Neuropsychiatrie : Klinik, Diagnostik, Therapie und Rehabilitation : Organ der Gesellschaft Osterreichischer Nervenarzte und Psychiater · 2025
Artificial intelligence-assisted visual elicitation in anorexia nervosa : Qualitative case studies.
СтатьяКлинический случайНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Chubinidze Dimitri, Perry Catherine, Tchanturia Kate
Аннотация
PURPOSE: This study explored the feasibility and therapeutic potential of combining artificial intelligence (AI)-assisted visual elicitation with sensory-attuned guided reflection to support emotional expression and engagement in individuals with anorexia nervosa (AN).
METHODS: We conducted a two-session, therapist-led intervention with two adults with restrictive AN. In session 1, we guided participants to reflect on emotionally challenging experiences using metaphor and sensory language cues. We translated these narratives into prompts for DALL·E (v3; OpenAI, San Francisco, CA, USA), an AI image-generation tool. In session 2, participants selected from curated images to reflect on and deepen their exploration of emotional experiences. We analysed the data using reflexive thematic analysis and performed a cross-case synthesis.
RESULTS: Visual metaphors helped to externalise and communicate emotions, evoke embodied responses and refine affective descriptions. The co-creative process fostered therapeutic engagement and a greater sense of agency in both participants.
CONCLUSION: AI-assisted visual elicitation, integrated into a structured therapeutic process, may offer an additional benefit to talking therapy for individuals with AN. By enabling visual expression, this approach could support emotional insight and communication in populations with emotion labelling and regulation differences.
METHODS: We conducted a two-session, therapist-led intervention with two adults with restrictive AN. In session 1, we guided participants to reflect on emotionally challenging experiences using metaphor and sensory language cues. We translated these narratives into prompts for DALL·E (v3; OpenAI, San Francisco, CA, USA), an AI image-generation tool. In session 2, participants selected from curated images to reflect on and deepen their exploration of emotional experiences. We analysed the data using reflexive thematic analysis and performed a cross-case synthesis.
RESULTS: Visual metaphors helped to externalise and communicate emotions, evoke embodied responses and refine affective descriptions. The co-creative process fostered therapeutic engagement and a greater sense of agency in both participants.
CONCLUSION: AI-assisted visual elicitation, integrated into a structured therapeutic process, may offer an additional benefit to talking therapy for individuals with AN. By enabling visual expression, this approach could support emotional insight and communication in populations with emotion labelling and regulation differences.