HOW IT WORKS?
With Otometri mobile app you can measure ears in seconds. On your phone screen you can instantly see the follow-up results and measurement history of your child. Instructions and help are included in the mobile app. The measurement is based on acoustical analysis of the ear. Selection of tiny acoustical stimulus are sent to ear. The response is analyzed with artificial intelligence based data-analysis - producing the image "red-yellow-green" of the ear condition. All this happens in seconds - being easy and comfortable for the patient – and what is the best – producing reliable reference image. Otometri® is simple to use:
1. Download and install the Otometri app
2. Attach the Otometri® measurement device to your mobile phone
3. Plug in the device via the phone’s headphone jack
4. Calibrate for accuracy
5. Measure and see instant results on your mobile phone screen:
- Green: Middle ear status is most likely normal.
- Yellow: Slightly increased risk of ear infection. Follow up is advised.
- Red: High risk of ear infection.
Easy to use measurement device
The Otometri measurement device is easy to attach to your phone. The snap-type mechanical clip is attached to smart phones of different models. The electrical connection is done with the earphone connector. No need for pairing - no need of batteries or charging.
Benefits of Otometri
Otometri provides you essential information of ear's status - and is especially useful during middle ear infection suspicions. The measurement history helps both parents and physicians in decision making – whether there is any reason to see doctor - and for doctors the data produces additional information about the ears. The measurements are also beneficial in follow up of situation of ears after diagnosed ear infection. Otometri creates better situational awareness and safety in middle ear suspicions and therefore improves ability for correct diagnosis. Nowadays – it is essential to aim for reducing antibiotics, which in earlier days were often used too liberally in middle ear infections and suspicions.
SCIENTIFIC AND CLINICAL BACKGROUND
The acoustic analysis is based on well established Acoustic Reflectometry (AR) and data analysis on artificial neural networks (ANN), both having a substantial amount of research behind. The performance of the AR in middle ear effusion analysis is comparable with the ear evaluation methods typically applied by professionals (tympanometry, pneumatic otoscope). The principle, quality surveillance and benefits of Otometri in health care has been evaluated with good results.
Results of the measurements
The measurement principle of Otometri is acoustic reflectometry [1-5] combined with artificial neural networks technology [6-9]. The measurement evaluates properties of tympanic membrane with help of small sound stimulus. If the functioning of tympanic membrane is decreased due to inflammation fluid in the middle ear it alters correspondingly the sound stimulus, which is analyzed using artificial intelligence system of Otometri.
Clinical Performance of acoustic reflectometry
Otometri follow operationally well-established Acoustic Reflectometry (AR) principles, known and studied since 1984. Otometri will continuously enhance the clinical performance of the system due to recent studies, referring to its cumulative artificial intelligence principle. Otometri provides impressive information of status of ears in visual easy-to-read format. This means improved follow-up according to revised medical recommendations of middle ear infection care; e.g. to monitor the ear infection situation three days - on the basis of spontaneous recovering -if possible.
Performance of Otometri compared to tympanometry
Tympanometry is widely used by professionals for evaluation of tympanic membrane. In previous studies Acoustic Reflectometry and Tympanometry has been compared in number of studies with good results; in a study by Barnett & et al (Comparison of spectral gradient acoustic reflectometry and other diagnostic techniques for detection of middle ear effusion in children with middle ear disease, Pediatr Infect Dis J, 1998; 17:556-559) it is summarized "SG-AR is easy to use, is comparable with pneumatic otoscopy and tympanometry in identifying the presence or absence of MEE..." (SG = Spectral Gradient). In an another study by Puhakka & al (Tympanometry for detection of middle ear effusion in children, The Pediatr Infect Dis J, 2014; 33:8) it is summarized "The test characteristics of SGAR and tympanometry for the detection of MEE diagnosed by pneumatic otoscopy were comparable" (MEE = Middle Ear Effusion). More recent clinical studies about the topic can be found from here.
Artificial intelligence in Otometri
The core of Otometri is cumulative artificial intelligence (AI) based analysis in cloud. Currently, Otometri holds world's largest uniform database of Acoustic Reflectometry measurements. The amount of data is increasing continuously – on the basis of increasing measurements. Daily the AI of Otometri checks if there exists - globally - any relevant new information, which should be taken into account in evaluation of predictability and reliability of Otometri operational algorithms. If needed, the AI of Otometri is automatically tuned for better performance. The cloud operations are automatically updated - utilizing the upcoming Otometri measurements.
 Linden H, Teppo H & Revonta M (2006) Spectral gradient acoustic reflectometry in the diagnosis of middle-ear fluid in children. Eur. Arch Otorhinolaryngol 264:477-481.
 Chianese J, Hoberman A, Paradise JL, Colborn DK, Kearney D, Rockette HE & Kurs-Lasky M (2007) Spectral gradient acoustic reflectometry compared with tympanometry in diagnosing middle ear effusion in children aged 6 to 24 months. Arch Pediatr Adolesc Med 161(9): 884-888.
 Walsh FP, Cox LC & MacDonald CB (1998) Historic perspective of the acoustic otoscope. J Am Acad Audiol 9: 35-40.
 Block SL, Pichichero ME, McLinn S, Aronovitz G, Kimball S (1999) Spectral Gradient Acoustic Reflectometry: Detection of Middle Ear Effusion in Suppurative Acute Otitis Media. The Pediatric Infectious Journal 18(8): 741-744.
 Teele DW & Teele J (1984) Detection of middle-ear fluid by acoustic reflectometry. J Pediatrics 104: 832-838.
 S. Haykin (1999) Neural networks, a comprehensive foundation. Prentice Hall, Upper Saddle River.
 Hannula M, Hinkula H, Holma T, Lofgren E and Sorri M (2009) Artificial Neural Network Analysis in Evaluation of Ear Canal and Tympanic Membrane Properties from Acoustic Reflectometry Data. Proceedings of 11th World Congress on Medical Physics and Biomedical Engineering.
 Hannula M, Holma T, Lofgren E, Hinkula H and Sorri M (2011) Preliminary results of clinical tests of a new neural-network-based otitis media analysis system. Proceedings of NCTA 2011 -conference, France, 2011
 Hannula M, Hirvikoski A, Hinkula H and Holma T (2008) Application of artificial neural network in analysis of acoustic reflectometry data. Proceedings of Artificial Intelligence Applications Conference, Innsbruck, Austria, 2008.