INTRODUCTION
Recent years have seen exponential development and quick technology breakthroughs in the domains of augmented reality (AR) and virtual reality (VR), which have revolutionized several sectors throughout the world. These game-changing technologies have emerged as useful resources with the potential to revolutionize the way doctors are educated and trained ( Thomas and Forbes, 2020). The study thoroughly examines the advantages and challenges of these innovations, emphasizing their positive impact on patient care, doctor–patient communication, and the security of medical data for disabled individuals. It highlights how AR and VR can facilitate remote diagnostics and patient profiling, enabling individuals with mobility constraints to access healthcare services from the comfort of their homes. Rising patient expectations have medical educators searching for fresh ways to help students make the connection between classroom learning and real-world practice. Although vital, traditional didactic teaching approaches sometimes fall short of providing students with the kind of immersive and experiential learning situations that would best prepare them for the issues they will face in the actual world of medicine ( Lee, 2018).
AR and VR simulations can be tailored to accommodate various disabilities, offering customizable interfaces, adaptive interactions, and sensory experiences that cater to individual needs. For instance, individuals with mobility impairments can virtually participate in medical procedures and surgeries, gaining a deeper understanding of the processes involved. Those with visual impairments can utilize auditory cues and haptic feedback to navigate and interact within these virtual environments effectively. Focusing on their ability to improve experiential learning and enrich medical training curricula, this review seeks to investigate the transformational potential of AR and VR in health education ( Kumar et al., 2022a). AR and VR technologies provide medical students and professionals with an unparalleled chance to engage in realistic, risk-free experiences by producing lifelike simulations, virtual settings, and interactive situations ( Gallagher, 2011). In this article, we will take a look at how AR and VR are being used in various settings to better educate future doctors. Simulations in this category include, but are not limited to, those of anatomy and surgery ( Sobel, 2020), patient contact situations ( Seager, 2020), diagnostic training ( Lu, 2020), and emergency responses ( Kononowicz, 2020). Learning important clinical skills, decision-making abilities, and cooperation in immersive virtual environments using AR and VR increases students’ sense of confidence and competence ( Dey, 2017).
Moreover, the review underscores the revolutionary potential of AR- and VR-enhanced therapies for mental health, which can be especially beneficial for disabled individuals who may face unique mental health challenges. These immersive therapeutic experiences can provide an alternative form of support that complements traditional methods. The cognitive and psychological benefits of using AR and VR for medical education will also be discussed. According to studies, students are better able to remember and understand complicated medical topics after participating in more active and rich educational experiences ( Won et al., 2017). In addition, students can develop empathy and improve their interpersonal skills through their interactions with virtual patients in simulated medical settings ( Rosseel, 2021). AR and VR provide medical students with novel options for active learning by placing them in simulated situations, where they may make decisions in real time and see the results of those decisions, strengthening their understanding of the material ( Chirico et al., 2021).
The examination of possible difficulties teachers and institutions may encounter as they work to include AR and VR into medical health education. Maximizing the revolutionary influence of emerging technologies on medical curriculum would require addressing concerns including cost, accessibility, technical skill, and content production ( Huston, 2013). Ethical considerations, privacy protections, and data safety in artificial intelligence (AI) and Internet of Things (IoT)-enabled healthcare settings are of paramount importance, particularly when catering to disabled individuals who may be more vulnerable to privacy breaches or data mishandling. The review emphasizes the necessity of incorporating universal design principles and accessibility standards to ensure that AR and VR applications are usable by individuals with diverse disabilities.
As we set out on this in-depth exploration of the exciting field of AR and VR in medical health education, it becomes clear that these game-changing technologies have the potential to radically alter the course of healthcare education in the years to come. AR and VR have the potential to train a new generation of medical professionals to be experts in their specialty while simultaneously possessing the soft skills and a humanistic perspective necessary to care for patients ( Bohr and Memarzadeh, 2020). In conclusion, this study provides a robust framework for harnessing the transformative capabilities of AR and VR technologies in medical health education, with a strong emphasis on their profound benefits for disabled individuals. By enabling experiential learning, remote participation, and immersive therapies, AR and VR contribute to a more equitable and inclusive healthcare education landscape, ultimately leading to improved health outcomes and enhanced quality of life for disabled individuals.
Evolving medical education through virtual environments
The metaverse concept is creating substantial excitement not only in technology communities but also in various other sectors. This growing interest is exemplified by notable moves such as Mark Zuckerberg’s renaming of Facebook to “Meta.” As per insights from GlobalData, the metaverse is poised to revolutionize multiple industries within the next 3 years. Key sectors like retail, financial services, and manufacturing are expected to undergo significant transformations. The impact of the metaverse on healthcare could be particularly profound, offering innovative applications in telehealth, therapeutic interventions, and virtual training.
The shift from traditional methods to simulation-based training
Medical education has traditionally involved intensive study of medical diagrams and hands-on cadaver dissections, a practice that is both costly and challenging. Additionally, the training of surgeons inherently carries the risk of medical errors during the learning process. However, recent advancements have ushered in a transformative shift toward simulation-based training, drawing inspiration from the aviation industry. This evolution in medical training leverages the capabilities of VR and AR technologies.
The emergence of the metaverse in medical training
A significant development in this domain is the potential integration of the metaverse, an immersive virtual world, into medical education. Rupantar Guha, an analyst at GlobalData, notes that while the metaverse’s definition varies across sectors, it generally refers to a virtual space where users engage in real-time interactions within simulated environments. This concept is particularly revolutionary in medical training, allowing for the creation of three-dimensional (3D), anatomically precise models of the human body, a stark contrast to the two-dimensional images that have been the cornerstone of medical study.
Practical applications and benefits in medical training
In the current era, characterized by the rapid evolution of the metaverse—a collective virtual shared space created by the convergence of virtually enhanced physical reality, AR, and VR—the framework for maximizing the potential of AR and VR in medical education is increasingly pivotal. This integration is not just about overlaying digital information onto the real world or immersing users in a completely virtual environment; it is about leveraging these technologies to create a seamless, interactive, and highly engaging educational platform. In medical education, the implementation of AR and VR within the metaverse framework promises a revolution in the way future healthcare professionals are trained. This involves using AR to superimpose digital information onto physical medical equipment or patients for real-time learning and employing VR for immersive learning experiences where students can practice surgeries or diagnose virtual patients in a risk-free, controlled environment. The synergy of these technologies within the metaverse framework amplifies their individual strengths, offering an unparalleled depth of educational experience that is interactive, customizable, and incredibly lifelike, thereby setting a new standard for medical training and education as shown in Figure 1.
The framework for maximizing the potential of AR and VR in medical education. Abbreviations: AR, augmented reality; VR, virtual reality.
In practical terms, the metaverse offers a virtual platform for medical professionals to refine their skills safely and effectively. Dr. Ioannis Skalidis from Lausanne University Hospital’s cardiology department observes a growing need for hands-on experience, especially in specialized fields like interventional cardiology. The metaverse addresses this by allowing simultaneous participation in virtual surgical operations, providing invaluable first-hand experience.
Moreover, contemporary medical students, often more acquainted with VR technologies and video games, show a natural comfort in navigating these virtual environments. This familiarity facilitates a smoother transition into exploring specialized medical fields within the metaverse, as they can intuitively control avatars and interact with complex simulations. Feedback indicates a strong interest among medical students in utilizing these advanced virtual platforms for in-depth learning and skill development in areas like cardiology.
The potential of metaverse-based medical education
The expansion of VR and AR in medical education presents a frontier for revolutionary changes in the field. Traditional methods, such as classroom lectures with PowerPoint presentations and textbooks, are being reimagined in the metaverse, transforming them into interactive 3D experiences akin to a laboratory setting. Instructors can utilize large 3D models for demonstrations, while students engage with smaller, detailed models to deepen their understanding. The metaverse’s programmable nature allows for enhanced information delivery about specific structures, offering dynamic visualizations of complex systems and pathways. This shift is expected to significantly impact knowledge acquisition and retention, particularly in studying anatomy. Evidence of this was seen in a study where students using AR to learn cardiac physiology outperformed their peers learning through traditional methods.
Application in clinical training and assessment
The metaverse’s capabilities extend to clinical training and assessment. For instance, in the objective structured clinical examination, traditionally reliant on role-playing, the metaverse can offer a more realistic and accessible “Mock Exam” environment. Similarly, in problem-based learning, the metaverse can simulate virtual patients, providing more engaging and realistic clinical scenarios. Institutions can tailor these virtual environments to align with specific curricular needs, like integrated block curricula, enhancing both the efficiency and effectiveness of learning.
Addressing the challenges in clinical training
The increasing skill burden on medical students and residents, coupled with limited hospital exposure, necessitates an effective training environment. The metaverse, with its immersive and customizable nature, offers a safe space for practicing medical procedures. Unlike mannequins and task trainers, which provide high-fidelity haptic feedback but lack versatility and patient interaction simulation, the metaverse enables trainees to experience complete clinical scenarios. This aspect is particularly beneficial in complex training such as advanced trauma and cardiac life support. Additionally, the resource intensiveness of traditional training methods makes the metaverse a cost-effective alternative. Studies have shown that VR/AR training can lead to comparable or better outcomes in various procedures, advocating for its use in surgical training to enhance performance and shorten learning curves.
Current implementations and future prospects
Despite the promising potential, current implementations of the metaverse in medical education remain largely experimental, often confined to studies comparing its efficacy with traditional teaching methods. Anatomical education, traditionally reliant on cadaver dissection, faces ethical, logistical, and emotional challenges. The metaverse offers a solution by providing spatial visualization of structures in 3D, which traditional methods cannot achieve. Some institutions have developed immersive VR programs to simulate operating rooms and anatomical structures, enhancing the learning experience. In terms of practical applications, VR/AR is already being used for various medical procedures and planning minimally invasive surgeries (MISs). Personalized 3D models, created from preoperative imaging, assist surgeons in visualizing patient anatomy and optimizing surgical strategies. These models can also be integrated into AR technologies for real-time guidance in surgeries, a technique currently explored in fields like neurosurgery and orthopedics.
The Literature Review section refers to literature reviews, the Research Needs and Gaps section discusses the research needs and gaps, indicating the necessity for more studies on the effects of various task performance, and user experiences (UXs) in AR interactions. It also raises concerns about data security (DS), privacy, and ethical issues with AI applications in healthcare. The Research Gaps section highlights a significant problem and evaluations for AR interactions due to a lack of comprehensive research. The Conclusion section presents research needs with specific recommendations for further analysis of exoskeleton types in AR interactions and ethical considerations in AI-powered healthcare. It also emphasizes the need for more long-term testing with diverse demographic groups. It concludes by reinforcing the potential of AR/VR in medical health education, underlining how they can revolutionize healthcare and education by integrating AI and IoT-enabled healthcare solutions. However, it also underlines the accompanying challenges, such as DS and privacy concerns. The article also reviews other related pieces of research throughout.
LITERATURE REVIEW
AR and VR are two examples of immersive technologies that are attracting a lot of interest in the healthcare and education sectors. New possibilities for training enhancement, enhanced learning environments, and the solution of previously intractable problems have arisen due to technological advancements. This article is a survey of the most up-to-date research on the outcomes and uses of immersive technology in healthcare and academia.
Medical and educational works that define immersive technologies and their uses
The consequences of an upper-limb inactive exoskeleton on musculoskeletal load, expressed pain, and task performance were studied by Bartalucci et al. (2023) in the context of AR interactions ( Bartalucci et al., 2023). Twenty healthy people took part in the trial, executing AR activities both with and without the exoskeleton. The results revealed that engaging in AR activities lacking the exoskeleton placed a heavy burden on the shoulder muscles, resulting in pain and an increased risk of injury. The employment of a passive upper-limb exoskeleton, on the other hand, significantly decreased muscular activity in certain muscles while doing AR tasks, therefore supporting the upper limbs and decreasing the risk of musculoskeletal tension and irritation. Task completion was not impacted by the exoskeleton, suggesting that using one might alleviate physical strain during AR interactions without sacrificing efficiency. This research shows how exoskeletons may be used to improve AR experiences and overcome physical barriers encountered in the course of interactive tasks.
The electrical and mathematical foundations of a finger exoskeleton system are presented by Kong et al. (2023). An STM32 development board and a Sparkfun interface board work together to regulate the input voltage and convert it to a stable 24 V supply voltage. The restricted Lagrangian approach is utilized to construct the dynamic model and analyze forces and torques exchanged by the system’s linked rigid components; the finger mechanism is a planar kinematic chain with 18 degrees of freedom. The results of this research show that a finger exoskeleton system may be successfully implemented to aid in hand movements and have beneficial uses in medical treatment and aids for technology.
The Diagnosis of Mental Health Issues in Counselling course at the graduate level was the focus of research by Lowell and Tagare (2023). The virtual reality learning environment (VRLE) featured role-playing exercises in a virtual clinical counseling facility. The results of the study showed that when students participated in VRLE, they felt more comfortable and positive about their learning. Because VRLEs are so immersive, students can use them to simulate counseling sessions with digital representations of real-life clients. The results of the study indicate that VRLEs may be used as a valuable adjunct to more conventional forms of instruction in the field of counseling education.
Smart glasses have been studied for their effect on human perception, namely in medical professionals by Sobieraj et al. (2023). The research incorporated both an online experiment and in-person focus groups. The results of the virtual experiment demonstrated the importance of smart glasses’ design in influencing people’s opinions about them. More positive evaluations were given to designs that were both familiar and inconspicuous on measures of warmth, competence, trustworthiness, contentment, and wrath. Participants in the focus group research show both bewilderment and interest when first being exposed to smart glasses. To increase trust and acceptability, the research recommends describing the usage of smart glasses. This is especially important in healthcare settings, where face-to-face interactions are essential.
The Immersive Technology Evaluation Measure (ITEM) was developed and validated in the context of healthcare education in a mixed-methods research by Jacobs et al. (2023). Participants in the research were given a variety of immersive experiences, and their positive reactions to the ITEM suggest that it might be useful for gauging the efficacy of immersive technology in medical training. As a framework for future research and evaluation, the study also developed the model of immersive technology in healthcare education to visualize connections between immersive technology and learning ideas.
The precision of an AR-based dynamic navigation system for dental implant placement was studied by Tao et al. (2023). Positive results were found for the study’s implant positioning accuracy, with aberrations about on par with those of a traditional dynamic navigation system. Using HoloLens 2 (HL), the AR navigation system may superimpose virtual implant routes, which may be useful in dental surgery and increase precision.
The potential of AR technology for urology surgical education was investigated by Dominique et al. (2023). The research showed that AR may be used to supplement in-person instructions and improve communication between instructors and students in distributed learning environments. Trainees thought AR training was just as good as in-person sessions, while teachers, influenced by their considerable expertise, frequently regarded virtual training as worse. The study stresses the need for more investigation to perfect the use of AR in surgical training.
To demonstrate the usefulness of VR photo scan technology in trauma-focused cognitive behavioral therapy (TF-CBT) for a patient with post-traumatic stress disorder (PTSD) and depression, Best et al. (2023) presented a case study. VR-enhanced TF-CBT was found to be effective in reducing symptoms of PTSD and depression, suggesting a role for accessible VR technology in the field of mental health ( Best et al., 2023).
To solve the robot-assisted surgery (RAS) video annotation problem, Portalés et al. (2023) suggested a method that takes into account object tracking and stereo matching at the same time ( Portalés et al., 2023). Although difficulties in choosing tracking algorithms and region of interest sizes need to be solved, the method demonstrated the practicality and potential effectiveness for real-time RAS video annotation.
During the COVID-19 epidemic, Yang et al. (2023) surveyed pharmacy students to determine their thoughts, feelings, and behaviors in response to virtual reality simulation (VRS). The majority of students in the research had a favorable impression of VRS, believing that it would help them acquire valuable skills and information in the real world. The research recommends enhancing pharmacy students’ VRS experiences through the use of information technologies like AR.
Recently, Apple has launched Apple’s Vision Pro leverages immersive technologies to redefine UXs across various domains. In the realm of healthcare, it offers advanced AR capabilities for precise medical visualization, enabling surgeons to overlay vital data directly onto patients during procedures. In education, Vision Pro enhances interactive learning by creating immersive virtual environments, allowing students to explore subjects like history and science first-hand. Additionally, the technology finds applications in the creative field, empowering artists with a dynamic canvas for immersive digital artistry. Beyond these sectors, Apple’s Vision Pro holds the potential for revolutionizing enterprise tasks through intuitive holographic interfaces, thereby propelling productivity and innovation to new heights. Creating a comparative analysis in a tabular format requires considering several factors and domains where immersive technologies like VR, AR, and mixed reality (MR) are used. Let us compare these technologies across different domains such as education, healthcare, entertainment, and retail.
Table 1 provides a general overview and may vary based on specific applications and advancements in each domain. It illustrates how immersive technologies are being uniquely adapted to meet the needs and challenges of different industries, while also hinting at future trends and potential growth areas.
Immersive technologies used in different domains.
| Factor | Education | Healthcare | Entertainment | Retail |
|---|---|---|---|---|
| Technology used | VR, AR, MR | VR, AR, MR | VR, AR | VR, AR |
| Primary application | Interactive learning, virtual classrooms, language training | Medical training, surgery simulation, patient therapy | Video games, virtual tours, immersive movies | Virtual try-ons, interactive product displays, in-store navigation |
| Key benefits | Enhances engagement, provides safe learning environments, allows remote learning | Improves surgical precision, aids in-patient rehabilitation, offers risk-free training environments | Increases user engagement, offers novel experiences, broadens storytelling capabilities | Enhances customer experience, provides detailed product visualization, improves buying decisions |
| Challenges | Technological accessibility, content development, integrating with traditional curricula | High costs of implementation, privacy concerns, need for specialized training | Technology adoption, motion sickness in VR, content moderation | Integrating with existing retail systems, user privacy, creating realistic experiences |
| Future trends | Widespread adoption in schools, use for special education, global classroom experiences | Telemedicine, enhanced patient care, advanced surgical training tools | Increased use of AR in movies and shows, more interactive gaming experiences | Personalized shopping experiences, AR in physical stores, integration with online shopping |
Abbreviations: AR, augmented reality; MR, mixed reality; VR, virtual reality.
AR/VR transformative potential articles related to medical health education
The study focuses on treating driving anxiety using VR-based psychological therapy. Driving anxiety is a significant problem stemming from the fear of driving or specific phobias associated with motor vehicle crashes (MVCs). Research indicates that approximately a quarter of people develop PTSD after MVC, resulting in avoiding driving or severe driving anxiety. While VR-based treatments have shown effectiveness in addressing similar disorders like fear of flying or social anxiety, their potential for treating driving anxiety is not thoroughly investigated. Crucially, though potentially beneficial, studies about VR-based treatments for driving anxiety are generally low in quality due to small participant sizes and the absence of controlled designs, indicating the need for further, more robust research ( Kumar et al., 2022b). In this article, Chengoden et al. (2023) examine the benefits and difficulties of applying the metaverse to healthcare, with a special emphasis on the integration of multiple technologies. The technologies reviewed range from blockchain to AI to the IoT to 5G and beyond to digital twins to big data to quantum computers to human–computer interface (HCI) to computer vision. Blockchain technology in the metaverse allows for decentralized digital asset and data collecting, thanks to its safe and transparent data management. It has the potential to expand access to medical treatment, strengthen doctor–patient relationships, and safeguard personal health information.
Using AI in the metaverse can fortify critical systems, deliver fully immersive 3D experiences, and enhance medical data processing. It is helpful for diagnostics, patient data management, and medication discovery, but it also brings up privacy and ethical concerns for patients. Remote patient monitoring (RPM), RASs, and management of chronic diseases are all made possible by the IoT and the metaverse. However, difficulties arise with regard to DS and standardization. Healthcare services in the metaverse, such as virtual wellness, mental health assistance, and remote procedures, are improved by the high speed and low latency connectivity made possible by 5G and beyond technology. Healthcare simulations, treatment planning, and individualized artificial organs can all benefit from the use of digital twins, which make digital copies of real-world things. Making faithful copies is difficult, as are the massive computational needs involved. Although big data in the metaverse can help provide useful insights for healthcare applications, doing so effectively needs the use of appropriate methods for processing massive amounts of data in real time. Despite its benefits to security and processing in the metaverse, quantum computing (QC) raises new questions about data privacy, energy efficiency (EE), and system integration. HCI technology, including head-mounted displays (HMDs) and haptic devices, improves medical training, consultation, and care in the metaverse. Immersive experiences in the metaverse are made possible with the help of computer vision, which is used for things like making avatars and identifying objects. It improves diagnostic imaging, treatment, and telehealth monitoring. Overall, the literature study demonstrates how combining these innovations with the metaverse can transform healthcare delivery, learning, and discovery. To reap the benefits of this integration, however, many obstacles must be overcome.
This article reviews the work by Ferrari et al. (2020) on reducing registration errors in AR optical see-through head-mounted displays (OST-HMDs) caused by viewpoint parallax. In order to properly align the real-world vision with the computer-generated content, users of conventional OST-HMDs must undergo a calibration procedure. The projection parameters of the virtual rendering camera are estimated during calibration. The viewpoint parallax causes registration issues, although the authors recommend using a magnifier in front of the OST screen to fix this problem. Like the relayed computer-generated images, the magnifier alters the visual sense of the real scene and projects it to infinity. The user’s average fixation point distance can be used to determine the focal distance of the magnifier, allowing for a parallax-free view of the real plane. To calculate the transformation between the tracking sensor and the eye, the authors describe a calibration technique in which a camera stands in for the user’s eye. The virtual rendering makes the necessary adjustments to the magnifier parameters to account for the scale factor, so that the virtual and real content are properly aligned. The experimental results show that the suggested method effectively reduces peripersonal registration mistakes.
An autostereoscopic surgical navigation framework for MIS is presented in this review by Zhang et al. (2022). This framework utilizes a 3D autostereoscopic display to show the surgeon preoperative medical models and intraoperative laparoscopic images. Segmentation and reconstruction of medical models from computed tomography/magnetic resonance imaging datasets are integral parts of the proposed framework’s preoperative data preparation. From laparoscopic pictures, point clouds of tissue surfaces are recreated intraoperatively using a semiglobal block matching technique. The preoperative models and intraoperative point clouds are registered using a coarse-to-fine deformable registration. In order to see the combined virtual overlay and laparoscopic scenes in three dimensions, an autostereoscopic 3D display system with lenticular lenses is used. The surgical workflow is mirrored in the automated structure of the underlying algorithms. Partial nephrectomy was used to test the framework’s ability to provide adequate medical data during operations, and it passed with flying colors.
Using deep neural models and extended reality (XR), Tai et al. (2021) provide an Intelligent Internet of Medical Things (IoMT) platform for COVID-19 diagnostics. The system comprised a 5G cloud for transferring and processing medical data and a k-nearest neighbor (KNN)-based adversarial conditional generative adversarial network (ACGAN) model for estimating the accuracy of COVID-19 predictions. Different deep neural algorithms are used to evaluate the system’s XR-based remote diagnostic and surgical implementations. To deal with data inconsistencies, the ACGAN-based COVID-19 intelligent prediction system uses KNN for missing data imputation. ACGANs are integrated into the deep training component to aid with prediction and classification. For better visualization and haptic feedback in virtual surgeries, the platform also features a 3D user interface. Attacks based on “model stealing” are also investigated as a means of training imitation networks. Different technological and model training scenarios are examined in relation to the transferability of adversarial samples.
Benmahdjoub et al. (2021) provide a thorough explanation of an AR system utilized for surgical alignment tasks. The hardware and software components of the AR system include the Microsoft HL 2 for projecting and visualizing 3D models and the NDI Aurora (v2) electromagnetic tracking system (EMTS) for tracking the position and orientation of an electromagnetic (EM) coil attached to a pointer simulating a surgical needle or drill. The system utilizes a multimodal marker, a hybrid trackable instrument, to synchronize the coordinate systems of the HL and EMTS. In the calibration process, the local coordinate system of the QR code-like marker is registered to the coordinate system of the EM coil at a series of predetermined points. Reportedly, the system’s submillimeter accuracy makes it ideal for monitoring surgical EMTS. The experimental design includes an alignment task in which participants use one of three visualizations—N (no instrument representation), R (realistic representation), or VE (virtual extensions representation)—to line up a pointer with a predetermined trajectory. Before the experiment, the participants receive training on how to use the AR system. The study’s overarching goal is to contrast user perceptions with hard data collected under varying degrees of visual complexity. The experiment’s hypotheses predict that R and VE will improve alignment accuracy over N, that VE will reduce the distances traveled by the pointer and the head, that VE will reduce the time to completion, that VE will increase pointer velocity and decrease head velocity, that VE will improve usability, and that VE will increase mental demand and frustration. Positional and orientation errors are lower for VE compared to N and R. The distances the head had to move were also lowered by VE compared to N. The time it took to finish the task did not vary much between the three scenarios. But compared to N and R, VE slowed both the pointer and the head speed. While there was no discernible difference in usability between VE, N, and R, there was a notable decrease in frustration with VE. Most volunteers also ranked VE as the best condition, which is consistent with their performance rankings. Alignment accuracy was higher with VE than with N and R, and this was true across a wide range of volunteers’ professions and levels of technical training. The results of the study show that VE helps with perception-based instrument alignment in AR surgery ( Benmahdjoub et al., 2021).
User profile in virtual technologies, such as AR and VR settings, is presented in a study by Tricomi et al. (2023). Users’ identities and inferred private information (such as their ages and genders) are the primary foci of this research. Raw data collection, bias elimination, time series engineering, and machine learning prediction are the four pillars of the proposed framework. In the data acquisition stage, we record information about how people utilize XR tools. The goal of this step is to get rid of any biases in the data that could cause inaccurate machine learning models. During the machine learning prediction phase, machine learning techniques are used to infer private information about users based on the data extracted during the time series engineering phase. Data from AR and VR situations were used to compile the dataset. Participants used Microsoft HL goggles and controlled an Xbox One while roaming around an outdoor area to engage with augmented targets in the AR experiment.
Visual discrimination, navigation, and a dual task including both were among the activities tested. Participants used HTC VIVE Pro Eye VR headsets and controllers to direct a simulated industrial robotic arm in the VR experiment. Both light and heavy loads were tested, with the tests focusing on controller-based and action-based jobs, respectively. User identification, age profiling, and gender profiling are all detailed in the report. Age and gender profiling attempt to infer a user’s age and gender based on behavioral data, while user identification includes identifying a specific user from a known population. Feature extraction and bias removal are two steps in the implementation process. Data points are compiled for each user, activity, and task based on features including head position, head rotation, eye data (pupil size and eye openness), and controller position and rotation. The suggested framework can facilitate future study and comparisons in the field by providing a standard against which to measure user profiles in a variety of XR devices and apps. With an eye on understanding model decisions and debugging, this research employs machine learning techniques including logistic regression, decision tree, and random forest for prediction tasks. Researchers in the field of user profiling (UP) in AR and VR settings will find the offered framework and dataset to be useful tools.
Qian et al. (2020) provide a comprehensive overview of the AR-Loupe system, discussing its components in depth. They go into hardware, field-of-view segmentation, system modeling, calibration, occlusion management, and magnified AR rendering. AR-Loupe’s hardware architecture is based around the Magic Leap One OST-HMD, to which a set of Galilean loupes and a coaxial lighting or sensor unit have been attached. In order to segment the user’s field of view, they must first manually align a series of circles with the loupe’s perimeter. In order to generate a projection transformation for enhanced AR, a system is modeled and calibrated. The problem of occlusion management is solved by displaying masked data in the display’s empty space. Normal and enlarged visualizations can be seamlessly combined due to the rendering pipeline’s thoughtful design. Unity is used for the implementation of Magic Leap One, and an eye-emulating camera setup is used to verify the calibration.
Touchless teleoperation in the context of gesture-based control and visualization is presented by Lin et al. (2021). Different colored boxes indicate obtained, previous, and visualization data, and their real-time flow is depicted to show the architecture of the touchless teleoperation framework. The gesture-based control system is a novel take on the traditional master–slave control scheme, allowing remote control of the robot through the use of touchless gesture detection. Robots can be made to perform three distinct actions in response to these gestures: deflect, translate, and rotate. The operator’s motions are read by sensors built inside an OST-HMD. In order to provide visual feedback during teleoperation, visualization entails the calibration and display of virtual models in real time on the OST-HMD. The created system, including form tracking, gesture-based control, and visualization, is demonstrated experimentally in an airway phantom. The research recommends enhancements to calibration accuracy and forms reconstruction techniques that can accommodate complicated shapes.
Researchers set out to determine if and how effectively a virtual reality-extracorporeal circulation simulator (VR-ECC) simulator may be used to educate future perfusionists ( Babar et al. 2023). The data were gathered by the administration of questionnaires, such as the tried-and-true USE questionnaire measuring usefulness, satisfaction, and ease of use. On a five-point Likert scale, participants expressed how they felt about the event. Both inexperienced and seasoned perfusionists participated in the trial, demonstrating the simulator’s validity in terms of face and substance. All of the participants thought the simulator was a good learning tool because it was realistic. The simulator was enjoyable for both newcomers and seasoned pros. It was emphasized that the simulator is more cost-effective than conventional training methods. The research showed that VR-ECC simulators have the potential to revolutionize perfusionist training and education. More research is needed to verify the simulator’s accuracy and determine how well it performs as a learning tool compared to more conventional ways of instruction ( Babar et al., 2023).
Methods for performing a systematic review and meta-analysis on the topic of X-reality therapies for controlling phantom limb concerns in amputees were the primary focus of this literature study. PubMed, Scopus, Web of Science, PsycINFO, Embase, and CINAHL were among the resources the writers combed through using a mix of keywords pertaining to phantom limb and X-reality ideas. They used a checklist based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses statement for determining what should be included in reports ( Cheung et al., 2023). Two authors performed the search on a predetermined day, and any discrepancies were settled by consensus with the corresponding author. In order to conduct a useful evaluation, specific inclusion and exclusion criteria were laid down. Extraction of data was undertaken to collect fundamental details about the eligible articles, patient demographics, and intervention technique and gaming. Intervention games and activities were thematically analyzed for classification purposes. Last but not least, a meta-analysis was performed to evaluate the total efficacy of X-reality therapies in alleviating phantom pain, with subgroup analyses performed according to X-reality modality and year of publication. To better understand the systematic strategy used to select and analyze relevant articles, this study provides a complete description of the methodologies followed in conducting the systematic review and meta-analysis. The study’s transparency and potential for replication are improved by the inclusion of specific information on search tactics, screening processes, and data extraction. The topic analysis and meta-analysis also provide important insights into the different kinds of X-reality therapies and how well they work to alleviate phantom limb symptoms. This literature review is a helpful tool for doctors and scientists studying the effects of X-reality therapies on amputees’ phantom limb pain.
Every day technology is changing and the recently launched Apple Vision Pro is going to add a new journey for medical AR and VR. The convergence of immersive technologies and healthcare is exemplified by the Apple Vision Pro and Microsoft HL, both of which promise to reshape the industry in profound ways. Vision Pro, hailing from Apple, introduces an AR solution that has the potential to revolutionize surgical procedures. By overlaying critical patient data directly onto the surgical field, surgeons equipped with Vision Pro can make informed decisions in real time, leading to enhanced precision and improved patient outcomes (POs). Furthermore, the Vision Pro’s adaptability extends beyond the operating room, offering immersive educational experiences that can transform how medical students learn complex anatomical structures and medical procedures.
In a parallel development, Microsoft’s HL brings a powerful MR platform to the healthcare landscape. Going beyond surgical applications, HL focuses on medical training and education. It allows healthcare professionals to simulate intricate medical scenarios in immersive 3D environments, creating opportunities for hands-on learning without real-world consequences. This technology not only empowers practitioners to hone their skills but also facilitates safer and more effective training methodologies. Additionally, HL holds promise for remote collaboration, enabling specialists to share holographic spaces and collaborate on medical cases, fostering comprehensive and cross-disciplinary diagnoses. As these immersive technologies continue to evolve, they hold the potential to reshape various facets of healthcare.
The Vision Pro and HL stand as pioneering tools that bridge the gap between technology and medicine, offering avenues for enhanced surgical precision, enriched medical education, and more collaborative healthcare practices. The convergence of AR and MR in the healthcare sector heralds an exciting era of innovation, propelling the industry toward improved patient care, advanced training methodologies, and, ultimately, a more holistic approach to healthcare delivery.
The emergence of the metaverse, powered by a convergence of cutting-edge technologies such as blockchain, AI, IoT, 5G connectivity, and digital twins, heralds a new era of interconnected digital experiences. In this immersive digital realm, users engage with AI-driven avatars, creating and interacting within virtual environments while blockchain ensures secure transactions and ownership of digital assets. IoT and 5G contribute to seamless connectivity, enabling real-time data exchange and enhancing the metaverse’s responsiveness. Meanwhile, digital twins bridge the gap between the physical and digital worlds, offering dynamic simulations and insights for everything from industrial processes to personalized healthcare. This technological fusion promises to redefine how we interact, transact, and experience the digital landscape, transcending current limitations and shaping the future of interconnected virtual existence.
RESEARCH NEEDS AND GAPS
While Bartalucci et al. (2023) investigated the advantages of a passive upper-limb exoskeleton for AR interactions, more research is needed to assess the effects of various exoskeleton types on musculoskeletal load, task performance, and UX. More information on the benefits and drawbacks of exoskeletons might be gleaned through long-term trials with ethnically and racially diverse individuals.
Security and morality in healthcare systems powered by AI
Patients’ privacy and ethical considerations are impacted by the metaverse’s incorporation of AI. More study is needed to build reliable data protection (DP) methods and guarantee that AI-based medical apps are ethically sound, which is essential for gaining patients’ confidence and obtaining their informed permission. While the IoT makes it possible to monitor patients remotely and do robot-assisted operations in the metaverse, there are still issues to be resolved in terms of DS and standardization. Sensitive health information sent over the Internet should be encrypted, and standardized procedures should be developed.
Effective real-time processing (RTP) methods are necessary for using large data for healthcare applications in the metaverse. In order to efficiently process large healthcare datasets and provide actionable insights for clinical decision-making, researchers in the future should investigate distributed computing architectures (DCAs) and cutting-edge algorithms. However, while the use of quantum computers in the metaverse can improve security and data processing, it also raises concerns about EE and data privacy. There has to be an investigation into the possibility of developing QC systems that are both power-efficient and in line with privacy laws.
Studies like Tricomi et al. (2023) show that UP is possible in XR contexts, raising concerns about privacy. However, additional study is needed to create privacy norms (PNs) and data protection mechanisms (DPMs) to guarantee the ethical use of user data in AR/VR software. Additional research is required to validate and replicate the efficacy of X-reality therapies for controlling phantom limb pain across different patient populations (PP) and settings, despite the fact that Cheung et al. (2023) conducted a systematic review and meta-analysis on such therapies.
Touchless teleoperation with gesture-based control and visualization was reported by Lin et al. (2021). They focused on the accuracy of calibration and shape reconstruction (SR) in this context. To allow more accurate and dependable touchless teleoperation in many applications, including medical operations, future research should focus on enhancing calibration accuracy and form reconstruction approaches.
The study by Babar et al. (2023) showed that VR-ECC simulators might be useful for perfusionist training in the long run. Although these simulators have been shown to improve procedural skills and POs, additional study is required to determine their long-term usefulness. The AR-Loupe system was described by Qian et al. (2020) and is intended for use in surgical procedures. To discover areas for development and optimize its practical application, more study is needed to assess the usability and UX of this technology in actual surgical settings. Table 2, represents the comparative analysis of the application of AR/VR in the medical industry.
Comparative analysis of the application of AR/VR in the medical industry.
| References | Technology | Application in medical education | Benefits | Challenges | Key findings |
|---|---|---|---|---|---|
| Chengoden et al. (2023) | VR, AR, AI, IoT, 5G, blockchain, digital twins, quantum computing, HCI, computer vision | Diverse applications including diagnostics, training, therapy, and surgery | Enhanced access to care, improved training and diagnostics, patient data security | Privacy concerns, data security, computational demands | Highlights the integration of multiple technologies to transform healthcare delivery |
| Ferrari et al. (2020) | AR OST-HMD | Reducing registration errors in AR displays | Improved alignment of virtual and real-world content | Calibration complexities | Suggests using a magnifier to correct viewpoint parallax issues |
| Zhang et al. (2022) | 3D autostereoscopic display | Surgical navigation for MIS | Provides accurate medical data during surgeries | Registration of preoperative and intraoperative data | Proved successful in partial nephrectomy surgeries |
| Tai et al. (2021) | XR, deep neural models | COVID-19 diagnostics on an IoMT platform | Enhances diagnostics and surgical procedures with 5G and deep learning | Data inconsistency and privacy concerns | Uses ACGANs for prediction and classification in medical diagnostics |
| Benmahdjoub et al. (2021) | AR, HoloLens 2, EMTS | Surgical alignment tasks | High accuracy in monitoring surgical tools | Visual complexity and user training | VE improves perception-based instrument alignment |
| Tricomi et al. (2023) | AR, VR | User profiling in virtual settings | Enhanced understanding of user behavior | Bias elimination and data privacy | Provides a framework for user profiling in XR |
| Qian et al. (2020) | AR-Loupe | Enhanced AR visualization for medical tasks | Combines normal and magnified visualizations | Calibration accuracy and occlusion management | Proposes a system model for improved AR experiences |
| Lin et al. (2021) | Touchless teleoperation | Gesture-based control for surgery | Allows touchless control of surgical robots | Calibration and form reconstruction | Recommends improvements for complex shape accommodation |
| Babar et al. (2023) | VR-ECC simulator | Perfusionist training | Cost-effective and realistic training tool | Need for further validation against traditional methods | Shows potential to revolutionize perfusionist education |
| Cheung et al. (2023) | X-reality therapies | Managing phantom limb pain | Effective in alleviating phantom pain | Methodology for systematic review and analysis | Conducted a meta-analysis on the efficacy of X-reality therapies |
Abbreviations: ACGANs, adversarial conditional generative adversarial network; AI, artificial intelligence; AR, augmented reality; EMTS, electromagnetic tracking system; HCI, human–computer interface; IoT, Internet of Things; IoMT, Intelligent Internet of Medical Things; MIS, minimally invasive surgery; OST-HMD, optical see-through head-mounted display; VE, virtual extension; VR, virtual reality; XR, extended reality.
Model for the development of medical education using AR and VR
In the domain of medical technology and education, current research has identified several areas needing further exploration and development.
Exoskeletons for AR: Bartalucci et al. (2023) highlighted the potential of passive upper-limb exoskeletons in AR. Future studies should quantify the impact on musculoskeletal load ( L), task performance ( P), and user experience ( U). Long-term trials could involve variables such as duration ( t), force ( F), and user diversity ( D), seeking a multidimensional function f( L, P, U, t, F, D) that can model the holistic impact of exoskeleton use.
AI in healthcare: With AI integration into healthcare systems, the challenge lies in balancing DP and ethical compliance ( EC). Research should aim to establish a model g( DP, EC) that maximizes patient trust ( T) and informed consent ( IC).
IoT in healthcare: IoT facilitates RPM and RASs. However, DS and standardization ( S) remain concerns. A proposed model might be h( RPM, RAS, DS, S), where encrypted communication ( EC) is a function of DS, and S is a set of protocols for interoperability.
Big data processing: The metaverse’s use of big data requires RTP. Research should explore DCAs and algorithms ( A) that enhance clinical decision-making ( CDM), modeled as i( RTP, DCA, A, CDM).
QC: QC promises enhanced security ( Sec) and processing ( Proc), but EE and privacy ( Priv) are concerns. An optimal model j( QC, Sec, Proc, EE, Priv) needs to be developed that considers the power-privacy trade-off.
UP in XR: Tricomi et al. (2023) demonstrated UP possibilities in XR. Future research must address PNs and DPM, seeking a privacy model k( UP, PN, DPM).
X-reality Therapies for Phantom Limb Pain: Cheung et al. (2023) provided a meta-analysis on X-reality therapies. Further validation ( V) across diverse PPs and settings ( S) is needed, aiming for a comprehensive effectiveness model l( V, PP, S).
Touchless Teleoperation: Lin et al. (2021) focused on gesture-based control accuracy ( CA) and SR. Research should enhance the model m( CA, SR) for reliable application in medical procedures.
VR-ECC Simulators: Babar et al. (2023) indicated the usefulness of VR-ECC simulators for perfusionist training. Further studies should evaluate long-term utility ( LTU), skill improvement ( SI), and POs, modeled as n( LTU, SI, PO).
AR-Loupe System in Surgery: Qian et al. (2020) introduced the AR-Loupe system, and further research should assess usability ( Us) and UX in real surgical environments, represented by o( T↓ UX).
Let us delve into these research needs and gaps, providing a corresponding mathematical model analysis for each.
Hypothetical mathematical model
Suppose we hypothesize that patient trust ( T) in AI-powered healthcare systems is a function of DP and EC:
where T, DP, and EC are quantifiable measures on a scale from 0 to 1. We could further hypothesize that patient trust is directly proportional to both DP and EC:
where α and β are coefficients representing the weight of each factor’s contribution to trust.
Proof of concept
To prove this concept, we would need to collect data on patient trust levels, DP standards, and EC from healthcare systems that use AI. Once we have these data, we can apply statistical methods to test the validity of our model. One way to do this is to use regression analysis, which would provide us with the coefficients α and β. If the model is correct, we would expect to find α, β > 0 and significant P values indicating that both DP and EC are positively associated with T. If we find that α and β are positive and statistically significant, this supports our hypothesis that patient trust increases with better DP and ethical standards.
Proof through hypothesis testing
The formal proof in the context of statistical models usually involves hypothesis testing. For our model, we could set up the following null hypotheses:
H 0: α = 0 (DP has no effect on trust)
H 0: β = 0 (EC has no effect on trust)
The alternative hypotheses would be:
H a : α > 0 (DP has a positive effect on trust)
H a : β > 0 (EC has a positive effect on trust)
We would use our collected data to conduct the regression analysis and look at the P values for α and β. If both P values are below a predetermined significance level (e.g. 0.05), we would reject the null hypotheses ₹↓ accept the alternative hypotheses, providing evidence for our model.
Framework for harnessing the transformative capabilities of AR and VR
A robust framework for harnessing the transformative capabilities of AR and VR in medical health education must encompass several key components to ensure efficacy, inclusivity, and ethical integrity.
This proposed framework, designed to revolutionize medical training and education, includes the following elements:
Customization and Accessibility: Let us denote the degree of customization and accessibility as C, where C varies from 0 (no customization) to 1 (fully customized for all abilities). The effectiveness of AR/VR in education, denoted as E, can be considered directly proportional to C. Therefore, we can express this as E = k 1· C, where k 1 is a proportionality constant.
Immersive and Experiential Learning: Let I represent the level of immersion, ranging from 0 (not immersive) to 1 (fully immersive). The retention rate of information, R, can be seen as a function of I, such as R = k 2· I 2, suggesting that retention improves exponentially with increased immersion. k 2 is a constant that scales this relationship.
Ethical and Privacy Considerations: Assign a variable P for privacy and ethical adherence, with 0 being noncompliant and 1 being fully compliant. The trust factor T in the technology can be modeled as T = k 3· P, where k 3 is a constant. Higher privacy standards lead to greater trust in the technology.
Interdisciplinary Collaboration: Representing collaboration as D(0 for no collaboration, 1 for full interdisciplinary collaboration), its impact on the overall effectiveness E can be modeled as a multiplicative factor: E = E· D, suggesting that collaboration amplifies the effectiveness of the framework.
Continuous Evaluation and Adaptation: Let A represent the adaptability level (0 for static, 1 for fully adaptive). The long-term sustainability S of the framework can be modeled as S = k 4· A, where k 4 adjusts for the rate of change in technology and educational needs.
Integration into Medical Curricula: Denote integration level as M (0 for no integration, 1 for full integration). The overall success O of the framework in educational settings can be expressed as O = k 5· M· E, where k 5 is a scaling constant.
Combining these, the overall utility U of the AR/VR framework can be conceptualized as a function of all these variables:
where each variable contributes to the outcome in a synergistic manner. This mathematical analysis, although simplified, helps to conceptualize how each component of the framework interrelates and impacts the overall effectiveness of AR/VR in medical education. By adhering to these principles, the proposed framework aims to maximize the potential of AR and VR in medical education, creating an inclusive, effective, and ethically responsible learning environment.
RESEARCH GAPS
In the realm of research, challenges are multifaceted and often complex. One significant hurdle is the rapid pace of technological advancement, which constantly reshapes the landscape, necessitating continuous adaptation and learning. Funding constraints also present a major obstacle, limiting the scope and depth of investigations. Furthermore, the increasing need for interdisciplinary approaches introduces complexities in collaboration, requiring integration across diverse fields with varying methodologies. Ethical concerns, particularly in human-centric studies, add another layer of complexity, requiring stringent adherence to ethical standards and regulatory compliance. Additionally, data management, especially in handling large datasets and ensuring privacy and security, remains a persistent challenge. These issues collectively demand a dynamic, innovative, and ethically grounded approach to research.
Evaluation Challenges of Exoskeletons in AR Interactions: Current research, including Bartalucci et al. (2023), has primarily focused on the benefits of passive upper-limb exoskeletons in AR interactions. However, there exists a significant gap in understanding how various exoskeleton types influence musculoskeletal load, task performance, and UX in AR settings. There is a particular need for in-depth research into the long-term effects of these exoskeletons on individuals from diverse racial and ethnic backgrounds.
Ethical and Privacy Concerns in AI-Driven Healthcare Systems: The integration of AI in healthcare systems within the metaverse raises critical issues regarding ethics and patient privacy. Although there have been advancements, there is a pressing need for more extensive research focused on ensuring the ethical application of AI in medical contexts and developing robust DP strategies. This research is vital to gain patient trust and ensure IC.
DS and Standardization in IoT-Enabled Healthcare: The growing use of the IoT in healthcare applications within the metaverse, such as RPM and RASs, brings forth significant DS challenges. Further research is required to establish effective encryption methods for transmitting private health data and to develop standardized protocols for data management.
Limitations in Real-time Processing of Large Healthcare Datasets in the Metaverse: A notable research gap exists in the development of collaborative computing systems and advanced algorithms that are capable of efficiently processing large healthcare datasets in real time within the metaverse. This gap hinders the ability to leverage these datasets for timely and actionable clinical insights.
Privacy and DS in VR Applications: Research by Tricomi et al. (2023) indicates that UP in XR raises privacy concerns. However, there is a scarcity of research addressing these issues. The lack of established privacy standards and DP measures complicates the ethical use of user data in AR/VR applications. Despite the systematic reviews and meta-analyses by Cheung et al. (2023), further research is essential to validate and replicate the effectiveness of X-reality therapies for treating phantom limb pain across various patient groups and settings.
The challenges identified in the realm of AR and VR in medical education and healthcare applications are multifaceted, encompassing technological, ethical, and data privacy concerns Kumar et al. (2023a, b). A promising approach to address these challenges is the development and implementation of hybrid models that combine various technological and methodological frameworks.
Hybrid models for exoskeleton evaluations in AR interactions
To tackle the challenge of evaluating various exoskeletons in AR, a hybrid model combining biomechanical analysis and UX metrics could be employed. This model would integrate quantitative biomechanical data, such as musculoskeletal load measurements, with qualitative assessments of UX gathered through surveys and interviews. By incorporating diverse participant profiles, this model could also address the need for more inclusive research across different races and ethnicities, offering a more comprehensive understanding of the long-term effects of exoskeleton use.
AI-driven healthcare systems: ethical and privacy solutions
In AI-driven healthcare systems, a hybrid model that combines advanced encryption algorithms with ethical AI frameworks could be implemented. This model would use state-of-the-art encryption techniques to secure patient data, while ethical AI principles guide the development and deployment of AI algorithms. This approach ensures that AI-based medical applications are both ethically sound and equipped with robust DP, thereby enhancing patient trust and IC.
IoT-enabled healthcare: security and standardization
For IoT-enabled healthcare, a hybrid model that merges standardized protocols with advanced cybersecurity measures is crucial. This model would standardize data formats and communication protocols to ensure interoperability and efficiency while implementing cutting-edge cybersecurity technologies to safeguard sensitive health information.
Real-time processing of large healthcare datasets
Addressing the challenge of processing large healthcare datasets in real time requires a hybrid model that combines DCAs with machine learning algorithms. This approach can efficiently process vast amounts of data, providing actionable insights for CDM. Leveraging the power of cloud computing and edge computing, this model would enable faster data processing and analysis.
Privacy and DS in AR/VR applications
For AR/VR applications, a hybrid model incorporating privacy-preserving techniques with user-centric design principles is recommended. This model would use methods like differential privacy and secure multiparty computation to protect user data while ensuring that AR/VR applications are designed with a focus on user consent and transparency.
Hybrid models present a viable solution to the challenges facing AR and VR applications in medical education and healthcare. By combining technological advancements with ethical, privacy-centric approaches, these models can help realize the full potential of AR and VR technologies, while addressing key concerns related to UX, DS, and ethical implications.
CONCLUSION
This article highlights the tremendous revolutionary potential of AR and VR in medical health education through hands-on instruction. Extending the availability of medical treatment, enhancing doctor–patient interactions, and protecting personal health information are all made possible by the integration of several cutting-edge technologies inside the metaverse. Medical simulations, surgical navigation, mental health help, and remote diagnostics are just a few examples of how AR and VR are already revolutionizing healthcare and education. With the introduction of AI and IoT-enabled healthcare solutions, however, this transformational path also brings issues such as privacy concerns, ethical considerations, and DS.
The review underscores the significance of AR and VR in extending medical education beyond geographical limitations. Disabled individuals often face mobility challenges that hinder their ability to access traditional medical learning environments. AR and VR break down these barriers by enabling remote learning experiences, offering virtual engagement with medical simulations, surgeries, and interactive training modules. In order to adopt these technologies securely and efficiently, overcoming these challenges is essential. QC also requires careful attention to standardization, energy economy, and DP. The utilization of XR technology in patient profiling and remote diagnostics, as well as the possibility of VR-enhanced therapy for mental health, offers significant promise for the future of healthcare. This study presents a useful paradigm for maximizing the revolutionary potential of AR and VR in medical health education, leading to superior experiential learning and better healthcare outcomes. Utilizing these cutting-edge tools has the potential to radically alter the medical education environment, which will in turn equip healthcare professionals and have a beneficial effect on patient care throughout the world. As these technologies revolutionize patient care, doctor–patient communication, and mental health support, it becomes imperative to ensure that disabled individuals are not left behind but rather are at the forefront of this transformative movement. By incorporating universal design principles and prioritizing data privacy, the medical community can ensure that the potential benefits of AR and VR are experienced equitably and without compromising individual rights. These technologies offer customizable simulations and interactive experiences that cater to the needs of disabled individuals, allowing them to engage in hands-on medical training and education that might otherwise be challenging.
This study demonstrates a vivid picture of the promising future that AR and VR hold for revolutionizing medical health education while emphasizing the invaluable contributions these technologies can make to the lives of disabled individuals. As the healthcare industry continues to explore and implement these technologies, it must do so with a deep commitment to inclusivity, ethical considerations, and the unwavering goal of enhancing the accessibility and quality of medical education and care for all, regardless of their physical abilities.