Good Ashley Priscilla, Horn Elizabeth
2m Foundation, Hillsborough, CA, United States.
Front Integr Neurosci. 2025 Jan 21;18:1496165. doi: 10.3389/fnint.2024.1496165. eCollection 2024.
The long-standing practice of using manualized inventories and observational assessments to diagnose and track motor function in autism overlooks critical data invisible to the naked eye. This subjective approach can introduce biases and hinder the translation of research into clinical applications that rely on objective markers of brain-body connections. Meanwhile, we are experiencing a digital healthcare revolution, marked by innovations in the collection and analysis of electronic health records, personal genomes, and diverse physiological measurements. Advanced technologies, including current wearable devices, integrate both active and passive (sensor-based) data collection, providing a more comprehensive view of human health. Despite advances in sensors, wearables, algorithms, machine learning, and agentic AI, autism research remains siloed, with many tools inaccessible to affected families and care teams. There is a pressing need to merge these technological advances and expedite their translation into accessible, scalable tools and solutions to diversify scientific understanding. In response, this Perspective introduces the Initiative, a coalition spearheaded by the nonprofit 2 m Foundation, composed of self-advocates, families, clinicians, researchers, entrepreneurs, and investors who aim to advance and refine the measurement of movement in autism. will make motor screenings more dynamic and longitudinal while supporting continuous assessment of targeted interventions. By fostering cross-disciplinary collaboration, seeks to accelerate the integration of the expanding knowledge base into widespread practice. Deep, longitudinal, multi-modal profiling of individuals with Autism Spectrum Disorder offers an opportunity to address gaps in current data and methods, enabling new avenues of inquiry and a more comprehensive understanding of this complex, heterogeneous condition.
长期以来,使用标准化量表和观察性评估来诊断和追踪自闭症患者运动功能的做法,忽略了肉眼无法看到的关键数据。这种主观方法可能会引入偏差,并阻碍将研究成果转化为依赖脑-体连接客观指标的临床应用。与此同时,我们正经历一场数字医疗革命,其标志是电子健康记录、个人基因组和各种生理测量数据的收集与分析方面的创新。包括当前可穿戴设备在内的先进技术,整合了主动和被动(基于传感器)的数据收集方式,能提供更全面的人类健康状况视图。尽管在传感器、可穿戴设备、算法、机器学习和智能人工智能方面取得了进展,但自闭症研究仍然各自为政,许多工具受影响家庭和护理团队无法使用。迫切需要将这些技术进步融合起来,并加快将其转化为易于获取、可扩展的工具和解决方案,以丰富科学认知。作为回应,本观点文章介绍了“ 倡议”,这是一个由非营利性的200万基金会牵头的联盟,成员包括自我倡导者、家庭、临床医生、研究人员、企业家和投资者,他们旨在推进和完善自闭症运动测量方法。“ 倡议”将使运动筛查更具动态性和纵向性,同时支持对针对性干预措施的持续评估。通过促进跨学科合作,“ 倡议”力求加速将不断扩大的知识库整合到广泛的实践中。对自闭症谱系障碍患者进行深入、纵向、多模式分析,为解决当前数据和方法中的差距提供了机会,从而开辟新的研究途径,并更全面地理解这种复杂的异质性疾病。