Impact of AI-powered animated video education on perioperative anxiety and information needs in thoracic surgery patients: a prospective pilot study

This study aimed to evaluate the effect of AI-assisted animated video training on perioperative anxiety and information needs in patients undergoing thoracic surgery. This prospective, quasi-experimental study included 56 patients scheduled for elective thoracic surgery, who were sequentially divided into control ( n = 28, standard verbal information) and experimental ( n = 28, AI-assisted animated video training in addition to standard information) groups. Anxiety was assessed using the STAI-State (T1: after information, T2: early postoperative), STAI-Trait (measured at baseline) and APAIS (T1: after information, T2: early postoperative) scales, and related factors were evaluated using multivariate regression analyses. No significant difference was found between the groups in preoperative STAI-State scores (45.5 vs. 49.5; p = 0.051); however, early postoperative STAI-State scores were significantly lower in the experimental group (32.5 vs. 45.0; p = 0.007). No significant difference was found between the groups in the STAI-Trait and APAIS anxiety scores. APAIS information need scores were significantly lower in the experimental group (2 vs. 6; p = 0.005), and in multivariate linear regression analysis, AI-assisted animated video education was independently associated with lower information needs (B=-1.815, β=-0.335, p = 0.015). In the multivariate logistic regression analysis, no independent variables were found to be associated with high preoperative anxiety. In this exploratory pilot study, AI-powered animated video training was associated with lower early postoperative anxiety levels and the need for preoperative information. However, these findings should be interpreted as hypothesis-generating, and larger randomized controlled trials are needed to confirm these observations and determine their definitive clinical applicability.