RESUMEN
BACKGROUND: Recent advancements in artificial intelligence (AI) and large language models (LLMs) have shown potential in medical fields, including dermatology. With the introduction of image analysis capabilities in LLMs, their application in dermatological diagnostics has garnered significant interest. These capabilities are enabled by the integration of computer vision techniques into the underlying architecture of LLMs. OBJECTIVE: This study aimed to compare the diagnostic performance of Claude 3 Opus and ChatGPT with GPT-4 in analyzing dermoscopic images for melanoma detection, providing insights into their strengths and limitations. METHODS: We randomly selected 100 histopathology-confirmed dermoscopic images (50 malignant, 50 benign) from the International Skin Imaging Collaboration (ISIC) archive using a computer-generated randomization process. The ISIC archive was chosen due to its comprehensive and well-annotated collection of dermoscopic images, ensuring a diverse and representative sample. Images were included if they were dermoscopic images of melanocytic lesions with histopathologically confirmed diagnoses. Each model was given the same prompt, instructing it to provide the top 3 differential diagnoses for each image, ranked by likelihood. Primary diagnosis accuracy, accuracy of the top 3 differential diagnoses, and malignancy discrimination ability were assessed. The McNemar test was chosen to compare the diagnostic performance of the 2 models, as it is suitable for analyzing paired nominal data. RESULTS: In the primary diagnosis, Claude 3 Opus achieved 54.9% sensitivity (95% CI 44.08%-65.37%), 57.14% specificity (95% CI 46.31%-67.46%), and 56% accuracy (95% CI 46.22%-65.42%), while ChatGPT demonstrated 56.86% sensitivity (95% CI 45.99%-67.21%), 38.78% specificity (95% CI 28.77%-49.59%), and 48% accuracy (95% CI 38.37%-57.75%). The McNemar test showed no significant difference between the 2 models (P=.17). For the top 3 differential diagnoses, Claude 3 Opus and ChatGPT included the correct diagnosis in 76% (95% CI 66.33%-83.77%) and 78% (95% CI 68.46%-85.45%) of cases, respectively. The McNemar test showed no significant difference (P=.56). In malignancy discrimination, Claude 3 Opus outperformed ChatGPT with 47.06% sensitivity, 81.63% specificity, and 64% accuracy, compared to 45.1%, 42.86%, and 44%, respectively. The McNemar test showed a significant difference (P<.001). Claude 3 Opus had an odds ratio of 3.951 (95% CI 1.685-9.263) in discriminating malignancy, while ChatGPT-4 had an odds ratio of 0.616 (95% CI 0.297-1.278). CONCLUSIONS: Our study highlights the potential of LLMs in assisting dermatologists but also reveals their limitations. Both models made errors in diagnosing melanoma and benign lesions. These findings underscore the need for developing robust, transparent, and clinically validated AI models through collaborative efforts between AI researchers, dermatologists, and other health care professionals. While AI can provide valuable insights, it cannot yet replace the expertise of trained clinicians.
RESUMEN
Acute liver injury is a destructive liver disorder resulting from overwhelming liver inflammation, oxidative stress and hepatocyte death. Puerarin is a natural flavonoid compound isolated from the traditional Chinese herb radix puerariae. This study investigated the protective effects of puerarin against lipopolysaccharide (LPS)/D-galactosamine (D-Gal)-induced liver injury and the potential mechanisms in mice. Mice were given an intraperitoneal administration of puerarin 200 mg/kg 2 h prior to LPS (50 µg/kg)/D-Gal (400 mg/kg) injection and were sacrificed 6 h post LPS/D-Gal treatment. The results showed that administration of puerarin substantially alleviated LPS/D-Gal-induced acute liver injury in mice by increased survival rates, improved liver histopathology, reduced plasma alanine aminotransferase (ALT) and aspartate aminotransferase (AST) levels, alleviated production of pro-inflammatory cytokines, and suppressed hepatocyte apoptosis. Moreover, puerarin pretreatment activated autophagy by increased the ratio of LC3B-II/I and the protein levels of Beclin-1, decreased the levels of p62 protein expression. Taken together, these findings demonstrated that puerarin could prevent the LPS/D-Gal-induced liver injury in mice, and its mechanisms might be associated with the increments of autophagy and suppression of apoptosis.
RESUMEN
Lipopolysaccharide/d-Galactosamine (LPS/d-Gal)-induced acute liver injury is characterized by significant inflammatory responses including TNF-α and interleukin-6 (IL-6) and is a widely applied experimental model for inflammation research. TNF-α is critical in the progression of LPS/d-Gal-induced liver injury. However, the role of IL-6 in this model is still unknown. In the present study, we aim to elucidate the involvement of IL-6 in the pathogenesis of acute liver injury induced by LPS/d-Gal in mice and its underlying mechanism. To induce acute liver injury, LPS (50µg/kg body weight) and d-Gal (400mg/kg body weight) were injected intraperitoneally in the C57BL/6 mice. The vehicle (saline) or a single dose of recombinant IL-6 (200µg/kg body weight) was administered 2h prior to LPS/d-Gal injection. Mice were sacrificed 2h and 6h after LPS/d-Gal injection. The results indicated that IL-6 treatment could protect mice from LPS/d-Gal-induced tissue damage, alanine aminotransferase (ALT) and aspartate aminotransferase (AST) elevation, as well as hepatocyte apoptosis and inflammation. Furthermore, in vitro study showed that IL-6 treatment could significantly suppress LPS-triggered expression of proinflammatory cytokines and chemokines, TNF-α, RANTES and MCP-1 in macrophages while promoting the expression of M2 markers, such as Arg-1 and Mrc-1 in macrophages. Taken together, these findings revealed a novel and unexpected role of IL-6 in ameliorating LPS/d-Gal-induced acute liver injury via regulating inflammatory responses in hepatic macrophages.