Prevention of ear diseases in newborns Malherbe (Pr Med. No. 16, 1932)

In order to combat deafness and ear diseases, Malherbe proposes (Rg No. 16, 1932) sterilization of the nasopharyngeal space of newborns.

Hearing healthcare gaps in LMICS: snapshot from a semi-urban community in Nigeria

Background: Low and middle-income countries (LMICs) have high prevalence of hearing loss which are mainly due to pre- ventable causes. While urban communities in LMICs are likely to have functional hearing healthcare delivery infrastructure, rural and semi-urban communities may have different reality. Objectives: This study aimed to provide: (i) a snapshot of the burden of ear diseases and (ii) a description of available hearing healthcare resources in a semi-urban Nigerian community. Methods: A cross-sectional study of households selected by multistage random sampling technique. Seventy-four partici- pants: 39 males and 35 females with mean age of 34 years ± 5.24 were recruited and answered a structured questionnaire. In addition, the availability of hearing healthcare services in 15 health centers within the community were determined. Results: All participants reported recent occurrence of ear complaints or gave similar history in a household member. Com- mon complaints were ear discharge, ear pain and hearing loss. Medical intervention was sought from patent medicine stores, hospitals and traditional healers. None of the assessed hospitals within the study site was manned by an ENT surgeon or ENT trained nurse. Conclusion: Despite the heavy burden of ear complaints there is inadequate hearing healthcare delivery in a typical LMIC community. This highlights the need for urgent improvement of hearing healthcare. Keywords: Hearing loss; healthcare delivery; disease burden; ear diseases; developing countries.

An Assistive Role of a Machine Learning Network in Diagnosis of Middle Ear Diseases

The present study aimed to develop a machine learning network to diagnose middle ear diseases with tympanic membrane images and to identify its assistive role in the diagnostic process. The medical records of subjects who underwent ear endoscopy tests were reviewed. From these records, 2272 diagnostic tympanic membranes images were appropriately labeled as normal, otitis media with effusion (OME), chronic otitis media (COM), or cholesteatoma and were used for training. We developed the “ResNet18 + Shuffle” network and validated the model performance. Seventy-one representative cases were selected to test the final accuracy of the network and resident physicians. We asked 10 resident physicians to make diagnoses from tympanic membrane images with and without the help of the machine learning network, and the change of the diagnostic performance of resident physicians with the aid of the answers from the machine learning network was assessed. The devised network showed a highest accuracy of 97.18%. A five-fold validation showed that the network successfully diagnosed ear diseases with an accuracy greater than 93%. All resident physicians were able to diagnose middle ear diseases more accurately with the help of the machine learning network. The increase in diagnostic accuracy was up to 18% (1.4% to 18.4%). The machine learning network successfully classified middle ear diseases and was assistive to clinicians in the interpretation of tympanic membrane images.

Ultrasound Microbubbles Enhance the Efficacy of Insulin-Like Growth Factor-1 Therapy for the Treatment of Noise-Induced Hearing Loss

The application of insulin-like growth factor 1 (IGF-1) to the round window membrane (RWM) is an emerging treatment for inner ear diseases. RWM permeability is the key factor for efficient IGF-1 delivery. Ultrasound microbubbles (USMBs) can increase drug permeation through the RWM. In the present study, the enhancing effect of USMBs on the efficacy of IGF-1 application and the treatment effect of USMB-mediated IGF-1 delivery for noise-induced hearing loss (NIHL) were investigated. Forty-seven guinea pigs were assigned to three groups: the USM group, which received local application of recombinant human IGF-1 (rhIGF-1, 10 µg/µL) following application of USMBs to the RWM; the RWS group, which received IGF-1 application alone; and the saline-treated group. The perilymphatic concentration of rhIGF-1 in the USM group was 1.95- and 1.67- fold of that in the RWS group, 2 and 24 h after treatment, respectively. After 5 h of 118 dB SPL noise exposure, the USM group had the lowest threshold shift in auditory brainstem response, least loss of cochlear outer hair cells, and least reduction in the number of synaptic ribbons on postexposure day 28 among the three groups. The combination of USMB and IGF-1 led to a better therapeutic response to NIHL. Two hours after treatment, the USM group had significantly higher levels of Akt1 and Mapk3 gene expression than the other two groups. The most intense immunostaining for phosphor-AKT and phospho-ERK1/2 was detected in the cochlea in the USM group. These results suggested that USMB can be applied to enhance the efficacy of IGF-1 therapy in the treatment of inner ear diseases.

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.