Enhancing Pharmacology Education through artificial intelligence Integrated Blended Learning: A Quasi-Experimental Study

Enhancing Pharmacology Education through artificial intelligence Integrated Blended Learning: A Quasi-Experimental Study | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Enhancing Pharmacology Education through artificial intelligence Integrated Blended Learning: A Quasi-Experimental Study Junxiu Zhang, Chunfei Wang, Lutan Zhou, Xianwei Li, Wusan Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7898712/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Pharmacology education, serving as a crucial bridge between basic and clinical medicine, faces challenges with traditional lecture-based pedagogies in meeting diverse student learning needs. While blended learning has enhanced educational flexibility, it struggles with real-time diagnosis of individual learning states. Artificial intelligence (Al) teaching assistants offer transformative potential for personalized pharmacology education through intelligent learning pathways and real-time guidance. Methods This quasi-experimental study evaluated 175 first-year pharmacy students across six classes over a 16-week pharmacology course. Students were randomized into control group(n = 88) receiving conventional blended learning and experimental group (n = 87) receiving Al-enhanced blended learning. The Al system provided personalized guidance through intelligent pre-class companions, in-class interactive guidance, and post-class targeted practice. Outcomes were assessed using standardized tests, competency evaluations, behavioral analytics, and learning experience surveys. Results The experimental group demonstrated significantly superior performance across all measured dimensions. Knowledge mastery showed dramatic improvements: core concepts (89.7% vs 69.9%, p < 0.001), drug properties (88.8% vs 53.7%, p < 0.001), and clinical reasoning abilities including multidimensional integration (57.6% vs 35.7%, p < 0.001). Critical thinking skills were markedly enhanced, with truth-seeking (7.9 vs 6.4, p < 0.001) and open-mindedness (8.2 vs 5.5, p < 0.001) showing substantial gains. Learning engagement increased significantly, with post-class exercise completion rising to 31.1 vs 22.1 questions/week (p < 0.001) and learning anxiety reduced (9.9 vs 14.4, p < 0.001). Conclusion Al-enhanced blended learning significantly improves pharmacology educational outcomes by providing personalized instruction that enhances knowledge mastery, critical thinking, and autonomous learning capabilities while reducing learning anxiety. This approach offers a scalable solution for addressing diverse learning needs in complex medical education contexts. Pharmacology education Blended learning Artificial intelligence Personalized instruction Higher-order competencies Introduction Pharmacology stands as an indispensable nexus between basic and clinical medicine, embodying a sophisticated knowledge base replete with abstract principles and subject to swift evolutionary changes. This dynamic field necessitates from students a robust suite of mnemonic, comprehension, and application proficiencies. Traditional lecture-centric pedagogies often fall short in tailoring to the diverse tapestry of student learning needs. While the burgeoning trend of blended learning—synergizing online and offline educational strategies—has indeed stretched the fabric of learning across time and space via digital mediums, enhancing flexibility, it continues to grapple with the challenge of precisely diagnosing individual learning states[ 1 ]. Educators frequently encounter difficulties in real-time tracking and comprehensively mapping each student's learning trajectory and knowledge gaps, thus impeding the delivery of genuinely personalized instruction[ 2 ]. The advent of artificial intelligence (AI) teaching assistants in pharmacology education heralds a transformative potential across a spectrum of micro-educational scenarios. These include crafting personalized learning itineraries predicated on students' mastery of knowledge graphs[ 3 – 5 ], dispensing targeted exercises to shore up deficiencies in complex subjects such as drug pharmacokinetics, offering real-time guidance and identifying knowledge lacunae through iterative dialogues during elucidation of drug mechanisms, and developing intelligent agent models for interactive guidance with students[ 6 ]. Against this backdrop, the present study posits a quasi-experimental framework[ 7 ] to appraise the efficacy of a blended learning paradigm infused with AI teaching assistants (experimental group) versus a conventional blended learning approach (control group) in fortifying pharmacology educational outcomes, with a particular focus on the attainment of personalized instruction. It is hypothesized that students in the experimental group, under the aegis of AI teaching assistant intervention, will manifest markedly superior academic performance, critical thinking acumen, and self-directed learning capabilities compared to their counterparts in the control group. Research Participants and Methods Research Participants The study participants were first-year undergraduate pharmacy students from the School of Pharmacy in the 2023 cohort, totaling 175 students across six small classes. To ensure equivalence in academic background, students' entry scores and average grades in prerequisite courses, such as Biochemistry and Physiology, were reviewed. No significant differences were found. The study used whole class randomization, dividing students into two groups: the control group (Classes 1–3, n = 88) received conventional blended learning, while the experimental group (Classes 4–6, n = 87) received an AI-enhanced blended learning model. Research Design This quasi-experimental study employed a pre-test/post-test control group design over a 16-week semester covering the entire Pharmacology course. A pre-test assessed baseline proficiency, and post-tests evaluated knowledge retention and skill development. Behavioral analyses tracked exercise completion rates, effective practice rates, repetition frequency for weak areas, and learning path adjustments. Questionnaire surveys assessed learning experiences based on clarity of objectives, feedback timeliness, self-awareness accuracy, and anxiety levels. Teaching Interventions To ensure consistency and control for instructor variables, both groups utilized the identical textbook and syllabus, delivered by the same instructional team. The control group engaged in a conventional blended learning approach, leveraging a Learning Management System (LMS) to facilitate pre-class activities, in-class discussions, and post-class assignments and discussions, with instructors offering feedback and reviews based on student performance. In contrast, the experimental group adopted an AI-enhanced blended learning model, where an AI teaching assistant system was integrated with the LMS to provide personalized guidance. This system encompassed intelligent preview companions, in-class interactive guidance, and post-class targeted practice and learning pathway planning, thereby enhancing the traditional blended learning experience with AI-driven support. Measurement Tools and Data Collection In the study, a comprehensive suite of measurement tools and data collection methods was employed to evaluate the effectiveness of the educational interventions. The level of mastery in pharmacological knowledge was assessed through a dimension-specific standardized test paper, which measured knowledge acquisition, skill application, and clinical reasoning. Pre- and post-tests were administered one week before and after the course to both the control and experimental groups. The developmental levels of advanced competencies in pharmacology were evaluated using a combination of Situational Judgement Tests, the revised Clinical Competency Taxonomy Development Index (CCTDI) scale, platform behavioral logs, and post-course interviews. Additionally, scientific research capability was assessed through experimental tasks and research report rubric scoring. Analysis of learning process behaviors was conducted over a 16-week period using an intelligent teaching platform, which tracked core metrics such as exercise completion rates and query frequencies. Lastly, student feedback on their learning experiences was gathered using a 5-point Likert scale, which covered aspects such as clarity of objectives, timeliness of feedback, self-weakness recognition, and anxiety levels. The questionnaire used in this study is provided as Supplementary Material (Supplementary File 1). This multifaceted approach to data collection ensured a thorough evaluation of the learning outcomes and experiences of the participants in both groups. Statistical Methods Descriptive statistics were used to understand data characteristics. Paired-sample t-tests compared pre- and post-tests within cohorts, and independent-sample t-tests compared post-tests between groups. ANOVA compared teaching mode impacts, with post-hoc tests for significant differences. Pearson's and Spearman's correlation coefficients assessed relationships between variables. Multiple linear regression analyses identified significant predictors of learning outcomes. Cronbach's α coefficient assessed reliability, and construct validity was evaluated through expert review and factor analysis. Data were organized and analyzed using SPSS 26.0 or R software. Ethical Considerations The study was approved by the institutional review board, and all participants provided informed consent. Results Impact of AI Teaching Assistant + Blended Learning on Students' Mastery of Pharmacological Knowledge The experimental group exhibited significantly higher post-test accuracy than the control group in core pharmacological knowledge and skills, as detailed in Table 1 . Specifically, the experimental group achieved higher accuracy in core concepts (89.7% vs 69.9%, p < 0.001), drug properties (88.8% vs 53.7%, p < 0.001), key parameters (82.1% vs 64.3%, p < 0.001), and fundamental principles (89.7% vs 75.5%, p < 0.001). They also demonstrated greater proficiency in practical skills such as dose calculation (81.4% vs 60.6%, p < 0.001), prescription review (82.2% vs 50.7%, p < 0.001), protocol design (72.6% vs 43.4%, p < 0.001), risk prediction (72.0% vs 42.3%, p < 0.001), and data analysis (70.7% vs 59.0%, p < 0.001). Furthermore, the experimental group scored significantly higher in all dimensions of clinical reasoning, including multidimensional integration (57.6% vs 35.7%, p < 0.001), dynamic anticipation (62.6% vs 36.2%, p < 0.001), priority decision-making (60.5% vs 36.9%, p < 0.001), evidence-based adjustment (56.1% vs 37.7%, p < 0.001), and humanistic balance (57.7% vs 38.4%, p < 0.001), which are also summarized in Table 1 . Table 1 Impact of AI Teaching Assistant + Blended Learning on Students' Mastery of Pharmacological Knowledge Dimension Indicator Control group %, n = 88 Experimental group %, n = 87 t-value P-value Knowledge mastery Core concepts 69.9 ± 6.9 89.7 ± 4.0 18.8805 0.0000 Drug properties 53.7 ± 10.7 88.8 ± 9.0 21.7043 0.0000 Key parameters 64.3 ± 9.1 82.1 ± 7.4 12.8926 0.0000 Fundamental law 75.5 ± 14.7 89.7 ± 7.2 6.3716 0.0000 Capacity application Dose calculation 60.6 ± 9.7 81.4 ± 11.0 14.1947 0.0000 Prescription review 50.7 ± 15.3 82.2 ± 13.6 13.5659 0.0000 Protocol design 43.4 ± 14.4 72.6 ± 14.7 13.3235 0.0000 Risk prediction 42.3 ± 14.5 72.0 ± 14.7 13.5411 0.0000 Data analysis 59.0 ± 15.8 70.7 ± 10.3 4.8717 0.0000 Clinical reasoning Multidimensional integration 35.7 ± 7.9 57.6 ± 18.1 18.2350 0.0000 Scores are expressed as percentages (mean ± SD) for the control (n = 88) and experimental (n = 87) groups. The t-values and P-values were calculated using independent samples t-tests to determine the significance of differences between groups. All reported P-values are two-tailed and statistically significant at P < 0.05, indicating a significant difference in performance between the two groups across all measured indicators. Impact of AI Teaching Assistants Combined with Blended Learning on Students' Higher-Order Competency Development As shown in Table 2 , the experimental group outperformed the control group in critical thinking skills, with higher post-test scores in truth-seeking (7.9 vs 6.4, p < 0.001), open-mindedness (8.2 vs 5.5, p < 0.001), analytical ability (7.5 vs 6.2, p < 0.001), systematisation ability (7.5 vs 5.7, p < 0.001), self-confidence (7.0 vs 6.1, p < 0.001), curiosity (6.9 vs 6.3, p = 0.007), and cognitive maturity (6.7 vs 5.8, p < 0.001). Additionally, the experimental group demonstrated superior self-directed learning abilities, with significantly higher scores in learning motivation (8.0 vs 7.3, p = 0.004), learning strategies (8.1 vs 7.1, p < 0.001), and self-management (7.5 vs 6.8, p = 0.005). In terms of scientific research abilities, the experimental group also showed higher post-test scores in experimental design (15.0 vs 13.9, p = 0.020), experimental operation (14.5 vs 13.2, p = 0.002), data analysis (16.8 vs 14.3, p < 0.001), interpretation of results (14.3 vs 13.0, p = 0.001), and report writing (13.6 vs 11.6, p < 0.001). These findings suggest that AI-integrated blended learning can significantly enhance students' critical thinking, self-directed learning, and scientific research skills in pharmacology education, as further detailed in Table 2 . Table 2 Impact of AI Teaching Assistants Combined with Blended Learning on Students' Higher-Order Competency Development Dimension Indicator Control group n = 88 Experimental group n = 87 t-value P-value Critical thinking Seeking truth 6.4 ± 1.0 7.9 ± 1.3 9.492 0.0000 Open-mindedness 5.5 ± 1.3 8.2 ± 1.4 13.8541 0.0000 Analytical ability 6.2 ± 1.0 7.5 ± 1.3 8.1866 0.0000 Systematic ability 5.7 ± 1.3 7.5 ± 1.6 9.3407 0.000 Self-confidence 6.1 ± 1.3 7.0 ± 1.3 3.9159 0.0006 Curiosity 6.3 ± 1.1 6.9 ± 1.7 3.4683 0.0071 Cognitive maturity 5.8 ± 1.8 6.7 ± 0.8 3.0018 0.0001 Autonomous learning ability Learning motivation 7.3 ± 1.7 8.0 ± 1.4 2.6912 0.0039 Learning strategies 7.1 ± 1.7 8.1 ± 1.5 3.7462 0.0000 Self-management 6.8 ± 1.6 7.5 ± 1.7 2.8783 0.0051 Scientific research capability Experimental design capability 13.9 ± 3.0 15.0 ± 2.9 2.2718 0.0203 Experimental operational competence 13.2 ± 2.9 14.5 ± 2.7 3.1395 0.0015 Data analysis ability 14.3 ± 2.7 16.8 ± 1.5 6.1616 0.0000 Ability to interpret results 13.0 ± 2.8 14.3 ± 2.9 3.3064 0.0013 Research report writing ability 11.6 ± 2.6 13.6 ± 3.0 4.8135 0.0000 Data are presented as mean scores ± standard deviation (SD) for control (n = 88) and experimental (n = 87) groups. The t-values and two-tailed P-values were calculated using independent samples t-tests to assess the statistical significance of differences between groups. A P-value < 0.05 was considered statistically significant, indicating that the experimental group demonstrated significantly higher competency development in all measured dimensions compared to the control group. The Impact of AI Teaching Assistants and Blended Learning on Student Learning Processes As detailed in Table 3 , students in the experimental group demonstrated greater learning engagement and focus. They completed a significantly higher number of post-class exercises (31.1 questions/week vs 22.1 questions/week, p < 0.001), indicating a higher level of participation. The effective exercise rate, which reflects the proportion of targeted training, was also significantly higher in the experimental group (80.9% vs 68.7%, p < 0.001). Furthermore, the frequency of repetition in weak areas was greater among experimental group students (4.2 times/person vs 1.7 times/person, p < 0.001), suggesting a more focused approach to learning. Additionally, students in the experimental group sought clarification more frequently, with AI-based clarifications at 3.6 times per person and teacher-based clarifications at 0.6 times per person, compared to 0.3 times per person in the control group (p < 0.001), as shown in Table 3 . They also adjusted their learning pathways more often (2.6 times per person vs 1.6 times per person, p < 0.001). These findings, supported by the data in Table 3 , indicate that the integration of AI teaching assistants with blended learning can effectively promote active and targeted learning processes among students. Table 3 The Impact of AI Teaching Assistants and Blended Learning on Student Learning Processes Behavioural indicators Control group n = 87 Experimental group n = 88 t-value P-value Post-class exercise completion rate (questions/week) 22.1 ± 3.5 31.1 ± 5.1 16.9434 0.0000 Effective practice rate = Targeted training volume for incorrect questions / Total practice volume 68.7 ± 13.2 80.9 ± 13.0 5.9703 0.0000 Q&A Frequency (times/person) AI Q&A 0 3.6 ± 1.4 0.0000 Teacher Q&A 0.3 ± 0.2 0.6 ± 0.2 5.5202 0.0000 Frequency of Repetitive Training for Weak Areas (times/person) 1.7 ± 0.5 4.2 ± 1.4 14.6934 0.0000 Number of learning path adjustments (times/person) 1.6 ± 0.5 2.6 ± 0.7 5.6172 0.0000 Behavioral indicators were compared between the control group (n = 87) and the experimental group (n = 86) using independent samples t-tests. Data are presented as mean ± standard deviation (SD). The t-values and p-values are reported to indicate the statistical significance of the differences observed. A p-value of less than 0.05 was considered statistically significant. All reported p-values are two-tailed. Impact of AI Teaching Assistants Combined with Blended Learning on Student Learning Experiences According to Table 4 , experimental group students reported significantly higher experience scores than the control group in learning goal clarity (14.4 vs 12.2, p < 0.001), feedback timeliness (16.0 vs 10.1, p < 0.001), and accuracy of personal weakness recognition (16.1 vs 12.5, p < 0.001). Additionally, as shown in Table 4 , experimental group students exhibited significantly lower levels of learning anxiety (9.9 vs 14.4, p < 0.001). These results indicate that the integration of AI teaching assistants with blended learning can enhance students' learning experiences by clarifying goals, improving feedback timeliness, increasing self-awareness of weaknesses, and reducing anxiety. Table 4 Impact of AI Teaching Assistants Combined with Blended Learning on Student Learning Experiences Dimension Control group n = 87 Experimental group n = 88 t-value P-value Clarity of learning objectives 12.2 ± 2.0 14.4 ± 2.7 7.3863 0.0000 Timeliness of feedback 10.1 ± 2.8 16.0 ± 3.0 13.8548 0.0000 Accuracy of self-Awareness regarding personal weaknesses 12.5 ± 4.1 16.1 ± 2.9 5.8276 0.0000 Level of learning anxiety 14.4 ± 3.0 9.9 ± 2.9 9.6724 0.0000 Data are presented as mean ± standard deviation (SD). The experimental group (n = 87) showed significantly higher scores compared to the control group (n = 88) across all dimensions of learning experiences. The t-values and corresponding two-tailed P-values were calculated using independent samples t-tests, with a P-value < 0.05 considered statistically significant. This indicates that the integration of AI teaching assistants with blended learning positively influenced students' experiences regarding the clarity of learning objectives, timeliness of feedback, accuracy of self-awareness regarding personal weaknesses, and reduced learning anxiety. Discussion In the context of contemporary educational reforms, traditional teaching methodologies are increasingly inadequate for addressing the diverse learning needs of students. Pharmacology, as a core bridge course connecting basic and clinical medicine, is characterized by a complex knowledge system, abstract concepts, and rapid updates, which place significant demands on students' memorization, comprehension, and application skills[ 8 ]. The recent rise of blended learning models, which integrate online and offline elements, has expanded learning time and space through digital resources[ 9 ]. However, these models still face challenges in accurately diagnosing individual student learning states[ 10 ]. The rapid advancement of AI technology has introduced AI teaching assistants, which offer data-driven optimization recommendations to enhance teaching effectiveness[ 11 ]. The primary objective of this study was to evaluate the effectiveness of a blended learning model incorporating AI teaching assistants in pharmacology instruction, specifically examining its impact on students' academic performance, critical thinking, and autonomous learning abilities. The research hypothesized that students in the experimental group receiving AI teaching assistant intervention would demonstrate significantly superior academic performance, critical thinking, and autonomous learning abilities compared to the control group. The findings revealed that the experimental group achieved significantly higher post-test scores than the control group across all dimensions, including mastery of pharmacology knowledge, application of skills, clinical reasoning abilities, critical thinking, autonomous learning capabilities, and scientific research competencies. This fully supports our research hypothesis. The significant improvements observed in the experimental group can be attributed to the multifaceted support provided by the AI teaching assistant system. Utilizing technologies such as deep learning, natural language processing, and knowledge graphs, the AI assistant conducts multidimensional, in-depth analyses of students' classroom learning behaviors, assignment completion, and academic assessment data[ 12 ]. This enables precise identification of discrepancies between individual learning profiles and instructional requirements, clarifying students' learning needs and challenges. Consequently, it furnishes data-driven optimization recommendations to assist educators in devising personalized guidance plans[ 13 ]. Specifically, the AI teaching assistant serves as an intelligent pre-class companion, delivers personalized interactive guidance during lessons, and provides targeted practice exercises and pathway planning for weak areas post-class, thereby aiding students in better understanding and applying pharmacology knowledge[ 14 ]. Through real-case analysis questions and multi-round dialogue technology, the AI teaching assistant guides students in multidimensional integration, dynamic forecasting, prioritized decision-making, evidence-based adjustments, and humanistic balance, thereby markedly elevating their clinical reasoning capabilities[ 15 ]. The AI teaching assistant also stimulates student motivation[ 16 ] while cultivating learning strategies and self-management skills, markedly elevating autonomous learning capabilities[ 17 ]. Concurrently, it delivers targeted guidance in experimental design, procedure execution, data analysis, result interpretation, and report writing, substantially enhancing students' scientific research competencies[ 18 , 19 ]. The findings of this study align with prior research on AI teaching assistants in education. For instance, studies have demonstrated that AI tutors can substantially enhance students' academic performance[ 20 – 22 ] and learning motivation[ 23 ]. However, unlike previous studies, this research focused specifically on pharmacology instruction, revealing significant effects of AI tutors in improving knowledge acquisition, skill application, and clinical reasoning abilities within pharmacology. This may relate to the distinctive characteristics and pedagogical demands of pharmacology courses. Although previous studies have identified positive impacts of AI tutors on student performance, their participants were from other disciplines, whereas this study involved undergraduate pharmacy students. This suggests that AI tutor effectiveness may be influenced by subject-specific characteristics and teaching content. Furthermore, through multi-dimensional assessment tools and detailed analysis of learning process behaviors, this study provides a more comprehensive demonstration of AI tutors' advantages in enhancing students' higher-order abilities and learning experiences. This study has several limitations. Firstly, the sample size was relatively small, comprising only 175 students, which may limit the generalizability of the findings. Secondly, the study duration was brief, spanning just one semester, making it challenging to assess the long-term effects of AI tutors. Furthermore, the research was conducted solely within the School of Pharmacy at one institution, potentially failing to fully reflect the circumstances of students at other universities or in different regions. Future research could expand the sample size to include students from different regions and academic years, thereby validating the generalizability of AI tutors in pharmacology teaching. Concurrently, long-term follow-up studies could assess their sustained impact on students' academic and professional development. Furthermore, subsequent investigations might explore the effectiveness of AI tutors across diverse disciplines, enriching their application within educational research. It is recommended that teaching staff experiment with AI teaching assistant systems in pharmacology instruction. Leveraging features such as intelligent pre-learning, personalized interactive guidance, and targeted practice for weak areas can stimulate student engagement and enhance teaching outcomes. Concurrently, educators should prioritize cultivating students' critical thinking and independent learning capabilities, using data provided by AI assistants to develop tailored teaching strategies. Institutions should provide training on AI teaching assistant systems to support faculty in implementing pedagogical reforms. Concurrently, universities may establish AI teaching assistant resource repositories, offering educators abundant instructional materials to facilitate the widespread adoption of AI technology in teaching. Education policymakers should encourage higher education institutions to undertake AI teaching assistant-driven pedagogical reforms, offering policy support and financial safeguards. Concurrently, AI teaching assistants should be incorporated into curriculum standards to facilitate broader implementation, thereby enhancing teaching quality and promoting students' holistic development. This study experimentally demonstrated the efficacy of blended learning models incorporating AI teaching assistants in enhancing students' mastery of pharmacology knowledge, application of skills, clinical reasoning abilities, critical thinking, autonomous learning capabilities, and scientific research competencies. This finding provides robust empirical support for pharmacology teaching reform. This research not only enriches the application studies of AI teaching assistants in education but also provides pharmacology educators with practical teaching methodologies. It contributes to enhancing teaching quality and fostering students' holistic development. Through the application of AI teaching assistant systems, educators can better address individual learning needs, elevate teaching effectiveness, and offer novel perspectives and directions for future medical education reform. Declarations Not applicable. Clinical trial number Not applicable. Ethics approval and consent to participate Ethics approval for this study was obtained from the Institutional Review Board of Wannan Medical College (Reference Number: 2023-045). All participants provided written informed consent. This study was conducted in accordance with the principles of the Declaration of Helsinki. Consent for publication Not applicable. Competing interests The authors declare no competing interests. Funding This study was funded by the following projects: Wannan Medical College Quality and Teaching Reform Project (2024jyxm05, 2024zhkc02), Anhui Provincial Higher Education Institutions Quality Engineering Project (2023xsxx259, 2024aijy314), and Anhui Provincial Department of Education Research Plan (2024AH051882). Author Contribution Junxiu Zhang and Chunfei Wang contributed equally to this work. Junxiu Zhang and Chunfei Wang were responsible for the conception and design of the study, and participated in data collection, analysis, and interpretation. Lutan Zhou and Xianwei Li played a key role in data collection and quality control. Wusan Wang and Shuguo Zheng, as corresponding authors, were responsible for the overall supervision of the study and the final revision of the manuscript. All authors contributed to the drafting and revision of the manuscript and agreed to be accountable for their contributions, ensuring the accuracy and integrity of the research. Acknowledgement Not applicable. Data Availability The datasets generated and/or analyzed during the current study are available from the corresponding author on reasonable request. References Wei HC, Lin YH, Chang LH. The Effectiveness of a Blended Learning-Based Life Design Course: Implications of Instruction and Application of Technology. SN Comput Sci. 2023;4(4):360. Sridharan K, Sequeira RP. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology & therapeutics case study. BMC Med Educ. 2024;24(1):431. Yang Y, Chen S, Zhu Y, Zhu H, Chen Z. Knowledge graph empowerment from knowledge learning to graduation requirements achievement. PLoS ONE. 2023;18(10):e0292903. Zhou LY, Wang YY. Simulation of personalized english learning path recommendation system based on knowledge graph and deep reinforcement learning. Sci Rep. 2025;15(1):34554. You X, Li M, Xiao Y, Liu H. The Feedback of the Chinese Learning Diagnosis System for Personalized Learning in Classrooms. Front Psychol. 2019;10:1751. Bhatia N, Khan MMU, Arora S. The Role of Artificial Intelligence in Revolutionizing Pharmacological Research. Curr Pharmacol Rep. 2024;10(6):323–9. Behi R, Nolan M. Quasi-experimental research designs. Br J Nurs. 1996;5(17):1079–81. Fyfe P. How to cheat on your final paper: Assigning AI for student writing. AI Soc. 2023;38(4):1395–405. Zhang Y, Liu J, Liang J, Lang J, Zhang L, Tang M, Chen X, Xie Y, Zhang J, Su L, et al. Online education isn't the best choice: evidence-based medical education in the post-epidemic era-a cross-sectional study. BMC Med Educ. 2023;23(1):744. Berg F, Andujar A, Chatman G, Rodriguez-Galindo C, Qaddoumi I, Moreira DC. Online Outcomes of a Pediatric Neuro-Oncology Course for Multidisciplinary Healthcare Professionals in Low- and Middle-Income Countries. J Cancer Educ 2025. Sriram A, Ramachandran K, Krishnamoorthy S. Artificial Intelligence in Medical Education: Transforming Learning and Practice. Cureus. 2025;17(3):e80852. Yang M-l. Artificial intelligence versus human teacher assistants and language learners’ progress in learning and retention of complex sentences. Curr Psychol. 2025;44(7):6292–304. Cetinkaya L. Redefining Mentorship in Medical Education with Artificial Intelligence: A Delphi Study on the Feasibility and Implications. Teach Learn Med 2025:1–11. Charles KA, Yousuf A, Chua HC, Matthews S, Harnett J, Hinton T. AI in action: Changes to student perceptions when using generative artificial intelligence for the creation of a multimedia project-based assessment. Eur J Pharmacol. 2025;998:177508. Hudon A, Kiepura B, Pelletier M, Phan V. Using ChatGPT in Psychiatry to Design Script Concordance Tests in Undergraduate Medical Education: Mixed Methods Study. JMIR Med Educ. 2024;10:e54067. Kowitlawakul Y, Tan JJM, Suebnukarn S, Nguyen HD, Poo DCC, Chai J, Kamala DM, Wang W. Development of an Artificial Intelligence Teaching Assistant System for Undergraduate Nursing Students: A Field Testing Study. Comput Inf Nurs. 2024;42(5):334–42. Sharma P, Harkishan M. Designing an intelligent tutoring system for computer programing in the Pacific. Educ Inf Technol (Dordr). 2022;27(5):6197–209. Cheng Z, Yang J, Shelnutt KP. Implementing GRATL and artificial intelligence in experiential learning of obesity physiology and etiology. Adv Physiol Educ. 2025;49(4):871–8. Hui Z, Zewu Z, Jiao H, Yu C. Application of ChatGPT-assisted problem-based learning teaching method in clinical medical education. BMC Med Educ. 2025;25(1):50. Wang P, Mi B, Lu J, Zheng F. Evaluating AI tutor feedback in medical education: a case study of computer basics and applications course for undergraduates. Disabil Rehabil Assist Technol 2025:1–15. Anderson JR, Boyle CF, Reiser BJ. Intelligent tutoring systems. Science. 1985;228(4698):456–62. Spitzer MWH, Moeller K. Performance increases in mathematics during COVID-19 pandemic distance learning in Austria: Evidence from an intelligent tutoring system for mathematics. Trends Neurosci Educ. 2023;31:100203. Janson MP, Wenker T, Baulke L. Only a matter of time? Using logfile data to evaluate temporal motivation theory in university students' examination preparation. Br J Educ Psychol. 2024;94(4):1192–207. Additional Declarations No competing interests reported. Supplementary Files SupplementaryFile1.pdf Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7898712","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":549918206,"identity":"dbc20636-6976-4608-95f7-035af9e91565","order_by":0,"name":"Junxiu Zhang","email":"","orcid":"","institution":"Wannan Medical College","correspondingAuthor":false,"prefix":"","firstName":"Junxiu","middleName":"","lastName":"Zhang","suffix":""},{"id":549918207,"identity":"761d49ab-2361-4017-bcb7-0135eb25a1bc","order_by":1,"name":"Chunfei Wang","email":"","orcid":"","institution":"Wannan Medical College","correspondingAuthor":false,"prefix":"","firstName":"Chunfei","middleName":"","lastName":"Wang","suffix":""},{"id":549918208,"identity":"5ee756de-85c1-4bb2-9e77-066b1e9e8fa4","order_by":2,"name":"Lutan Zhou","email":"","orcid":"","institution":"Wannan Medical College","correspondingAuthor":false,"prefix":"","firstName":"Lutan","middleName":"","lastName":"Zhou","suffix":""},{"id":549918209,"identity":"5c9747bc-68c5-43a3-a533-4c8988983be0","order_by":3,"name":"Xianwei Li","email":"","orcid":"","institution":"Wannan Medical College","correspondingAuthor":false,"prefix":"","firstName":"Xianwei","middleName":"","lastName":"Li","suffix":""},{"id":549918210,"identity":"01de4842-9047-4f9c-a629-14892f723bc1","order_by":4,"name":"Wusan Wang","email":"","orcid":"","institution":"Wannan Medical College","correspondingAuthor":false,"prefix":"","firstName":"Wusan","middleName":"","lastName":"Wang","suffix":""},{"id":549918211,"identity":"097de4fd-127c-4f14-8afb-947ef60deb88","order_by":5,"name":"Shuguo Zheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4UlEQVRIiWNgGAWjYDACCQglx8bM2PggoaKGeC3G/OzNhw0enDlGvJbEmT3H0iQftjAT1iE/u/nYwy9/ahk33Mgxq0hsYGPgb+9OwKuFcc6xdGPZtuPMBkAtNxJ3yDBInDm7Aa8WZokcM2nJhmNsEC1n2BgMJHLxa2GTyP8mLfHnGA9IS0FiGzNhLTwSOWySH9hqJCSB3mcgSouERJqZNGPbAQNQIEsknDnGQ9Av8jOSn0n++FNX3waMyo8/Kmrk+Nt78WsBAWYehsMIlxJUDgKMPxjqiFI4CkbBKBgFIxQAAIBlSm69P5cGAAAAAElFTkSuQmCC","orcid":"","institution":"Wannan Medical College","correspondingAuthor":true,"prefix":"","firstName":"Shuguo","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2025-10-19 13:08:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7898712/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7898712/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96719141,"identity":"5b9f719e-daae-4d0e-96ac-20a807d658e2","added_by":"auto","created_at":"2025-11-25 10:56:48","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64427,"visible":true,"origin":"","legend":"","description":"","filename":"20251027.docx","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/df39090c7b69e270e83f1620.docx"},{"id":96913559,"identity":"649ac829-2fc0-4ffd-8c0b-9d993aa27170","added_by":"auto","created_at":"2025-11-27 14:02:45","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8319,"visible":true,"origin":"","legend":"","description":"","filename":"fe20815ab730427c8a0d02423528e53f.json","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/6eb4672f8b4b071b759b44d3.json"},{"id":96719154,"identity":"de8b55d3-d31c-4305-a78c-dc27b0963afe","added_by":"auto","created_at":"2025-11-25 10:56:49","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":162359,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFile1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/61c0831123bf3e2f2cf79977.pdf"},{"id":96719156,"identity":"d591c95b-8dbd-4590-9993-dd1a48d533ed","added_by":"auto","created_at":"2025-11-25 10:56:49","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90146,"visible":true,"origin":"","legend":"","description":"","filename":"fe20815ab730427c8a0d02423528e53f1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/c13cbe21e6a9101b0b645c43.xml"},{"id":96719152,"identity":"ba27b094-6eb0-44f0-9114-0cfb1fad1fe2","added_by":"auto","created_at":"2025-11-25 10:56:49","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88156,"visible":true,"origin":"","legend":"","description":"","filename":"fe20815ab730427c8a0d02423528e53f1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/346ec6f8765b26d94f20e1e7.xml"},{"id":96719157,"identity":"3a30bd4e-933e-4008-88c0-27c913d3b98a","added_by":"auto","created_at":"2025-11-25 10:56:50","extension":"html","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94412,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/1f88e82cc1678104fbf355ee.html"},{"id":100645602,"identity":"afcef263-5862-44ac-8d8a-9e26311978eb","added_by":"auto","created_at":"2026-01-20 04:31:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":962440,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/74c38c27-dc54-4503-9ac8-f71fe7b4064d.pdf"},{"id":96719158,"identity":"75a821fd-291d-4b99-adb3-ec66a7133541","added_by":"auto","created_at":"2025-11-25 10:56:50","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":162359,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFile1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7898712/v1/ec7b59f638bec7867de5d1d9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Pharmacology Education through artificial intelligence Integrated Blended Learning: A Quasi-Experimental Study","fulltext":[{"header":"Introduction","content":"\u003cp\u003ePharmacology stands as an indispensable nexus between basic and clinical medicine, embodying a sophisticated knowledge base replete with abstract principles and subject to swift evolutionary changes. This dynamic field necessitates from students a robust suite of mnemonic, comprehension, and application proficiencies. Traditional lecture-centric pedagogies often fall short in tailoring to the diverse tapestry of student learning needs. While the burgeoning trend of blended learning\u0026mdash;synergizing online and offline educational strategies\u0026mdash;has indeed stretched the fabric of learning across time and space via digital mediums, enhancing flexibility, it continues to grapple with the challenge of precisely diagnosing individual learning states[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Educators frequently encounter difficulties in real-time tracking and comprehensively mapping each student's learning trajectory and knowledge gaps, thus impeding the delivery of genuinely personalized instruction[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe advent of artificial intelligence (AI) teaching assistants in pharmacology education heralds a transformative potential across a spectrum of micro-educational scenarios. These include crafting personalized learning itineraries predicated on students' mastery of knowledge graphs[\u003cspan additionalcitationids=\"CR4\" citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e], dispensing targeted exercises to shore up deficiencies in complex subjects such as drug pharmacokinetics, offering real-time guidance and identifying knowledge lacunae through iterative dialogues during elucidation of drug mechanisms, and developing intelligent agent models for interactive guidance with students[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAgainst this backdrop, the present study posits a quasi-experimental framework[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e] to appraise the efficacy of a blended learning paradigm infused with AI teaching assistants (experimental group) versus a conventional blended learning approach (control group) in fortifying pharmacology educational outcomes, with a particular focus on the attainment of personalized instruction. It is hypothesized that students in the experimental group, under the aegis of AI teaching assistant intervention, will manifest markedly superior academic performance, critical thinking acumen, and self-directed learning capabilities compared to their counterparts in the control group.\u003c/p\u003e\n\u003ch3\u003eResearch Participants and Methods\u003c/h3\u003e\n\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eResearch Participants\u003c/h2\u003e\u003cp\u003eThe study participants were first-year undergraduate pharmacy students from the School of Pharmacy in the 2023 cohort, totaling 175 students across six small classes. To ensure equivalence in academic background, students' entry scores and average grades in prerequisite courses, such as Biochemistry and Physiology, were reviewed. No significant differences were found. The study used whole class randomization, dividing students into two groups: the control group (Classes 1\u0026ndash;3, n\u0026thinsp;=\u0026thinsp;88) received conventional blended learning, while the experimental group (Classes 4\u0026ndash;6, n\u0026thinsp;=\u0026thinsp;87) received an AI-enhanced blended learning model.\u003c/p\u003e\u003c/div\u003e"},{"header":"Research Design","content":"\u003cp\u003eThis quasi-experimental study employed a pre-test/post-test control group design over a 16-week semester covering the entire Pharmacology course. A pre-test assessed baseline proficiency, and post-tests evaluated knowledge retention and skill development. Behavioral analyses tracked exercise completion rates, effective practice rates, repetition frequency for weak areas, and learning path adjustments. Questionnaire surveys assessed learning experiences based on clarity of objectives, feedback timeliness, self-awareness accuracy, and anxiety levels.\u003c/p\u003e\n\u003ch3\u003eTeaching Interventions\u003c/h3\u003e\n\u003cp\u003eTo ensure consistency and control for instructor variables, both groups utilized the identical textbook and syllabus, delivered by the same instructional team. The control group engaged in a conventional blended learning approach, leveraging a Learning Management System (LMS) to facilitate pre-class activities, in-class discussions, and post-class assignments and discussions, with instructors offering feedback and reviews based on student performance. In contrast, the experimental group adopted an AI-enhanced blended learning model, where an AI teaching assistant system was integrated with the LMS to provide personalized guidance. This system encompassed intelligent preview companions, in-class interactive guidance, and post-class targeted practice and learning pathway planning, thereby enhancing the traditional blended learning experience with AI-driven support.\u003c/p\u003e\n\u003ch3\u003eMeasurement Tools and Data Collection\u003c/h3\u003e\n\u003cp\u003eIn the study, a comprehensive suite of measurement tools and data collection methods was employed to evaluate the effectiveness of the educational interventions. The level of mastery in pharmacological knowledge was assessed through a dimension-specific standardized test paper, which measured knowledge acquisition, skill application, and clinical reasoning. Pre- and post-tests were administered one week before and after the course to both the control and experimental groups. The developmental levels of advanced competencies in pharmacology were evaluated using a combination of Situational Judgement Tests, the revised Clinical Competency Taxonomy Development Index (CCTDI) scale, platform behavioral logs, and post-course interviews. Additionally, scientific research capability was assessed through experimental tasks and research report rubric scoring. Analysis of learning process behaviors was conducted over a 16-week period using an intelligent teaching platform, which tracked core metrics such as exercise completion rates and query frequencies. Lastly, student feedback on their learning experiences was gathered using a 5-point Likert scale, which covered aspects such as clarity of objectives, timeliness of feedback, self-weakness recognition, and anxiety levels. The questionnaire used in this study is provided as Supplementary Material (Supplementary File 1). This multifaceted approach to data collection ensured a thorough evaluation of the learning outcomes and experiences of the participants in both groups.\u003c/p\u003e\n\u003ch3\u003eStatistical Methods\u003c/h3\u003e\n\u003cp\u003eDescriptive statistics were used to understand data characteristics. Paired-sample t-tests compared pre- and post-tests within cohorts, and independent-sample t-tests compared post-tests between groups. ANOVA compared teaching mode impacts, with post-hoc tests for significant differences. Pearson's and Spearman's correlation coefficients assessed relationships between variables. Multiple linear regression analyses identified significant predictors of learning outcomes. Cronbach's α coefficient assessed reliability, and construct validity was evaluated through expert review and factor analysis. Data were organized and analyzed using SPSS 26.0 or R software.\u003c/p\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003eEthical Considerations\u003c/h2\u003e\u003cp\u003e The study was approved by the institutional review board, and all participants provided informed consent.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003eImpact of AI Teaching Assistant\u0026thinsp;+\u0026thinsp;Blended Learning on Students' Mastery of Pharmacological Knowledge\u003c/h2\u003e\u003cp\u003eThe experimental group exhibited significantly higher post-test accuracy than the control group in core pharmacological knowledge and skills, as detailed in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Specifically, the experimental group achieved higher accuracy in core concepts (89.7% vs 69.9%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), drug properties (88.8% vs 53.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), key parameters (82.1% vs 64.3%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and fundamental principles (89.7% vs 75.5%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). They also demonstrated greater proficiency in practical skills such as dose calculation (81.4% vs 60.6%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), prescription review (82.2% vs 50.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), protocol design (72.6% vs 43.4%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), risk prediction (72.0% vs 42.3%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and data analysis (70.7% vs 59.0%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Furthermore, the experimental group scored significantly higher in all dimensions of clinical reasoning, including multidimensional integration (57.6% vs 35.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), dynamic anticipation (62.6% vs 36.2%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), priority decision-making (60.5% vs 36.9%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), evidence-based adjustment (56.1% vs 37.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and humanistic balance (57.7% vs 38.4%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), which are also summarized in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eImpact of AI Teaching Assistant\u0026thinsp;+\u0026thinsp;Blended Learning on Students' Mastery of Pharmacological Knowledge\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDimension\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIndicator\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eControl group\u003c/p\u003e\u003cp\u003e%, n\u0026thinsp;=\u0026thinsp;88\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eExperimental group\u003c/p\u003e\u003cp\u003e%, n\u0026thinsp;=\u0026thinsp;87\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003et-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e\u003cp\u003eKnowledge mastery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCore concepts\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e69.9\u0026thinsp;\u0026plusmn;\u0026thinsp;6.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e89.7\u0026thinsp;\u0026plusmn;\u0026thinsp;4.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e18.8805\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDrug properties\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e53.7\u0026thinsp;\u0026plusmn;\u0026thinsp;10.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e88.8\u0026thinsp;\u0026plusmn;\u0026thinsp;9.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e21.7043\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eKey parameters\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e64.3\u0026thinsp;\u0026plusmn;\u0026thinsp;9.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e82.1\u0026thinsp;\u0026plusmn;\u0026thinsp;7.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e12.8926\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eFundamental law\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e75.5\u0026thinsp;\u0026plusmn;\u0026thinsp;14.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e89.7\u0026thinsp;\u0026plusmn;\u0026thinsp;7.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e6.3716\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"4\" rowspan=\"5\"\u003e\u003cp\u003eCapacity application\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDose calculation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e60.6\u0026thinsp;\u0026plusmn;\u0026thinsp;9.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e81.4\u0026thinsp;\u0026plusmn;\u0026thinsp;11.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e14.1947\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003ePrescription review\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e50.7\u0026thinsp;\u0026plusmn;\u0026thinsp;15.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e82.2\u0026thinsp;\u0026plusmn;\u0026thinsp;13.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e13.5659\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eProtocol design\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e43.4\u0026thinsp;\u0026plusmn;\u0026thinsp;14.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e72.6\u0026thinsp;\u0026plusmn;\u0026thinsp;14.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e13.3235\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eRisk prediction\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e42.3\u0026thinsp;\u0026plusmn;\u0026thinsp;14.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e72.0\u0026thinsp;\u0026plusmn;\u0026thinsp;14.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e13.5411\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eData analysis\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e59.0\u0026thinsp;\u0026plusmn;\u0026thinsp;15.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e70.7\u0026thinsp;\u0026plusmn;\u0026thinsp;10.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e4.8717\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClinical reasoning\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMultidimensional integration\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e35.7\u0026thinsp;\u0026plusmn;\u0026thinsp;7.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e57.6\u0026thinsp;\u0026plusmn;\u0026thinsp;18.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e18.2350\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eScores are expressed as percentages (mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD) for the control (n\u0026thinsp;=\u0026thinsp;88) and experimental (n\u0026thinsp;=\u0026thinsp;87) groups. The t-values and P-values were calculated using independent samples t-tests to determine the significance of differences between groups. All reported P-values are two-tailed and statistically significant at P\u0026thinsp;\u0026lt;\u0026thinsp;0.05, indicating a significant difference in performance between the two groups across all measured indicators.\u003c/em\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003eImpact of AI Teaching Assistants Combined with Blended Learning on Students' Higher-Order Competency Development\u003c/h2\u003e\u003cp\u003eAs shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, the experimental group outperformed the control group in critical thinking skills, with higher post-test scores in truth-seeking (7.9 vs 6.4, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), open-mindedness (8.2 vs 5.5, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), analytical ability (7.5 vs 6.2, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), systematisation ability (7.5 vs 5.7, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), self-confidence (7.0 vs 6.1, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), curiosity (6.9 vs 6.3, p\u0026thinsp;=\u0026thinsp;0.007), and cognitive maturity (6.7 vs 5.8, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Additionally, the experimental group demonstrated superior self-directed learning abilities, with significantly higher scores in learning motivation (8.0 vs 7.3, p\u0026thinsp;=\u0026thinsp;0.004), learning strategies (8.1 vs 7.1, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and self-management (7.5 vs 6.8, p\u0026thinsp;=\u0026thinsp;0.005). In terms of scientific research abilities, the experimental group also showed higher post-test scores in experimental design (15.0 vs 13.9, p\u0026thinsp;=\u0026thinsp;0.020), experimental operation (14.5 vs 13.2, p\u0026thinsp;=\u0026thinsp;0.002), data analysis (16.8 vs 14.3, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), interpretation of results (14.3 vs 13.0, p\u0026thinsp;=\u0026thinsp;0.001), and report writing (13.6 vs 11.6, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). These findings suggest that AI-integrated blended learning can significantly enhance students' critical thinking, self-directed learning, and scientific research skills in pharmacology education, as further detailed in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eImpact of AI Teaching Assistants Combined with Blended Learning on Students' Higher-Order Competency Development\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDimension\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eIndicator\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eControl group\u003c/p\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;88\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eExperimental group\u003c/p\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;87\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003et-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e\u003cp\u003eCritical thinking\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSeeking truth\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e6.4\u0026thinsp;\u0026plusmn;\u0026thinsp;1.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e7.9\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e9.492\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eOpen-mindedness\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e5.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e8.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e13.8541\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAnalytical ability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e6.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e7.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e8.1866\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSystematic ability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e5.7\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e7.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e9.3407\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSelf-confidence\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e6.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e7.0\u0026thinsp;\u0026plusmn;\u0026thinsp;1.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.9159\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0006\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCuriosity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e6.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e6.9\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.4683\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0071\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCognitive maturity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e5.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e6.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.0018\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eAutonomous learning ability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLearning motivation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e7.3\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e8.0\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2.6912\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0039\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLearning strategies\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e7.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e8.1\u0026thinsp;\u0026plusmn;\u0026thinsp;1.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.7462\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSelf-management\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e6.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e7.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2.8783\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0051\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"4\" rowspan=\"5\"\u003e\u003cp\u003eScientific research capability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eExperimental design capability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e13.9\u0026thinsp;\u0026plusmn;\u0026thinsp;3.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e15.0\u0026thinsp;\u0026plusmn;\u0026thinsp;2.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e2.2718\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0203\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eExperimental operational\u003c/p\u003e\u003cp\u003ecompetence\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e13.2\u0026thinsp;\u0026plusmn;\u0026thinsp;2.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e14.5\u0026thinsp;\u0026plusmn;\u0026thinsp;2.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.1395\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0015\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eData analysis ability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e14.3\u0026thinsp;\u0026plusmn;\u0026thinsp;2.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e16.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e6.1616\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAbility to interpret results\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e13.0\u0026thinsp;\u0026plusmn;\u0026thinsp;2.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e14.3\u0026thinsp;\u0026plusmn;\u0026thinsp;2.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e3.3064\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0013\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eResearch report writing ability\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e11.6\u0026thinsp;\u0026plusmn;\u0026thinsp;2.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c4\"\u003e\u003cp\u003e13.6\u0026thinsp;\u0026plusmn;\u0026thinsp;3.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e4.8135\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eData are presented as mean scores\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD) for control (n\u0026thinsp;=\u0026thinsp;88) and experimental (n\u0026thinsp;=\u0026thinsp;87) groups. The t-values and two-tailed P-values were calculated using independent samples t-tests to assess the statistical significance of differences between groups. A P-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant, indicating that the experimental group demonstrated significantly higher competency development in all measured dimensions compared to the control group.\u003c/em\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003eThe Impact of AI Teaching Assistants and Blended Learning on Student Learning Processes\u003c/h2\u003e\u003cp\u003eAs detailed in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, students in the experimental group demonstrated greater learning engagement and focus. They completed a significantly higher number of post-class exercises (31.1 questions/week vs 22.1 questions/week, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), indicating a higher level of participation. The effective exercise rate, which reflects the proportion of targeted training, was also significantly higher in the experimental group (80.9% vs 68.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Furthermore, the frequency of repetition in weak areas was greater among experimental group students (4.2 times/person vs 1.7 times/person, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), suggesting a more focused approach to learning. Additionally, students in the experimental group sought clarification more frequently, with AI-based clarifications at 3.6 times per person and teacher-based clarifications at 0.6 times per person, compared to 0.3 times per person in the control group (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), as shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. They also adjusted their learning pathways more often (2.6 times per person vs 1.6 times per person, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). These findings, supported by the data in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, indicate that the integration of AI teaching assistants with blended learning can effectively promote active and targeted learning processes among students.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe Impact of AI Teaching Assistants and Blended Learning on Student Learning Processes\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBehavioural indicators\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eControl group\u003c/p\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;87\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eExperimental group\u003c/p\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;88\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003et-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePost-class exercise completion rate (questions/week)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e22.1\u0026thinsp;\u0026plusmn;\u0026thinsp;3.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e31.1\u0026thinsp;\u0026plusmn;\u0026thinsp;5.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e16.9434\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eEffective practice rate\u0026thinsp;=\u0026thinsp;Targeted training volume for incorrect questions / Total practice volume\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e68.7\u0026thinsp;\u0026plusmn;\u0026thinsp;13.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e80.9\u0026thinsp;\u0026plusmn;\u0026thinsp;13.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5.9703\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eQ\u0026amp;A Frequency (times/person)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAI Q\u0026amp;A\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e3.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTeacher Q\u0026amp;A\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.3\u0026thinsp;\u0026plusmn;\u0026thinsp;0.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e0.6\u0026thinsp;\u0026plusmn;\u0026thinsp;0.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5.5202\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFrequency of Repetitive Training for Weak Areas (times/person)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.7\u0026thinsp;\u0026plusmn;\u0026thinsp;0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e4.2\u0026thinsp;\u0026plusmn;\u0026thinsp;1.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e14.6934\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNumber of learning path adjustments (times/person)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.6\u0026thinsp;\u0026plusmn;\u0026thinsp;0.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e2.6\u0026thinsp;\u0026plusmn;\u0026thinsp;0.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5.6172\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eBehavioral indicators were compared between the control group (n\u0026thinsp;=\u0026thinsp;87) and the experimental group (n\u0026thinsp;=\u0026thinsp;86) using independent samples t-tests. Data are presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD). The t-values and p-values are reported to indicate the statistical significance of the differences observed. A p-value of less than 0.05 was considered statistically significant. All reported p-values are two-tailed.\u003c/em\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003eImpact of AI Teaching Assistants Combined with Blended Learning on Student Learning Experiences\u003c/h2\u003e\u003cp\u003eAccording to Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, experimental group students reported significantly higher experience scores than the control group in learning goal clarity (14.4 vs 12.2, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), feedback timeliness (16.0 vs 10.1, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and accuracy of personal weakness recognition (16.1 vs 12.5, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Additionally, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, experimental group students exhibited significantly lower levels of learning anxiety (9.9 vs 14.4, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). These results indicate that the integration of AI teaching assistants with blended learning can enhance students' learning experiences by clarifying goals, improving feedback timeliness, increasing self-awareness of weaknesses, and reducing anxiety.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eImpact of AI Teaching Assistants Combined with Blended Learning on Student Learning Experiences\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\"\u0026plusmn;\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDimension\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eControl group\u003c/p\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;87\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eExperimental group\u003c/p\u003e\u003cp\u003en\u0026thinsp;=\u0026thinsp;88\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003et-value\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eP-value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eClarity of learning objectives\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e\u003cp\u003e12.2\u0026thinsp;\u0026plusmn;\u0026thinsp;2.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e14.4\u0026thinsp;\u0026plusmn;\u0026thinsp;2.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7.3863\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTimeliness of feedback\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e\u003cp\u003e10.1\u0026thinsp;\u0026plusmn;\u0026thinsp;2.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e16.0\u0026thinsp;\u0026plusmn;\u0026thinsp;3.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e13.8548\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAccuracy of self-Awareness regarding personal weaknesses\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e\u003cp\u003e12.5\u0026thinsp;\u0026plusmn;\u0026thinsp;4.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e16.1\u0026thinsp;\u0026plusmn;\u0026thinsp;2.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5.8276\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLevel of learning anxiety\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c2\"\u003e\u003cp\u003e14.4\u0026thinsp;\u0026plusmn;\u0026thinsp;3.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\"\u0026plusmn;\" colname=\"c3\"\u003e\u003cp\u003e9.9\u0026thinsp;\u0026plusmn;\u0026thinsp;2.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e9.6724\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.0000\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eData are presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD). The experimental group (n\u0026thinsp;=\u0026thinsp;87) showed significantly higher scores compared to the control group (n\u0026thinsp;=\u0026thinsp;88) across all dimensions of learning experiences. The t-values and corresponding two-tailed P-values were calculated using independent samples t-tests, with a P-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 considered statistically significant. This indicates that the integration of AI teaching assistants with blended learning positively influenced students' experiences regarding the clarity of learning objectives, timeliness of feedback, accuracy of self-awareness regarding personal weaknesses, and reduced learning anxiety.\u003c/em\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn the context of contemporary educational reforms, traditional teaching methodologies are increasingly inadequate for addressing the diverse learning needs of students. Pharmacology, as a core bridge course connecting basic and clinical medicine, is characterized by a complex knowledge system, abstract concepts, and rapid updates, which place significant demands on students' memorization, comprehension, and application skills[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. The recent rise of blended learning models, which integrate online and offline elements, has expanded learning time and space through digital resources[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. However, these models still face challenges in accurately diagnosing individual student learning states[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. The rapid advancement of AI technology has introduced AI teaching assistants, which offer data-driven optimization recommendations to enhance teaching effectiveness[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe primary objective of this study was to evaluate the effectiveness of a blended learning model incorporating AI teaching assistants in pharmacology instruction, specifically examining its impact on students' academic performance, critical thinking, and autonomous learning abilities. The research hypothesized that students in the experimental group receiving AI teaching assistant intervention would demonstrate significantly superior academic performance, critical thinking, and autonomous learning abilities compared to the control group. The findings revealed that the experimental group achieved significantly higher post-test scores than the control group across all dimensions, including mastery of pharmacology knowledge, application of skills, clinical reasoning abilities, critical thinking, autonomous learning capabilities, and scientific research competencies. This fully supports our research hypothesis.\u003c/p\u003e\u003cp\u003eThe significant improvements observed in the experimental group can be attributed to the multifaceted support provided by the AI teaching assistant system. Utilizing technologies such as deep learning, natural language processing, and knowledge graphs, the AI assistant conducts multidimensional, in-depth analyses of students' classroom learning behaviors, assignment completion, and academic assessment data[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. This enables precise identification of discrepancies between individual learning profiles and instructional requirements, clarifying students' learning needs and challenges. Consequently, it furnishes data-driven optimization recommendations to assist educators in devising personalized guidance plans[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eSpecifically, the AI teaching assistant serves as an intelligent pre-class companion, delivers personalized interactive guidance during lessons, and provides targeted practice exercises and pathway planning for weak areas post-class, thereby aiding students in better understanding and applying pharmacology knowledge[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. Through real-case analysis questions and multi-round dialogue technology, the AI teaching assistant guides students in multidimensional integration, dynamic forecasting, prioritized decision-making, evidence-based adjustments, and humanistic balance, thereby markedly elevating their clinical reasoning capabilities[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. The AI teaching assistant also stimulates student motivation[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] while cultivating learning strategies and self-management skills, markedly elevating autonomous learning capabilities[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. Concurrently, it delivers targeted guidance in experimental design, procedure execution, data analysis, result interpretation, and report writing, substantially enhancing students' scientific research competencies[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe findings of this study align with prior research on AI teaching assistants in education. For instance, studies have demonstrated that AI tutors can substantially enhance students' academic performance[\u003cspan additionalcitationids=\"CR21\" citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e] and learning motivation[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. However, unlike previous studies, this research focused specifically on pharmacology instruction, revealing significant effects of AI tutors in improving knowledge acquisition, skill application, and clinical reasoning abilities within pharmacology. This may relate to the distinctive characteristics and pedagogical demands of pharmacology courses.\u003c/p\u003e\u003cp\u003eAlthough previous studies have identified positive impacts of AI tutors on student performance, their participants were from other disciplines, whereas this study involved undergraduate pharmacy students. This suggests that AI tutor effectiveness may be influenced by subject-specific characteristics and teaching content. Furthermore, through multi-dimensional assessment tools and detailed analysis of learning process behaviors, this study provides a more comprehensive demonstration of AI tutors' advantages in enhancing students' higher-order abilities and learning experiences.\u003c/p\u003e\u003cp\u003eThis study has several limitations. Firstly, the sample size was relatively small, comprising only 175 students, which may limit the generalizability of the findings. Secondly, the study duration was brief, spanning just one semester, making it challenging to assess the long-term effects of AI tutors. Furthermore, the research was conducted solely within the School of Pharmacy at one institution, potentially failing to fully reflect the circumstances of students at other universities or in different regions. Future research could expand the sample size to include students from different regions and academic years, thereby validating the generalizability of AI tutors in pharmacology teaching. Concurrently, long-term follow-up studies could assess their sustained impact on students' academic and professional development. Furthermore, subsequent investigations might explore the effectiveness of AI tutors across diverse disciplines, enriching their application within educational research.\u003c/p\u003e\u003cp\u003eIt is recommended that teaching staff experiment with AI teaching assistant systems in pharmacology instruction. Leveraging features such as intelligent pre-learning, personalized interactive guidance, and targeted practice for weak areas can stimulate student engagement and enhance teaching outcomes. Concurrently, educators should prioritize cultivating students' critical thinking and independent learning capabilities, using data provided by AI assistants to develop tailored teaching strategies.\u003c/p\u003e\u003cp\u003eInstitutions should provide training on AI teaching assistant systems to support faculty in implementing pedagogical reforms. Concurrently, universities may establish AI teaching assistant resource repositories, offering educators abundant instructional materials to facilitate the widespread adoption of AI technology in teaching. Education policymakers should encourage higher education institutions to undertake AI teaching assistant-driven pedagogical reforms, offering policy support and financial safeguards. Concurrently, AI teaching assistants should be incorporated into curriculum standards to facilitate broader implementation, thereby enhancing teaching quality and promoting students' holistic development.\u003c/p\u003e\u003cp\u003eThis study experimentally demonstrated the efficacy of blended learning models incorporating AI teaching assistants in enhancing students' mastery of pharmacology knowledge, application of skills, clinical reasoning abilities, critical thinking, autonomous learning capabilities, and scientific research competencies. This finding provides robust empirical support for pharmacology teaching reform. This research not only enriches the application studies of AI teaching assistants in education but also provides pharmacology educators with practical teaching methodologies. It contributes to enhancing teaching quality and fostering students' holistic development. Through the application of AI teaching assistant systems, educators can better address individual learning needs, elevate teaching effectiveness, and offer novel perspectives and directions for future medical education reform.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eNot applicable.\u003c/p\u003e\u003ch2\u003eClinical trial number\u003c/h2\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003cp\u003e Ethics approval for this study was obtained from the Institutional Review Board of Wannan Medical College (Reference Number: 2023-045). All participants provided written informed consent. This study was conducted in accordance with the principles of the Declaration of Helsinki.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e\u003cp\u003eThis study was funded by the following projects: Wannan Medical College Quality and Teaching Reform Project (2024jyxm05, 2024zhkc02), Anhui Provincial Higher Education Institutions Quality Engineering Project (2023xsxx259, 2024aijy314), and Anhui Provincial Department of Education Research Plan (2024AH051882).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eJunxiu Zhang and Chunfei Wang contributed equally to this work. Junxiu Zhang and Chunfei Wang were responsible for the conception and design of the study, and participated in data collection, analysis, and interpretation. Lutan Zhou and Xianwei Li played a key role in data collection and quality control. Wusan Wang and Shuguo Zheng, as corresponding authors, were responsible for the overall supervision of the study and the final revision of the manuscript. All authors contributed to the drafting and revision of the manuscript and agreed to be accountable for their contributions, ensuring the accuracy and integrity of the research.\u003c/p\u003e\u003ch2\u003eAcknowledgement\u003c/h2\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets generated and/or analyzed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eWei HC, Lin YH, Chang LH. The Effectiveness of a Blended Learning-Based Life Design Course: Implications of Instruction and Application of Technology. SN Comput Sci. 2023;4(4):360.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSridharan K, Sequeira RP. Artificial intelligence and medical education: application in classroom instruction and student assessment using a pharmacology \u0026amp; therapeutics case study. BMC Med Educ. 2024;24(1):431.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang Y, Chen S, Zhu Y, Zhu H, Chen Z. Knowledge graph empowerment from knowledge learning to graduation requirements achievement. PLoS ONE. 2023;18(10):e0292903.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhou LY, Wang YY. Simulation of personalized english learning path recommendation system based on knowledge graph and deep reinforcement learning. Sci Rep. 2025;15(1):34554.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYou X, Li M, Xiao Y, Liu H. The Feedback of the Chinese Learning Diagnosis System for Personalized Learning in Classrooms. Front Psychol. 2019;10:1751.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBhatia N, Khan MMU, Arora S. The Role of Artificial Intelligence in Revolutionizing Pharmacological Research. Curr Pharmacol Rep. 2024;10(6):323\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBehi R, Nolan M. Quasi-experimental research designs. Br J Nurs. 1996;5(17):1079\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFyfe P. How to cheat on your final paper: Assigning AI for student writing. AI Soc. 2023;38(4):1395\u0026ndash;405.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhang Y, Liu J, Liang J, Lang J, Zhang L, Tang M, Chen X, Xie Y, Zhang J, Su L, et al. Online education isn't the best choice: evidence-based medical education in the post-epidemic era-a cross-sectional study. BMC Med Educ. 2023;23(1):744.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBerg F, Andujar A, Chatman G, Rodriguez-Galindo C, Qaddoumi I, Moreira DC. Online Outcomes of a Pediatric Neuro-Oncology Course for Multidisciplinary Healthcare Professionals in Low- and Middle-Income Countries. J Cancer Educ 2025.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSriram A, Ramachandran K, Krishnamoorthy S. Artificial Intelligence in Medical Education: Transforming Learning and Practice. Cureus. 2025;17(3):e80852.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYang M-l. Artificial intelligence versus human teacher assistants and language learners\u0026rsquo; progress in learning and retention of complex sentences. Curr Psychol. 2025;44(7):6292\u0026ndash;304.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCetinkaya L. Redefining Mentorship in Medical Education with Artificial Intelligence: A Delphi Study on the Feasibility and Implications. Teach Learn Med 2025:1\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCharles KA, Yousuf A, Chua HC, Matthews S, Harnett J, Hinton T. AI in action: Changes to student perceptions when using generative artificial intelligence for the creation of a multimedia project-based assessment. Eur J Pharmacol. 2025;998:177508.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHudon A, Kiepura B, Pelletier M, Phan V. Using ChatGPT in Psychiatry to Design Script Concordance Tests in Undergraduate Medical Education: Mixed Methods Study. JMIR Med Educ. 2024;10:e54067.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKowitlawakul Y, Tan JJM, Suebnukarn S, Nguyen HD, Poo DCC, Chai J, Kamala DM, Wang W. Development of an Artificial Intelligence Teaching Assistant System for Undergraduate Nursing Students: A Field Testing Study. Comput Inf Nurs. 2024;42(5):334\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSharma P, Harkishan M. Designing an intelligent tutoring system for computer programing in the Pacific. Educ Inf Technol (Dordr). 2022;27(5):6197\u0026ndash;209.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCheng Z, Yang J, Shelnutt KP. Implementing GRATL and artificial intelligence in experiential learning of obesity physiology and etiology. Adv Physiol Educ. 2025;49(4):871\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHui Z, Zewu Z, Jiao H, Yu C. Application of ChatGPT-assisted problem-based learning teaching method in clinical medical education. BMC Med Educ. 2025;25(1):50.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWang P, Mi B, Lu J, Zheng F. Evaluating AI tutor feedback in medical education: a case study of computer basics and applications course for undergraduates. Disabil Rehabil Assist Technol 2025:1\u0026ndash;15.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAnderson JR, Boyle CF, Reiser BJ. Intelligent tutoring systems. Science. 1985;228(4698):456\u0026ndash;62.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSpitzer MWH, Moeller K. Performance increases in mathematics during COVID-19 pandemic distance learning in Austria: Evidence from an intelligent tutoring system for mathematics. Trends Neurosci Educ. 2023;31:100203.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJanson MP, Wenker T, Baulke L. Only a matter of time? Using logfile data to evaluate temporal motivation theory in university students' examination preparation. Br J Educ Psychol. 2024;94(4):1192\u0026ndash;207.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Pharmacology education, Blended learning, Artificial intelligence, Personalized instruction, Higher-order competencies","lastPublishedDoi":"10.21203/rs.3.rs-7898712/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7898712/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003ePharmacology education, serving as a crucial bridge between basic and clinical medicine, faces challenges with traditional lecture-based pedagogies in meeting diverse student learning needs. While blended learning has enhanced educational flexibility, it struggles with real-time diagnosis of individual learning states. Artificial intelligence (Al) teaching assistants offer transformative potential for personalized pharmacology education through intelligent learning pathways and real-time guidance.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003eThis quasi-experimental study evaluated 175 first-year pharmacy students across six classes over a 16-week pharmacology course. Students were randomized into control group(n\u0026thinsp;=\u0026thinsp;88) receiving conventional blended learning and experimental group (n\u0026thinsp;=\u0026thinsp;87) receiving Al-enhanced blended learning. The Al system provided personalized guidance through intelligent pre-class companions, in-class interactive guidance, and post-class targeted practice. Outcomes were assessed using standardized tests, competency evaluations, behavioral analytics, and learning experience surveys.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eThe experimental group demonstrated significantly superior performance across all measured dimensions. Knowledge mastery showed dramatic improvements: core concepts (89.7% vs 69.9%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), drug properties (88.8% vs 53.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001), and clinical reasoning abilities including multidimensional integration (57.6% vs 35.7%, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Critical thinking skills were markedly enhanced, with truth-seeking (7.9 vs 6.4, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and open-mindedness (8.2 vs 5.5, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) showing substantial gains. Learning engagement increased significantly, with post-class exercise completion rising to 31.1 vs 22.1 questions/week (p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and learning anxiety reduced (9.9 vs 14.4, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001).\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eAl-enhanced blended learning significantly improves pharmacology educational outcomes by providing personalized instruction that enhances knowledge mastery, critical thinking, and autonomous learning capabilities while reducing learning anxiety. This approach offers a scalable solution for addressing diverse learning needs in complex medical education contexts.\u003c/p\u003e","manuscriptTitle":"Enhancing Pharmacology Education through artificial intelligence Integrated Blended Learning: A Quasi-Experimental Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-25 10:56:44","doi":"10.21203/rs.3.rs-7898712/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"32d9052d-daf6-4df9-858a-3d3677e7190b","owner":[],"postedDate":"November 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-20T04:29:17+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-25 10:56:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7898712","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7898712","identity":"rs-7898712","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}