How to improve the accuracy of diagnosing otitis media with effusion in a pediatric population

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.

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.

Does Otitis Media Affect Later Language Ability? A Prospective Birth Cohort Study

Purpose The aim of the study was to examine whether otitis media (OM) in early childhood has an impact on language development in later childhood. Methods We analyzed data from 1,344 second-generation (Generation 2) participants in the Raine Study, a longitudinal pregnancy cohort established in Perth, Western Australia, between 1989 and 1991. OM was assessed clinically at 6 years of age. Language development was measured using the Peabody Picture Vocabulary Test-Revised (PPVT-R) at 6 and 10 years of age and the Clinical Evaluation of Language Fundamentals-Third Edition at 10 years of age. Logistic regression analysis accounted for a wide range of social and environmental covariates. Results There was no significant relationship between bilateral OM and language ability at 6 years of age (β = -0.56 [-3.78, 2.66], p = .732). However, while scores were within the normal range for the outcome measures at both time points, there was a significant reduction in the rate of receptive vocabulary growth at 10 years of age (PPVT-R) for children with bilateral OM at 6 years of age (β = -3.17 [-6.04, -0.31], p = .030), but not for the combined unilateral or bilateral OM group (β = -1.83 [-4.04, 0.39], p = .106). Conclusions Children with OM detected at 6 years of age in this cohort had average language development scores within the normal range at 6 and 10 years of age. However, there was a small but statistically significant reduction in the rate of receptive vocabulary growth at 10 years of age (on the PPVT-R measure only) in children who had bilateral OM at 6 years of age after adjusting for a range of sociodemographic factors.

Initial findings of shortwave infrared otoscopy in a pediatric population

OBJECTIVE

To evaluate the feasibility of Shortwave infrared (SWIR) otoscopy in a pediatric population and establish differences with visible otoscopy.

METHODS

Pediatric patients 3 years of age and older seen in the otolaryngology clinic with an audiogram and tympanogram obtained within a week of the visit were recruited for video otoscopy using visible light otoscopy and SWIR otoscopy. Videos were rated by two otolaryngologists based on ability to identify the promontory, ability to identify the ossicular chain and presence or absence of middle ear fluid.

RESULTS

A total of 74 video recordings of ears were obtained in 20 patients. We obtained interpretable images in 63/74 (85.1%) ears. There was no statistical significance between ability to perform SWIR otoscopy versus white light video otoscopy as indicated by a p-value of 0.376. There was high inter-rater agreement for identification of both the promontory and the ossicular chain with Kappa values of 0.81 and 0.92 respectively. There was statistical significance between SWIR otoscopy and visible otoscopy in the ability to image the promontory (p = 0.012) and the ossicular chain (p = 0.010). Increased contrast of middle ear fluid was seen in SWIR otoscopy when compared to visible otoscopy.

CONCLUSION

SWIR otoscopy is feasible in a pediatric population and could offer some advantages over visible light otoscopy such as better visualization of the middle ear structures through the tympanic membrane and increased contrast for middle ear effusions.

Differential diagnosis of otitis media with effusion using label-free Raman spectroscopy: A pilot study

Otitis media with effusion (OME) is an important and common condition affecting hearing in pediatric patients characterized by the presence of fluid in the middle ear space. The fluid is normally described as serous or mucoid based on differences in the fluid viscosity. The differential diagnosis of two OMEs, namely serous and mucoid is of significant clinical value because while the former is self-limiting, surgical procedure is commonly required for the latter. However, accurate identification of fluid types remains a challenging target unattainable with current clinical modalities due to unavailability of nonperturbative molecular tools. Here, we report an emerging spectroscopy approach featuring Raman scattering and multivariate analysis of spectral patterns to discern serous and mucoid fluids, obtained from pediatric patients undergoing myringotomy and tube placement, by providing information of differentially expressed molecules with high specificity. We demonstrate the feasibility of Raman spectroscopy-based approach to categorize middle ear effusion based on the characteristic spectral markers, notably of mucin, with classification accuracy of 91% and 93% for serous and mucoid, respectively. Our findings pave the way for further development of such a tool for fully noninvasive application that will lead to objective and accurate diagnosis thereby reducing unnecessary visits and surgical procedures.

Diagnosis and treatment of otitis media with effusion: CODEPEH recommendations

The incidence and the prevalence rates of otitis media with effusion (OME) are high. However, there is evidence that only a minority of professionals follow the recommendations provided in clinical practice guidelines. For the purpose of improving diagnosis and treatment of OME in children to prevent and/or reduce its impact on children's development, the Commission for the Early Detection of Deafness (CODEPEH) has deeply reviewed the scientific literature on this field and has drafted a document of recommendations for a correct clinical reaction to of OME, including diagnosis and medical and surgical treatment methodology. Among others, medication, in particular antibiotics and corticoids, should not be prescribed and 3 months of watchful waiting should be the first adopted measure. If OME persists, an ENT doctor should assess the possibility of sugical treatment. The impact of OME in cases of children with a comorbidity is higher, so it requires immediate reaction, without watchful waiting.

Otitis media

Otitis media (OM) or middle ear inflammation is a spectrum of diseases, including acute otitis media (AOM), otitis media with effusion (OME; 'glue ear') and chronic suppurative otitis media (CSOM). OM is among the most common diseases in young children worldwide. Although OM may resolve spontaneously without complications, it can be associated with hearing loss and life-long sequelae. In developing countries, CSOM is a leading cause of hearing loss. OM can be of bacterial or viral origin; during 'colds', viruses can ascend through the Eustachian tube to the middle ear and pave the way for bacterial otopathogens that reside in the nasopharynx. Diagnosis depends on typical signs and symptoms, such as acute ear pain and bulging of the tympanic membrane (eardrum) for AOM and hearing loss for OME; diagnostic modalities include (pneumatic) otoscopy, tympanometry and audiometry. Symptomatic management of ear pain and fever is the mainstay of AOM treatment, reserving antibiotics for children with severe, persistent or recurrent infections. Management of OME largely consists of watchful waiting, with ventilation (tympanostomy) tubes primarily for children with chronic effusions and hearing loss, developmental delays or learning difficulties. The role of hearing aids to alleviate symptoms of hearing loss in the management of OME needs further study. Insertion of ventilation tubes and adenoidectomy are common operations for recurrent AOM to prevent recurrences, but their effectiveness is still debated. Despite reports of a decline in the incidence of OM over the past decade, attributed to the implementation of clinical guidelines that promote accurate diagnosis and judicious use of antibiotics and to pneumococcal conjugate vaccination, OM continues to be a leading cause for medical consultation, antibiotic prescription and surgery in high-income countries.

Hospital clinical trial: Homeopathy (Agraphis nutans 5CH, Thuya occidentalis 5CH, Kalium muriaticum 9CH and Arsenicum iodatum 9CH) as adjuvant, in children with otitis media with effusion

BACKGROUND

Otitis media with effusion (OME) is the most common cause of paediatric hearing loss. No single treatment has proved its effectiveness. There is a lack of evidence-based medicine studies in the area of homeopathy.

METHOD

A prospective randomized, double blinded interventional placebo control study was conducted. Patients, from 2 months to 12 years, with OME diagnosed by pneumatic otoscopy (PNO) and tympanometry, were randomized into two groups. Both groups received aerosol therapy (mucolytics and corticosteroids). In addition, the experimental group (EG) received homeopathy (Agraphis nutans 5CH, Thuya Occidentalis 5CH, Kalium muriaticum 9CH and Arsenicum iodatum), and the placebo group (PG) placebo, both of them for 3 months. Patients were evaluated by PNO examination and tympanometry at baseline, at 45 and 90 days.

RESULTS

97 patients were enrolled. In the EG, 61.9% of individuals were cured (PNO went from negative in the 1st visit to positive in the 3rd visit) compared with 56.8% of patients treated with placebo. 4.8% of patients in the EG suffered a recurrence (positive PNO in the 2nd visit changed to negative in the 3rd visit) while 11.4% did in the PG. No significant difference was found. Adverse events were distributed similarly, except in the case of upper respiratory tract infections, which were less frequent in EG (3 vs. 13, p: 0.009).

CONCLUSION

The homeopathic scheme used as adjuvant treatment cannot be claimed to be an effective treatment in children with OME.

TRIAL REGISTRATION

EUDRACT number: 2011-006086-17, PROTOCOL code: 55005646.

Longitudinal results of intratympanic injection of budesonide for otitis media with effusion in children over 12 years and adults

OBJECTIVE

To assess the longitudinal curative effect and improvement of subjective symptoms by using intratympanic injection of Budesonide(BUD) for otitis media with effusion (OME) patients older than 12 years and adults.

STUDY DESIGN

A single-blind, randomized, parallel-controlled prospective study.

SETTING

Hospital, outpatient.

PATIENTS

Ninety patients (112 ears) who were diagnosed as having OME were recruited and then randomized to BUD, dexamethasone (DEX), and sodium chloride (NS) groups, the latter two served as controls.

INTERVENTIONS

The randomly allocated patients received intratympanic injection of BUD (0.5 mg/1 ml), DEX (2 mg/1 ml), or 0.9% NS solution (1 ml) once a week.

MAIN OUTCOME MEASURES

Survival analysis was applied to compare the longitudinal curative effects among the 3 groups. Meanwhile, the 6 main subjective symptoms were scored by 10-point visual scale, and physician's evaluations were preformed during treatment and follow-up.

RESULTS

After adjustment for course of disease, volume, and characters of effusion, the relative risk (RR) of BUD is 0.139 (95% CI, 0.054-0.358) when compared with NS. Survival curve demonstrated that the rank of longitudinal therapeutic efficacy was BUD, DEX, and NS (p < 0.05). Both BUD and DEX showed improvements in subjective symptoms and quality of life compared with NS (p < 0.05). In the aspect of improving the symptom of stuffy ear, BUD showed advantage over both DEX and NS. During and after treatment, no serious complications or sequelae were observed.

CONCLUSION

Intratympanic injection with BUD for OME patients showed advantages in improving long-term therapeutic efficacy, it was a safe and effective intervention for adolescents and adults with OME.

Applicability of spectral gradient acoustic reflectometry (EarCheck): screening patients who need surgical treatment for chronic otitis media with effusion

OBJECTIVES

We aimed to conduct a prospective, observational study of the applicability of EarCheck (Innovia Medical LLC, Omaha, NE) in the surgical management of chronic otitis media with effusion (COME).

MATERIALS AND METHODS

Between February 2013 and July 2013, 84 patients (165 ears) who had been diagnosed with COME and underwent surgical management were recruited. Information concerning patient sex, age, body mass index, EarCheck score, pure-tone averages (PTAs), speech reception thresholds (SRTs), and characteristics of middle ear fluid (MEF) were documented and statistically analyzed.

RESULTS

MEF was detected in 87.3% (n=144/165) of the 165 ears. Based on EarCheck scores ≥ 3 (as a criterion for abnormal findings), the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy of EarCheck were 56.9%, 90.5%, 82%, 23.5%, and 61.2%, respectively. Significant positive correlation was found between EarCheck, both pure-tone thresholds at all frequencies and mean PTAs, and SRTs. The mean PTAs and SRTs of the patients with EarCheck scores ≥ 3 was 37.79 dB and 33.26 dB, respectively; these scores were significantly higher than the mean PTAs and SRTs (30.56 dB and 25.88 dB, respectively) of the patients with EarCheck scores <3 (p<0.05).

CONCLUSION

Although it is not preferable to conduct the EarCheck test alone when diagnosing COME because of its low accuracy, because of its additional hearing level clues, EarCheck can be used in deciding whether to perform tympanostomy tube insertion when conventional audiometry is not possible.

Korean clinical practice guidelines: otitis media in children

Acute otitis media (AOM) and otitis media with effusion (OME) are common infections in children, and their diagnosis and treatment have significant impacts on the health of children and the costs of providing national medical care. In 2009, the Korean Otologic Society organized a committee composed of experts in the field of otolaryngology, pediatrics, and family medicine to develop Korean clinical practice guidelines (CPG) for otitis media in children with the goal of meeting regional medical and social needs in Korea. For this purpose, the committee adapted existing guidelines. A comprehensive literature review was carried out primarily from 2004 to 2009 using medical search engines including data from Korea. A draft was written after a national questionnaire survey and several public audits, and it was editorially supervised by senior advisors before publication of the final report. These evidence-based guidelines for the management of otitis media in children provide recommendations to primary practitioners for the diagnosis and treatment of children younger than 15 yr old with uncomplicated AOM and OME. The guidelines include recommendations regarding diagnosis, treatment options, prevention and parent education, medical records, referral, and complementary/alternative medicine for treating pediatric otitis media.