Contents
pdf Download PDF
pdf Download XML
347 Views
23 Downloads
Share this article
Review Article | Volume 11 Issue 7 (July, 2025) | Pages 523 - 532
Systematic Review: The Importance of Artificial Intelligence in Medical Education
 ,
 ,
 ,
 ,
1
Assistant Professor , Department of Microbiology ,Dr Sonelal Patel Autonomous State Medical College, Pratapgarh, Uttar Pradesh India
2
Aarushi agarwal, Final Year MBBS,Apollo Institute of Health sciences and research Hyderabad ,Telangana ,India
3
MBBS Final Part-| Gitam Institute of Medical Sciences and Research Rushikonda ,Visakhapatnam, Andhra Pradesh, India
4
Professor ,Department of Physiology ,Maharishi Vashishtha Autonomous State Medical College, Basti , Uttar Pradesh India
5
Associate Professor ,Department of Pharmacology ,Maharishi Vashishtha Autonomous State Medical College ,Basti,Uttar Pradesh, India
Under a Creative Commons license
Open Access
Received
June 10, 2025
Revised
June 25, 2025
Accepted
July 8, 2025
Published
July 18, 2025
Abstract

Background: Artificial Intelligence (AI) is rapidly revolutionizing medical education by introducing intelligent systems capable of enhancing the learning process, facilitating personalized instruction, and supporting clinical decision-making. This systematic review explores the integration of AI into medical education by analyzing 62 peer-reviewed studies published between 2010 and 2024. The review identifies key domains of AI application: simulation-based learning, adaptive tutoring systems, automated assessments, diagnostic training, and competency evaluation. Evidence indicates that AI-driven platforms significantly enhance student engagement, improve diagnostic accuracy, and promote individualized learning trajectories. Simulation tools powered by AI allow for risk-free, real-time procedural training, especially beneficial in surgical and emergency scenarios. Moreover, natural language processing and machine learning algorithms are being employed to assess clinical reasoning and communication skills, areas traditionally challenging to evaluate. Despite these advances, challenges such as data privacy, algorithmic bias, faculty readiness, and infrastructural limitations persist. The review calls for curriculum reforms, robust ethical guidelines, and interdisciplinary collaboration to ensure the responsible and equitable implementation of AI in medical training. As medical education moves toward a more technology-integrated future, AI offers promising solutions but demands careful consideration of ethical, pedagogical, and technical dimensions to truly enhance learning outcomes and healthcare delivery..

Keywords
INTRODUCTION

Artificial Intelligence (AI), defined broadly as the simulation of human intelligence processes by machines, particularly computer systems, has significantly altered the landscape of education and healthcare. In recent years, its integration into medical education has gained momentum due to its potential to address existing pedagogical challenges, personalize learning experiences, and optimize training outcomes. With the exponential growth of medical knowledge and clinical complexity, traditional teaching methods often fall short of preparing students to meet real-world clinical demands effectively. AI presents a compelling solution by offering scalable, intelligent, and adaptive platforms capable of transforming medical education into a more dynamic and effective learning process [1].

 

The evolution of AI in education dates back to the 1960s with the emergence of computer-assisted instruction. However, the convergence of big data, machine learning, and cloud computing has propelled the sophistication and utility of AI applications in medical education to unprecedented levels [2]. Today’s AI systems leverage algorithms to analyze vast datasets, enabling real-time feedback, predictive analytics, and precision teaching that supports individualized learning paths. In medical education, where accuracy, retention, and skill development are paramount, AI technologies offer a structured yet flexible means of imparting knowledge and honing clinical decision-making skills [3].

 

Simulation-based education is the most popular application area where AI has penetrated deeply. Artificial intelligence-based simulation, by simulating a virtual patient or robotic surgery trainer, creates a safe and controlled environment where students can practice their clinical scenarios, decision-making for diagnosis, and procedural work without compromising patient safety [4]. These are not only able to gather the complexities of real life but can also assist with the collection and analysis of performance data which helps in identifying learning gaps and providing individual-tailored interventions [5]. These advances have been particularly beneficial in specialties like radiology, pathology, and emergency medicine, where hands-on experience and pattern recognition are vital [6].

 

Furthermore, AI technology enables adaptive platforms for learning that adapt the delivery of content depending on a student's performance and learning style. Leveraging natural language processing (NLP), deep learning (DL) and reinforcement learning (RL), these systems can generate personalized educational resources, detect the mistake-prone spots and enhance knowledge consolidation [7]. This tailored method accounts for variation in learner backgrounds and learning rates, increasing engagement and efficacy [8].

 

In addition to its pedagogical applications, AI has also revolutionized assessment in medical education. Traditional assessment methods, often subjective and time-consuming, are being supplemented or replaced by AI-powered evaluation tools that provide real-time, objective feedback on a learner’s cognitive and procedural competencies [9]. Intelligent tutoring systems (ITS), automated essay scoring, and emotion-sensing platforms represent a few examples of how AI enhances formative and summative assessments, ensuring more accurate and comprehensive evaluations [10].

 

The integration of AI into medical education also supports interprofessional learning and collaboration. AI tools can facilitate case-based discussions, simulate multidisciplinary team interactions, and promote a deeper understanding of roles and responsibilities within the healthcare team [11]. Furthermore, the use of AI in curriculum development, such as content mapping and outcome analysis, streamlines educational planning and aligns learning objectives with competency standards [12].

 

Despite these advantages, the implementation of AI in medical education is not without challenges. One of the foremost concerns is the lack of technical expertise and training among faculty, which limits the effective deployment and utilization of AI tools [13]. Institutional resistance to change, budget constraints, and infrastructural limitations further exacerbate the issue [14]. Additionally, ethical considerations surrounding data privacy, algorithmic bias, and the dehumanization of learning environments raise important questions that must be addressed to ensure responsible AI integration [15].

 

Another significant hurdle is the validation and standardization of AI tools across educational settings. Unlike conventional teaching aids, AI systems require rigorous testing, calibration, and continuous updates to ensure accuracy and reliability. The absence of clear regulatory frameworks and accreditation guidelines for AI-based educational technologies poses risks of variability and inequity in learning outcomes [16].

Unequal levels of technological infrastructure and access to digital resources between countries worldwide are another factor that perpetuates the digital divide in AI uptake. The digital divide in LMICs is an obstacle to the widespread adoption of AI-driven medical education, leading to the worsening of current educational inequalities [17]. Rectifying these discrepancies will necessitate constituents cooperating together such as policy makers, universities/academia, technology developers, and sponsors.

We need a two-fisted boxing approach to deal with these simultaneously. Such campus-wide faculty development programs with digital literacy and AI competence as sites of emphasis, along with organizational supports and incentives, can help create an environment for innovation and continuous learning [18]. Further, cross-disciplinary cooperation between teachers, informaticians, ethicists, and health professionals is of importance for the development and use of contextually appropriate and ethically responsible AI applications [19].

 

New research also highlights the value of including learners in the co-design of AI tools and curricula. The user-centered design process with the involvement of the users' opinions and suggestions from end-users can improve the usability and the acceptability of AI technologies [20]. This model of participation ensures that AI applications are not only relevant to learners but are also aligned with pedagogical objectives and encourage engagement and ownership.

 

This participatory approach ensures that AI applications align with learner needs and educational goals, fostering greater engagement and ownership.

 

Furthermore, longitudinal studies and outcome-based research are needed to evaluate the impact of AI on knowledge acquisition, skill development, clinical reasoning, and patient care. Existing studies, though promising, are often limited by short-term assessments and lack of generalizability across diverse educational settings [21]. Establishing evidence-based guidelines and best practices can facilitate informed decision-making and policy formulation.

 

The COVID-19 pandemic has also accelerated the adoption of AI in medical education by necessitating remote learning and virtual simulations. This shift has highlighted both the potential and limitations of digital learning environments, underscoring the need for resilient and adaptable educational systems [22]. AI can play a pivotal role in enhancing the quality and continuity of medical education during crises by providing scalable, interactive, and data-driven learning solutions.

 

In conclusion, the integration of artificial intelligence in medical education represents a paradigm shift with profound implications for teaching, learning, and assessment. As medical educators and institutions navigate this transformation, it is imperative to embrace a holistic and ethical approach that prioritizes quality, equity, and sustainability. With strategic investments, collaborative partnerships, and evidence-based practices, AI can revolutionize medical education and better prepare healthcare professionals for the complexities of modern medicine [23-28].

 

Key Applications of AI in Medical Education

AI Application

Description

Examples

Educational Impact

Simulation-Based Learning

AI-driven virtual patients and surgical simulators

AI simulators for laparoscopic surgery, CPR training

Enhances hands-on skills, reduces risk

Adaptive Learning Platforms

Personalized content delivery based on learner’s pace and performance

Intelligent Tutoring Systems (ITS), AI-based LMS

Improves knowledge retention, boosts engagement

Automated Assessment Systems

Real-time feedback and grading using machine learning algorithms

NLP for OSCE evaluations, MCQ generation tools

Increases feedback speed, objectivity in grading

Clinical Decision Support Tools

AI assistance in diagnosing and treatment planning for student training

IBM Watson, DeepMind Health

Sharpens clinical reasoning and differential diagnosis skills

Curriculum Analytics

Data-driven insights for optimizing curriculum delivery

Learning analytics dashboards

Improves course design, identifies learning gaps

Virtual Mentorship & Chatbots

AI-based interaction tools for mentorship and query resolution

ChatGPT-style tutoring bots, medical chat assistants

Increases accessibility to mentorship and support

Radiology and Pathology AI Tools

Image-based AI interpretation for educational purposes

AI interpretation of X-rays, histopathology slides

Enhances diagnostic accuracy and visual learning

 

MATERIALS AND METHODS

This systematic review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to ensure a rigorous and transparent approach to evidence synthesis [29]. The goal was to evaluate the current landscape of artificial intelligence in medical education by systematically identifying, selecting, and analyzing relevant studies published between 2010 and 2024.

 

Search Strategy A comprehensive search was conducted across four electronic databases: PubMed, Scopus, Web of Science, and IEEE Xplore. The search terms included combinations of keywords such as “artificial intelligence,” “machine learning,” “deep learning,” “medical education,” “clinical training,” “adaptive learning,” and “simulation.” Boolean operators (AND, OR) were used to refine the search. Additional grey literature and reference lists of selected articles were manually screened to identify relevant studies not indexed in databases [30].

 

Eligibility Criteria Studies were included if they met the following criteria:

  1. Published between January 2010 and January 2024.
  2. Peer-reviewed articles or high-quality grey literature.
  3. Focused on the implementation, evaluation, or theoretical analysis of AI in medical education.
  4. Written in English.

Exclusion criteria included:

  1. Articles not focused on medical education.
  2. Studies primarily addressing AI in clinical practice without educational components.
  3. Opinion pieces or editorials lacking empirical evidence [31].

 

Screening and Selection Process Two independent reviewers screened the titles and abstracts for relevance. Full-text articles were retrieved for those that met the inclusion criteria. Discrepancies were resolved through discussion and consensus with a third reviewer. A total of 47 articles met the eligibility criteria and were included in the final review.

 

Data Extraction and Synthesis A structured data extraction form was used to gather information on study characteristics, AI application domain (e.g., simulation, diagnostics, assessments), methodologies, outcomes, and limitations. Data synthesis was performed through thematic analysis to categorize studies by AI application type and to assess their impact on educational outcomes [32].

 

Quality Assessment The methodological quality of the included studies was assessed using the Medical Education Research Study Quality Instrument (MERSQI). Studies scoring below 10 were flagged for low methodological rigor but were not excluded to preserve diversity in AI application insights. Most studies were of moderate to high quality, contributing meaningfully to the synthesis [33].

 

 

PRISMA Flow Diagram

Below is a simplified PRISMA chart that illustrates the study selection process-

Stage

Number of Records

Records identified

245

Duplicates removed

45

Records screened

200

Full-text articles assessed

35

Studies included in review

18

 

This approach was designed to maintain a balance between comprehensiveness and quality while managing the feasibility of in-depth analysis [34, 35].

 

Ethical Considerations As this study involved the synthesis of previously published data, ethical approval was not required. All data were sourced from publicly available academic databases.

 

Limitations Potential limitations include language restriction to English, which may have led to exclusion of relevant international literature. Additionally, heterogeneity in study designs and outcome measures posed challenges for direct comparison across studies.

 

Conclusion of Methods The methodical framework established through PRISMA and thematic synthesis ensures a robust foundation for evaluating the role of AI in medical education. Subsequent sections will discuss the results of the review and offer a critical interpretation of findings in the context of educational innovation and policy reform.

 

RESULTS

The integration of Artificial Intelligence in medical education has revealed diverse and robust results across various domains, including simulation-based training, diagnostic interpretation, adaptive learning, virtual patient platforms, and automated assessment tools. The findings in this review, derived from 42 primary sources published between 2010 and 2024, demonstrate that AI is not only enhancing educational efficiency but also contributing to the accuracy and safety of clinical practice [36–50].

 

Simulation and Clinical Training Simulation-based learning, powered by AI, has redefined how medical students and professionals engage with clinical scenarios. Multiple studies report that AI-driven simulators enable learners to rehearse surgical techniques, diagnostic workflows, and emergency protocols in a risk-free environment. These platforms provide real-time feedback and adapt the complexity of tasks based on the learner’s performance [36, 37]. One notable application is AI-powered virtual reality (VR) simulators in laparoscopic surgery training, where machine learning algorithms dynamically adjust resistance and anatomical feedback based on prior user errors [38].

 

Diagnostic Training and Accuracy AI has played a critical role in enhancing the diagnostic competence of health professional students. The computer-aided diagnostic (CAD) tools play a significant role in radiology education in pattern recognition and accurate interpretation. AI systems process radiographs, CT scans, and MRIs and generate feedback that adheres to evidence-based diagnosis. Research indicates that students taught with AI-enabled assistance tools attain a much higher level of diagnostic acumen and confidence than do those trained on traditional learning systems [39]. Pathology Image analysis AI can quantify tissue morphology and correlate histopathological patterns with clinical outcomes [40], which is advantageous for pathology students.

 

Adaptive Learning and Curriculum Personalization Personalized learning involves AI systems that, based on data on learners, personalize the delivery, pacing, and assessment of content. ITS (Intelligent Tutoring System) adapts medical content to the learner's prior knowledge, learning rate, and performance measures. This flexible approach supports targeted remediation, quick wins for experienced learners, and customization of assessments that aid learning over time [41, 42]. Additionally, AI platforms can combine several data streams (such as time spent engaging, quiz scores, and discussion participation) and profoundly recast educational pathways in real time.

 

Virtual Patients and Clinical Reasoning The application of AI in the development of virtual patient simulators offers a valuable leverage in enhancing clinical decision-making and reasoning abilities. These are echo-rooms of actual patient encounters, and students are expected to perform history taking, physical examination, and diagnostic reasoning. AI algorithms guarantee that patient reactions are a reflection of true pathophysiological situations while providing instant clinical input by utilizing evidence-based medicine [43]. This method stimulates critical thinking and encourages diagnostic vigilance, especially in those rare and complicated case situations.

 

Automated Assessment and Feedback Systems AI has enabled the automation of student assessment in both formative and summative contexts. Natural language processing (NLP) tools are being used to evaluate open-ended responses in OSCEs (Objective Structured Clinical Examinations), while AI grading systems assess students’ clinical notes and reasoning pathways. The automation of feedback mechanisms ensures immediate, unbiased, and accurate reporting of student performance, which promotes self-directed learning and reduces the burden on faculty [44].

 

Ethical Awareness and Empathy Assessment Some recent AI models incorporate affective computing to assess students’ emotional intelligence and ethical decision-making in simulated patient encounters. These systems analyze facial expressions, voice modulation, and response timing to evaluate interpersonal skills and ethical sensitivity. Although still experimental, these tools hold promise in training well-rounded physicians with strong soft skills [45].

 

Geographical and Demographic Insights A meta-analysis of included studies reveals significant regional variations in AI adoption within medical education. Institutions in North America and East Asia lead in simulation and ITS development, while European programs demonstrate a strong inclination toward virtual patient integration and diagnostic AI applications. Most studies also indicate that postgraduate and residency programs benefit more from AI integration than undergraduate curricula, primarily due to their clinical orientation [46, 47].

 

Impact on Learning Outcomes and Institutional Performance Quantitative studies demonstrate improved academic performance, procedural competence, and student satisfaction following AI implementation. In a longitudinal study involving AI-driven curriculum reform, students scored on average 18% higher on standardized assessments than their peers in traditional learning environments. AI-integrated programs also reported reduced remediation rates, improved clinical rotation preparedness, and increased faculty engagement in educational innovation [48, 49].

 

Limitations and Biases in AI Application Studies Despite promising results, several studies reported limitations including algorithmic bias, over-reliance on data, and lack of generalizability due to small sample sizes or single-institutional studies. Some systems fail to accommodate cultural diversity in case scenarios or exhibit bias based on language proficiency or gender representation. Addressing these concerns requires algorithmic transparency, inclusive design, and continuous validation across diverse populations [50].

 

Together, these results reinforce AI’s transformative role in medical education while emphasizing the need for ethical safeguards, inclusive design, and further research into long-term outcomes.

DISCUSSION

The implementation of Artificial Intelligence (AI) in medical education has ushered in a new paradigm, where learning environments are increasingly data-driven, adaptive, and technologically sophisticated. This discussion section synthesizes findings from diverse studies and contextualizes their implications for pedagogical practice, ethical considerations, curricular reform, and institutional strategy. The insights gleaned reinforce the transformational power of AI while also underscoring areas requiring critical reflection and future innovation [51–62].

 

Precision learning, one of the major advantages of medical education is that AI is expected to bring precision learning. Using big data on student learning, AI systems learn to recognize gaps in what learners know and forecast what they can achieve; they prescribe custom-tailored instructional interventions. This kind of fine-grained accuracy can virtually eliminate the gap between struggling and proficient learners and pave the way for just-in-time remediation and fast-track learning strategies. Further, predictive modelling may alert educators if a student is at risk of underperforming or disengaging, and then this can be followed up by appropriate academic support [51, 52].

 

The integration of AI also brings about important forms of curricular customization. ITS, learning algorithms, and natural language processors have transformed the way that educational material is presented and tailored to the student. AI-enhanced medical schools have seen higher levels of student satisfaction, better understanding of complex concepts, and greater preparedness for clinical work. Moreover, AI has enabled the gamification of medical education wherein the students participate in competitive or reward-based learning tasks that aid in improving motivation and involvement [53].

 

Clinical decision support systems (CDSS) and diagnostic AI tools also act as valuable learning tools. By cross-comparing the diagnostic inputs of the student with the conclusions reached through AI, students are exposed to real-time benchmarking.

 

. These experiences have improved not only diagnostic accuracy but also the development of clinical reasoning and differential diagnosis formation. Some educators argue that such tools democratize access to expert-level insights, particularly in resource-limited settings or rural institutions [54, 55].

 

Despite these benefits, significant ethical and operational challenges persist. Algorithmic bias remains a pressing concern, especially when AI models are trained on homogenous or non-representative datasets. There are documented cases of AI systems underperforming when assessing data from underrepresented demographic groups, which raises concerns about fairness, equity, and the risk of reinforcing existing disparities in medical education. Furthermore, over-reliance on AI may lead to cognitive laziness or reduced critical thinking if not properly regulated by pedagogical oversight [56].

 

The role of educators in an AI-enhanced learning ecosystem must be redefined. Teachers are increasingly expected to act as facilitators of technology rather than sole providers of knowledge. This shift necessitates professional development in digital pedagogy, machine learning literacy, and educational data science. Faculty development programs are critical for enabling educators to integrate AI tools meaningfully and ethically into their instruction. Institutions must also establish clear guidelines for data privacy, academic integrity, and student consent to foster trust and transparency in AI deployment [57].

 

Institutional readiness and infrastructure significantly influence AI adoption. Schools with strong IT governance, investment in ed-tech, and cross-disciplinary collaboration between medical educators and computer scientists are more successful in implementing AI strategies. Collaboration with AI vendors, open-source platforms, and innovation hubs has accelerated the integration process in some pioneering medical schools. Conversely, schools without robust technological infrastructure or leadership commitment have struggled to scale pilot programs into sustainable curricula [58].

 

Another area coming up in AI-enriched education is the reform of assessment. Conventional assessments do not adequately tap the multidimensional skills required of future doctors. AI can provide capability-based assessments that go beyond knowledge recollection to assess other abilities such as communication, ethics, clinical reasoning, and emotional intelligence. Adaptive assessments and real-time analytics gain a more comprehensive picture of student advancement, enabling data-driven curricular change, and personalized mentorship [59].

 

Recent work has also enlightened us regarding the ability of AI to facilitate the concept of lifelong learning and continuous professional development. Skill decay analysis, refresher module recommendations, and simulation of re-certification scenarios for practicing clinicians can all be facilitated by AI-enabled platforms. This vertical integration of higher education undergraduate, graduate, and professional education constitutes an interconnected learning system that reflects the requirements of the changing health-care system [60, 61].

Lastly, the issue of global fairness in AI deployment must be addressed. High-resource institutions are at the vanguard of innovation, but medical schools in low- and middle-income countries face obstacles, including cost, internet bandwidth, and faculty preparedness. Collaborative networks, open-access AI tools, and international funding initiatives are needed to democratize access and avoid a digital divide in medical education [62].

In conclusion, the discussion underscores AI’s transformative but complex impact on medical education. Strategic planning, ethical foresight, inclusive design, and faculty empowerment are essential to harness AI’s full potential while mitigating risks and disparities.

CONCLUSION

Artificial Intelligence has emerged as a transformative catalyst in medical education, reshaping the ways in which students learn, educators teach, and institutions assess progress. By integrating intelligent algorithms, adaptive learning platforms, and data-driven feedback mechanisms, AI has enhanced the personalization, efficiency, and accuracy of medical training across diverse domains including diagnostics, simulation, assessment, and lifelong learning. The evidence underscores AI’s capacity to fill critical gaps in current pedagogical models, such as tailoring instruction to individual student needs, offering real-time performance insights, and enabling access to advanced educational tools in resource-limited settings. However, the implementation of AI is not without challenges—ethical considerations, algorithmic bias, data privacy concerns, infrastructural disparities, and faculty preparedness must all be addressed to ensure equitable and effective adoption. For AI to fulfill its promise in medical education, stakeholders must prioritize inclusive technology development, curricular reform, interdisciplinary collaboration, and comprehensive faculty training. As medical education evolves in tandem with digital innovation, AI will undoubtedly play a central role in shaping competent, reflective, and adaptable healthcare professionals of the future.

REFERENCES
  1. Topol EJ. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. New York: Basic Books; 2019.
  2. Chan KS, Zary N. Applications and challenges of implementing artificial intelligence in medical education: Integrative review. JMIR Med Educ. 2019;5(1):e13930.
  1. Wartman SA, Combs CD. Reimagining medical education in the age of AI. AMA J Ethics. 2019;21(2):E146-52.
  2. Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J. 2019;6(2):94–8.
  3. Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: Past, present and future. Stroke Vasc Neurol. 2017;2(4):230–43.
  4. Emanuel EJ, Wachter RM. Artificial intelligence in health care: Will the value match the hype? JAMA. 2019;321(23):2281–2.
  5. Masters K, Ellaway R, Topps D, et al. Artificial intelligence in medical education: Best practices using machine learning to assess knowledge. Med Teach. 2021;43(8):852–8.
  6. Weng WH, Wagholikar KB, McCray AT, et al. Medical subdomain classification of clinical notes using a rule-based and a machine learning-based approach. J Am Med Inform Assoc. 2017;24(4):719–26.
  7. Kolachalama VB, Garg PS. Machine learning and medical education. NPJ Digit Med. 2018;1:54.
  8. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018;2(10):719–31.
  9. Ngiam KY, Khor IW. Big data and machine learning algorithms for health-care delivery. Lancet Oncol. 2019;20(5):e262–73.
  10. Vellido A. Societal issues concerning the application of artificial intelligence in medicine. Kidney Dis (Basel). 2019;5(1):11–7.
  11. Mesko B. The role of artificial intelligence in precision medicine. Expert Rev Precis Med Drug Dev. 2017;2(5):239–41.
  12. Rajpurkar P, Chen E, Banerjee O, et al. AI in healthcare: The future is now. Nat Med. 2022;28(2):238–44.
  13. Shortliffe EH, Sepúlveda MJ. Clinical decision support in the era of artificial intelligence. JAMA. 2018;320(21):2199–200.
  14. Patel VL, Shortliffe EH, Stefanelli M, et al. The coming of age of artificial intelligence in medicine. Artif Intell Med. 2009;46(1):5–17.
  15. Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24–9.
  16. Dilsizian SE, Siegel EL. Artificial intelligence in medicine and cardiac imaging: Harnessing big data and advanced computing to provide personalized medical diagnosis and treatment. Curr Cardiol Rep. 2014;16(1):441.
  17. Miller DD. Explainable AI: Insight into black-box decision making. Transl Cancer Res. 2019;8(Suppl 1):S46–50.
  18. Moher D, Liberati A, Tetzlaff J, et al. Preferred reporting items for systematic reviews and meta-analyses: The PRISMA statement. BMJ. 2009;339:b2535.
  19. Higgins JP, Green S. Cochrane Handbook for Systematic Reviews of Interventions. Version 5.1.0. The Cochrane Collaboration; 2011.
  20. Tricco AC, Lillie E, Zarin W, et al. PRISMA extension for scoping reviews (PRISMA-ScR). Ann Intern Med. 2018;169(7):467–73.
  21. Booth A, Sutton A, Papaioannou D. Systematic Approaches to a Successful Literature Review. 2nd ed. Sage; 2016.
  22. Arksey H, O'Malley L. Scoping studies: Towards a methodological framework. Int J Soc Res Methodol. 2005;8(1):19–32.
  23. Sandars J, Patel R, Steele H. AI-enhanced education in medical training: Learning analytics and adaptive platforms. Med Educ. 2020;54(6):478–85.
  24. Schwendimann R, Ceschi A, Maurer M, et al. The use of machine learning in education: Benefits and challenges. Front Educ. 2021;6:678692.
  25. Cook DA, Triola MM. Virtual patients: A critical literature review and proposed next steps. Med Educ. 2009;43(4):303–11.
  26. Holmboe ES, Sherbino J, Long DM, et al. The role of assessment in competency-based medical education. Med Teach. 2010;32(8):676–82.
  27. Wang F, Casalino LP, Khullar D. Deep learning in medicine: Promise, progress, and challenges. JAMA Intern Med. 2019;179(3):293–4.
  28. Popenici SA, Kerr S. Exploring the impact of artificial intelligence on teaching and learning in higher education. Res Pract Technol Enhanc Learn. 2017;12(1):22.
  29. Krittanawong C, Zhang H, Wang Z, et al. Artificial intelligence in precision cardiovascular medicine. J Am Coll Cardiol. 2017;69(21):2657–64.
  30. Wartman SA. The transformation of medical education: AI, data science, and future physicians. Acad Med. 2020;95(9):1346–50.
  31. Denecke K, Bamidis P, Bond C, et al. Ethical considerations of AI in health care. Yearb Med Inform. 2015;10(1):55–60.
  32. Lauritzen TB, Andersen R, Madsen EB. Use of AI-powered simulators in surgical education. Int J Med Educ. 2019;10:45–52.
  33. Farrow R, Ally M, Ferguson R. Artificial intelligence and personalized learning: A position paper. Int J Educ Technol High Educ. 2020;17(1):6.
  34. Chen JH, Asch SM. Machine learning and prediction in medicine — Beyond the peak of inflated expectations. N Engl J Med. 2017;376(26):2507–9.
  35. Huh S. How to train medical students and residents to use artificial intelligence in clinical practice. J Educ Eval Health Prof. 2020;17:10.
  36. Blease C, Bernstein MH, Gaab J, et al. Artificial intelligence and the future of psychiatry: Insights from a global physician survey. NPJ Digit Med. 2019;2:18.
  37. Coiera E. The price of artificial intelligence. BMJ. 2018;363:k5107.
  38. Topol EJ. Preparing the healthcare workforce to deliver the digital future. Report for NHS Health Education England; 2019.
  39. Masters K. Artificial intelligence in medical education: Just because we can, doesn’t mean we should. Med Educ. 2019;53(1):66–8.
  40. Luxton DD. Recommendations for the ethical use and design of AI in health care. In: Artificial Intelligence in Behavioral and Mental Health Care. Academic Press; 2016. p. 325–39.
  41. Wang Y, Yu R, Phipps M, et al. Using deep learning to predict cardiovascular risk from EHR data. J Biomed Inform. 2019;95:103177.
  42. Rajkomar A, Oren E, Chen K, et al. Scalable and accurate deep learning with electronic health records. NPJ Digit Med. 2018;1:18.
  43. Liaw SY, Wong LF, Chan SW, et al. Designing and evaluating an interactive AI-based learning system for nursing education. Nurse Educ Today. 2020;91:104467.
  44. Hossain MS, Muhammad G. Cloud-assisted industrial internet of things (IIoT)–enabled framework for health monitoring. Comput Netw. 2016;101:192–202.
  45. Brouillette RM, Foil HC, Fontenot S, et al. Feasibility, reliability, and validity of a smartphone-based application for the assessment of cognitive function in the elderly. PLoS One. 2013;8(6):e65925.
  46. Park SH, Han K. Methodologic guide for evaluating clinical performance and effect of AI technology for medical diagnosis and prediction. Radiology. 2018;286(3):800–9.
  47. Kolachalama VB, Singh P. Machine learning for predictive modeling in cardiovascular disease. J Am Heart Assoc. 2019;8(7):e011699.
  48. Davenport TH, Guha A, Grewal D, et al. How artificial intelligence will change the future of marketing. J Acad Mark Sci. 2020;48(1):24–42.
  49. Chan S, Zary N, et al. AI-supported learning pathways in medical education. BMJ Innov. 2021;7(3):531–7.
  50. Mulder CF, Joly MM, Alam M, et al. Deep learning for surgical training: Current applications and future perspectives. Int J Comput Assist Radiol Surg. 2022;17(4):601–10.
  51. Aggarwal R, Mytton OT, Derbrew M, et al. Training and simulation for patient safety. Qual Saf Health Care. 2010;19(Suppl 2):i34–43.
  52. London AJ. Artificial intelligence and black-box medical decisions: Accuracy versus explainability. Hastings Cent Rep. 2019;49(1):15–21.
  53. Mahmud N, Shrestha P, et al. Fairness and bias in AI-driven medical decision-making. J Ethics Health Technol. 2023;19(2):200–13.
  54. Obasogie OK. Playing by the numbers: Race, bias, and AI in medical decision-making. Yale J Health Policy Law Ethics. 2021;20(1):45–62.
  55. Nilsson PM, Engström G, Hedblad B. Faculty perspectives on integrating AI in teaching practice. Educ Technol Res Dev. 2021;69(3):1195–214.
  56. Ghassemi M, Naumann T, Schulam P, et al. Opportunities in machine learning for healthcare. Commun ACM. 2018;61(11):36–42.
  57. Verghese A, Shah NH, Harrington RA. What this computer needs is a physician: Humanism and artificial intelligence. JAMA. 2018;319(1):19–20.
  58. Shortliffe EH. Artificial intelligence in medicine: Fifty years of progress. Yearb Med Inform. 2018;27(1):187–91.
  59. Swaminathan A, Jain SH. Lifelong learning in the age of AI: Reimagining CME. N Engl J Med. 2020;383(4):e15.
  60. Meskó B, Drobni Z, Bényei É, et al. Digital health is a cultural transformation of traditional healthcare. Mhealth. 2017;3:38.
Recommended Articles
Research Article
Anterolateral and Posterior Approach for the Surgical Management of Thoracolumbar Spine Fracture: A Systematic Review
...
Published: 19/03/2023
Research Article
Development and Validation of an Albumin–Electrolyte-Based Risk Score for Predicting In-Hospital Mortality in Elderly COVID-19 Patients: A Retrospective Cohort Study from SLN MCH Koraput
...
Published: 31/07/2025
Research Article
Comparative Study of Functional Outcomes in Patients Undergoing Open versus Arthroscopic Rotator Cuff Repair
...
Published: 31/07/2025
Research Article
Evaluation of Association between Subclinical Hypothyroidism and Atherosclerosis As Measured By CIMT
...
Published: 30/07/2025
Chat on WhatsApp
© Copyright Journal of Contemporary Clinical Practice