Kerth Janna-Lina, Bischops Anne Christine, Hagemeister Maurus, Reinhart Lisa, Konrad Kerstin, Heinrichs Bert, Meissner Thomas
Klinik für Allgemeine Pädiatrie, Neonatologie und Kinderkardiologie, Medizinische Fakultät und Universitätsklinikum Düsseldorf, Heinrich-Heine-Universität Düsseldorf, Moorenstr. 5, 40225, Düsseldorf, Deutschland.
Klinik für Psychiatrie, Psychosomatik und Psychotherapie des Kindes- und Jugendalters, Uniklinik Aachen, Aachen, Deutschland.
Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz. 2025 Jun 30. doi: 10.1007/s00103-025-04096-4.
The use of artificial intelligence (AI) in pediatric and adolescent medicine offers numerous possibilities, particularly in the prevention of chronic diseases. AI-powered applications such as machine learning for the analysis of speech or movement patterns can, for example, help in the early diagnosis of autism spectrum disorders or motor development delays. In addition, AI-based systems support the treatment of children with type 1 diabetes through automated insulin dosing (AID) systems.AI enables more accurate diagnoses and personalized therapeutic approaches and helps relieve the burden on medical personnel. At the same time, there are challenges associated with the use of AI, which is why only a few applications have so far become part of routine clinical practice. These challenges include the protection of sensitive data and the respect for informational self-determination, ensuring freedom from discrimination, algorithmic transparency, and the acceptance of AI by all involved groups such as children, adolescents, parents, and medical professionals. All stakeholders express concerns about potential misjudgments, the loss of personal interactions, and the possible commercial use of data. Parents and professionals emphasize the importance of clear communication, shared decision-making, and training to promote better understanding. Moreover, there is often a lack of structured, high-quality, large datasets in compatible formats to effectively train AI systems.A sustainable integration of AI in pediatric and adolescent medicine requires large-scale clinical studies, access to high-quality datasets, and a nuanced analysis of the ethical and social implications.
人工智能(AI)在儿科和青少年医学中的应用提供了众多可能性,尤其是在慢性病预防方面。例如,诸如用于分析语音或运动模式的机器学习等人工智能驱动的应用程序有助于早期诊断自闭症谱系障碍或运动发育迟缓。此外,基于人工智能的系统通过自动胰岛素给药(AID)系统支持1型糖尿病患儿的治疗。人工智能能够实现更准确的诊断和个性化治疗方法,并有助于减轻医务人员的负担。与此同时,使用人工智能也存在挑战,这就是为什么到目前为止只有少数应用程序成为常规临床实践的一部分。这些挑战包括保护敏感数据、尊重信息自决权、确保不受歧视、算法透明度以及儿童、青少年、家长和医疗专业人员等所有相关群体对人工智能的接受度。所有利益相关者都对潜在的误判、人际互动的丧失以及数据的可能商业用途表示担忧。家长和专业人员强调清晰沟通、共同决策和培训以促进更好理解的重要性。此外,通常缺乏格式兼容的结构化、高质量、大型数据集来有效训练人工智能系统。人工智能在儿科和青少年医学中的可持续整合需要大规模临床研究、获取高质量数据集以及对伦理和社会影响进行细致分析。