Large language models (LLMs), a form of generative artificial intelligence (AI), are increasingly explored for clinical applications due to their ability to synthesize medical information. In breast cancer care, where therapeutic decision-making is complex because of expanding treatment options, AI-based decision support tools may improve efficiency and consistency. However, their clinical validity and safety remain insufficiently evaluated in real-world settings. The present study aimed to compare the characteristics of treatment recommendations generated by a large language model with those proposed by breast cancer specialists using identical clinical information. This retrospective observational study included 100 patients with advanced or recurrent breast cancer. Clinical information was provided to ChatGPT using a standardized prompt to generate treatment recommendations. Six board-certified breast cancer specialists independently proposed treatment strategies for the same cases. Recommendations were evaluated using five predefined criteria: 1. Comprehensiveness and appropriateness of literature selection, 2. Accuracy of interpretation of key evidence, 3. Clinical appropriateness and diversity of treatment options, 4. Accuracy of adverse event information, 5. Time required to generate recommendations. Group comparisons were performed using linear mixed-effects models with case and evaluator as random effects. ChatGPT achieved higher scores than specialists across all five evaluation criteria, with the largest difference observed for accuracy of key evidence interpretation. The mean total score was 93.7 for ChatGPT and 44.1 for specialists, and linear mixed-effects model analysis confirmed a significantly higher total score for ChatGPT (p < 0.001). These findings suggest that AI-generated responses tended to provide more comprehensive and structured summaries of available evidence within the predefined evaluation framework. LLMs were able to generate comprehensive and structured treatment recommendations based on the provided clinical information. However, these findings primarily reflect differences in information synthesis under predefined evaluation criteria rather than superiority in real-world clinical decision-making. Given the potential risk of hallucinations, AI should be positioned as an assistive tool to support specialist-led decision-making in breast cancer care.
A female patient in her late 20s, with a history of ulcerative colitis since adolescence, underwent ileoanal canal anastomosis for ulcerative colitis. She developed diarrhea, rectal pain, and pyoderma gangrenosum and underwent resection of the remaining rectum and ileal pouch-anal anastomosis. One year postoperatively, she developed ileocolitis, left sacroiliitis, and right dorsal foot pain, which were diagnosed as extraintestinal manifestations, and adalimumab was effective. The patient should be introduced to biologic agents at an earlier stage, considering the possibility of flare-ups or the emergence of new extraintestinal complications when inflammation is present in the residual postoperative rectal mucosa and ileocecal sac.
Systemic lupus erythematosus (SLE) is a systemic autoimmune disease characterized by diverse clinical manifestations. This case report describes a 14-year-old female patient diagnosed with neuropsychiatric SLE (NP-SLE) following status epilepticus. The patient was a 14-year-old previously healthy female and was transported to the emergency department owing to fever and status epilepticus. Based on imaging findings, clinical findings, and the patient's age, anti-N-methyl-D-aspartate (NMDA) receptor encephalitis (NMDARE) was suspected, and intensive care was initiated. However, persistent renal dysfunction and cytopenia prompted detailed investigation, leading to a diagnosis of NP-SLE. SLE is a systemic disease requiring long-term treatment. In such cases, where characteristic rashes are absent, differential diagnosis based on physical findings is difficult. Although NP-SLE and NMDARE share many standard features, including clinical symptoms and age of onset, measuring antinuclear antibody (ANA) and complement levels may be valuable in the differential diagnosis.
BACKGROUND/AIM:This multicenter retrospective study aimed to compare the oncological outcomes of laparoscopic colorectal cancer (CRC) resection as a bridge to surgery after self-expanding metal stent (SEMS) insertion for patients with obstructive CRC (OCRC) with those of elective laparoscopic CRC resection for patients with non-OCRC. PATIENTS AND METHODS:One hundred patients with stage II or III OCRC who underwent SEMS placement as bridge to surgery (SEMS group) and 657 patients with non-OCRC who underwent elective surgery (control group) were included in this study. A propensity score-matching analysis was performed to eliminate confounding factors for prognosis. RESULTS:One hundred patients in the control and SEMS groups were identified using propensity score matching. The incidence of postoperative complications did not differ between the groups. There was no significant difference in 5-year overall survival (control group: 74.1% vs. SEMS group: 82.8%, p=0.365) or cancer-specific survival rates (control group: 82.1% vs. SEMS group: 88.2%, p=0.375). Subgroup analyses stratified by pathological stage or tumor location demonstrated no difference in prognosis between the two groups. CONCLUSION:SEMS placement followed by laparoscopic surgery is a feasible treatment modality for patients with OCRC.
