1
|
Lim B, Cevik J, Seth I, Sofiadellis F, Ross RJ, Rozen WM, Cuomo R. Evaluating Artificial Intelligence's Role in Teaching the Reporting and Interpretation of Computed Tomographic Angiography for Preoperative Planning of the Deep Inferior Epigastric Artery Perforator Flap. JPRAS Open 2024; 40:273-285. [PMID: 38708385 PMCID: PMC11067004 DOI: 10.1016/j.jpra.2024.03.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2024] [Accepted: 03/30/2024] [Indexed: 05/07/2024] Open
Abstract
Background Artificial intelligence (AI) has the potential to transform preoperative planning for breast reconstruction by enhancing the efficiency, accuracy, and reliability of radiology reporting through automatic interpretation and perforator identification. Large language models (LLMs) have recently advanced significantly in medicine. This study aimed to evaluate the proficiency of contemporary LLMs in interpreting computed tomography angiography (CTA) scans for deep inferior epigastric perforator (DIEP) flap preoperative planning. Methods Four prominent LLMs, ChatGPT-4, BARD, Perplexity, and BingAI, answered six questions on CTA scan reporting. A panel of expert plastic surgeons with extensive experience in breast reconstruction assessed the responses using a Likert scale. In contrast, the responses' readability was evaluated using the Flesch Reading Ease score, the Flesch-Kincaid Grade level, and the Coleman-Liau Index. The DISCERN score was utilized to determine the responses' suitability. Statistical significance was identified through a t-test, and P-values < 0.05 were considered significant. Results BingAI provided the most accurate and useful responses to prompts, followed by Perplexity, ChatGPT, and then BARD. BingAI had the greatest Flesh Reading Ease (34.7±5.5) and DISCERN (60.5±3.9) scores. Perplexity had higher Flesch-Kincaid Grade level (20.5±2.7) and Coleman-Liau Index (17.8±1.6) scores than other LLMs. Conclusion LLMs exhibit limitations in their capabilities of reporting CTA for preoperative planning of breast reconstruction, yet the rapid advancements in technology hint at a promising future. AI stands poised to enhance the education of CTA reporting and aid preoperative planning. In the future, AI technology could provide automatic CTA interpretation, enhancing the efficiency, accuracy, and reliability of CTA reports.
Collapse
Affiliation(s)
- Bryan Lim
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- Faculty of Medicine, Monash University, Melbourne, Victoria, 3004, Australia
| | - Jevan Cevik
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- Faculty of Medicine, Monash University, Melbourne, Victoria, 3004, Australia
| | - Ishith Seth
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- Faculty of Medicine, Monash University, Melbourne, Victoria, 3004, Australia
| | - Foti Sofiadellis
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
| | - Richard J. Ross
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
| | - Warren M. Rozen
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- Faculty of Medicine, Monash University, Melbourne, Victoria, 3004, Australia
| | - Roberto Cuomo
- Plastic Surgery Unit, Department of Medicine, Surgery and Neuroscience, University of Siena, 53100, Italy
| |
Collapse
|
2
|
Cevik J, Lim B, Seth I, Sofiadellis F, Ross RJ, Cuomo R, Rozen WM. Assessment of the bias of artificial intelligence generated images and large language models on their depiction of a surgeon. ANZ J Surg 2024; 94:287-294. [PMID: 38087912 DOI: 10.1111/ans.18792] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 10/22/2023] [Accepted: 11/12/2023] [Indexed: 03/20/2024]
Affiliation(s)
- Jevan Cevik
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- The Alfred Centre, Central Clinical School at Monash University, 99 Commercial Rd, Melbourne, Victoria, 3004, Australia
| | - Bryan Lim
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- The Alfred Centre, Central Clinical School at Monash University, 99 Commercial Rd, Melbourne, Victoria, 3004, Australia
| | - Ishith Seth
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- The Alfred Centre, Central Clinical School at Monash University, 99 Commercial Rd, Melbourne, Victoria, 3004, Australia
| | - Foti Sofiadellis
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
| | - Richard J Ross
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
| | - Roberto Cuomo
- Plastic Surgery Unit, Department of Medicine, Surgery and Neuroscience, University of Siena, Siena, 53100, Italy
| | - Warren M Rozen
- Department of Plastic Surgery, Peninsula Health, Melbourne, Victoria, 3199, Australia
- The Alfred Centre, Central Clinical School at Monash University, 99 Commercial Rd, Melbourne, Victoria, 3004, Australia
| |
Collapse
|
3
|
Mu X, Lim B, Seth I, Xie Y, Cevik J, Sofiadellis F, Hunter‐Smith DJ, Rozen WM. Comparison of large language models in management advice for melanoma: Google's AI BARD, BingAI and ChatGPT. Skin Health Dis 2024; 4:e313. [PMID: 38312244 PMCID: PMC10831541 DOI: 10.1002/ski2.313] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Revised: 10/08/2023] [Accepted: 11/03/2023] [Indexed: 02/06/2024]
Abstract
Large language models (LLMs) are emerging artificial intelligence (AI) technology refining research and healthcare. Their use in medicine has seen numerous recent applications. One area where LLMs have shown particular promise is in the provision of medical information and guidance to practitioners. This study aims to assess three prominent LLMs-Google's AI BARD, BingAI and ChatGPT-4 in providing management advice for melanoma by comparing their responses to current clinical guidelines and existing literature. Five questions on melanoma pathology were prompted to three LLMs. A panel of three experienced Board-certified plastic surgeons evaluated the responses for reliability using reliability matrix (Flesch Reading Ease Score, the Flesch-Kincaid Grade Level and the Coleman-Liau Index), suitability (modified DISCERN score) and comparing them to existing guidelines. t-Test was performed to calculate differences in mean readability and reliability scores between LLMs and p value <0.05 was considered statistically significant. The mean readability scores across three LLMs were same. ChatGPT exhibited superiority with a Flesch Reading Ease Score of 35.42 (±21.02), Flesch-Kincaid Grade Level of 11.98 (±4.49) and Coleman-Liau Index of 12.00 (±5.10), however all of these were insignificant (p > 0.05). Suitability-wise using DISCERN score, ChatGPT 58 (±6.44) significantly (p = 0.04) outperformed BARD 36.2 (±34.06) and was insignificant to BingAI's 49.8 (±22.28). This study demonstrates that ChatGPT marginally outperforms BARD and BingAI in providing reliable, evidence-based clinical advice, but they still face limitations in depth and specificity. Future research should improve LLM performance by integrating specialized databases and expert knowledge to support patient-centred care.
Collapse
Affiliation(s)
- Xin Mu
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
| | - Bryan Lim
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
- Central Clinical SchoolMonash UniversityMelbourneVictoriaAustralia
| | - Ishith Seth
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
- Central Clinical SchoolMonash UniversityMelbourneVictoriaAustralia
| | - Yi Xie
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
| | - Jevan Cevik
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
| | - Foti Sofiadellis
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
| | - David J. Hunter‐Smith
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
- Central Clinical SchoolMonash UniversityMelbourneVictoriaAustralia
| | - Warren M. Rozen
- Department of Plastic SurgeryPeninsula HealthMelbourneVictoriaAustralia
- Central Clinical SchoolMonash UniversityMelbourneVictoriaAustralia
| |
Collapse
|
4
|
Lim B, Seth I, Kah S, Sofiadellis F, Ross RJ, Rozen WM, Cuomo R. Using Generative Artificial Intelligence Tools in Cosmetic Surgery: A Study on Rhinoplasty, Facelifts, and Blepharoplasty Procedures. J Clin Med 2023; 12:6524. [PMID: 37892665 PMCID: PMC10607912 DOI: 10.3390/jcm12206524] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2023] [Revised: 10/03/2023] [Accepted: 10/13/2023] [Indexed: 10/29/2023] Open
Abstract
Artificial intelligence (AI), notably Generative Adversarial Networks, has the potential to transform medical and patient education. Leveraging GANs in medical fields, especially cosmetic surgery, provides a plethora of benefits, including upholding patient confidentiality, ensuring broad exposure to diverse patient scenarios, and democratizing medical education. This study investigated the capacity of AI models, DALL-E 2, Midjourney, and Blue Willow, to generate realistic images pertinent to cosmetic surgery. We combined the generative powers of ChatGPT-4 and Google's BARD with these GANs to produce images of various noses, faces, and eyelids. Four board-certified plastic surgeons evaluated the generated images, eliminating the need for real patient photographs. Notably, generated images predominantly showcased female faces with lighter skin tones, lacking representation of males, older women, and those with a body mass index above 20. The integration of AI in cosmetic surgery offers enhanced patient education and training but demands careful and ethical incorporation to ensure comprehensive representation and uphold medical standards.
Collapse
Affiliation(s)
- Bryan Lim
- Department of Plastic and Reconstructive Surgery, Peninsula Health, Frankston, VIC 3199, Australia
- Central Clinical School, Faculty of Medicine, Monash University, Melbourne, VIC 3004, Australia
| | - Ishith Seth
- Department of Plastic and Reconstructive Surgery, Peninsula Health, Frankston, VIC 3199, Australia
- Central Clinical School, Faculty of Medicine, Monash University, Melbourne, VIC 3004, Australia
| | - Skyler Kah
- Department of Plastic and Reconstructive Surgery, Peninsula Health, Frankston, VIC 3199, Australia
| | - Foti Sofiadellis
- Department of Plastic and Reconstructive Surgery, Peninsula Health, Frankston, VIC 3199, Australia
| | - Richard J. Ross
- Department of Plastic and Reconstructive Surgery, Peninsula Health, Frankston, VIC 3199, Australia
| | - Warren M. Rozen
- Department of Plastic and Reconstructive Surgery, Peninsula Health, Frankston, VIC 3199, Australia
- Central Clinical School, Faculty of Medicine, Monash University, Melbourne, VIC 3004, Australia
| | - Roberto Cuomo
- Plastic Surgery Unit, Department of Medicine, Surgery and Neuroscience, University of Siena, 53100 Siena, Italy
| |
Collapse
|
5
|
Sofiadellis F, Grinsell D. Refinements and restoring contour in head and neck reconstruction. ANZ J Surg 2015; 86:675-80. [PMID: 25904390 DOI: 10.1111/ans.13061] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/08/2015] [Indexed: 11/28/2022]
Abstract
BACKGROUND To date head and neck reconstructions of oncological defects have concentrated on primarily filling the defect to achieve primary wound healing, secondly restore function and lastly cosmesis. This paper describes a refinement of existing free tissue transfer techniques for improvement of contour, function and aesthetics. METHODS A retrospective review of 38 patients operated on by one surgeon at St Vincent's, Royal Melbourne and Western Hospitals over a 3-year period was conducted. Data were collected on patient demographics, tumour details, nature of the defect, type of reconstructive procedure, nature of additional tissue used, radiotherapy, complications and outcome. RESULTS We present refinements in using de-epithelialized skin paddles, flexor hallucis longus, and rectus and vastus lateralis muscle in order to achieve optimal reconstruction. Free tissue transfer refinements are discussed in anterolateral thigh, fibula, rectus and anteromedial thigh free flaps. The average defect size and volume of neck dissection prior to reconstruction is presented. A variation of radical, modified radical and selective neck dissections were required for oncological staging and clearance. Rare and minor associated complications are discussed. Post-operative radiotherapy treatment was used in the majority of patients with preoperative adjuvant therapy required in some salvage cases. All patients achieved primary wound healing post-operatively with no salivary leaks, flap failures or exposure of neck vessels. CONCLUSIONS Supplementary microsurgical tissue transfer of de-epithelialized skin, vastus lateralis, flexor hallucis longus and rectus muscles is a valuable option for restoring contour, aesthetics and vessel protection post-radiotherapy.
Collapse
Affiliation(s)
- Foti Sofiadellis
- Department of Plastics and Reconstructive Surgery, The Royal Melbourne Hospital, Melbourne, Victoria, Australia
| | - Damien Grinsell
- Department of Plastics and Reconstructive Surgery, St Vincent's Hospital, The Western Hospital, The Royal Melbourne Hospital, Melbourne, Victoria, Australia
| |
Collapse
|
6
|
Liu DSH, Sofiadellis F, Ashton M, MacGill K, Webb A. Early soft tissue coverage and negative pressure wound therapy optimises patient outcomes in lower limb trauma. Injury 2012; 43:772-8. [PMID: 22001504 DOI: 10.1016/j.injury.2011.09.003] [Citation(s) in RCA: 86] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/07/2011] [Accepted: 09/07/2011] [Indexed: 02/07/2023]
Abstract
BACKGROUND The timing of soft tissue reconstruction for severe open lower limb trauma is critical to its successful outcome, particularly in the setting of exposed metalware and pre-existing wound infection. The use of negative pressure wound therapy (NPWT) may allow a delay in soft tissue coverage without adverse effects. This study evaluated the impact of delayed free-flap reconstruction, prolonged metalware exposure, pre-flap wound infection, and the efficacy of NPWT on the success of soft tissue coverage after open lower limb injury. METHODS Retrospective review of all free-flap reconstructions for lower limb trauma undertaken at a tertiary trauma centre between June 2002 and July 2009. RESULTS 103 patients underwent 105 free-flap reconstructions. Compared with patients who were reconstructed within 3 days of injury, the cohort with delayed reconstruction beyond 7 days had significantly increased rates of pre-flap wound infection, flap re-operation, deep metal infection and osteomyelitis. Pre-flap wound infection independently predicted adverse surgical outcomes. In the setting of exposed metalware, free-flap transfer beyond one day significantly increased the flap failure rate. These patients required more surgical procedures and a longer hospital stay. The use of NPWT significantly lowered the rate of flap re-operations and venous thrombosis, but did not allow a delay in reconstruction beyond 7 days from injury without a concomitant rise in skeletal and flap complications. CONCLUSIONS Following open lower limb trauma, soft tissue coverage within 3 days of injury and immediately following fracture fixation with exposed metalware minimises pre-flap wound infection and optimises surgical outcomes. NPWT provides effective temporary wound coverage, but does not allow a delay in definitive free-flap reconstruction.
Collapse
Affiliation(s)
- David Shi Hao Liu
- Department of Plastics and Reconstructive Surgery, The Royal Melbourne Hospital, Australia
| | | | | | | | | |
Collapse
|
7
|
Sofiadellis F, Liu D, Webb A, MacGill K, Rozen W, Ashton M. Fasciocutaneous Free Flaps Are More Reliable Than Muscle Free Flaps in Lower Limb Trauma Reconstruction: Experience in a Single Trauma Center. J Reconstr Microsurg 2012; 28:333-40. [DOI: 10.1055/s-0032-1313764] [Citation(s) in RCA: 24] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/28/2022]
Affiliation(s)
- Foti Sofiadellis
- The Taylor Lab, Department of Anatomy and Neurosciences, The University of Melbourne, Parkville, Victoria, Australia
| | - David Liu
- The Taylor Lab, Department of Anatomy and Neurosciences, The University of Melbourne, Parkville, Victoria, Australia
| | - Angela Webb
- The Taylor Lab, Department of Anatomy and Neurosciences, The University of Melbourne, Parkville, Victoria, Australia
| | - Kirsty MacGill
- The Taylor Lab, Department of Anatomy and Neurosciences, The University of Melbourne, Parkville, Victoria, Australia
| | - Warren Rozen
- The Taylor Lab, Department of Anatomy and Neurosciences, The University of Melbourne, Parkville, Victoria, Australia
| | - Mark Ashton
- The Taylor Lab, Department of Anatomy and Neurosciences, The University of Melbourne, Parkville, Victoria, Australia
| |
Collapse
|