Mengqi Deng

AI-driven patient-centered care: A digital transformation framework for gynecologic cancer genetic counseling

Objectives This study evaluates artificial intelligence (AI) reasoning capabilities in gynecologic cancer genetic counseling, comparing the performance of ChatGPT and DeepSeek models to guide patient-centered AI implementation in clinical genetics. Methods Using 40 National Comprehensive Cancer Network-aligned counseling scenarios, we conducted blinded dual-oncologist evaluations of two large language models. Methodological rigor included model anonymization, a pre-calibrated scoring framework, and validated metrics (Global Quality Scale and Patient Education Materials Assessment Tool) assessing informational coherence, understandability, and actionability. Results DeepSeek demonstrated superior informational breadth (mean character difference: −609.0, p  < .0001) and visual communication (diagram integration, p  < .01), with 49-fold greater probability in recommending clear and actionable actions ( p  < .01, OR = 49.0). ChatGPT excelled in concise summarization (22% faster response generation, p  = .013). Conclusion Strategic AI model selection—leveraging DeepSeek's visually-rich, structured educational approach for complex information, and ChatGPT's concise, rapid summarization for efficient communication—enhances patient-centered genetic education when combined with clinician oversight. This framework supports healthcare's digital transformation by optimizing human-AI collaboration in hereditary cancer care.

The prognostic significance of primary tumor site in vulvar cancer: a population-based cohort study

To investigate the association of primary tumor site with prognosis in vulvar cancer, stratified by vulvar squamous cell carcinoma (SCC) and non-SCC histological types. This population-based retrospective study enrolled patients with vulvar cancer from the Surveillance, Epidemiology, and End Results database between January 2000 and December 2018. The primary outcome was cancer-specific survival (CSS). The prognostic difference between labium majus, labium minus and clitoris groups was investigated using Kaplan-Meier analyses and Cox proportional hazards regression analyses. A total of 3,465 eligible patients with vulvar cancer were included with a mean age of 54.5 years. Among the 1,076 (31.1%) patients with non-SCC, the multivariate Cox regression analyses showed that labium minus-sited disease (hazard ratio [HR]=1.85; 95% confidence interval [CI]=1.27-2.71; p=0.001) and clitoris-sited disease (HR=2.37; 95% CI=1.47-3.85; p0.05). Kaplan-Meier analyses also showed that the primary tumor site had a significant prognostic effect in vulvar non-SCC (p<0.001) but not in vulvar SCC (p=0.330). Among vulvar non-SCC, patients with labium minus-sited disease had a significantly worse prognosis than those with labium majus-sited disease, and a significantly better prognosis than those with clitoris-sited disease. Gynecologic oncologists should consider the prognostic effect of primary tumor site in vulvar non-SCC, and make optimal, personalized treatment and surveillance strategies based on different primary tumor sites.