1
|
Haltaufderheide J, Ranisch R. The ethics of ChatGPT in medicine and healthcare: a systematic review on Large Language Models (LLMs). NPJ Digit Med 2024; 7:183. [PMID: 38977771 PMCID: PMC11231310 DOI: 10.1038/s41746-024-01157-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Accepted: 05/29/2024] [Indexed: 07/10/2024] Open
Abstract
With the introduction of ChatGPT, Large Language Models (LLMs) have received enormous attention in healthcare. Despite potential benefits, researchers have underscored various ethical implications. While individual instances have garnered attention, a systematic and comprehensive overview of practical applications currently researched and ethical issues connected to them is lacking. Against this background, this work maps the ethical landscape surrounding the current deployment of LLMs in medicine and healthcare through a systematic review. Electronic databases and preprint servers were queried using a comprehensive search strategy which generated 796 records. Studies were screened and extracted following a modified rapid review approach. Methodological quality was assessed using a hybrid approach. For 53 records, a meta-aggregative synthesis was performed. Four general fields of applications emerged showcasing a dynamic exploration phase. Advantages of using LLMs are attributed to their capacity in data analysis, information provisioning, support in decision-making or mitigating information loss and enhancing information accessibility. However, our study also identifies recurrent ethical concerns connected to fairness, bias, non-maleficence, transparency, and privacy. A distinctive concern is the tendency to produce harmful or convincing but inaccurate content. Calls for ethical guidance and human oversight are recurrent. We suggest that the ethical guidance debate should be reframed to focus on defining what constitutes acceptable human oversight across the spectrum of applications. This involves considering the diversity of settings, varying potentials for harm, and different acceptable thresholds for performance and certainty in healthcare. Additionally, critical inquiry is needed to evaluate the necessity and justification of LLMs' current experimental use.
Collapse
Affiliation(s)
- Joschka Haltaufderheide
- Faculty of Health Sciences Brandenburg, University of Potsdam, Am Mühlenberg 9, Potsdam, 14476, Germany
| | - Robert Ranisch
- Faculty of Health Sciences Brandenburg, University of Potsdam, Am Mühlenberg 9, Potsdam, 14476, Germany.
| |
Collapse
|
2
|
Bsisu I, Alqassieh R, Aloweidi A, Abu-Humdan A, Subuh A, Masarweh D. Attitudes of Jordanian Anesthesiologists and Anesthesia Residents towards Artificial Intelligence: A Cross-Sectional Study. J Pers Med 2024; 14:447. [PMID: 38793029 PMCID: PMC11121815 DOI: 10.3390/jpm14050447] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2024] [Revised: 03/29/2024] [Accepted: 04/24/2024] [Indexed: 05/26/2024] Open
Abstract
Success in integrating artificial intelligence (AI) in anesthesia depends on collaboration with anesthesiologists, respecting their expertise, and understanding their opinions. The aim of this study was to illustrate the confidence in AI integration in perioperative anesthetic care among Jordanian anesthesiologists and anesthesia residents working at tertiary teaching hospitals. This cross-sectional study was conducted via self-administered online questionnaire and includes 118 responses from 44 anesthesiologists and 74 anesthesia residents. We used a five-point Likert scale to investigate the confidence in AI's role in different aspects of the perioperative period. A significant difference was found between anesthesiologists and anesthesia residents in confidence in the role of AI in operating room logistics and management, with an average score of 3.6 ± 1.3 among residents compared to 2.9 ± 1.4 among specialists (p = 0.012). The role of AI in event prediction under anesthesia scored 3.5 ± 1.4 among residents compared to 2.9 ± 1.4 among specialists (p = 0.032) and the role of AI in decision-making in anesthetic complications 3.3 ± 1.4 among residents and 2.8 ± 1.4 among specialists (p = 0.034). Also, 65 (55.1%) were concerned that the integration of AI will lead to less human-human interaction, while 81 (68.6%) believed that AI-based technology will lead to more adherence to guidelines. In conclusion, AI has the potential to be a revolutionary tool in anesthesia, and hesitancy towards increased dependency on this technology is decreasing with newer generations of practitioners.
Collapse
Affiliation(s)
- Isam Bsisu
- Department of Anesthesia and Intensive Care, School of Medicine, The University of Jordan, Amman 11942, Jordan; (A.A.); (A.A.-H.); (D.M.)
- UCSF Center for Health Equity in Surgery and Anesthesia, San Francisco, CA 94158, USA
- Department of Anesthesia and Intensive Care, Arab Medical Center, Amman 11181, Jordan
| | - Rami Alqassieh
- Department of General Surgery and Anesthesia and Urology, Faculty of Medicine, The Hashemite University, Zarqa 13133, Jordan;
| | - Abdelkarim Aloweidi
- Department of Anesthesia and Intensive Care, School of Medicine, The University of Jordan, Amman 11942, Jordan; (A.A.); (A.A.-H.); (D.M.)
| | - Abdulrahman Abu-Humdan
- Department of Anesthesia and Intensive Care, School of Medicine, The University of Jordan, Amman 11942, Jordan; (A.A.); (A.A.-H.); (D.M.)
| | - Aseel Subuh
- Department of Internal Medicine, School of Medicine, The University of Jordan, Amman 11942, Jordan;
| | - Deema Masarweh
- Department of Anesthesia and Intensive Care, School of Medicine, The University of Jordan, Amman 11942, Jordan; (A.A.); (A.A.-H.); (D.M.)
| |
Collapse
|
3
|
Liu HY, Alessandri-Bonetti M, Arellano JA, Egro FM. Can ChatGPT be the Plastic Surgeon's New Digital Assistant? A Bibliometric Analysis and Scoping Review of ChatGPT in Plastic Surgery Literature. Aesthetic Plast Surg 2024; 48:1644-1652. [PMID: 37853081 DOI: 10.1007/s00266-023-03709-0] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2023] [Accepted: 09/30/2023] [Indexed: 10/20/2023]
Abstract
BACKGROUND ChatGPT, an artificial intelligence (AI) chatbot that uses natural language processing (NLP) to interact in a humanlike manner, has made significant contributions to various healthcare fields, including plastic surgery. However, its widespread use has raised ethical and security concerns. This study examines the presence of ChatGPT, an artificial intelligence (AI) chatbot, in the literature of plastic surgery. METHODS A bibliometric analysis and scoping review of the ChatGPT plastic surgery literature were performed. PubMed was queried using the search term "ChatGPT" to identify all biomedical literature on ChatGPT, with only studies related to plastic, reconstructive, or aesthetic surgery topics being considered eligible for inclusion. RESULTS The analysis included 30 out of 724 articles retrieved from PubMed, focusing on publications from December 2022 to July 2023. Four key areas of research emerged: applications in research/creation of original work, clinical application, surgical education, and ethics/commentary on previous studies. The versatility of ChatGPT in research, its potential in surgical education, and its role in enhancing patient education were explored. Ethical concerns regarding patient privacy, plagiarism, and the accuracy of information obtained from ChatGPT-generated sources were also highlighted. CONCLUSION While ethical concerns persist, the study underscores the potential of ChatGPT in plastic surgery research and practice, emphasizing the need for careful utilization and collaboration to optimize its benefits while minimizing risks. LEVEL OF EVIDENCE V This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
Collapse
Affiliation(s)
- Hilary Y Liu
- Department of Plastic Surgery, University of Pittsburgh Medical Center, 1350 Locust Street, Pittsburgh, PA, G10315219, USA
| | - Mario Alessandri-Bonetti
- Department of Plastic Surgery, University of Pittsburgh Medical Center, 1350 Locust Street, Pittsburgh, PA, G10315219, USA
| | - José Antonio Arellano
- Department of Plastic Surgery, University of Pittsburgh Medical Center, 1350 Locust Street, Pittsburgh, PA, G10315219, USA
| | - Francesco M Egro
- Department of Plastic Surgery, University of Pittsburgh Medical Center, 1350 Locust Street, Pittsburgh, PA, G10315219, USA.
| |
Collapse
|
4
|
Boyd CJ, Hemal K, Sorenson TJ, Patel PA, Bekisz JM, Choi M, Karp NS. Artificial Intelligence as a Triage Tool during the Perioperative Period: Pilot Study of Accuracy and Accessibility for Clinical Application. PLASTIC AND RECONSTRUCTIVE SURGERY-GLOBAL OPEN 2024; 12:e5580. [PMID: 38313585 PMCID: PMC10836902 DOI: 10.1097/gox.0000000000005580] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Accepted: 12/05/2023] [Indexed: 02/06/2024]
Abstract
Background Given the dialogistic properties of ChatGPT, we hypothesized that this artificial intelligence (AI) function can be used as a self-service tool where clinical questions can be directly answered by AI. Our objective was to assess the content, accuracy, and accessibility of AI-generated content regarding common perioperative questions for reduction mammaplasty. Methods ChatGPT (OpenAI, February Version, San Francisco, Calif.) was used to query 20 common patient concerns that arise in the perioperative period of a reduction mammaplasty. Searches were performed in duplicate for both a general term and a specific clinical question. Query outputs were analyzed both objectively and subjectively. Descriptive statistics, t tests, and chi-square tests were performed where appropriate with a predetermined level of significance of P less than 0.05. Results From a total of 40 AI-generated outputs, mean word length was 191.8 words. Readability was at the thirteenth grade level. Regarding content, of all query outputs, 97.5% were on the appropriate topic. Medical advice was deemed to be reasonable in 100% of cases. General queries more frequently reported overarching background information, whereas specific queries more frequently reported prescriptive information (P < 0.0001). AI outputs specifically recommended following surgeon provided postoperative instructions in 82.5% of instances. Conclusions Currently available AI tools, in their nascent form, can provide recommendations for common perioperative questions and concerns for reduction mammaplasty. With further calibration, AI interfaces may serve as a tool for fielding patient queries in the future; however, patients must always retain the ability to bypass technology and be able to contact their surgeon.
Collapse
Affiliation(s)
- Carter J Boyd
- From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y
| | - Kshipra Hemal
- From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y
| | - Thomas J Sorenson
- From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y
| | | | - Jonathan M Bekisz
- From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y
| | - Mihye Choi
- From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y
| | - Nolan S Karp
- From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y
| |
Collapse
|
5
|
Younis HA, Eisa TAE, Nasser M, Sahib TM, Noor AA, Alyasiri OM, Salisu S, Hayder IM, Younis HA. A Systematic Review and Meta-Analysis of Artificial Intelligence Tools in Medicine and Healthcare: Applications, Considerations, Limitations, Motivation and Challenges. Diagnostics (Basel) 2024; 14:109. [PMID: 38201418 PMCID: PMC10802884 DOI: 10.3390/diagnostics14010109] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2023] [Revised: 12/02/2023] [Accepted: 12/04/2023] [Indexed: 01/12/2024] Open
Abstract
Artificial intelligence (AI) has emerged as a transformative force in various sectors, including medicine and healthcare. Large language models like ChatGPT showcase AI's potential by generating human-like text through prompts. ChatGPT's adaptability holds promise for reshaping medical practices, improving patient care, and enhancing interactions among healthcare professionals, patients, and data. In pandemic management, ChatGPT rapidly disseminates vital information. It serves as a virtual assistant in surgical consultations, aids dental practices, simplifies medical education, and aids in disease diagnosis. A total of 82 papers were categorised into eight major areas, which are G1: treatment and medicine, G2: buildings and equipment, G3: parts of the human body and areas of the disease, G4: patients, G5: citizens, G6: cellular imaging, radiology, pulse and medical images, G7: doctors and nurses, and G8: tools, devices and administration. Balancing AI's role with human judgment remains a challenge. A systematic literature review using the PRISMA approach explored AI's transformative potential in healthcare, highlighting ChatGPT's versatile applications, limitations, motivation, and challenges. In conclusion, ChatGPT's diverse medical applications demonstrate its potential for innovation, serving as a valuable resource for students, academics, and researchers in healthcare. Additionally, this study serves as a guide, assisting students, academics, and researchers in the field of medicine and healthcare alike.
Collapse
Affiliation(s)
- Hussain A. Younis
- College of Education for Women, University of Basrah, Basrah 61004, Iraq
| | | | - Maged Nasser
- Computer & Information Sciences Department, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia;
| | - Thaeer Mueen Sahib
- Kufa Technical Institute, Al-Furat Al-Awsat Technical University, Kufa 54001, Iraq;
| | - Ameen A. Noor
- Computer Science Department, College of Education, University of Almustansirya, Baghdad 10045, Iraq;
| | | | - Sani Salisu
- Department of Information Technology, Federal University Dutse, Dutse 720101, Nigeria;
| | - Israa M. Hayder
- Qurna Technique Institute, Southern Technical University, Basrah 61016, Iraq;
| | - Hameed AbdulKareem Younis
- Department of Cybersecurity, College of Computer Science and Information Technology, University of Basrah, Basrah 61016, Iraq;
| |
Collapse
|
6
|
Miao J, Thongprayoon C, Suppadungsuk S, Garcia Valencia OA, Qureshi F, Cheungpasitporn W. Innovating Personalized Nephrology Care: Exploring the Potential Utilization of ChatGPT. J Pers Med 2023; 13:1681. [PMID: 38138908 PMCID: PMC10744377 DOI: 10.3390/jpm13121681] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2023] [Revised: 12/02/2023] [Accepted: 12/02/2023] [Indexed: 12/24/2023] Open
Abstract
The rapid advancement of artificial intelligence (AI) technologies, particularly machine learning, has brought substantial progress to the field of nephrology, enabling significant improvements in the management of kidney diseases. ChatGPT, a revolutionary language model developed by OpenAI, is a versatile AI model designed to engage in meaningful and informative conversations. Its applications in healthcare have been notable, with demonstrated proficiency in various medical knowledge assessments. However, ChatGPT's performance varies across different medical subfields, posing challenges in nephrology-related queries. At present, comprehensive reviews regarding ChatGPT's potential applications in nephrology remain lacking despite the surge of interest in its role in various domains. This article seeks to fill this gap by presenting an overview of the integration of ChatGPT in nephrology. It discusses the potential benefits of ChatGPT in nephrology, encompassing dataset management, diagnostics, treatment planning, and patient communication and education, as well as medical research and education. It also explores ethical and legal concerns regarding the utilization of AI in medical practice. The continuous development of AI models like ChatGPT holds promise for the healthcare realm but also underscores the necessity of thorough evaluation and validation before implementing AI in real-world medical scenarios. This review serves as a valuable resource for nephrologists and healthcare professionals interested in fully utilizing the potential of AI in innovating personalized nephrology care.
Collapse
Affiliation(s)
- Jing Miao
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (J.M.); (C.T.); (S.S.); (O.A.G.V.); (F.Q.)
| | - Charat Thongprayoon
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (J.M.); (C.T.); (S.S.); (O.A.G.V.); (F.Q.)
| | - Supawadee Suppadungsuk
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (J.M.); (C.T.); (S.S.); (O.A.G.V.); (F.Q.)
- Chakri Naruebodindra Medical Institute, Faculty of Medicine Ramathibodi Hospital, Mahidol University, Samut Prakan 10540, Thailand
| | - Oscar A. Garcia Valencia
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (J.M.); (C.T.); (S.S.); (O.A.G.V.); (F.Q.)
| | - Fawad Qureshi
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (J.M.); (C.T.); (S.S.); (O.A.G.V.); (F.Q.)
| | - Wisit Cheungpasitporn
- Division of Nephrology and Hypertension, Department of Medicine, Mayo Clinic, Rochester, MN 55905, USA; (J.M.); (C.T.); (S.S.); (O.A.G.V.); (F.Q.)
| |
Collapse
|
7
|
Abi-Rafeh J, Hanna S, Bassiri-Tehrani B, Kazan R, Nahai F. Complications Following Facelift and Neck Lift: Implementation and Assessment of Large Language Model and Artificial Intelligence (ChatGPT) Performance Across 16 Simulated Patient Presentations. Aesthetic Plast Surg 2023; 47:2407-2414. [PMID: 37589944 DOI: 10.1007/s00266-023-03538-1] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2023] [Accepted: 07/19/2023] [Indexed: 08/18/2023]
Abstract
INTRODUCTION ChatGPT represents a potential resource for patient guidance and education, with the possibility for quality improvement in healthcare delivery. The present study evaluates the role of ChatGPT as an interactive patient resource, and assesses its performance in identifying, triaging, and guiding patients with concerns of postoperative complications following facelift and neck lift surgery. METHODS Sixteen patient profiles were generated to simulate postoperative patient presentations, with complications of varying acuity and severity. ChatGPT was assessed for its accuracy in generating a differential diagnosis, soliciting a history, providing the most-likely diagnosis, the appropriate disposition, treatments/interventions to begin from home, and red-flag symptoms necessitating an urgent presentation to the emergency department. RESULTS Overall accuracy in providing a complete differential diagnosis in response to simulated presentations was 85%, with an accuracy of 88% in identifying the most-likely diagnosis after history-taking. However, appropriate patient dispositions were suggested in only 56% of cases. Relevant home treatments/interventions were suggested with an 82% accuracy, and red-flag symptoms with a 73% accuracy. A detailed analysis, stratified according to latency of postoperative presentation (<48 h, 48 h-1 week, or >1 week), and according to acuity of complications, is presented herein. CONCLUSIONS ChatGPT overestimated the urgency of indicated patient dispositions in 44% of cases, concerning for potential unnecessary increase in healthcare resource utilization. Imperfect performance, and the tool's tendency for overinclusion in its responses, risk increasing patient anxiety and straining physician-patient relationships. While artificial intelligence has great potential in triaging postoperative patient concerns, and improving efficiency and resource utilization, ChatGPT's performance, in its current form, demonstrates a need for further refinement before its safe and effective implementation in facial aesthetic surgical practice. LEVEL OF EVIDENCE IV This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
Collapse
Affiliation(s)
- Jad Abi-Rafeh
- Division of Plastic, Reconstructive, and Aesthetic Surgery, McGill University Health Centre, Montreal, QC, Canada
| | - Steven Hanna
- Manhattan Eye, Ear and Throat Hospital, New York, NY, USA
| | | | - Roy Kazan
- Division of Plastic and Reconstructive Surgery, University of Pittsburgh, Pittsburgh, PA, USA
| | - Foad Nahai
- Former Maurice J. Jurkiewicz Chair and Professor of Plastic Surgery, Department of Surgery, Emory University, Atlanta, GA, USA.
| |
Collapse
|
8
|
Lupariello F, Sussetto L, Di Trani S, Di Vella G. Artificial Intelligence and Child Abuse and Neglect: A Systematic Review. CHILDREN (BASEL, SWITZERLAND) 2023; 10:1659. [PMID: 37892322 PMCID: PMC10605696 DOI: 10.3390/children10101659] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Revised: 09/30/2023] [Accepted: 10/06/2023] [Indexed: 10/29/2023]
Abstract
All societies should carefully address the child abuse and neglect phenomenon due to its acute and chronic sequelae. Even if artificial intelligence (AI) implementation in this field could be helpful, the state of the art of this implementation is not known. No studies have comprehensively reviewed the types of AI models that have been developed/validated. Furthermore, no indications about the risk of bias in these studies are available. For these reasons, the authors conducted a systematic review of the PubMed database to answer the following questions: "what is the state of the art about the development and/or validation of AI predictive models useful to contrast child abuse and neglect phenomenon?"; "which is the risk of bias of the included articles?". The inclusion criteria were: articles written in English and dated from January 1985 to 31 March 2023; publications that used a medical and/or protective service dataset to develop and/or validate AI prediction models. The reviewers screened 413 articles. Among them, seven papers were included. Their analysis showed that: the types of input data were heterogeneous; artificial neural networks, convolutional neural networks, and natural language processing were used; the datasets had a median size of 2600 cases; the risk of bias was high for all studies. The results of the review pointed out that the implementation of AI in the child abuse and neglect field lagged compared to other medical fields. Furthermore, the evaluation of the risk of bias suggested that future studies should provide an appropriate choice of sample size, validation, and management of overfitting, optimism, and missing data.
Collapse
Affiliation(s)
- Francesco Lupariello
- Dipartimento di Scienze della Sanità Pubblica e Pediatriche, Sezione di Medicina Legale, Università degli Studi di Torino, 10126 Torino, Italy
| | | | | | | |
Collapse
|
9
|
Erren TC, Lewis P, Shaw DM. Brave (in a) new world: an ethical perspective on chatbots for medical advice. Front Public Health 2023; 11:1254334. [PMID: 37663854 PMCID: PMC10470018 DOI: 10.3389/fpubh.2023.1254334] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Accepted: 07/31/2023] [Indexed: 09/05/2023] Open
Affiliation(s)
- Thomas C. Erren
- University of Cologne, University Hospital of Cologne, Cologne, North Rhine-Westphalia, Germany
| | - Philip Lewis
- University of Cologne, University Hospital of Cologne, Cologne, North Rhine-Westphalia, Germany
| | - David M. Shaw
- Care and Public Health Research Institute, Maastricht University, Maastricht, Netherlands
- Institute for Biomedical Ethics, University of Basel, Basel, Switzerland
| |
Collapse
|