Purpose: This study aimed to evaluate the diagnostic accuracy of three multimodal large language models (LLMs) in radiological image interpretation and to assess the impact of prompt engineering strategies and input conditions. Methods: This study analyzed 67 radiological quiz cases from the Korean Society of Ultrasound in Medicine. Three multimodal LLMs (Claude 3.5 Sonnet, GPT-4o, and Gemini-1.5-Pro-002) were evaluated using six types of prompts (basic [without system prompt], original [specific instructions], chain-of-thought, reflection, multiagent, and artificial intelligence [AI]–generated). Performance was assessed across various factors, including tumor versus non-tumor status, case rarity, difficulty, and knowledge cutoff dates. A subgroup analysis compared diagnostic accuracy between imaging-only inputs and combined imaging-descriptive text inputs. Results: With imaging-only inputs, Claude 3.5 Sonnet achieved the highest overall accuracy (46.3%, 186/402), followed by GPT-4o (43.5%, 175/402) and Gemini-1.5-Pro-002 (39.8%, 160/402). AI-generated prompts yielded superior combined accuracy across all three models, with significant improvements over the basic (7.96%, P=0.009), chain-of-thought (6.47%, P=0.029), and multiagent prompts (5.97%, P=0.043). The integration of descriptive text significantly enhanced diagnostic accuracy for Claude 3.5 Sonnet (46.3% to 66.2%, P<0.001), GPT-4o (43.5% to 57.5%, P<0.001), and Gemini-1.5-Pro-002 (39.8% to 60.4%, P<0.001). Model performance was significantly influenced by case rarity for GPT-4o (rare: 6.7% vs. nonrare: 53.9%, P=0.001) and by knowledge cutoff dates for Claude 3.5 Sonnet (post-cutoff: 23.5% vs. pre-cutoff: 64.0%, P=0.005). Conclusion Claude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.

Purpose: This study aimed to evaluate the diagnostic accuracy of three multimodal large language models (LLMs) in radiological image interpretation and to assess the impact of prompt engineering strategies and input conditions. Methods: This study analyzed 67 radiological quiz cases from the Korean Society of Ultrasound in Medicine. Three multimodal LLMs (Claude 3.5 Sonnet, GPT-4o, and Gemini-1.5-Pro-002) were evaluated using six types of prompts (basic [without system prompt], original [specific instructions], chain-of-thought, reflection, multiagent, and artificial intelligence [AI]–generated). Performance was assessed across various factors, including tumor versus non-tumor status, case rarity, difficulty, and knowledge cutoff dates. A subgroup analysis compared diagnostic accuracy between imaging-only inputs and combined imaging-descriptive text inputs. Results: With imaging-only inputs, Claude 3.5 Sonnet achieved the highest overall accuracy (46.3%, 186/402), followed by GPT-4o (43.5%, 175/402) and Gemini-1.5-Pro-002 (39.8%, 160/402). AI-generated prompts yielded superior combined accuracy across all three models, with significant improvements over the basic (7.96%, P=0.009), chain-of-thought (6.47%, P=0.029), and multiagent prompts (5.97%, P=0.043). The integration of descriptive text significantly enhanced diagnostic accuracy for Claude 3.5 Sonnet (46.3% to 66.2%, P<0.001), GPT-4o (43.5% to 57.5%, P<0.001), and Gemini-1.5-Pro-002 (39.8% to 60.4%, P<0.001). Model performance was significantly influenced by case rarity for GPT-4o (rare: 6.7% vs. nonrare: 53.9%, P=0.001) and by knowledge cutoff dates for Claude 3.5 Sonnet (post-cutoff: 23.5% vs. pre-cutoff: 64.0%, P=0.005). Conclusion Claude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.

Purpose: This study aimed to evaluate the diagnostic accuracy of three multimodal large language models (LLMs) in radiological image interpretation and to assess the impact of prompt engineering strategies and input conditions. Methods: This study analyzed 67 radiological quiz cases from the Korean Society of Ultrasound in Medicine. Three multimodal LLMs (Claude 3.5 Sonnet, GPT-4o, and Gemini-1.5-Pro-002) were evaluated using six types of prompts (basic [without system prompt], original [specific instructions], chain-of-thought, reflection, multiagent, and artificial intelligence [AI]–generated). Performance was assessed across various factors, including tumor versus non-tumor status, case rarity, difficulty, and knowledge cutoff dates. A subgroup analysis compared diagnostic accuracy between imaging-only inputs and combined imaging-descriptive text inputs. Results: With imaging-only inputs, Claude 3.5 Sonnet achieved the highest overall accuracy (46.3%, 186/402), followed by GPT-4o (43.5%, 175/402) and Gemini-1.5-Pro-002 (39.8%, 160/402). AI-generated prompts yielded superior combined accuracy across all three models, with significant improvements over the basic (7.96%, P=0.009), chain-of-thought (6.47%, P=0.029), and multiagent prompts (5.97%, P=0.043). The integration of descriptive text significantly enhanced diagnostic accuracy for Claude 3.5 Sonnet (46.3% to 66.2%, P<0.001), GPT-4o (43.5% to 57.5%, P<0.001), and Gemini-1.5-Pro-002 (39.8% to 60.4%, P<0.001). Model performance was significantly influenced by case rarity for GPT-4o (rare: 6.7% vs. nonrare: 53.9%, P=0.001) and by knowledge cutoff dates for Claude 3.5 Sonnet (post-cutoff: 23.5% vs. pre-cutoff: 64.0%, P=0.005). Conclusion Claude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.

Purpose: This study aimed to evaluate the diagnostic accuracy of three multimodal large language models (LLMs) in radiological image interpretation and to assess the impact of prompt engineering strategies and input conditions. Methods: This study analyzed 67 radiological quiz cases from the Korean Society of Ultrasound in Medicine. Three multimodal LLMs (Claude 3.5 Sonnet, GPT-4o, and Gemini-1.5-Pro-002) were evaluated using six types of prompts (basic [without system prompt], original [specific instructions], chain-of-thought, reflection, multiagent, and artificial intelligence [AI]–generated). Performance was assessed across various factors, including tumor versus non-tumor status, case rarity, difficulty, and knowledge cutoff dates. A subgroup analysis compared diagnostic accuracy between imaging-only inputs and combined imaging-descriptive text inputs. Results: With imaging-only inputs, Claude 3.5 Sonnet achieved the highest overall accuracy (46.3%, 186/402), followed by GPT-4o (43.5%, 175/402) and Gemini-1.5-Pro-002 (39.8%, 160/402). AI-generated prompts yielded superior combined accuracy across all three models, with significant improvements over the basic (7.96%, P=0.009), chain-of-thought (6.47%, P=0.029), and multiagent prompts (5.97%, P=0.043). The integration of descriptive text significantly enhanced diagnostic accuracy for Claude 3.5 Sonnet (46.3% to 66.2%, P<0.001), GPT-4o (43.5% to 57.5%, P<0.001), and Gemini-1.5-Pro-002 (39.8% to 60.4%, P<0.001). Model performance was significantly influenced by case rarity for GPT-4o (rare: 6.7% vs. nonrare: 53.9%, P=0.001) and by knowledge cutoff dates for Claude 3.5 Sonnet (post-cutoff: 23.5% vs. pre-cutoff: 64.0%, P=0.005). Conclusion Claude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.

Purpose: This study aimed to evaluate the diagnostic accuracy of three multimodal large language models (LLMs) in radiological image interpretation and to assess the impact of prompt engineering strategies and input conditions. Methods: This study analyzed 67 radiological quiz cases from the Korean Society of Ultrasound in Medicine. Three multimodal LLMs (Claude 3.5 Sonnet, GPT-4o, and Gemini-1.5-Pro-002) were evaluated using six types of prompts (basic [without system prompt], original [specific instructions], chain-of-thought, reflection, multiagent, and artificial intelligence [AI]–generated). Performance was assessed across various factors, including tumor versus non-tumor status, case rarity, difficulty, and knowledge cutoff dates. A subgroup analysis compared diagnostic accuracy between imaging-only inputs and combined imaging-descriptive text inputs. Results: With imaging-only inputs, Claude 3.5 Sonnet achieved the highest overall accuracy (46.3%, 186/402), followed by GPT-4o (43.5%, 175/402) and Gemini-1.5-Pro-002 (39.8%, 160/402). AI-generated prompts yielded superior combined accuracy across all three models, with significant improvements over the basic (7.96%, P=0.009), chain-of-thought (6.47%, P=0.029), and multiagent prompts (5.97%, P=0.043). The integration of descriptive text significantly enhanced diagnostic accuracy for Claude 3.5 Sonnet (46.3% to 66.2%, P<0.001), GPT-4o (43.5% to 57.5%, P<0.001), and Gemini-1.5-Pro-002 (39.8% to 60.4%, P<0.001). Model performance was significantly influenced by case rarity for GPT-4o (rare: 6.7% vs. nonrare: 53.9%, P=0.001) and by knowledge cutoff dates for Claude 3.5 Sonnet (post-cutoff: 23.5% vs. pre-cutoff: 64.0%, P=0.005). Conclusion Claude 3.5 Sonnet achieved the highest diagnostic accuracy in radiological quiz cases, followed by GPT-4o and Gemini-1.5-Pro-002. The use of AI-generated prompts and the integration of descriptive text inputs enhanced model performance.

Chronic kidney disease (CKD) patients are hospitalized for various conditions. Hospitalization increases the readmission rate and mortality rate, seriously deteriorating patients’ quality of life. Consequently, it is crucial to analyze the reasons for hospitalization in CKD patients from a broader perspective according to CKD grade. Methods: This is a prospective cohort study of CKD patients entitled the KoreaN cohort study for Outcomes in patients With Chronic Kidney Disease (KNOW-CKD). A total of 2,238 patients were examined, and the reasons for hospitalization were classified into 16 disease categories. The incidence rate ratio (IRR) according to CKD stage was compared using negative bimodal regression analysis. Results: The all-cause hospitalization incidence was 184.96 per 1,000 person-years. The most common reason for hospitalization was circulatory system disease, followed by infection and digestive system disease. Among hospitalizations for acute kidney injury, endocrine-nutrition-metabolic–related illness, blood-related disease, and diseases of the nervous system and sensory organs, IRR increased as CKD grade advanced. The incidence of ophthalmologic surgery during hospitalization increased according to the CKD stage. The IRR of KNOW-CKD patients was 6.19 (95% confidence interval, 5.92–6.48; p < 0.001) compared with the general population. Conclusion: This in-depth analysis of hospitalizations among CKD patients confirmed that CKD patients were hospitalized for various reasons, such as metabolic, ophthalmic, and hematologic diseases. Early detection and intervention regarding causative diseases of CKD are important to reduce the hospitalization burden and improve patients’ quality of life.

Purpose: This study aimed to determine whether micro-flow imaging (MFI) offers diagnostic performance comparable to that of contrast-enhanced ultrasonography (CEUS) in detecting segmental congestion among patients undergoing living donor liver transplantation (LDLT). Methods: Data from 63 patients who underwent LDLT between May and December 2022 were retrospectively analyzed. MFI and CEUS data collected on the first postoperative day were quantified. Segmental congestion was assessed based on imaging findings and laboratory data, including liver enzymes and total bilirubin levels. The reference standard was a postoperative contrast-enhanced computed tomography scan performed within 2 weeks of surgery. Additionally, a subgroup analysis examined patients who underwent reconstruction of the middle hepatic vein territory. Results: The sensitivity and specificity of MFI were 73.9% and 67.5%, respectively. In comparison, CEUS demonstrated a sensitivity of 78.3% and a specificity of 75.0%. These findings suggest comparable diagnostic performance, with no significant differences in sensitivity (P=0.655) or specificity (P=0.257) between the two modalities. Additionally, early postoperative laboratory values did not show significant differences between patients with and without congestion. The subgroup analysis also indicated similar diagnostic performance between MFI and CEUS. Conclusion MFI without contrast enhancement yielded results comparable to those of CEUS in detecting segmental congestion after LDLT. Therefore, MFI may be considered a viable alternative to CEUS.

A single exposure to stress can induce functional changes in neurons, potentially leading to acute stress disorder or post-traumatic stress disorder.In this study, we used in vivo wide-field optical mapping to simultaneously measure neural calcium signals and hemodynamic responses over the whole cortical area. We found that cortical mapping to whisker stimuli was altered under acute stress conditions. In particular, callosal projections in the anterior cortex (primary/secondary motor, somatosensory forelimb cortex) relative to barrel field (S1BF) of somatosensory cortex were weakened. On the contrary, the projections in posterior cortex relative to S1BF were mostly unchanged or were only occasionally strengthened. In addition, changes in intra-cortical connection were opposite to those in inter-cortical connection. Thus, the S1BF connections to the anterior cortex were strengthened while those to the posterior cortex were weakened. This suggests that the well-known barrel cortex projection route was enhanced. In summary, our in vivo wide-field optical mapping study indicates that a single acute stress can impact whole-brain networks, affecting both neural and hemodynamic responses.

Purpose: This study aimed to determine whether micro-flow imaging (MFI) offers diagnostic performance comparable to that of contrast-enhanced ultrasonography (CEUS) in detecting segmental congestion among patients undergoing living donor liver transplantation (LDLT). Methods: Data from 63 patients who underwent LDLT between May and December 2022 were retrospectively analyzed. MFI and CEUS data collected on the first postoperative day were quantified. Segmental congestion was assessed based on imaging findings and laboratory data, including liver enzymes and total bilirubin levels. The reference standard was a postoperative contrast-enhanced computed tomography scan performed within 2 weeks of surgery. Additionally, a subgroup analysis examined patients who underwent reconstruction of the middle hepatic vein territory. Results: The sensitivity and specificity of MFI were 73.9% and 67.5%, respectively. In comparison, CEUS demonstrated a sensitivity of 78.3% and a specificity of 75.0%. These findings suggest comparable diagnostic performance, with no significant differences in sensitivity (P=0.655) or specificity (P=0.257) between the two modalities. Additionally, early postoperative laboratory values did not show significant differences between patients with and without congestion. The subgroup analysis also indicated similar diagnostic performance between MFI and CEUS. Conclusion MFI without contrast enhancement yielded results comparable to those of CEUS in detecting segmental congestion after LDLT. Therefore, MFI may be considered a viable alternative to CEUS.