Smartphone-enabled otoscopy: method evaluation in clinical practice

Kravchychyn, Fernanda Dal Bem; Meurer, Ana Taíse de Oliveira; Nogueira, Maria Helena Salgado Delamain Pupo; Balieiro, Fernando Oto; Balsalobre, Fernando de Andrade; Filho, Iulo Sérgio Barauna; Stamm, Aldo Eden Cassol

doi:10.1016/j.bjorl.2021.08.012

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Buyn et al evaluated the benefit of a DL-enabled digital otoscopy model designed to help residents diagnose middle-ear diseases and showed an increase of 7% in accuracy 15 . DL-enabled otoscopy also has potential applications in telemedicine 24 , 25 : patients could acquire otoscopic images themselves and then send them for DL-assisted interpretation. At the moment, because the test set evaluation only points to high accuracy for distinguishing between normal vs. abnormal images and detecting wax plugs, i-Nside’s primary utility appears to lie in the triage of patients for targeted referrals.…”

Section: Discussionmentioning

confidence: 99%

“…The i-Nside diagnostic system could have several roles in managing patients with suspected middle-ear conditions 23 . In remote areas and resource-limited settings, the DL-enabled system could be used as a triage test for mass screening and targeted referral [24][25][26][27] . In primary care, where clinicians may lack expertise in otoscopy, i-Nside could be used as an add-on test to help improve the accurate detection of middle-ear conditions, in line with the principles of "augmented medicine" 28 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images

Dubois,

Eigen,

Simon

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

Middle-ear conditions are common causes of primary care visits, hearing impairment, and inappropriate antibiotic use. Deep learning (DL) may assist clinicians in interpreting otoscopic images. This study included patients over 5 years old from an ambulatory ENT practice in Strasbourg, France, between 2013 and 2020. Digital otoscopic images were obtained using a smartphone-attached otoscope (Smart Scope, Karl Storz, Germany) and labeled by a senior ENT specialist across 11 diagnostic classes (reference standard). An Inception-v2 DL model was trained using 41,664 otoscopic images, and its diagnostic accuracy was evaluated by calculating class-specific estimates of sensitivity and specificity. The model was then incorporated into a smartphone app called i-Nside. The DL model was evaluated on a validation set of 3,962 images and a held-out test set comprising 326 images. On the validation set, all class-specific estimates of sensitivity and specificity exceeded 98%. On the test set, the DL model achieved a sensitivity of 99.0% (95% confidence interval: 94.5–100) and a specificity of 95.2% (91.5–97.6) for the binary classification of normal vs. abnormal images; wax plugs were detected with a sensitivity of 100% (94.6–100) and specificity of 97.7% (95.0–99.1); other class-specific estimates of sensitivity and specificity ranged from 33.3% to 92.3% and 96.0% to 100%, respectively. We present an end-to-end DL-enabled system able to achieve expert-level diagnostic accuracy for identifying normal tympanic aspects and wax plugs within digital otoscopic images. However, the system’s performance varied for other middle-ear conditions. Further prospective validation is necessary before wider clinical deployment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images

Dubois,

Eigen,

Simon

et al. 2024

npj Digit. Med.

View full text Add to dashboard Cite

show abstract

“…Outcomes were selected based on performance characteristics commonly reported in the literature from previously studied otoscopes, including the 3D-printed otoscope by Capobussi and Moja (19), digital otoscopes (20), smartphone otoscopes (21,22), and the solar-powered Arclight otoscope. (23) Additionally, the research team, by consensus, selected the most wavelengths in the range of approximately 430 nm to 670 nm, with a full-width half-max of 40 nm, through an integrated aperture that provides a ±20 º field of view.…”

Section: Benchtop Evaluationmentioning

confidence: 99%

Design and Validation of a Low-Cost, Open-Source, 3D-Printed Otoscope

Lowe,

Bagha,

Inayat

et al. 2023

Preprint

View full text Add to dashboard Cite

The modern otoscope is an indispensable instrument utilized by primary care physicians as the gold standard tool to diagnose an array of otologic diseases and conditions. At present, commercially available, traditional otoscopes remain cost-prohibitive to many potential users despite limited innovation since its invention in the early 19th century. In this publication, the design and assembly of a low-cost, open-source, 3D-printed otoscope, the Glia Otoscope V1.0, is outlined. Subsequently, we describe the benchtop evaluation conducted, which measured several outcomes relevant to otoscopy performance against a traditional, gold standard otoscope, the Welch Allyn Rechargeable V3.5 Halogen HPX Otoscope. Measured outcomes included illuminance, correlated color temperature, color rendering index, spatial resolution, field of view, weight, battery life, and cost. Overall, the Glia Otoscope V1.0 demonstrated comparable performance across measured outcomes against the traditional otoscope. Further validation in the clinical setting is warranted as the Glia Otoscope V1.0 and its future iterations hold tremendous potential in improving access and alleviating the burden of otologic disease in lower and middle-income countries. Finally, we present a novel tool, the Otoscope Assessment Tool, which establishes a standard set of performance characteristics for benchtop evaluation of otoscope performance.

show abstract

Smartphone-based video-otoscopy performed by non-ENT physicians as a complementary tool to conventional otoscopy for tympanic membrane diagnosis

Fuentes

2023

Speech, Language and Hearing

View full text Add to dashboard Cite

Smartphone-enabled otoscopy: method evaluation in clinical practice

Cited by 3 publications

References 14 publications

Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images

Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images

Design and Validation of a Low-Cost, Open-Source, 3D-Printed Otoscope

Smartphone-based video-otoscopy performed by non-ENT physicians as a complementary tool to conventional otoscopy for tympanic membrane diagnosis

Contact Info

Product

Resources

About