Akademik Veri Yönetim Sistemi
EUROPEAN JOURNAL OF CANCER, cilt.221, 2025 (SCI-Expanded, Scopus)
Background: Psychological distress is prevalent among newly diagnosed cancer patients, often exacerbating treatment-related anxiety and depression. Artificial intelligence (AI)-driven interventions, such as large language models (LLMs), offer scalable solutions for patient education. However, their effectiveness in mitigating psychological distress in oncology remains unverified. Methods: We conducted a prospective, two-center, randomized controlled trial between July and October 2024 to evaluate the effect of a ChatGPT-based digital counseling intervention on anxiety and depression in chemotherapy-na & iuml;ve cancer patients. Participants were randomized 1:1 to either a ChatGPT-assisted counseling group or a standard clinician-led education group. The primary outcome was the change in Hospital Anxiety and Depression Scale (HADS) scores before the second chemotherapy cycle. Secondary outcomes included patient engagement behavior and the accuracy of AI-generated responses. Multivariable logistic regression assessed independent predictors of anxiety and depression reduction. The trial is registered with ClinicalTrials.gov (NCT06854315). Findings: Of 196 screened patients, 160 were randomized (ChatGPT: n = 80; control: n = 80). The final cohort comprised 150 patients (median age: 64 years; 53.3 % female). At follow-up, the ChatGPT group exhibited significantly lower median HADS-Anxiety (6 [0-17] vs. 8 [1-17]; P = 0.002) and HADS-Depression (6 [0-20] vs. 9 [0-19]; P < 0.001) scores compared to controls. ChatGPT use was the strongest predictor of anxiety reduction (OR, 18.684; 95 % CI, 3.981-87.685; P < 0.001). AI responses were deemed appropriate in 88.5 % of cases, with inaccuracies most common in dietary and sexual health recommendations. Interpretation: A ChatGPT-based counseling intervention significantly reduced anxiety and depression among newly diagnosed cancer patients prior to chemotherapy. These findings support the potential integration of AI-driven digital tools as adjuncts to conventional oncology education, enhancing patient support and engagement. Further research is needed to refine AI implementation in clinical practice.