episodes in 6 months or > 4 episodes in 1 year) at our Otitis Media paediatric outpatient clinic were retrospectively screened, in order to collect any diagnosis of AOM episode (and the related clinical findings/middle ear complaints) performed by primary care paediatricians/emergency room paediatricians. Diagnosis of AOM episode was validated by the same experienced physician (FF) in case of otoscopic relief of a bulging eardrum with at least one of the following: hyperaemia or yellow-like colour. The diagnostic concordance in detection of AOM episodes between primary care/emergency room paediatricians and our internal validator was expressed as the percentage of matching diagnosis.ResultsOne hundred and thirty-four single AOM episodes occurring in 87 children (mean age: 26.9 +/- 18.9 months) were included in the analysis. Diagnostic concordance in detection of AOM episodes between primary care/emergency room paediatricians and our internal validator was reported in 72.4% of cases. The most common pitfall found in our study was the misleading diagnosis of AOM in case of hyperaemic tympanic membrane without bulging (32/37 out of non-validated diagnoses).ConclusionsAOM diagnosis still represents a relevant issue among paediatricians in our country, and the presence of tympanic membrane hyperaemia without concomitant bulging can be confusing.

Clinical case of tuberculous otitis media in early childhood

Nowadays, the incidence of tuberculosis remains high all over the world, despite the vaccination, medical support, social policy. The main reasons for this are the high level of migration, the prevalence of bad habits, the prevalence of immunodeficiency conditions, the formation of resistance to antimicrobial drugs, the tendency to refuse vaccination. At the same time, great difficulties arise in the diagnosis of extrapulmonary forms of infection. The purpose of this publication is to remind about the peculiarities of the course and diagnosis of tuberculous otitis media. According to the literature, the main characteristic features of tuberculous of the middle ear are prolonged suppuration without pronounced pain syndrome, inefficiency of standard antibacterial therapy, the anamnestic data about contacts or violation of the vaccination schedule, multiple perforations and a pronounced granulation process during otoscopy, a pronounced destructive process in the temporal bone during X-ray examination. The article presents a clinical case of the development of tuberculous otitis media in a young child with delayed diagnostics and the development of mastoiditis with required emergency surgical treatment. Verification of the etiology of the disease and the specific treatment carried out made it possible to achieve complete relief of ear symptoms, restoration of the tympanic membrane and ventilation of the middle ear.

Factors associated with inappropriateness of antibiotic prescriptions for acutely ill children presenting to ambulatory care in high-income countries: a systematic review and meta-analysis.

Acutely ill children are at risk of unwarranted antibiotic prescribing. Data on the appropriateness of antibiotic prescriptions provide insights into potential tailored interventions to promote antibiotic stewardship. To examine factors associated with the inappropriateness of antibiotic prescriptions for acutely ill children presenting to ambulatory care in high-income countries. On 8 September 2022, we systematically searched articles published since 2002 in MEDLINE, Embase, CENTRAL, Web of Science, and grey literature databases. We included studies with acutely ill children presenting to ambulatory care settings in high-income countries reporting on the appropriateness of antibiotic prescriptions. The quality of the studies was evaluated using the Appraisal tool for Cross-Sectional Studies and the Newcastle-Ottawa Scale. Pooled ORs were calculated using random-effects models. Meta-regression, sensitivity and subgroup analysis were also performed. We included 40 articles reporting on 30 different factors and their association with inappropriate antibiotic prescribing. 'Appropriateness' covered a wide range of definitions. The following factors were associated with increased inappropriate antibiotic prescribing: acute otitis media diagnosis [pooled OR (95% CI): 2.02 (0.54-7.48)], GP [pooled OR (95% CI) 1.38 (1.00-1.89)] and rural setting [pooled OR (95% CI) 1.47 (1.08-2.02)]. Older patient age and a respiratory tract infection diagnosis have a tendency to be positively associated with inappropriate antibiotic prescribing, but pooling of studies was not possible. Prioritizing acute otitis media, GPs, rural areas, older children and respiratory tract infections within antimicrobial stewardship programmes plays a vital role in promoting responsible antibiotic prescribing. The implementation of a standardized definition of appropriateness is essential to evaluate such programmes.

Chronic Otitis Media among Patients Visiting Community-Based Static Outreach Clinics.

Chronic otitis media is a chronic inflammation of the middle ear and mastoid cavity, with recurrent ear discharges or otorrhoea through a tympanic perforation for the past 3 months. It is a common cause of hearing impairment, disability, and poor scholastic performance and can lead to fatal intracranial infections and acute mastoiditis. This study aimed to find out the prevalence of chronic otitis media among patients visiting community-based static outreach clinics. A descriptive cross-sectional study was conducted among patients visiting the community-based static outreach clinics from 1 January 2017 to 31 December 2019. The ethical approval was taken from the Ethical Review Board. The diagnosis of chronic otitis media was done using otoscopy. The records of patients coming to outreach clinics visiting for ear, nose and throat care were reviewed using a pre-designed study proforma. A systematic random sampling method was used. The point estimate was calculated at a 95% Confidence Interval. Among 385 patients, 37 (9.61%) (6.67-12.55, 95% Confidence Interval) had chronic otitis media. The mean age of patients with chronic otitis media was 27.59±13.24 years, with 28 (75.67%) patients aged between 18-60 years. Among them, 30 (81.08%) had unilateral and 34 (91.89%) had a mucosal type. The prevalence of chronic otitis media was lower than in other studies done in similar settings. community health services; otitis media; patients; prevalence.

Deep learning reconstruction improves the image quality of low-dose temporal bone CT with otitis media and mastoiditis patients

ObjectiveTo evaluate the image quality of low-dose temporal bone computed tomography (CT) in otitis media and mastoiditis patients by using deep learning reconstruction (DLR). Materials and methodsA total of ninety-seven temporal bones from 53 consecutive adult patients who had suspected otitis media and mastoiditis and underwent temporal bone CT were prospectively enrolled. All patients underwent high resolution CT protocol (group A) and an additional low-dose protocol (group B). In group A, high resolution data were reconstructed by filter back projection (FBP). In group B, low-dose data were reconstructed by DLR mild (B1), DLR standard (B2) and DLR strong (B3). The objective image quality was analyzed by measuring the CT value and image noise on the transverse image and calculating the signal-to-noise ratio (SNR) on incudomallear joint, retroauricular muscle, vestibule and subcutaneous fat. Subjective image quality was analyzed by using a five-point scale to evaluate nine anatomical structures of middle and inner ear. The number of temporal bone lesions which involved in five structures of middle ear were assessed in group A, B1, B2 and B3 images. ResultsThere were no significant differences in the CT values of the four reconstruction methods at four structures (all p > 0.05). The DLR group B1, B2 and B3 had significantly less image noise and a significantly higher SNR than group A at four structures (all p < 0.001). The group B1 had comparable subjective image quality as group A in nine structures (all p > 0.05), however, the group B3 had lower subjective image quality than group A in modiolus, spiral osseous lamina and stapes (all p < 0.001), the group B2 had lower subjective image quality than group A in modiolus and spiral osseous lamina (both p < 0.05). The number of temporal bone lesions which involved in five structures for group A, B1 and B2 images were no significant difference (all p > 0.05), however, the number of temporal bone lesions which involved in mastoid for group B3 images were significantly more than group A (p < 0.05). The radiation dose of high resolution CT protocol and low-dose protocol were 0.55 mSv and 0.11 mSv, respectively. ConclusionCompared with high resolution CT protocol, in the low-dose protocol of temporal bone CT, DLR mild and standard could improve the objective image quality, maintain good subjective image quality and satisfy clinical diagnosis of otitis media and mastoiditis patients.

Otitis media at 6-monthly assessments of Australian First Nations children between ages 12–36 months: Findings from two randomised controlled trials of combined pneumococcal conjugate vaccines

ObjectivesIn remote communities of northern Australia, First Nations children with hearing loss are disproportionately at risk of poor school readiness and performance compared to their peers with no hearing loss. The aim of this trial is to prevent early childhood persisting otitis media (OM), associated hearing loss and developmental delay. To achieve this, we designed a mixed pneumococcal conjugate vaccine (PCV) schedule that could maximise immunogenicity and thereby prevent bacterial otitis media (OM) and a trajectory of educational and social disadvantage. MethodsIn two sequential parallel, open-label, randomised controlled trials, eligible infants were first allocated 1:1:1 to standard or mixed PCV primary schedules at age 28–38 days, then at age 12 months to a booster dose (1:1) of 13-valent PCV, PCV13 (Prevenar13®, +P), or 10-valent pneumococcal non-typeable Haemophilus influenzae protein D conjugated vaccine, PHiD-CV10 (Synflorix®, +S). Here we report findings of standardised ear assessments conducted six-monthly from age 12–36 months, by booster dose. ResultsFrom March 2013 to September 2018, 261 children were allocated to booster + P (n = 131) or + S (n = 130). There were no significant differences in prevalence of any OM diagnosis by booster dose or when stratified by primary schedule. We found high, almost identical prevalence of OM in both boost groups at each age (for example 88% of 129 and 91% of 128 children seen, respectively, at primary endpoint age 18 months, difference −3% [95% Confidence Interval −11, 5]). At each age prevalence of bilateral OM was 52%–78%, and tympanic membrane perforation was 10%–18%. ConclusionDespite optimal pneumococcal immunisation, the high prevalence of OM persists throughout early childhood. Novel approaches to OM prevention are needed, along with improved early identification strategies and evaluation of expanded valency PCVs.

ISOM 2023 research Panel 4 - Diagnostics and microbiology of otitis media.

To identify and review key research advances from the literature published between 2019 and 2023 on the diagnosis and microbiology of otitis media (OM) including acute otitis media (AOM), recurrent AOM (rAOM), otitis media with effusion (OME), chronic suppurative otitis media (CSOM) and AOM complications (mastoiditis). PubMed database of the National Library of Medicine. All relevant original articles published in Medline in English between July 2019 and February 2023 were identified. Studies that were reviews, case studies, relating to OM complications (other than mastoiditis), and studies focusing on guideline adherence, and consensus statements were excluded. Members of the panel drafted the report based on these search results. For the diagnosis section, 2294 unique records screened, 55 were eligible for inclusion. For the microbiology section 705 unique records were screened and 137 articles were eligible for inclusion. The main themes that arose in OM diagnosis were the need to incorporate multiple modalities including video-otoscopy, tympanometry, telemedicine and artificial intelligence for accurate diagnoses in all diagnostic settings. Further to this, was the use of new, cheap, readily available tools which may improve access in rural and lowmiddle income (LMIC) settings. For OM aetiology, PCR remains the most sensitive method for detecting middle ear pathogens with microbiome analysis still largely restricted to research use. The global pandemic response reduced rates of OM in children, but post-pandemic shifts should be monitored. Cheap, easy to use multi-technique assessments combined with artificial intelligence and/or telemedicine should be integrated into future practice to improve diagnosis and treatment pathways in OM diagnosis. Longitudinal studies investigating the in-vivo process of OM development, timings and in-depth interactions between the triad of bacteria, viruses and the host immune response are still required. Standardized methods of collection and analysis for microbiome studies to enable inter-study comparisons are required. There is a need to target underlying biofilms if going to effectively prevent rAOM and OME and possibly enhance ventilation tube retention.

AI Model VersusClinician 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% vs59.4%, 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.

An advanced machine learning approach for high accuracy automated diagnosis of otitis media with effusion in different age groups using 3D wideband acoustic immittance

Wideband Acoustic Immittance (WAI) is a diagnostic tool for identifying middle ear dysfunction. The challenge to its widespread use is difficulty in interpreting the complex data. This study aimed to develop advanced Machine Learning (ML) tools to automatically diagnose ears with otitis media with effusion (OME) in different age groups from the WAI data. A total of 1177 sets of WAI data were collected from 551 normal middle ears and 626 ears with OME, divided into three age groups. A Titan IMP440 was used to measure wideband absorbance at frequencies from 226 to 8000 Hz, and pressure between +200 daPa and −300 daPa. A two-stage ML approach was used to achieve a highly accurate diagnosis of OME in each age group. In the first stage, a convolutional neural network (CNN) was developed to classify the WAI data set. In the second stage, another neural network with a self-attention mechanism was used to classify the most discriminative regions of the data. These regions were extracted areas that had the top 2.5 % most statistically significant difference between normal and OME ears in the training WAI data. Final classification considered outputs from the two stages. The two-stage ML approach achieved classification accuracy of 96.6 %, 94.1 %, and 90.7 % for the three age groups, respectively. The importance of this research is its contribution to the development of an automated diagnostic tool for OME. This tool will be easy to use, highly accurate, works across age groups and which will support clinicians in their diagnostic decisions.

Clinical Spectrum of Tuberculosis Otitis Media (TBOM) and Management Outcomes.

To determine the initial clinical diagnoses of patients with tuberculous otitis media (TBOM), to determine the value of PCR test, biopsy, and ancillary diagnostic procedures in detecting middle ear TB infection, and to establish the differences in treatment outcomes. The clinical records of twenty-eight patients identified with middle ear TB infection by PCR test and biopsy, from January 2010 to December 2016, were reviewed to determine their initial clinical diagnoses. The positivity rates of PCR test and biopsy were compared. The records of 12 patients included in a previous publication were revisited and included in the present study population. The combined cases were classified according to clinical diagnosis to constitute a summary of demographic characteristics, clinical diagnoses, laboratory tests, and treatment outcomes. Results of diagnostic and surgical procedures were reviewed and analyzed. Clinical findings and hearing test results before and after treatment were compared. Of the 28 patients, eight different clinical diagnoses of patients confirmed with middle ear TB were determined. PCR test diagnosed most cases belonging to the early and chronic stages of the disease process. Biopsy diagnosed mostly the chronic cases but failed to diagnose acute cases and late cases with diagnosis of chronic suppurative otitis media with cholesteatoma. By including the twelve cases that were published in 2011, the range of clinical diagnoses was expanded and an outcome of eleven clinical diagnoses confirmed with TB infection was established. Analysis of treatment outcomes showed that the clinical and hearing outcomes were better for patients managed at the early stage of the disease than for those presenting at the late stages of the disease process who underwent more complicated surgical procedures. Our study supports the concept of tuberculous otitis media (TBOM) clinical spectrum, implying a paradigm shift in the established thinking that TBOM presents only as a chronic disease. The combined use of PCR and biopsy is a potential diagnostic tool to improve case detection rate, further broaden the scope of the clinical spectrum, and develop better control and preventive strategies for TBOM.

Using Geometric Morphometric Analysis of Magnetic Resonance Imaging to Assess the Anatomy of the Eustachian Tube in Children with and without Otitis Media.

Otitis media (OM) is among the most common of childhood illnesses. It has long been hypothesized that children under age two are predisposed to OM due to differences in the anatomy of the Eustachian tube (ET), including the angle of the ET. OM in later childhood is less common but does occur, begging the question, are there shape differences in the ET that persist underlying later occurrences of OM? To answer this question, a novel method, which applied geometric and morphometric shape analysis to landmarks obtained from MRI data, was used. MRI scans were performed on 16 children (5 control, 3 cOME, and 8 rAOM) between 2011 and 2015. Sixteen landmarks representing the shape of the ET, cranial base, and palate were analyzed. The results of a Procrustes ANOVA indicate that the shape of the ET varies significantly (p < 0.01) between the OM and control groups. The shape differences between the OM group and the control are a medial and low attachment site of the tensor veli palatini (TVP) muscle, a posterior and high torus tubarius, and an anteriorly projected palate. These results support previous findings that a relatively horizontal ET is associated with a predisposition for OM. This study used a novel approach to examine anatomical differences in children with and without OM. First, the data set is unique in that it includes MRI scans of children with a confirmed OM diagnosis. Second, the use of MRI scans in craniofacial anatomy OM research is novel and allows for the collection of soft tissue landmarks and the visualization of soft tissue structures. Third, geometric morphometric shape analysis is a statistical method that captures shape differences, offering a more universal picture of nuanced changes within the entire set of landmarks, in contrast to more traditional linear and angular measurements used in prior OM studies examining craniofacial anatomy.