G. 2095  
Page 1  
Global Research journal of Natural Science  
& Technology (GRJNST)  
Volume: 04 - Issue 3 (2026), 2095  
ISSN P: 2790-7643 ISSN E: 2790-7651  
www.grjnst.net  
https://doi.org/10.53762/grjnst.04.03.16  
Digital Pure Tone Audiometer: A Smart and Self-Administered Hearing  
Test System  
Received: 02 April 2026. Accepted: 06 May 2026. Published: 30 May 2026  
Pareesa Shoro  
Institute of Biomedical Engineering and Technology,Faculty of Basic Medical Sciences,  
Liaquat University of Medical and Health Sciences, Jamshoro, 76090, Pakistan  
pareesabuxshoro@gmail.com  
Aliza  
Institute of Biomedical Engineering and Technology, Faculty of Basic Medical Sciences,  
Liaquat University of Medical and Health Sciences, Jamshoro, 76090, Pakistan  
alizarana43@gmail.com  
Hamna Khan Alias Palwasha  
Institute of Biomedical Engineering and Technology, Faculty of Basic Medical Sciences,  
Liaquat University of Medical and Health Sciences, Jamshoro, 76090, Pakistan  
hamnakayy@gmail.com  
Saeed Ahmed Maitlo (Corresponding Author)  
Institute of Biomedical Engineering and Technology, Faculty of Basic Medical Sciences,  
Liaquat University of Medical and Health Sciences, Jamshoro, 76090, Pakistan  
saeed.maitlo@lumhs.edu.pk  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
Copyright © 2026 GRJNST. This article is published under an Open Access model. It is made available to the public under the terms of the Creative  
Commons Attribution 4.0 International (CC BY 4.0) license, which permits unrestricted use and distribution  
G. 2095  
Page 2  
Sarmad Shams  
Institute of Biomedical Engineering and Technology, Faculty of Basic Medical Sciences,  
Liaquat University of Medical and Health Sciences, Jamshoro, 76090, Pakistan  
sarmad.shams@lumhs.edu.pk  
Abstract:  
Hearing loss affects over 430 million people globally, with the World  
Health Organization projecting this figure to rise to 700 million by 2050.  
Despite its prevalence, access to affordable and accurate diagnostic tools  
remains limited, particularly in low-resource settings. Traditional  
audiometry systems rely on complex hardware and proprietary software,  
limiting their scalability and adaptability. This device reimagines such  
systems by utilizing open-source technologies to create a user-friendly  
device. The core problem lies in bridging the gap between affordability and  
diagnostic accuracy while ensuring compliance with international  
audiometric standards. The solution integrates a Raspberry Pi with  
headphones and a touchscreen interface, capable of performing pure-tone  
audiometry across frequencies (125 Hz–8 kHz) at intensities up to 120  
decibel Hearing Level. Key features include automated threshold detection,  
real-time audiogram visualization, and dual operational modes  
(manual/auto) to accommodate diverse clinical workflows. The auto mode  
uses adaptive algorithms to reduce testing time, while the manual mode  
allows clinicians fine control for unusual cases. The procedures  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 3  
encompassed iterative prototyping, software development for tone  
generation and response logging, and rigorous clinical validation.  
Calibration was performed using a reference sound level meter, while  
usability metrics (e.g., touch responsiveness, test duration) were quantified  
through timed trials. Results demonstrated a mean threshold deviation of  
±4 decibel Hearing Level compared to the commercial device. Testing  
involved 49 participants, including clinicians and patients, to evaluate  
accuracy, usability, and efficiency. This device underscores the viability of  
open-source, low-cost solutions in bridging healthcare disparities, offering a  
scalable model for hearing loss diagnosis.  
Keywords: Audiometric testing, Digital pure tone audiometer, Patient  
response, Raspberry-pi, Real-time representation, User interface  
1
INTRODUCTION  
Auditory loss is a widespread health issue affecting millions of people across  
the globe. According to the World Health Organization, around 1.5 billion  
individuals currently live with some degree of Auditory loss and this figure is  
expected to rise to over 2.5 billion by 2050 [1]. This progressing problem  
creates challenges not only for those directly impacted but also for society, as it  
causes emotional and financial difficulties. It is estimated that untreated  
hearing impairments result in global financial fatalities amounting to hundreds  
1
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 4  
of billions of dollars every year, including costs associated to lost productivity  
and healthcare. This highlights the importance of early diagnosis and intrusion  
to decrease the long-term consequences of hearing loss. One of the most  
effective methods accessible for diagnosing hearing loss is pure-tone  
audiometry. It is stared as the gold standard for evaluating a person's sensitivity  
to innumerable sound frequencies and figuring out the lowermost decibel levels  
they can perceive.  
The information obtained from pure tone audiometry is crucial for creating  
successful hearing treatment plans in addition to diagnosis. For those who use  
hearing aids, audiograms let audiologists adjust devices to each person's unique  
hearing necessities. Pure tone audiometry is used to evaluate eligibility and  
establish expectations for post-surgery hearing outcomes in instances that  
require cochlear implants [2].  
Due to financial restrictions, many healthcare amenities find it difficult to  
purchase the required technology, especially those in underserved or rural  
locations. The public health problem of untreated hearing loss may deteriorate  
as a result of this financial restriction, which may prevent early detection and  
care [3]. For conventional audiometers to function efficiently, specific training  
is repeatedly needed. If workers are not appropriately skilled, the  
multifariousness of testing procedures and equipment calibration may result in  
inconsistent outcomes. Due to the need for experienced staff, audiometric  
evaluations can only be achieved in a limited number of locations, including  
community health centres and other non-specialized settings [4].  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 5  
In order to improve diagnosis accuracy and produce further personalized  
treatment strategies, the audiometry device and results facilitate by production  
of vital information on the kind and severity of hearing loss along with other  
associated diseases, i.e, rheumatoid arthritis [5]. The audiometer helps with  
consistent audiometric data collection, which is crucial for figuring out the  
pervasiveness and effects of hearing loss, in addition to its diagnostic benefits.  
Public health drives and the design of plans to improve hearing health more  
broadly can both benefit from such data [6]. By reassuring more people to get  
assessments and take preemptive action, it can endorse improved auditory  
health in various populations [7].  
The project advances audiology and improves user experience by leveraging  
components such as the Raspberry Pi and IQ Audio DAC (Digital to Analog  
Converter). This audiometer's adaptability makes it appropriate for use in a  
variety of settings, such as community health programs, educational  
institutions, and clinical settings, which ensures that hearing assessments can be  
carried out in a variety of settings, meeting the demands of various  
populations. Additionally, this system allows efficient data sharing and  
communication. The audiometer's original features complement the most  
recent developments in medical technology. Furthermore, the project can  
reduce financial problem that untreated hearing loss places on healthcare  
systems to assist early identification and interference [8].  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 6  
In 2018, a MATLAB-based audiometry system was developed, using a  
modified Hughson-Westlake procedure for efficacious detection of hearing  
thresholds [9]. This design featured a bi-aural audiogram comparator with a  
GUI (Graphic User Interface) that allows a clinician to compare bilateral  
audiograms. In 2020, a significant leap toward self-administered hearing  
assessments was represented by the open-source Python audiometer.  
Constructed on a Raspberry Pi 3 B+, this device automated the Hughson-  
Westlake protocol, allowing users to conduct audiometric tests independently  
[10]. The result was an audiogram, in a format that showed the results of the  
assessment and allowed the kind of data sorting and organizing that enhanced  
the ability to make use of the results. A model was introduced in 2020,  
offering an architecture for MVVM-based (Model-view-viewmodel based)  
hearing diagnosis applications. The modularity in design helped keep the app  
manageable, provided a means to apply its parts elsewhere, and assisted in  
conceptualizing data standards clinicians might grasp in workflow contexts.  
Testing by an otolaryngologist it demonstrated heightened efficiency in  
diagnostics but required considerable medical proficiency to translate its results  
for the deaf and hard of hearing [11]. A work in 2022 presented an audiogram  
digitization algorithm for insurance. It claimed adjudication with 5dB  
(Decibel) accuracy in scanned report threshold extraction. The open-source  
solution combined computer vision with JSON (JavaScript Object Notation)  
output generation, minimizing adjudication time via semi-automated data  
conversion [12]. In 2022, researchers used machine learning to identify  
auditory thresholds by building a binary classification model using SVM  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 7  
(Support Vector Machine), in which 3 kernls were used. The audiograms and  
data were collected through a smartphone application, for subjects between the  
ages of 18 to 22 years [13]. In 2023, was confirmed a teleaudiology system  
which compared on-site and remote pure-tone thresholds in 50 participants.  
The KUDUwave audiometer with 5G connectivity revealed ≤3dB differences  
between test conditions, proving suitability for rural use [14]. The 2023 low-  
cost audiometer used consumer grade materials and achieved ±1% intensity  
error [15]. 2024 witnessed an internet-based hearing check tool for Japanese  
health examinations. 92% concordance was evident with respect to clinical  
audiometry [16]. Year 2024 developments involved a decision tree based  
hearing loss classification mobile audiometry app. The hardware calibrated,  
cross platform solution featured educational content, with clinical-grade  
frequency range coverage [17]. In 2025 mobile phone audiometry study  
obtained 90% accuracy at thresholds greater than 40 dB in detecting mild loss  
through adaptive step size algorithms [18].  
Methods and Procedures  
The methodology involves the hardware assembly, software configuration and  
development of graphic user interface to ensure the user friendly audiometry. It  
includes the software and hardware integration. This prototype needs the  
components of Raspberry Pi 3 model B, IQaudio DAC, patient response  
button, 7 inch HDMI (High Definition Multimedia Interface) display, Audio  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 8  
stereo plug adapter, TRRS (Tip Ring Ring Sleeve) stereo breakout extension  
board, headphones and an adapter for power supply. Raspberry Pi, provides  
enough computational power to encourage the audiometry testing. The  
audiologist will decide the type of audiometry to be performed, i.e., manual  
audiometry and auto audiometry. The patient is to wear the headphones and is  
given a patient response button, then the audiologist will start the audiometry  
process.  
The IQaudio DAC ensures the quality of the audio output in the headphones  
by efficiently converting a digital signal into an analog signal. HDMI  
touchscreen provides a user friendly interface to the audiologist for selection of  
the audiometric testing parameters. When the patient responds positively the  
further testing will continue, and if they respond negatively, then the audio  
signal threshold gets displayed on the audiometer. The process of this  
audiometry process is shown in Fig.1.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 9  
Fig. 1. Flow chart of pure tone audiometry process.  
The final audiometry result in the form of an audiogram can be displayed in  
the pdf form as well upon generation of a report by an audiologist. The digital  
pure tone audiometer ensures accomplishment of the guidelines of WHO and  
12 ASHA (American Speech Language Hearing Association).  
A. Hardware Interface  
The hardware of the system interfaces with the application, which is controlled  
by the caretaker. A single-board Raspberry Pi 3 Model B operates as the core  
processor unit that runs every program while managing both the device  
interface and data logging and response controls. The GPIO (General Purpose  
Input/Output) headers together with USB (Universal serial Bus) and HDMI  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 10  
ports on this device enable users to easily connect various peripheral  
components. The audio output functions of the Raspberry Pi operate through  
its connection to an IQaudio DAC device which interfaces with the 40-pin  
GPIO header. The DAC device reinforces the Raspberry Pi's standard sound  
quality to generate minimal distortion stereo at high resolution outputs needed  
for diagnostic testing precision. A stereo jack at the DAC produces analog  
audio signals which are transmitted to patient earpieces powered by P9 Pro  
Max Headphones configured with the main unit. The system interaction is  
equipped with a 7-inch HDMI touchscreen display for operation. The HDMI  
connector and USB interface enable convenience so the audiologist can operate  
the system through its graphical user interface by connecting the display to the  
Raspberry Pi. Users of this interface have real-time access for adjusting test  
parameters and initiating sessions as well as reviewing obtained results. During  
testing the patient relies on the response button to show their perception of a  
detected tone. It is connected to Raspberry Pi GPIO pins by targeting a digital  
input pin and 3.3V (VCC) or GND based on pull-up or pull-down logic  
configuration. GPIO monitoring operates within the system program to detect  
button events so the system delivers precise real time response evaluation  
during testing procedures. A system power supply comes from a 5V/2.5A  
micro USB power adapter which provides power to both the Raspberry Pi and  
its connected peripherals simultaneously. The system's block diagram is  
displayed in Fig. 2.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 11  
Fig. 2. Block diagram of the system.  
B. Software Interface  
Software development in making of this audiometry system is based on  
object-oriented and modular programming techniques using the Python  
programming language and related libraries. Source code was divided into  
many ‘.py’ modules to enable separation of concerns, e.g., one module  
controlled the main interface (audiometer_app.py), another the patient data  
input (patient_data.py), and one for tone generation (sound_module.py).  
Helper files like storage of audio samples, font assets, background graphics,  
and PDF (Portable Document Format) templates were organized in an  
ordered directory structure for portability and ease of maintenance. The  
AudiometerApp class is responsible for event driven reaction to user actions  
coordinates playback of tones by frequency and volume selections and  
refreshes the graphical audiogram in real time. It keeps the application state  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 12  
intact, with ear side switching, frequency progressions, and patient responses  
recorded accordingly. When a tone generation request is received, the Signal  
Processing Layer generates the requested signal. This is accomplished via a  
sine wave generator algorithm in Equation (1).  
(1)  
Where f is the chosen frequency, A is the amplitude (adjusted according to the  
chosen dB level), and t is the time vector for tone duration (typically 1–2  
seconds). Upon triggering a test tone a sine wave of the selected parameters is  
generated and played through the audio output channel. The tone is then  
played out through the system's default sound (headphones) through the use of  
the library. Volume is programmed to correspond to the chosen dB level,  
adjusted through scaling the waveform amplitude. When the test is complete,  
the user may generate a report consisting of the audiograms, and patient  
information. Fig. 3 shows the system after the integration of the hardware  
components and software algorithms used to make the digital pure tone  
audiometer.  
Fig. 3. Final layout of designed system.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 13  
Results and discussion  
The results and accuracy of calibration of the audiometry system were obtained  
through a comparison between expected and actual values for decibels (dB).  
The study involved measuring error margins in terms of amplitude (dB) to  
check the technical capability of the system. In order to ensure the accuracy of  
dB levels derived, sound level meter (SLM) mobile application was used.  
Standard pure tones (e.g., 1 kHz to at 20 to 80 dB HL) were presented and  
then were analyzed by SLM app. Error (dB) values are calculated for each value  
using (2).  
(2)  
The experimental observations and the calculated error are summarized in  
Table I. The relationship is defined as follows:"  
EdB  
is the calculated error in decibels;  
Sexp  
represents the expected sound pressure level;  
Smeas  
denotes the measured sound pressure level recorded by the application.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 14  
TABLE I  
OBSERVED VALUES AND CALCULATED ERROR IN DB  
Frequency (Hz)  
Expected dB  
Measured dB (App)  
Error (dB)  
+4.0  
-2  
1000  
2000  
500  
20  
30  
40  
65  
70  
16  
32  
37  
57  
68  
+3.0  
+8.0  
+2.0  
125  
4000  
This method is reliant on the constraint of accuracy placed on consumer-  
decibel meter applications. Contrary to professional sound level meters  
complying with industry standards of calibration, mobile apps used in this  
experiment tend to display an error tolerance between ±2 and ±5 dB. These  
differences are the result of various smartphone microphone capacities, ambient  
noises, and capability limitations of mobile digital signal processing. Therefore,  
while the app's output is a fairly close approximation of real sound pressure  
levels, it cannot be depended on for clinical or regulatory-quality accuracy.  
Clinical testing of the developed audiometer system was carried out to validate  
its performance characteristics in medical settings under careful supervision.  
Testing the device appealed to both patients and volunteers under guidance to  
compare its functionality versus standard clinical audiometers. From February  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 15  
17th, 2025 to April 2nd, 2025, audiometric records were collected from 49  
subjects using this system. Of these patients, 38.8% were male and 61.2% were  
female. The average age was 23.6 years. The mean hearing level (in decibels,  
dB) is reported for frequencies of 500 Hz, 1000 Hz, 2000 Hz and 4000 Hz.  
The mean hearing level for all patients was 28.98 dB (±24.1) in the right ear  
and 24.69 dB (±24.1) in the left. Using this audiometry device, the raw data  
can be retrieved and used with statistics software. For example, the distribution  
of the mean hearing levels at different age groups can be calculated in a short  
time typical of hearing decline can be observed with increasing age or another  
trait. Measurement results enable both validation of the device performance  
while directing to enhance functionality.  
The bar chart in Fig.4 compares hearing loss severity between right and left ears  
across 49 individuals. Statistical analysis reveals that 71.4% of right ears (35  
patients) exhibit mild hearing loss (21-40 dB), while left ears show a higher  
proportion of slight loss (30.6%, 15 patients). The right ear’s higher severity  
suggests potential asymmetric noise exposure or physiological dominance, as  
observed in occupational hearing damage. Only 1 patient (2%) reached  
moderately severe loss in the right ear, indicating most cases are mild.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 16  
Fig. 4. Right ears show higher rates of mild impairment (71.4%) compared to  
left ears (57.1%)  
The audiometric results shown a chart in Fig. 5 stratifies hearing loss by gender,  
revealing 61.2% of patients are women (30/49), but men dominate moderate cases  
(e.g., 4/5 moderate right-ear cases). Women cluster in slight/mild categories (e.g.,  
12/15 slight left-ear cases), possibly due to lower noise exposure or hormonal protective  
effects. Men’s higher moderate rates (e.g., 60 dB right ear) align with studies linking  
male occupations to noise-induced loss.The subjects under 20 exhibit normal/slight loss  
(e.g., 11/23 cases), while 40+ group has 5/12 in moderate+. The 30–40 bracket  
marks the transition, with 4/16 patients showing moderate+ loss, suggesting  
presbycusis onset.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 17  
Fig. 5. Women comprise 61.2% of cases but dominate milder categories (80% of  
slight losses)  
The audiograms of developed system and a clinical device were compared, by  
subjecting an individual to audiometry from both devices. Mentioned in Fig. 6  
and Fig. 7 is the comparison between audiograms of this developed device and  
that of a clinical audiometer, namely Amplivox (Model 270).  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 18  
Fig. 7. Audiogram obtained via the developed system shows thresholds for the same subject,  
demonstrating diagnostic grade accuracy by showing strong agreement (<5dB difference) with  
clinical audiometer  
Fig. 6. Pure-tone audiogram from clinical audiometer (Amplivox 270) showing thresholds at standard  
frequencies. Circles for right ear (left plot) and crosses for left ear (right plot) indicate air conduction.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 19  
This direct subject specific validation demonstrates the functional accuracy of  
the developed system relative to standard clinical results this analysis confirms  
consistency and reliability. The device also underwent clinical evaluation by a  
licensed practitioner to validate its performance in preliminary hearing  
assessments. The evaluation confirmed that the device operates satisfactorily for  
air conduction testing in controlled clinical environments, meeting standards of  
accuracy, safety and usability within its intended scope.  
The analysis of the audiometry system uncovered various aspects especially  
experimental results that varied from predicted values. The dB level accuracy  
variations were noted during calibration testing, when the system's output was  
compared to reference measurements, with most discrepancies arising within a  
±3 dB range for the majority of frequencies. These variations were most  
significant at far ends of the frequency range (125 Hz and 8 kHz). Relative  
error percentages determined over test frequencies averaged 2.8%, marginally  
above the desired threshold of 2%, indicated potential for enhancement in  
signal generation accuracy. Frequency accuracy held steady at ±1.2% of  
intended values, although intermittent anomalies cropped up in simultaneous  
multifrequency testing, presumably from allocation of processing resources  
within the audio generation subsystem. Some test cases exhibited significant  
departures from predicted results that are worthy of special consideration. On  
12% of auto mode threshold detection, the algorithm detected thresholds 5-10  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 20  
dB greater than those in manual mode for identical subjects, especially at 4 kHz  
frequencies. This difference seemed associated with the system's conservative  
method of incrementing amplitude when there was no response, tending to  
overestimate the actual threshold of the digital pure tone audiometer.  
Conclusion  
The designed audiometry system is effective to get hearing threshold and  
through its dual modes it achieves automatic frequency progression through its  
system design to provide efficient testing and maintain uniform test results  
while shortening the evaluation duration. The combination of automatic data  
presentation with resulting outputs displayed as graphs allows the patient and  
clinician to quickly understand evaluation data better.  
This audiometer supports better treatment standards during hearing tests by  
getting rid of the problems and variations of traditional analog instruments.  
Provides real-time graphical representations of air conduction test results which  
increases clinical information sharing during diagnosis. This visual feedback  
pre-sent in the audiometer enables instant communication between clinician  
and patient about their hearing abilities. Clear and easy to read result  
presentation helps clinical practitioners make better decisions in their work.  
The designed audiometer brings both affordable operation and comprehensive  
functionality to offer better access for healthcare providers and their patient  
populations during advanced hearing tests.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 21  
Future work  
There are some ideas to make it more useful. By expanding its functionality  
through additional testing features that include speech audiometry and  
extended frequency range testing. These inclusion tests will give professionals  
the ability to examine various aspects of a patient's hearing abilities for  
comprehensive diagnosis. The application and integration of AI (Artificial  
Intelligence) features shall enable predictions of hearing loss advancement  
through evaluation data and medical indicators for delivering enhanced targeted  
patient care. Teleaudiometry can also prove to be convenient. Through the  
deployment of mobile application, individuals will gain the ability to schedule  
tests, track their progress, view their results in graphical form, store historical  
data for future reference and connect with experts from a distance.  
REFERENCES  
[1]  
[2]  
[3]  
W. H. Organization, World Report on Hearing. Geneva, Switzerland: WHO, 2021, ISBN:  
978-92-4-002049-8. [Online]. Available: www.who.int/publications/i/item/world-report-  
on-hearing. [Accessed: Aug. 17, 2024].  
A. C. Carl, M. H. Hohman, and J. Cornejo, "Audiology Pure Tone Evaluation," in  
StatPearls [Online]. Treasure Island (FL): StatPearls Publishing; 2023 Jan. Available:  
(www.ncbi.nlm.nih.gov/books/NBK580531).  
Jayawardena, Asitha & Waller, Bianca & Edwards, Bruce & Larsen-Reindorf, R & Anomah,  
Joyce & Frimpong, B & Gina, Ayanda & Netterville, James & Saunders, J & Basura, Gregory,  
“Portable audiometric screening platforms used in low-resource settings: A review”, The  
Journal  
of  
Laryngology  
&
Otology,  
vol.  
133,  
pp.  
1-6,  
2018,  
doi:  
10.1017/S0022215118001925.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 22  
[4]  
[5]  
M. F. Bhutta, X. Bu, P. C. de Muñoz, S. Garg, and K. Kong, "Training for hearing care  
providers," Bull World Health Organ, vol. 97, no. 10, pp. 691–698, 2019, doi:  
10.2471/BLT.18.224659.  
Hyemin Jeong, Young-Soo Chang, Sun Young Baek, Seon Woo Kim, Yeong Hee Eun, In  
Young Kim, Jaejoon Lee, Eun-Mi Koh, Hoon-Suk Cha, “Evaluation of audiometric test  
results to determine hearing impairment in patients with rheumatoid arthritis: Analysis of  
data from the Korean National Health and Nutrition Examination Survey,” PLoS ONE, vol.  
11, no. 10, p. e0164591, 2016, doi: 10.1371/journal.pone.0164591.  
[6]  
[7]  
Mandy K. Salmon, Jason Brant, Marc H. Hohman, Danielle Leibowitz, "Audiogram  
Interpretation," in StatPearls [Online]. Treasure Island, FL: StatPearls Publishing, 2025 Jan.  
Available: (www.ncbi.nlm.nih.gov/books/NBK578179).  
K. Cienkowski, D. Culbertson, K. Dowd, W. Kaf, A. K. Meehan, C. Mosley, A. Olson, G.  
Poling, G. Saunders, P. Souza, and B. Weinstein, "Adult Hearing Screening," American  
Speech-Language-Hearing  
Association  
(Online).  
Available:  
www.asha.org/Practice-  
Portal/Professional-Issues/Adult-Hearing-Screening/.  
[8]  
[9]  
V. Isnard, V. Chastres, and G. Andéol, "Description of a new low-cost and open-source  
audiometer and its validation with normal-hearing listeners: The Aupiometer," PLoS ONE,  
vol. 19, no. 8, p. e0306751, 2024, doi: 10.1371/journal.pone.0306751.  
M. Gargouri, M. Chaoui and A. Kachouri, "Conception of a Software Pure Tone  
Audiometer Application," 2018 15th International Multi-Conference on Systems, Signals &  
Devices (SSD), 2018, pp. 619-622, doi: 10.1109/SSD.2018.8570587.  
[10] M. Gargouri, M. Chaoui and P. Wira, "Development of hearing self-assessment pure tone  
audiometer," 2020 IEEE International Conference on Design & Test of Integrated Micro &  
Nano-Systems (DTS), 2020, pp. 1-5, doi: 10.1109/DTS48731.2020.9196165.  
[11] W. Sheikh and N. Sheikh, "A Model-View-ViewModel (MVVM) Application Framework  
for Hearing Impairment Diagnosis - Class Inheritance Architecture," 2020 Intermountain  
Engineering,  
Technology  
and  
Computing  
(IETC),  
2020,  
pp.  
1-6,  
doi:  
10.1109/IETC47856.2020.9249215.  
[12] F. Charih and J. R. Green, "Audiogram Digitization Tool for Audiological Reports," in  
IEEE Access, vol. 10, pp. 110761-110769, 2022, doi: 10.109/ACCESS.2022.3215972.  
[13] A. Gopinath, A. H, A. Loomba, R. Kumar and C. Narayanappa, "Data Driven Machine  
Learning Model for Audiometric Threshold classification," 2022 4th International  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16  
G. 2095  
Page 23  
Conference on Circuits, Control, Communication and Computing (I4C), 2022, pp. 236-  
239, doi: 10.1109/I4C57141.2022.10057711.  
[14] T. Denga, B. Malila and L. Petersen, "Synchronous Tele-audiology School-aged Hearing  
Screening in a Low-resource Community of Khayelitsha, Cape Town," 2023 IST-Africa  
Conference  
(IST-Africa),  
2023,  
pp.  
1-11,  
doi:  
10.23919/IST-  
Africa60249.2023.10187843.  
[15] W. Auccahuasi et al., "Methodology for the design of low cost medical devices for screaning  
use: audiometer case," 2023 International Conference on Sustainable Computing and Data  
Communication  
Systems  
(ICSCDS),  
2023,  
pp.  
1697-1701,  
doi:  
10.1109/ICSCDS56580.2023.10104670.  
[16] M. Ueda, K. Odagiri and T. Tanaka, "Development of a Convenient Hearing Test System  
for the Prevention of Frailty," in 2024 16th IIAI International Congress on Advanced  
Applied  
Informatics  
(IIAI-AAI),  
2024,  
pp.  
716-717,  
doi:  
10.1109/IIAI-  
AAI63651.2024.00150.  
[17] P. Kanimozhi, P. JebaSanthiya, T. A. Kumar, M. Hussain, C. Ananth, and E. Preethi,  
"Revolutionizing Hearing Health: Mobile-based Audiometry Assessment Enhanced by  
Machine Learning Integration," in 2024 8th International Conference on Inventive Systems  
and Control (ICISC), 2024, pp. 60–66. doi: 10.1109/ICISC62624.2024.00017.  
[18] S. Kumar, A. Dutta, S. Khan, A. Gupta, and J. Shivanand, "Smartphone-Based Audiometry:  
A Feasible Tool for Hearing Loss Screening," Indian Journal of Otolaryngology and Head &  
Neck Surgery. Head Neck, vol. 77, 2025. doi: 10.1007/s12070-025-05719-7.  
GRJNST, Volume: 04 - Issue 3 (2026) / ISSN P: 2790-7643  
Article ID: 2095  
https://doi.org/10.53762/grjnst.04.03.16