Application and Utilisation of Neurotechnology

docx

School

Moi University *

*We aren’t endorsed by this school

Course

Subject

Medicine

Date

Nov 24, 2024

Type

docx

Pages

Uploaded by ElderInternet10287

1 Application and Utilisation of Neurotechnology, Artificial Intelligence, and Virtual Reality in Neurosurgical Practice: A Scoping Review Materials and Methods The research adopts a scoping review to effectively provide evidence that neurotechnology, VR, and AI are applicable and relevant tools that surgical practitioners can use. The scoping review will map a wide range of relevant literature and provide evidence on the applicability and effectiveness of neurotechnology tools and novel technologies in neurosurgical practices (Munn et al., 2022). The scoping review took place in five stages: identifying the research question, identifying studies relevant to the question, selecting inclusion studies, data and information charting, result collection, summary, and reporting (Ghalibaf et al., 2017). First, the research question for the scoping study was; “What are the current possibilities that utilise neurotechnology, AI and VR in neurosurgical practices?” Second, the study identified relevant studies. The study’s search strategy involved a comprehensive search of Google Scholar, Science Direct, and PubMed articles. Also, the second step considered articles from 2013 to 2023 and manual checks of selected studies’ reference lists. Also, the search for literature and articles utilised key terms such as AI, neurotechnology, VR, and neurosurgery. Third, the study selection process adopted an eligibility criterion to ensure studies are tailored to the basic concept of neurotechnology. Therefore, it embraced inclusion and exclusion criteria. The inclusion criteria considered all articles on using neurotechnology, VR, and AI in neurosurgery. Also, it includes all English articles within the ten years (2013 to 2023). Lastly, it includes articles that provide evidence on the effectiveness of neurotechnology, AI, and VR. The exclusion criteria exempted all articles that did not have the key terms published before 2013 and were researched outside neurosurgery. Fourth, we conducted data charting. The data charting

2 form identified extraction variables. General data focused on publication years and the presence of peer-reviewed articles. Comprehensive data extraction considered the inclusion criteria and themes. Results A Study Flowchart on the Scoping Review Database Search Records: n=25 Additional Records: n=0 Articles included in review articles: n=13 Articles for eligibility): n=20 Records (Screened): n=25 Records (After eliminating duplicates): n=25 Records (Excluded): n=5 Excluded articles: n=7

3 The scoping review identified 20 original studies that focused on utilising neurotechnology and other technologies in neurosurgery practice and its effectiveness. The study flowchart on the scoping review and the mapped data. All studies were conducted within the time frame of ten years. Also, all studies were peer-reviewed. However, the study discussion includes data and evidence from unpublished reliable articles. Twenty full texts were subjected to eligibility, with seven articles excluded and twelve included. Included articles focused on neurotechnologies such as BCI and BMI (3), ChatGPT (1), Artificial Intelligence (6), and Virtual Reality (3). A graphical representation of concepts discussed in the included articles BCI/BMI ChatGPT AI VR 0 1 2 3 4 5 6 7 Nuerosurgery Technologies Nuerosurgery Technologies Discussion The scoping review and detailed analysis of research findings provided adequate evidence on how current neurotechnologies, VR, AI, and ChatGPT have revolutionised neurosurgical practice. These technologies share an interrelationship, and surgical teams can

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

4 adopt one or more technologies for better patient outcomes. For instance, BCI and BMI are machine learning techniques that surgeons can consider after using AI tools during diagnosis, prognosis, and operatives. Neurotechnologies Applied in Neurosurgery The articles on invasive Brain-Computer Interface (BCI) and Brain-Machine Interface (BCI) reveal that these technologies provide adequate information for neurosurgery and allow for interoperability and alignment of human health needs and well-being. Bergeron et al. (2023) reveal that BCI has been an effective neurosurgical tool; it alleviates disabilities for persons with neurologic injuries through BCI systems provided in fully implantable devices for paediatrics. Pediatrics with critical neurologic disabilities, such as cervical spine trauma or cerebral palsy, Virtual Reality/Augmented Reality Nuerosurgery-based AI ChatGPT Learning Machine Learning Technologies Brain-Machine Interfacing Technologies BCI/EEG/ MEG combinati ons

5 can benefit from the technology through its ability to provide communication and interoperability with motor, emotional-cognitive, and sensory interfaces. These implants can improve paediatric health for challenging neurological conditions. Persons with spinal cord injuries who experience locomotor deficits can use EES to remedy and restore neurological functions affected after paralysis effectively (Wagner et al., 2018). Further, the research by Philip et al. (2023) reveals that BCI systems’ deep-learning models help neurological disease victims interact with their environments. Therefore, these models have integrated techniques and classification that detect and remove noise while increasing the signal-noise ratio for MEG-based BCI systems. Also, BMI systems’ sensing technologies represent the technology area with the highest level of standardisation in neurosurgery (et al., 2021). BMI utilises end-effector systems, dual storage, sharing, representation, and consumer-grade sensors to enhance device performance, effectiveness, and safety standards (Paek et al., 2020). Both invasive and non-invasive modalities provide for synchronisation and improve neurosurgical outcomes. The article on ChatGPT acknowledges the tool as an effective, accurate, and reliable medium for neurosurgical education for practitioners. Access to neurosurgical education for students and practitioners has increased since the emergence of AI-based education tools, such as ChatGPT. As an alternative educational method, the chat engine is useful in case questions, report preparation, and academic research on neurosurgery (Sallam, 2023). While its reliability is a contentious issue that requires evaluation and improvement, its adoption, alongside other academic tools, could prompt better access to neurosurgical information. Giannos (2023) reveals that ChatGPT’s recent updates have specialised in information on medical practice and education and improved its reliability and institutional relevance in the evolving neurosurgery field.

6 Articles on artificial intelligence focus on its utilisation in operative care (pre-, intra-, and post-operation), decision-making, surgery process, prognosis, and diagnosis. With the increase in AI use in medicine, neurosurgery benefits from the technology since it complements surgeons’ skills, provides top-notch care (interventional and non-interventional) and improves patients’ diagnosis and prognosis outcomes before and after treatment (Mofatteh, 2021). Further, researchers affirm that, since AI and neuroscience have a close relationship, neuroscience theories. Surianarayanan et al. (2023) affirm that these theories have enhanced AI and allowed for treatment and procedure improvisation, such as creating deep neural networks, developing applications that allow for robotic neurosurgery, and analysing complex neuroscience data. Therefore, AI approaches contribute to enhanced detection of neurological disorders. Other AI tools revolutionising neurosurgery include machine learning, NLP, EMR, and computer vision (Hashimoto et al., 2018). Adopting these AI tools increases sensitivity, accuracy, and specificity by over 50% in surgical departments. Iqbal et al. (2022) draw from a futuristic perspective and point to AI as a transformative tool in neurosurgery, where it creates a patient-centred approach. Research opines that AI will address many neurosurgical challenges associated with access to high-quality data and information, management of clinical tasks, post-operative care and assessment, patient privacy, and overreliance on human support (Sobhanian et al., 2022). Another article noted that AI is useful in neurosurgery, where it focuses on machine learning’s ability to accurately predict complications, identify massive occlusions, aid practitioners in classifying brain tumours from MRIs, and predict head injury outcomes (Gabriel et al., 2022). Machine Learning, AI, and Deep Learning have a considerable relationship that contributed to multi-layered networks that mimic human-like behaviour patterns during surgical practices.

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

7 Articles on VR and AR reveal the tools’ potential in global neurosurgery through minimally invasive techniques. A research study on the effectiveness of VR in neurosurgical tumour resection reveals that adopted ML algorithms have 90% accuracy and can classify practitioners into expertise levels. Surgical simulations allow for VR to allow for psychomotor skills quantification. Also, healthcare facilities can depend on VR as it can effectively classify neurosurgical practitioners into expertise levels after a VR procedure (Winkler-Schwartz et al., 2019). Scott et al. (2021) note that integrating VR and VR-related neuroscience into neurosurgery is integral in improving patient care, operative planning and execution, procedural navigation, rehabilitation, and surgical training. Another study showcased that using VR in neurosurgery solves staffing problems, improves surgeons’ operations, and mitigates duty-hour reductions’ deleterious effects (Jean, 2021). VR's minimally invasive techniques remedy skill deficits and staff shortages and enhance surgical patient outcomes. Relationship between Artificial Intelligence, Machine Learning, and Deep Learning Machine Learning embraces surgery-based statistics to improve AI tools’ experiences Artificial Intelligence (mimic human behaviour and perform tasks they perform) Deep Learning uses multi- layered and deep neural networks to develop algorithms and computations in tasks such as neurological image classification

8 Conclusion Neurosurgical practice is a critical healthcare sector that faces rapid evolution and the need for advanced technologies. Adopting novel technologies provides healthcare solutions to challenging neurological conditions that seemed insolvable in the recent past. AI, VR, ChatGPT, BMI, and BCI have revolutionised surgical procedures, increased expertise and efficiency, allowed for better patient outcomes, and solved challenges such as staff shortage and improved neurosurgery. Also, the prospects of these technologies, such as ChatGPT, indicate that future learning and knowledge acquisition will be easier as ChatGPT will provide reliable information for practitioners. Therefore, the present and future of all neurosurgical technologies are geared towards better practice.

9 References Bergeron, D., Iorio-Morin, C., Bonizzato, M., Lajoie, G., Gaucher, N., Racine, E., & Weil, A. G. (2023). Use of Invasive Brain-Computer Interfaces in Pediatric Neurosurgery: Technical and ethical considerations. Journal of Child Neurology , 38 (3–4), 223–238. https://doi.org/10.1177/08830738231167736 Chavarriaga, R., Carey, C., Contreras-Vidal, J. L., McKinney, Z., & Bianchi, L. (2021). Standardisation of Neurotechnology for Brain-Machine Interfacing: State of the art and recommendations. IEEE Open Journal of Engineering in Medicine and Biology , 2 , 71– 73. https://doi.org/10.1109/ojemb.2021.3061328 El-Hajj, V. G., Gharios, M., Edström, E., & Elmi-Terander, A. (2023). Artificial Intelligence in Neurosurgery: A Bibliometric analysis. World Neurosurgery , 171 , 152-158.e4. https://doi.org/10.1016/j.wneu.2022.12.087 Ghalibaf, A. K., Nazari, E., Gholian-Aval, M., Tabesh, H., & Tara, M. (2017). Comprehensive overview of computer-based health information tailoring: a scoping review protocol. BMJ Open , 7 (12), e019215. https://doi.org/10.1136/bmjopen-2017-019215 Hashimoto, D. A., Rosman, G., Rus, D., & Meireles, O. R. (2018). Artificial intelligence in surgery: promises and perils. Annals of Surgery , 268 (1), 70–76. https://doi.org/10.1097/sla.0000000000002693 Iqbal, J., Jahangir, K., Mashkoor, Y., Sultana, N., Mehmood, D., Ashraf, M., Iqbal, A., & Hafeez, M. H. (2022). The future of artificial intelligence in neurosurgery: A narrative review. Surgical Neurology International , 13 , 536. https://doi.org/10.25259/sni_877_2022

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

10 Jean, W. C. (2022). Virtual and Augmented Reality in Neurosurgery: The Evolution of its Application and Study Designs. World Neurosurgery , 161 , 459–464. https://doi.org/10.1016/j.wneu.2021.08.150 Mofatteh, M. (2021). Neurosurgery and artificial intelligence. AIMS Neuroscience , 8 (4), 477– 495. https://doi.org/10.3934/neuroscience.2021025 Munn, Z., Pollock, D., Khalil, H., Alexander, L., Mclnerney, P. A., Godfrey, C., Peters, M. D. J., & Tricco, A. C. (2022). What are scoping reviews? Providing a formal definition of scoping reviews as a type of evidence synthesis. JBI Evidence Synthesis , 20 (4), 950–952. https://doi.org/10.11124/jbies-21-00483 Paek, A., Brantley, J., Evans, B. J., & Contreras-Vidal, J. L. (2021). Concerns in the blurred divisions between medical and consumer neurotechnology. IEEE Systems Journal , 15 (2), 3069–3080. https://doi.org/10.1109/jsyst.2020.3032609 Philip, B. S., Prasad, G., & Hemanth, D. J. (2023). A systematic review on artifact removal and classification techniques for enhanced MEG-based BCI systems. Brain-Computer Interfaces , 1–15. https://doi.org/10.1080/2326263x.2023.2233368 Sevgi, U. T., Erol, G., Doğruel, Y., Sönmez, O. F., Tubbs, R. S., & Güngör, A. (2023a). The role of an open artificial intelligence platform in modern neurosurgical education: a preliminary study. Neurosurgical Review , 46 (1). https://doi.org/10.1007/s10143-023- 01998-2 Sevgi, U. T., Erol, G., Doğruel, Y., Sönmez, O. F., Tubbs, R. S., & Güngör, A. (2023b). The role of an open artificial intelligence platform in modern neurosurgical education: a preliminary study. Neurosurgical Review , 46 (1). https://doi.org/10.1007/s10143-023- 01998-2

11 Sobhanian, P., Shafizad, M., Karami, S., Mozaffari, F., Arab, A., Razani, G., Shafiekhani, P., & Safari, S. (2022). Artificial intelligence applications in clinical neurosurgery. Precision Medicine and Clinical Omics , 2 (1). https://doi.org/10.5812/pmco-133563 Surianarayanan, C., Lawrence, J. J., Raj, P., Prakash, E., & Hewage, C. (2023). Convergence of Artificial Intelligence and Neuroscience towards the Diagnosis of Neurological Disorders —A Scoping Review. Sensors , 23 (6), 3062. https://doi.org/10.3390/s23063062 Tangsrivimol, J. A., Schonfeld, E., Zhang, M., Veeravagu, A., Smith, T. R., Härtl, R., Lawton, M. T., El-Sherbini, A. H., Prevedello, D. M., Glicksberg, B. S., & Krittanawong, C. (2023). Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future. Diagnostics , 13 , 1–33. https://doi.org/10.3390/diagnostics13142429 Wagner, F., Mignardot, J., Goff-Mignardot, C. G. L., Demesmaeker, R., Komi, S., Capogrosso, M., Rowald, A., Seáñez, I., Caban, M., Pirondini, E., Vat, M., McCracken, L., Heimgartner, R., I, F., Watrin, A., Seguin, P., Paoles, E., Van Den Keybus, K., Eberle, G., . . . Courtine, G. (2018). Targeted neurotechnology restores walking in humans with spinal cord injury. Nature , 563 (7729), 65–71. https://doi.org/10.1038/s41586-018-0649-2 Winkler-Schwartz, A., Yilmaz, R., Mirchi, N., Bissonnette, V., Ledwos, N., Siyar, S., Azarnoush, H., Karlik, B., & Del Maestro, R. (2019). Machine learning identification of surgical and operative factors associated with surgical expertise in virtual reality simulation. JAMA Network Open , 2 (8), e198363. https://doi.org/10.1001/jamanetworkopen.2019.8363

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Application and Utilisation of Neurotechnology

Related Documents