Vo
lu
m
e
5,
Fe
br
ua
ry
,2
02
5
,
M
ED
IC
AL
SC
IE
N
CE
S.
IM
PA
CT
FA
CT
OR
:7
,8
9
A QUESTIONNAIRE STUDY FOR DENTAL STUDENTS’ SATISFACTION WITH
“THE USE OF ARTIFICIAL INTELLIGENCE IN DENTISTRY’’
Axmadaliyev Qaxramonjon Xusanbayevich
Department of therapeutic dentistry
Andijan state medical institute
Abstract:
Background/purpose: Using artificial intelligence to “detect cephalometric
landmarks” can effectively improve dentist’s effectiveness. This study evaluated dental
students’ satisfaction with the use of artificial intelligence to detect cephalometric landmarks
in 2023 and 2024 at Tashkent State Dental Institute, Uzbekistan.
Keywords:
Artificial intelligence; Cephalometrics; machine learning.
Materials and methods:
For the use of detecting cephalometric landmarks artificial
intelligence-based applications have been very common in recent years. In Tashkent State
Dental Institute fifth-year dental students have been asked to complete an online-based
questionnaire with three survey questions regarding their satisfaction with the use of AI to
detect cephalometric landmarks using 5-point Likert scale ratings.
Results:
Seventy-six (89%) of 118 and 72 (96%) of 134 students answered the questions in
2023 and 2024 respectively. The satisfaction rates improved from 64% in 2023 to 81% in
2024. The satisfaction rate is 81% in 2024 for the use of AI to detect cephalometric
landmarks.
Conclusion:
The results of this study suggest that the inclusion of the using artificial
intelligence to detect cephalometric landmarks in 2024 marked an increase in satisfaction
rates than 2023.
Introduction
. A range of studies have explored the use of artificial intelligence in detecting
cephalometric landmarks, with promising results. Kafieh (2007) introduced a method
combining active shape models and a neural network, achieving high accuracy in landmark
detection. Chen (2011) proposed a deformable template approach, demonstrating both
accurate and efficient landmark identification. More recently, Junaid (2022) conducted a
systematic review of AI systems, highlighting the potential of deep learning-based
convolutional neural networks in achieving clinically acceptable diagnostic performance.
These studies collectively suggest that AI can significantly improve the accuracy and
efficiency of cephalometric landmark detection. Artificial intelligence (AI) is increasingly
being integrated into dentistry, with a focus on enhancing precision, efficiency, and patient
care. AI applications, such as CAD/CAM engineering and neural networks, are being used
to improve diagnosis, treatment planning, and surgical procedures. The use of AI in
dentistry is particularly beneficial in preventive healthcare, where it can aid in early
diagnosis and treatment optimization, leading to improved clinical outcomes and patient
experience . In orthodontics, AI has emerged as a particularly valuable tool, demonstrating
superior accuracy, precision, and time-efficiency in cephalometric landmark detection. The
study focused on assessing dental students' satisfaction with the use of artificial intelligence
Vo
lu
m
e
5,
Fe
br
ua
ry
,2
02
5
,
M
ED
IC
AL
SC
IE
N
CE
S.
IM
PA
CT
FA
CT
OR
:7
,8
9
(AI) in detecting cephalometric landmarks during 2023 and 2024. Surveys were utilized to
collect data on students' perceptions and satisfaction rates regarding AI applications. This
approach facilitated the analysis of prevailing trends and themes, providing insights into the
effectiveness of AI in dental education. By comparing students' perspectives, the study
aimed to enhance the development and improvement of AI technologies within dental
institutions. The findings could potentially lead to more accurate and efficient diagnostic
tools, ultimately benefiting both dental education and clinical practice.
Materials and methods.
This study evaluated dental students’ satisfaction with the use of
AI applications for detecting cephalometric landmarks at Tashkent State Dental Institute in
two successive years of 2023 and 2024. The fifth-year dentistry students in the Orthodontics
course were granted access to AI applications as a component of their normal curriculum.
The use of AI in orthodontics course consisted of detecting cephalometric landmarks and
doing various types of analyses like Downs, Kim’s as well as Steiner’s analysis instead of
manual analysing. Students used AI applications like WebCeph or CephX.
Following their courses, the students were promptly instructed to fill out an online
questionnaire consisting of three survey questions [4]. These questions aimed to gauge their
satisfaction with the utilization of AI applications, with scores provided on a 5-point Likert
scale. In addition, students have the option to submit unstructured textual feedback,
expressing either good or negative comments and suggestions regarding the utilization of AI.
This study was conducted in accordance with the principles outlined in the Declaration of
Helsinki. The participation in the survey study was voluntary and anonymous. The Likert
scale scores and free text comments underwent statistical analysis [7]. A comparison was
made between the responses of two cohorts of fifth-year dental students from the years 2023
and 2024. Descriptive statistics were used to describe the findings, and the main themes in
the qualitative comments were highlighted.
Results.
In this survey study, Seventy-six (89%) of 118 and 72 (96%) of 134 students
answered the questions in 2023 and 2024 respectively. The satisfaction rates improved from
64% in 2023 to 81% in 2024. The satisfaction rate is 81% in 2024 for the use of AI to detect
cephalometric landmarks. In general, the dental students reported relatively higher
satisfaction rates than 2023.
More qualitative comments were given by the dental students with a response rate of 42% in
2024 versus a response rate of 36% in 2023. In 2024, positive feedback of ‘’very good’’ was
given by 68% of the dental students. Moreover, 12% of dental students asked to improve
providing AI application quality while 9% of the dental students commented negatively
about the applications’ complexity.
Discussion.
The main results of this survey study were the relatively higher overall
students’ satisfaction rates with the use of artificial intelligence to detecting cephalometric
landmarks in 2024. This also means that an adequate explanation of the frameworks and
mechanisms of AI use in dentistry especially in orthodontics is important to promote an
understanding of cephalometrics. Recent studies have demonstrated the potential of artificial
intelligence and machine learning in cephalometrics. Nishimoto and Hwang both developed
automated landmark prediction systems using deep learning, with Nishimoto achieving
Vo
lu
m
e
5,
Fe
br
ua
ry
,2
02
5
,
M
ED
IC
AL
SC
IE
N
CE
S.
IM
PA
CT
FA
CT
OR
:7
,8
9
accurate predictions and Hwang's latest AI showing superior performance compared to
previous methods.
Alshamrani proposed the use of machine learning models for
cephalometric location recognition, which could significantly speed up the process.
Schwendicke conducted a systematic review and meta-analysis, concluding that DL models
consistently show high accuracy in detecting cephalometric landmarks, particularly in 2-D
imagery. However, the studies highlighted the need for further research to demonstrate the
generalizability and clinical usefulness of these AI and ML applications in cephalometrics.
Using artificial intelligence is becoming more convenient in Tashkent State Dental Institute,
department of orthodontics. Promoting students’ suggestions may influence to improve
effective learning as well as diagnosing more precisely with better therapy in the future.
Declaration of competing interest.
The authors have no conflicts of interests relevant to
this article.
Acknowledgements.
We would like to thank Iroda Nigmatova for her help and
demonstration of how to use artificial intelligence to detect cephalometric landmarks more
accurately.
References
1.
Alshamrani K, Alshamrani K, Alqahtani FF, Alshehri A. Automation of
cephalometrics using machine learning methods. Computational Intelligence and
Neuroscience
[Internet].
2022
Jun
21;2022:1–13.
Available
from:
https://doi.org/10.1155/2022/3061154
2.
Chen Y, Potetz B, Luo B, Chen XW, Lin Y. Cephalometric Landmark Tracing Using
Deformable Templates. IEEE First International Conference on Healthcare Informatics,
Imaging and Systems Biology [Internet]. 2011 Jul 1; Available from:
https://doi.org/10.1109/hisb.2011.14
3.
Hwang H, Moon J, Kim M, Donatelli RE, Lee SJ. Evaluation of automated
cephalometric analysis based on the latest deep learning method. the Angle Orthodontist
[Internet]. 2021 Jan 12;91(3):329–35. Available from: https://doi.org/10.2319/021220-100.1
4.
Bakhodirovna, M.D. and Taxirovich, A.S., 2024. CHARACTERISTICS OF
RHINOVIRUS INFECTION. International journal of medical sciences, 4(08), pp.55-59.
5.
Kafieh R, Sadri S, Mehri A, Raji HR. Using a Combination of Model Based and
Intelligent methods in Automatic Landmark Detection in Cephalometry. International
Conference on Innovations in Information Technology [Internet]. 2007 Nov 1; Available
from: https://doi.org/10.1109/iit.2007.4430366
6.
Naidu VK, Jaju S. CAD/CAM engineering and artificial intelligence in dentistry.
IOP Conference Series Materials Science and Engineering [Internet]. 2022 Oct
1;1259(1):012018. Available from: https://doi.org/10.1088/1757-899x/1259/1/012018
7.
Abdukodirov Sherzod Taxirovich (2025) “THE ROLE OF THE ACL (ACTIVE
COLLABORATIVE
LEARNING)
MODEL
IN
EDUCATION”,
International
Multidisciplinary Journal for Research & Development, 12(01), pp. 513–515. Available at:
https://www.ijmrd.in/index.php/imjrd/article/view/2507 (Accessed: 5 February 2025).
8.
Ossowska A, Kusiak A, Świetlik D. Artificial Intelligence in Dentistry—Narrative
Review. International Journal of Environmental Research and Public Health/International
Vo
lu
m
e
5,
Fe
br
ua
ry
,2
02
5
,
M
ED
IC
AL
SC
IE
N
CE
S.
IM
PA
CT
FA
CT
OR
:7
,8
9
Journal of Environmental Research and Public Health [Internet]. 2022 Mar 15;19(6):3449.
Available from: https://doi.org/10.3390/ijerph19063449
9.
Schwendicke F, Chaurasia A, Arsiwala-Scheppach LT, Lee JH, Elhennawy K,
Jost‐Brinkmann P, et al. Deep learning for cephalometric landmark detection: systematic
review and meta-analysis. Clinical Oral Investigations [Internet]. 2021 May 27;25(7):4299–
309. Available from: https://doi.org/10.1007/s00784-021-03990-w
10.
Sikri A, Sikri J, Piplani V, Thakur YS. pplications of Artificial Intelligence in
Dentistry: A Narrative Review. South Asian Research Journal of Oral and Dental Sciences
[Internet].
2024
Jan
3;6(01):1–10.
Available
from:
https://doi.org/10.36346/sarjods.2024.v06i01.001
