ACADEMIC RESEARCH IN MODERN SCIENCE
International scientific-online conference
51
IMPLEMENTATION OF AN AI-BASED PERSONALIZED LEARNING
PLATFORM (LMS) IN THE EDUCATIONAL PROCESS OF
MICROBIOLOGY AND VIROLOGY
Abdullayev Goyibsher Abdulohamidovich
Fergana Institute of Public Health Medicine
ORCID: 0000-0003-1232-5577
Email: sherhan1991big@mail.ru
https://doi.org/10.5281/zenodo.16601719
Abstract:
This study explores the integration of an AI-based personalized learning
management system (LMS) into the teaching of microbiology and virology. As
these disciplines require a strong synthesis of theoretical and practical
knowledge, traditional educational models often fail to meet the needs of diverse
learners. The research presents a comparative analysis between conventional
and adaptive AI-supported instruction, detailing the design and implementation
of an LMS platform tailored to students’ individual progress and learning
profiles. Experimental results from a controlled study involving pre- and post-
testing, user feedback, and statistical analysis demonstrate a significant
improvement in knowledge acquisition and engagement among students using
the AI-based LMS. The findings highlight the system’s effectiveness in enhancing
motivation, providing real-time feedback, and delivering virtual laboratory
simulations that closely mirror real-world practice. The study concludes with
pedagogical recommendations and outlines future directions for AI integration
in medical education.
Keywords:
Artificial intelligence, personalized learning, microbiology education,
virology, LMS, adaptive learning, medical education, digital pedagogy, real-time
feedback, virtual laboratories.
This thesis analyzes the necessity, opportunities, and advantages of
introducing AI-powered personalized learning platforms (LMS) into complex
and sensitive disciplines such as microbiology and virology within the
framework of modern educational systems. The study presents a comparative
analysis of traditional and digital teaching methods, explores the impact of AI
technologies on learning effectiveness, and reports the outcomes achieved
through an experimentally designed personalized LMS module. Based on
experimental data, statistical analysis, and user feedback, pedagogical
conclusions are drawn, and practical recommendations are offered to improve
educational quality. This work specifically examines the scientific and practical
ACADEMIC RESEARCH IN MODERN SCIENCE
International scientific-online conference
52
foundations, experimental results, effectiveness, and prospects of integrating an
AI-based LMS platform into the teaching of microbiology and virology.
Research Results and Analysis:
The advancement of contemporary
science and technology, especially in the fields of biology, medicine, and
sanitary-epidemiology, requires the education system to train highly qualified
specialists. From this perspective, microbiology and virology are among the
most complex disciplines, as they demand the integration of both theoretical
knowledge and practical application. In teaching these subjects, students must
not only grasp difficult scientific concepts but also reinforce them through
experiential learning.
However, traditional teaching formats face various challenges, such as the
lack of individualized approaches, time constraints, limited availability of
laboratory equipment, and insufficient support beyond classroom hours. These
issues adversely affect students’ comprehension and motivation levels.
In recent years, the rapid development of artificial intelligence (AI)
technologies has brought about fundamental transformations in the field of
education. Notably, personalized learning platforms (Learning Management
Systems – LMS) now make it possible to create content tailored to each learner’s
needs, monitor knowledge levels, identify problematic areas, and provide real-
time recommendations based on data analysis.
Objectives for Assessing the Effectiveness of Implementing AI-Based
Personalized LMS in Microbiology and Virology Education:
1.
Designing the LMS system (with integrated content, analytics, and
feedback modules);
2.
Forming an experimental group;
3.
Evaluating knowledge change based on pre-test and post-test
performance;
4.
Analyzing the feedback of teachers and students.
The experiment was conducted during the 2023–2024 academic year at
medical institutions in Fergana. Two groups comprising 80 students in total
were formed:
Experimental group
(taught using AI-based LMS);
Control group
(taught using traditional methods).
Indicator
Control
Group
(Traditional)
Experimental Group (AI-
LMS)
Average
pre-test
score
52.4%
53.1%
ACADEMIC RESEARCH IN MODERN SCIENCE
International scientific-online conference
53
Indicator
Control
Group
(Traditional)
Experimental Group (AI-
LMS)
Average
post-test
score
65.7%
83.2%
Improvement rate
13.3%
30.1%
According to t-test statistical analysis, the difference was significant at
p
<
0.01.
88% of students rated the LMS as “convenient and motivating”;
76% considered the 3D laboratories to be close to practical experience;
92% stated that real-time feedback deepened their understanding of the
subject.
4.3 Teacher Feedback:
60% of instructors reported a reduction in lesson preparation and
monitoring workload;
80% noted that the LMS enabled more efficient individualized work with
students based on system-generated results.
Conclusion:
The results of the study demonstrate that AI-based LMS systems
significantly enhance educational outcomes through differentiated instruction,
real-time analytics, adaptive content, virtual laboratories, and tools for self-
directed learning. Specifically:
1.
The adaptive LMS adjusts to the learner’s individual knowledge
level, reinforcing key topics through repetition;
2.
Real-time feedback helps correct learning mistakes immediately and
supports deeper conceptual understanding;
3.
3D laboratory simulations offer a safe and engaging alternative to
traditional practical sessions.
Thus, the integration of AI-powered LMS platforms into microbiology and
virology education provides a scientifically grounded and pedagogically effective
approach for improving teaching quality and learner outcomes.
References:
1.
Johnson, M. E., & Patel, R. K. (2021). Artificial Intelligence in Medical
Education: Strategies and Outcomes. Springer Nature.
2.
Karimov, S. T., & Tursunova, N. K. (2023). Integration of Adaptive Learning
Technologies in Microbiology Curriculum. Tashkent Medical University Press.
