I Asked a ChatGPT to Write an Editorial About How We Can Incorporate Chatbots Into Neurosurgical Research and Patient Care…
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Efforts to apply artificial intelligence (AI) and machine learning in the medical field and specifically in neurosurgery are actively underway.1-7 Currently, imaging-based diagnosis, disease diagnosis, and methods of prediction using clinical data and genomic data are fields that receive the most attention.3-6,8-11 However, AI technologies associated with natural language processing are also being investigated.12 Conversational AI is an application of natural language processing that refers to AI technologies capable of communicating with people.13 These include chatbots or virtual agents using generative pretraining transformer (GPT) language models. These technologies are rapidly advancing and are poised to make a significant contribution to medical research and patient care. Multiple groups have already put various conversational AI platforms to use them foradvance patient care including taking down medical histories, assisting in psychotherapy, and improving care in chronic conditions.7,13-16 However, the conventional conversational AI platforms were limited with mostly structured rules of engagement. ChatGPT has new potential roles in both patient care and research including producing primary documents and assisting in research conceptualization/design. We gave a ChatGPT (OpenAI LLC) with the following prompt: Write me a research editorial for the journal: Neurosurgery about how we can incorporate chatbots into neurosurgical research and neurosurgical patient care and received an insightful and well-written correspondence completely generated by the software. We comment on how as a community we need to carefully embrace these powerful technologies to improve neurosurgical research and patient outcomes. “Integrating Chatbot Technology into Neurosurgical Research and Patient Care: A Research Editorial Over the past few years, chatbot technology has made significant strides in the field of health care, with chatbots being used to assist with tasks such as patient education, appointment scheduling, and symptom management. The use of chatbots in neurosurgery is a relatively new area of exploration, but it has the potential to revolutionize the way we conduct research and deliver care to patients with brain and nervous system conditions. One potential application of chatbot technology in neurosurgery is in the field of research. Chatbots can be used to gather data from large numbers of patients, streamlining the process of data collection and analysis. This can be particularly useful in longitudinal studies, where chatbots can be used to track patient outcomes over time. Chatbots can also be used to administer surveys or questionnaires to patients, allowing researchers to gather data on patient experiences and preferences. Another potential use of chatbot technology in neurosurgery is in the delivery of patient care. Chatbots can be used to provide patients with timely and accurate information about their care and treatment, helping to alleviate anxiety and confusion. Chatbots can also be used to triage patients with urgent issues, reducing the burden on emergency departments and allowing patients to receive care more quickly. In addition, chatbots can be used to facilitate communication between patients and their health care providers, allowing patients to receive care remotely and reducing the need for in-person visits. There are, of course, challenges to the integration of chatbot technology into neurosurgery. One concern is the potential for chatbots to misdiagnose or provide incorrect information, which could have serious consequences for patients. It is important for chatbots to be carefully designed and tested to ensure their accuracy and reliability. In addition, there may be privacy and security concerns surrounding the use of chatbots because sensitive patient information could be transmitted through chatbot conversations. These concerns will need to be carefully addressed as chatbot technology is developed and implemented in the field of neurosurgery. In conclusion, chatbot technology has the potential to revolutionize the way we conduct research and deliver care to patients with brain and nervous system conditions. Although there are challenges to be addressed, the potential benefits of chatbots in neurosurgery are significant, and it is important for researchers and health care providers to explore and invest in this promising area of technology.” (Text generated by OpenAI's Assistant AI:https://openai.com). As with anyone currently exploring ChatGPT technologies, we were impressed with the ease of use and abilities of the chatbot. However, because it becomes easier to write a manuscript than it is to read a manuscript or to have a chatbot respond to patient questions and triage medical necessity, the medical field and neurosurgery as its own community must begin thinking now about how to best integrate these advances into our profession. We must consider the ethics of using content generating A
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This implies that health providers can leverage chatbots to provide health information and support to patients [8,51,52].”
From Investigating the impact of user trust on the adoption and use of ChatGPT: Survey analysis (2023) · cites this paper as [52]
Citations
Cites
Hollon, T. C., Pandian, B., Adapa, A. R., Urias, E., Save, A. V., Khalsa, S. S. S., Eichberg, D. G., D’Amico, R. S., Farooq, Z. U., Lewis, S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-019-0715-9 · Cited by 790
Self-citationThe Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review
Milne-Ives, M., de Cock, C., Lim, E., Shehadeh, M. H., de Pennington, N., Mole, G., Normando, E., & Meinert, E. (2020) · Journal of Medical Internet Research · doi:10.2196/20346 · Cited by 626
Xu, L., Sanders, L., Li, K., & Chow, J. C. L. (2021) · JMIR Cancer · doi:10.2196/27850 · Cited by 571
Machine learning–based preoperative predictive analytics for lumbar spinal stenosis
Siccoli, A., de Wispelaere, M. P., Schröder, M. L., & Staartjes, V. E. (2019) · Neurosurgical FOCUS · doi:10.3171/2019.2.focus18723 · Cited by 93
Validity of Chatbot Use for Mental Health Assessment: Experimental Study
Schick, A., Feine, J., Morana, S., Maedche, A., & Reininghaus, U. (2022) · JMIR mhealth and uhealth · doi:10.2196/28082 · Cited by 84
Hollon, T. C., Pandian, B., Khalsa, S. S. S., D’Amico, R. S., Sisti, M. B., Bruce, J. N., Muraszko, K. M., Thompson, G. B., Freudiger, C. W., Hervey‐Jumper, S. L., et al. (2019) · Neurosurgery · doi:10.1093/neuros/nyz310_634 · Cited by 81
Self-citationMachine learning in neurosurgery: a global survey
Staartjes, V. E., Stumpo, V., Kernbach, J. M., Klukowska, A. M., Gadjradj, P. S., Schröder, M. L., Veeravagu, A., Stienen, M. N., van Niftrik, C. H. B., Serra, C., et al. (2020) · Acta Neurochirurgica · doi:10.1007/s00701-020-04532-1 · Cited by 80
Nam, K. H., Kim, D. H., Choi, B. K., & Han, I. H. (2019) · Neurospine · doi:10.14245/ns.1938388.194 · Cited by 76
Machine Learning and Artificial Intelligence in Neurosurgery: Status, Prospects, and Challenges
Dagi, T. F., Barker, F. G., & Glass, J. L. (2021) · Neurosurgery · doi:10.1093/neuros/nyab170 · Cited by 61
Marcus, A. P., Marcus, H. J., Camp, S., Nandi, D., Kitchen, N. D., & Thorne, L. W. (2020) · Scientific Reports · doi:10.1038/s41598-020-62160-2 · Cited by 37
Cited by
Sallam, M. (2023) · Healthcare · doi:10.3390/healthcare11060887 · Cited by 3,126
Haleem, A., Javaid, M., & Singh, R. P. (2022) · BenchCouncil Transactions on Benchmarks, Standards and Evaluations · doi:10.1016/j.tbench.2023.100089 · Cited by 694
ChatGPT in education: Strategies for responsible implementation
Halaweh, M. (2023) · Contemporary Educational Technology · doi:10.30935/cedtech/13036 · Cited by 607
Ethical Considerations of Using ChatGPT in Health Care
Wang, C., Liu, S., Yang, H., Guo, J., Wu, Y., & Liu, J. (2023) · Journal of Medical Internet Research · doi:10.2196/48009 · Cited by 541
“In health care, ChatGPT offers numerous benefits [17], including optimizing radiology reporting [18], generating patient discharge summaries [19], improving patient care [20], providing antimicrobial advice [21], and improving clinical decision support [22].”
Investigating the impact of user trust on the adoption and use of ChatGPT: Survey analysis
Choudhury, A., & Shamszare, H. (2023) · Journal of Medical Internet Research · doi:10.2196/47184 · Cited by 470
“This implies that health providers can leverage chatbots to provide health information and support to patients [8,51,52].”
Metadata
- Authors
- D'Amico, R. S., White, T. G., Shah, H. A., & Langer, D. J.
- Affiliations
- Lenox Hill Hospital (US)
- Venue
- Neurosurgery
- Published
- 2023-02-09
- Volume
- 92
- Issue
- 4
- Pages
- 663-664
- ISSN
- 0148-396X (ISSN-L)
- 1524-4040
- OpenAlex
- W4319656339
- Cited by
- 118
- References
- 17
- Citations by year
- 2026: 6 · 2025: 16 · 2024: 35 · 2023: 59
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Neurosurgery (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Keywords
- chatbots, conversational AI, ChatGPT, generative AI, natural language processing, patient care, clinical research data collection, patient education, clinical decision support, neurosurgical outcomes, survey administration
- MeSH terms
- Patient Care, Humans, Writing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: I Asked a ChatGPT to Write an Editorial About How We Can Incorporate Chatbots Into Neurosurgical Research and Patient Care…. https://app.cochat.ai/papers/10.1227/neu.0000000000002414
- The paper
- D'Amico, R. S., White, T. G., Shah, H. A., & Langer, D. J. (2023). I Asked a ChatGPT to Write an Editorial About How We Can Incorporate Chatbots Into Neurosurgical Research and Patient Care…. Neurosurgery. https://doi.org/10.1227/neu.0000000000002414
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.