Berrezueta-Guzman Santiago, Kandil Mohanad, Martín-Ruiz María-Luisa, Pau de la Cruz Iván, Krusche Stephan
Applied Software Engineering Research Group, School of Computation, Information, and Technology, Technical University of Munich, 80333 Munich, Germany.
Grupo de Investigación Innovación Tecnológica para las Personas (InnoTep), Departamento de Ingeniería Telemática y Electrónica, ETSIS de Telecomunicación, Campus Sur, Universidad Politécnica de Madrid, 28031 Madrid, Spain.
Healthcare (Basel). 2024 Mar 19;12(6):683. doi: 10.3390/healthcare12060683.
This study explores the integration of large language models (LLMs), like ChatGPT, to improve attention deficit hyperactivity disorder (ADHD) treatments. Utilizing the Delphi method for its systematic forecasting capabilities, we gathered a panel of child ADHD therapy experts. These experts interacted with our custom ChatGPT through a specialized interface, thus engaging in simulated therapy scenarios with behavioral prompts and commands. Using empirical tests and expert feedback, we aimed to rigorously evaluate ChatGPT's effectiveness in therapy settings to integrate AI into healthcare responsibly. We sought to ensure that AI contributes positively and ethically to therapy and patient care, thus filling a gap in ADHD treatment methods. Findings show ChatGPT's empathy, adaptability, and communication strengths, thereby highlighting its potential to significantly improve ADHD care. The study points to ChatGPT's capacity to transform therapy practices through personalized and responsive patient care. However, it also notes the need for enhancements in privacy, cultural sensitivity, and interpreting nonverbal cues for ChatGPT's effective healthcare integration. Our research advocates for merging technological innovation with a comprehensive understanding of patient needs and ethical considerations, thereby aiming to pioneer a new era of AI-assisted therapy. We emphasize the ongoing refinement of AI tools like ChatGPT to meet ADHD therapy and patient care requirements more effectively.
本研究探讨了将诸如ChatGPT之类的大语言模型整合起来,以改善注意力缺陷多动障碍(ADHD)的治疗方法。利用德尔菲法的系统预测能力,我们召集了一组儿童ADHD治疗专家。这些专家通过一个专门的界面与我们定制的ChatGPT进行交互,从而参与带有行为提示和指令的模拟治疗场景。通过实证测试和专家反馈,我们旨在严格评估ChatGPT在治疗环境中的有效性,以便将人工智能负责任地整合到医疗保健中。我们力求确保人工智能在治疗和患者护理方面做出积极且符合道德规范的贡献,从而填补ADHD治疗方法中的空白。研究结果显示了ChatGPT的同理心、适应性和沟通优势,从而凸显了其显著改善ADHD护理的潜力。该研究指出ChatGPT有能力通过个性化且响应迅速的患者护理来改变治疗实践。然而,研究也指出,为了使ChatGPT有效地融入医疗保健,需要在隐私、文化敏感性以及解读非语言线索方面加以改进。我们的研究主张将技术创新与对患者需求和道德考量的全面理解相结合,从而致力于开创人工智能辅助治疗的新时代。我们强调要持续改进像ChatGPT这样的人工智能工具,以便更有效地满足ADHD治疗和患者护理的要求。