I-Corps: Artificial Intelligence Driven Prediction, Monitoring, and Management of Unwanted Behavior in Patients with Autism: Realtime, Smart, Automated, and Personalized

这个i-Corps项目的更广泛的影响/商业潜力是开发一个人工智能(AI)驱动的平台，用于持续、实时、个性化地预测、监测和管理自闭症和发育障碍患者的不良行为。这项拟议的技术旨在为自闭症患者的家庭提供实时洞察和个性化的策略建议，提高他们的生活质量。该平台实现的早期干预也可能为保险公司和医院带来好处，因为与药品有关的节省和反复的急诊科就诊。此外，从业者和学校可能受益于自动化数据分析，增强基于证据的决策和学生支持。精神病院可以改进治疗方法，减少住院和紧急情况。建议的人工智能驱动平台可用于行为分析，对自闭症患者及其家庭产生积极影响。这项拟议的技术可能会导致自闭症和发育障碍的个性化行为管理策略的进步。这个i-Corps项目基于开发一种人工智能(AI)方法来预测和管理自闭症患者的不想要的行为。拟议的平台利用先进的人工智能和机器学习算法从视觉、听觉和动觉数据中提取模式，并使用这些数据来促进早期风险评估和支持性循证管理计划。收集的数据，包括不可穿戴传感器信息和护理者输入，经过高级分析，以实现个性化预防策略和最佳风险管理。通过集成多数据流传感器数据融合、人工智能驱动的模式挖掘和实时分析，该项目弥合了现有行为干预方法和尖端技术之间的差距。其贡献在于融合不同的数据源以提取有意义的模式，为照顾者、从业者、学校和医院提供可操作的行为管理见解。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project is the development of an artificial intelligence (AI) powered platform for continuous, real-time, personalized prediction, monitoring, and management of unwanted behavior in patients with autism and developmental disabilities. The proposed technology is designed for families of individuals with autism to receive real-time insights and personalized strategy suggestions, improving their quality of life. Early intervention enabled by this platform also may lead to benefits for insurance companies and hospitals due to savings related to pharmaceuticals and repeated emergency department visits. In addition, practitioners and schools may benefit from automated data analysis, enhancing evidence-based decision-making and student support. Psychiatric hospitals may improve treatment approaches, reducing hospitalizations and emergencies. The proposed AI-driven platform may be used for behavior analysis, positively impacting individuals with autism and their families. The proposed technology may lead to an advancement in personalized behavior management strategies for autism and developmental disabilities.This I-Corps project is based on the development of an artificial intelligence (AI) approach to the prediction and management of unwanted behavior in autism patients. The proposed platform leverages advanced AI and machine learning algorithms to extract patterns from visual, auditory, and kinesthetic data, and uses these data to facilitate early risk assessment and supportive evidence-based management plans. The collected data, including non-wearable sensor information and caregiver input, undergoes advanced analysis for personalized prevention strategies and optimal risk management. By integrating multi-stream sensor data fusion, AI-driven pattern mining, and real-time analysis, the project bridges the gap between existing behavioral intervention methods and cutting-edge technology. The contribution lies in the fusion of diverse data sources to extract meaningful patterns, providing caregivers, practitioners, schools, and hospitals with actionable insights for behavior management.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.