Performance of artificial intelligence chatbots in interpreting clinical images of pressure injuries.

To evaluate the accuracy of AI chatbots in staging pressure injuries according to the National Pressure Injury Advisory Panel (NPIAP) Staging through clinical image interpretation, a cross-sectional design was conducted to assess five leading publicly available AI chatbots. As a result, three chatbots were unable to interpret the clinical images, whereas GPT-4 Turbo achieved a high accuracy rate (83.0%) in staging pressure injuries, notably outperforming BingAI Creative mode (24.0%) with statistical significance (p < 0.001). GPT-4 Turbo accurately identified Stages 1 (p < 0.001), 3 (p = 0.001), and 4 (p < 0.001) pressure injuries, and suspected deep tissue injuries (p < 0.001), while BingAI demonstrated significantly lower accuracy across all stages. The findings highlight the potential of AI chatbots, especially GPT-4 Turbo, in accurately diagnosing images and aiding the subsequent management of pressure injuries.

Chronic Pain Following Breast Reconstruction: A Scoping Review.

BACKGROUND: Breast cancer survival rates have increased significantly, underscoring the importance of enhancing long-term health-related quality of life. Breast reconstruction following mastectomy has emerged as a common approach that contributes to improved health-related quality of life. Nonetheless, chronic pain following breast reconstruction is a prevalent issue that has a negative impact on overall well-being. METHODS: To examine recent findings on chronic pain after breast reconstruction and progress in pain management, we performed a review of the literature through independent searches using the MEDLINE database within NIH National Library of Medicine PubMed. RESULTS: The review suggested that autologous reconstruction causes chronic postsurgical pain, especially at specific donor sites, whereas implant-based reconstruction does not seem to increase the risk of chronic pain. Moreover, certain operational and patient factors are also associated with chronic pain. Appropriate pain management can reduce chronic pain and prevent the transition from acute to chronic pain. CONCLUSION: This scoping review evaluated the characteristics of long-term chronic pain after breast reconstruction. The findings provide patients with important treatment information and will assist with their decision on their preferred treatment.

Treatment Effectiveness and Recurrence of Extracranial Arteriovenous Malformations Following Surgical Operations: A 15-Year Retrospective Cohort Study.

BACKGROUND: At present, there is no golden standard for treatment of extracranial arteriovenous malformations (AVMs) and recurrence remains a major challenge with limited available evidence on the associated factors. This study aimed to evaluate the effectiveness of surgical treatment options, in terms of size reduction, symptoms, and early recurrence in patients treated surgically for AVMs. METHODS: A retrospective cohort study was conducted to evaluate patients with AVMs following surgical treatment in 2 centers from 2005 to 2020. Posttreatment lesion size and symptoms, as well as recurrence, were assessed. Multiple regression analysis was performed to identify factors associated with recurrence. RESULTS: Forty-four surgical treatment cases in 31 patients were assessed with a mean follow-up duration period of 67.9 ± 39.5 months. Treatment included total resection in 26 cases (59.1%) and partial resection 18 (40.9%), with free flap coverage used in 19 cases (43.2%). No acute exacerbation following treatment was observed in our cohort. Total resection significantly reduced posttreatment lesion size ( P < 0.001), symptoms ( P < 0.001), and recurrence (20.0%, P = 0.03). The recurrence rate was significantly higher after partial resection (73.7%, P = 0.03). Total resection was identified as an associated factor for significantly reduced AVM recurrence (odds ratio: 0.12; 95% confidence interval: 0.03, 0.52). However, the use of free flaps did not significantly reduce recurrence, post treatment size or improve AVM symptoms. CONCLUSIONS: Total resection is the optimal treatment for AVMs. Free flaps are useful in covering large defects but the regulative effect of free flap remains controversial.

Generating Informed Consent Documents Related to Blepharoplasty Using ChatGPT.

PURPOSE: This study aimed to demonstrate the performance of the popular artificial intelligence (AI) language model, Chat Generative Pre-trained Transformer (ChatGPT) (OpenAI, San Francisco, CA, U.S.A.), in generating the informed consent (IC) document of blepharoplasty. METHODS: A total of 2 prompts were provided to ChatGPT to generate IC documents. Four board-certified plastic surgeons and 4 nonmedical staff members evaluated the AI-generated IC documents and the original IC document currently used in the clinical setting. They assessed these documents in terms of accuracy, informativeness, and accessibility. RESULTS: Among board-certified plastic surgeons, the initial AI-generated IC document scored significantly lower than the original IC document in accuracy ( p < 0.001), informativeness ( p = 0.005), and accessibility ( p = 0.021), while the revised AI-generated IC document scored lower compared with the original document in accuracy ( p = 0.03) and accessibility ( p = 0.021). Among nonmedical staff members, no statistical significance of 2 AI-generated IC documents was observed compared with the original document in terms of accuracy, informativeness, and accessibility. CONCLUSIONS: The results showed that current ChatGPT cannot be used as a distinct patient education resource. However, it has the potential to make better IC documents when improving the professional terminology. This AI technology will eventually transform ophthalmic plastic surgery healthcare systematics by enhancing patient education and decision-making via IC documents.

ChatGPT and Clinical Questions on the Practical Guideline of Blepharoptosis: Reply.

In a recent Letter to the Editor authored by Daungsupawong et al. in Aesthetic Plastic Surgery, titled "ChatGPT and Clinical Questions on the Practical Guideline of Blepharoptosis: Correspondence," the authors emphasized important points regarding the input language differences between input and output references. However, advanced versions, such as GPT-4, have shown marginal differences between English and Chinese inputs, possibly because of the use of larger training data. To address this issue, non-English-language-oriented large language models (LLMs) have been developed. The ability of LLMs to refer to existing references varies, with newer models, such as GPT-4, showing higher reference rates than GPT-3.5. Future research should focus on addressing the current limitations and enhancing the effectiveness of emerging LLMs in providing accurate and informative answers to medical questions across multiple languages.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 .

The Potential of Chat-Based Artificial Intelligence Models in Differentiating Between Keloid and Hypertrophic Scars: A Pilot Study.

BACKGROUND: Lasting scars such as keloids and hypertrophic scars adversely affect a patient's quality of life. However, these scars are frequently underdiagnosed because of the complexity of the current diagnostic criteria and classification systems. This study aimed to explore the application of Large Language Models (LLMs) such as ChatGPT in diagnosing scar conditions and to propose a more accessible and straightforward diagnostic approach. METHODS: In this study, five artificial intelligence (AI) chatbots, including ChatGPT-4 (GPT-4), Bing Chat (Precise, Balanced, and Creative modes), and Bard, were evaluated for their ability to interpret clinical scar images using a standardized set of prompts. Thirty mock images of various scar types were analyzed, and each chatbot was queried five times to assess the diagnostic accuracy. RESULTS: GPT-4 had a significantly higher accuracy rate in diagnosing scars than Bing Chat. The overall accuracy rates of GPT-4 and Bing Chat were 36.0% and 22.0%, respectively (P = 0.027), with GPT-4 showing better performance in terms of specificity for keloids (0.6 vs. 0.006) and hypertrophic scars (0.72 vs. 0.0) than Bing Chat. CONCLUSIONS: Although currently available LLMs show potential for use in scar diagnostics, the current technology is still under development and is not yet sufficient for clinical application standards, highlighting the need for further advancements in AI for more accurate medical diagnostics. 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 .

Blepharoptosis Consultation with Artificial Intelligence: Aesthetic Surgery Advice and Counseling from Chat Generative Pre-Trained Transformer (ChatGPT).

BACKGROUND: Chat generative pre-trained transformer (ChatGPT) is a publicly available extensive artificial intelligence (AI) language model that leverages deep learning to generate text that mimics human conversations. In this study, the performance of ChatGPT was assessed by offering insightful and precise answers to a series of fictional questions and emulating a preliminary consultation on blepharoplasty. METHODS: ChatGPT was posed with questions derived from a blepharoplasty checklist provided by the American Society of Plastic Surgeons. Board-certified plastic surgeons and non-medical staff members evaluated the responses for accuracy, informativeness, and accessibility. RESULTS: Nine questions were used in this study. Regarding informativeness, the average score given by board-certified plastic surgeons was significantly lower than that given by non-medical staff members (2.89 ± 0.72 vs 4.41 ± 0.71; p = 0.042). No statistically significant differences were observed in accuracy (p = 0.56) or accessibility (p = 0.11). CONCLUSIONS: Our results emphasize the effectiveness of ChatGPT in simulating doctor-patient conversations during blepharoplasty. Non-medical individuals found its responses more informative compared with the surgeons. Although limited in terms of specialized guidance, ChatGPT offers foundational surgical information. Further exploration is warranted to elucidate the broader role of AI in esthetic surgical consultations. LEVEL OF EVIDENCE V: Observational study under respected authorities. 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 .

Performance of ChatGPT in Answering Clinical Questions on the Practical Guideline of Blepharoptosis.

BACKGROUND: ChatGPT is a free artificial intelligence (AI) language model developed and released by OpenAI in late 2022. This study aimed to evaluate the performance of ChatGPT to accurately answer clinical questions (CQs) on the Guideline for the Management of Blepharoptosis published by the American Society of Plastic Surgeons (ASPS) in 2022. METHODS: CQs in the guideline were used as question sources in both English and Japanese. For each question, ChatGPT provided answers for CQs, evidence quality, recommendation strength, reference match, and answered word counts. We compared the performance of ChatGPT in each component between English and Japanese queries. RESULTS: A total of 11 questions were included in the final analysis, and ChatGPT answered 61.3% of these correctly. ChatGPT demonstrated a higher accuracy rate in English answers for CQs compared to Japanese answers for CQs (76.4% versus 46.4%; p = 0.004) and word counts (123 words versus 35.9 words; p = 0.004). No statistical differences were noted for evidence quality, recommendation strength, and reference match. A total of 697 references were proposed, but only 216 of them (31.0%) existed. CONCLUSIONS: ChatGPT demonstrates potential as an adjunctive tool in the management of blepharoptosis. However, it is crucial to recognize that the existing AI model has distinct limitations, and its primary role should be to complement the expertise of medical professionals. LEVEL OF EVIDENCE V: Observational study under respected authorities. 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 .

Advancement of Generative Pre-trained Transformer Chatbots in Answering Clinical Questions in the Practical Rhinoplasty Guideline.

BACKGROUND: The Generative Pre-trained Transformer (GPT) series, which includes ChatGPT, is an artificial large language model that provides human-like text dialogue. This study aimed to evaluate the performance of artificial intelligence chatbots in answering clinical questions based on practical rhinoplasty guidelines. METHODS: Clinical questions (CQs) developed from the guidelines were used as question sources. For each question, we asked GPT-4 and GPT-3.5 (ChatGPT), developed by OpenAI, to provide answers for the CQs, Policy Level, Aggregate Evidence Quality, Level of Confidence in Evidence, and References. We compared the performance of the two types of artificial intelligence (AI) chatbots. RESULTS: A total of 10 questions were included in the final analysis, and the AI chatbots correctly answered 90.0% of these. GPT-4 demonstrated a lower accuracy rate than GPT-3.5 in answering CQs, although without statistically significant difference (86.0% vs. 94.0%; p = 0.05), whereas GPT-4 showed significantly higher accuracy for the level of confidence in Evidence than GPT-3.5 (52.0% vs. 28.0%; p < 0.01). No statistical differences were observed in Policy Level, Aggregate Evidence Quality, and Reference Match. In addition, GPT-4 rated significantly higher in presenting existing references than GPT-3.5 (36.9% vs. 24.1%; p = 0.01). CONCLUSIONS: The overall performance of GPT-4 was similar to that of GPT-3.5. However, GPT-4 provided existing references at a higher rate than GPT-3.5. GPT-4 has the potential to provide a more accurate reference in professional fields, including rhinoplasty. 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 .

Characteristics and distribution of chronic pain after mastectomy and breast reconstruction: a long-term prospective cohort study.

PURPOSE: Chronic pain following breast surgery is a concern for breast cancer survivors; however, few studies have investigated the localization of persistent postoperative pain. We conducted this study to identify the location of pain following breast reconstruction. METHODS: A total of 213 Japanese women undergoing mastectomy only or breast reconstruction with a tissue expander/implant (TE/Imp) or a deep inferior epigastric perforator (DIEP) flap were enrolled in the study. Questionnaires related to pain location were sent to patients at the end of postoperative year (POY) 1 and POY 5. Multiple comparisons of the types of operation and cross-tabulation were made between the two time points. RESULTS: Surveys were completed by 107 of the women. Severe pain in the upper medial breast was significantly more common in POY 1 after DIEP reconstruction than after mastectomy only (P = 0.01), whereas abdominal pain was worse in POY 5 after DIEP reconstruction than after mastectomy only (P = 0.04). Pain in the medial arm and axilla had resolved better after TE/Imp (P = 0.03) and DIEP reconstruction (P = 0.01) than after mastectomy only by POY 5, but the difference between TE/Imp and DIEP reconstruction was not significant. CONCLUSIONS: These results show that localization of prolonged postoperative pain following breast reconstruction differs depending on the surgical strategy.

Tsugishige Kondo, The Father of Japanese Surgery: Exploring the History of Hideyo Noguchi's Hand Reconstruction With a Forearm Flap Before the Establishment of Plastic Surgery in Japan.

ABSTRACT: Hideyo Noguchi is one of the most famous scientists in Japan's history, and his portrait has adorned the ¥1,000 banknotes since 2004. He had a childhood burn injury resulting in severe hand scarring and contracture that plagued his early life and education.The resulting hand deformity required 3 separate reconstructions with the third and most complex surgery performed by Professor Tsugishige Kondo just before Noguchi's final medical doctor license examination in 1897. In this surgery, Kondo released the contractures using the first radial forearm flap performed in Japan long before the establishment of plastic surgery in the country.Reviewing the history of Kondo, we find that he likely learned the art of reconstructive surgery along with many other surgical techniques during his stay in Europe from 1891 to 1896 where he was mentored by 4 prominent surgeons of the era: Christian Albert Theodor Billroth, Vincenz Czerny, James Israel, and Carl Nicoladoni. During this period, Czerny reported performing the world's first breast reconstruction using lipoma transfer, and Nicoladoni performed the world's first thumb reconstruction with a chest flap and with toe-to-thumb transfer. Kondo may have watched these world's first operations and may have also been taught these innovative techniques including the forearm flap directly by these pioneers. He returned to Japan and successfully applied these reconstructive surgery methods in his practice and teaching, as evidenced by the landmark surgery of Hideyo Noguchi's hand, and laid the foundations for the development of plastic surgery in Japan.

Localization of Chronic Pain in Postmastectomy Patients: A Prospective Comparison Between Patients With and Without Breast Reconstruction.

BACKGROUND: After breast surgery with or without immediate reconstruction, chronic pain can be a major problem for patients. However, few studies have examined the details of the sites of long-lasting postoperative pain. In this study, we specified the postoperative pain location after breast surgery, including reconstruction, to find ways to improve surgical procedures or provide effective pain relief. METHODS: The subjects were 205 Japanese women undergoing mastectomy or breast reconstruction with a tissue expander (TE)/implant or a deep inferior epigastric perforator (DIEP) flap. Patients were asked whether they had pain in different parts of the body at 1 year after surgery. Differences were assessed by cross-tabulation and χ2 statistics. RESULTS: Surveys were completed by 157 subjects. Deep inferior epigastric perforator flap cases had significantly more pain and TE/Imp cases had significantly less pain in the medial breast, upper breast, breast upper medial quadrant, and abdomen (P = 0.006, P = 0.006, P < 0.001, P < 0.001, respectively). In the neck area, pain in TE/Imp cases was significantly worse than that in all other patients (P = 0.025). There was no significant difference in chronic pain in any other body regions among the mastectomy only, TE/Imp, and DIEP flap groups. CONCLUSIONS: The results of the present study revealed that the localization of prolonged postoperative pain after breast surgery differs depending on the surgical procedure. In DIEP flap reconstruction, there was a marked tendency for pain in the inner and upper chest and in the abdomen, whereas TE/IMP surgery resulted in pain around the neck of the affected side. These findings may help improve surgical methods and establish effective pain relief that focuses on the identified pain areas.

Utility of transoral motion-mode ultrasonography to detect tongue fasciculation in patients with amyotrophic lateral sclerosis.

INTRODUCTION: Increasing evidence suggests the utility of the submandibular approach for ultrasonography to detect tongue fasciculation in amyotrophic lateral sclerosis (ALS). We hypothesized that transoral motion-mode ultrasonography (TOMU) would be useful to detect tongue fasciculation in patients with ALS. METHODS: Patients with sporadic ALS showing clinically definite tongue fasciculation were enrolled, and the ultrasonography findings of patients' tongues on TOMU and ultrasonography by the conventional submandibular approach were analyzed. RESULTS: Six patients with clinically definite ALS were enrolled in this study. Although small, irregular muscle movements of 5 to 10 mm in amplitude and 0.1 to 0.2 second in duration were detected in all patients by TOMU, similar muscle movements were detected in only two of the six patients by the submandibular approach. DISCUSSION: TOMU appeared to be useful for detecting tongue fasciculation in ALS patients. Further study is needed to better determine its role as a diagnostic tool for ALS.

Subjective postural vertical in Parkinson's disease with lateral trunk flexion.

BACKGROUND: Patients with Parkinson's disease (PD) and associated lateral trunk flexion (LTF) cannot accurately perceive their own verticality. OBJECTIVE: We measured the subjective postural vertical in coronal plane (SPVc) angle on patients' ipsilateral and contralateral sides and combined to clarify the effects of SPVc on LTF. We also investigated effects of the SPVc angle on LTF severity. METHODS: Thirty-nine patients (aged 74.1 ± 7.6 years) were divided between those with mild LTF (LTF angle < 10°, n = 34) and those with moderate to severe LTF (LTF angle ≥ 10°, n = 5) for comparison of the LTF angle, SPVc angle on both sides, inter-measurement variation in the SPVc angle, and the LTF to SPVc angle ratio (SPVc ratio). RESULTS: We found significant positive correlation between LTF and the SPVc angle on the combined (r = .54, P = .001), ipsilateral (r = .51, P = .002), and contralateral (r = .50, P = .002) sides. We found significant negative correlation between the LTF angle and the SPVc ratio on the combined SPVc (r = -.82, P = .001), ipsilateral (r = -.69, P = .001), and contralateral (r = -.75, P = .001) sides and between the LTF and ipsilateral side coefficient of variation (r = -.34, P = .038). SPVc angles on ipsilateral and contralateral sides were significantly greater in cases of moderate to severe LTF than in cases of mild LTF (P < .01). CONCLUSIONS: Subjective postural vertical in coronal plane assessment may be useful for assessing patients with PD and associated LTF.

Relationship Between Asymptomatic Intracranial Stenosis and Extracranial Arteriosclerotic Findings in Workplace Health Checkups: A Pilot Study.

BACKGROUND: Intracranial arteriosclerotic disease (ICAD) is common in Asians and has been presumed to be largely associated with metabolic syndrome (MetS), but the risks for asymptomatic ICAD detectable in examinations of the brain, among other tests, are not well known. The present study is aimed at identifying the risks for asymptomatic ICAD using data on risk factors obtained in health checkups, including data from magnetic resonance imaging (MRI), chest computed tomography (CT), and neck echography. METHODS: Subjects comprised 103 examinees more than equal to 40 years old (56.9 ± 4.7 years, 93 men) who underwent head MRI, chest CT, and carotid echography in the same period in a workplace health checkup between April and September 2014. Subjects were evaluated for ICAD based on stenosis of bilateral middle cerebral arteries and the basilar artery on previously reported scores from magnetic resonance angiography. Evaluations for extracranial arteriosclerotic disease (ECAD) were based on findings from carotid echography, and total calcium scores were calculated based on the number, areas, and peak Hounsfield computed tomographic numbers of the aortic arch calcified lesion detected. RESULTS: ICAD, including mild cases with stenosis less than 50%, was seen in 21 subjects (20.3%); and MetS was evident in 12 subjects (11.7%). Logistic regression analysis with multivariate adjustment for major vascular risk factor demonstrated that echogenic of plaque was significantly associated with the ICAD (OR 3.69, 95%CI 1.02-13.3), however age was significant predictor of the risk profile in patients with ECAD. CONCLUSIONS: Carotid atherosclerosis could predict intracranial atherosclerosis in middle-aged people. However, further study with large sample size is warranted.

Spread of shingles impeded by previous surgical scar?

We herein report an atypical case of shingles caused by varicella zoster virus after surgery. The virus, which goes along with the cutaneous nerve from the ganglia, was unable to spread across the previous surgical scar due to damage of the cutaneous nerves, but made a detour to the upper left direction from the scar.

Microsurgical Treatment for Arteriovenous Malformations in the Hand.

Vascular malformations in the extremities are a common site of occurrence; arteriovenous malformations (AVMs) are the least frequent of all vascular malformations, estimated at 5% to 20%. The first step in management is to perform a thorough clinical examination. Symptoms are assessed, and staging is performed using the Schobinger classification. Next, ultrasonography and contrast-enhanced computed tomography are used to confirm the diagnosis of AVM and to confirm the extent of the malformation. Surgery is the first-line treatment and reconstruction is performed. In cases where surgery is not feasible, embolization and sclerotherapy may be used to alleviate symptoms.

Appropriateness of Artificial Intelligence Chatbots in Diabetic Foot Ulcer Management.

Type 2 diabetes is a significant global health concern. It often causes diabetic foot ulcers (DFUs), which affect millions of people and increase amputation and mortality rates. Despite existing guidelines, the complexity of DFU treatment makes clinical decisions challenging. Large language models such as chat generative pretrained transformer (ChatGPT), which are adept at natural language processing, have emerged as valuable resources in the medical field. However, concerns about the accuracy and reliability of the information they provide remain. We aimed to assess the accuracy of various artificial intelligence (AI) chatbots, including ChatGPT, in providing information on DFUs based on established guidelines. Seven AI chatbots were asked clinical questions (CQs) based on the DFU guidelines. Their responses were analyzed for accuracy in terms of answers to CQs, grade of recommendation, level of evidence, and agreement with the reference, including verification of the authenticity of the references provided by the chatbots. The AI chatbots showed a mean accuracy of 91.2% in answers to CQs, with discrepancies noted in grade of recommendation and level of evidence. Claude-2 outperformed other chatbots in the number of verified references (99.6%), whereas ChatGPT had the lowest rate of reference authenticity (66.3%). This study highlights the potential of AI chatbots as tools for disseminating medical information and demonstrates their high degree of accuracy in answering CQs related to DFUs. However, the variability in the accuracy of these chatbots and problems like AI hallucinations necessitate cautious use and further optimization for medical applications. This study underscores the evolving role of AI in healthcare and the importance of refining these technologies for effective use in clinical decision-making and patient education.