Timmons Adela C, Tutul Abdullah Aman, Avramidis Kleanthis, Duong Jacqueline B, Carta Kayla E, Walters Sierra N, Jumonville Grace A, Carrasco Alyssa S, Freitag Gabrielle F, Romero Daniela N, Ahle Matthew W, Comer Jonathan S, Narayanan Shrikanth S, Khurd Ishita P, Chaspari Theodora
University of Texas at Austin, Austin, TX, USA.
Colliga Apps, Austin, TX, USA.
Npj Ment Health Res. 2025 Aug 6;4(1):34. doi: 10.1038/s44184-025-00147-5.
The integration of artificial intelligence (AI) and pervasive computing offers new opportunities to sense mental health symptoms and deliver just-in-time adaptive interventions via mobile devices. This pilot study tested personalized versus generalized machine learning models for detecting individual and family mental health symptoms as a foundational step toward JITAI development, using data collected through the Colliga app on smart devices. Over a 60-day period, data from 35 families resulted in approximately 14 million data points across 52 data streams. Findings showed that personalized models consistently outperformed generalized models. Model performance varied significantly based on individual factors and symptom profiles, underscoring the need for tailored approaches. These preliminary findings suggest that successful implementation of passive sensing technologies for mental health will require accounting for users' unique characteristics. Further research with larger samples is needed to refine the models, address data heterogeneity, and develop scalable systems for personalized mental health interventions.
人工智能（AI）与普适计算的融合为感知心理健康症状并通过移动设备提供即时自适应干预带来了新机遇。这项试点研究测试了个性化与通用机器学习模型，用于检测个体和家庭心理健康症状，作为朝着即时自适应干预（JITAI）发展的基础步骤，使用通过智能设备上的Colliga应用程序收集的数据。在60天的时间里，来自35个家庭的数据产生了跨越52个数据流的约1400万个数据点。研究结果表明，个性化模型始终优于通用模型。模型性能因个体因素和症状特征而异，突出了采用量身定制方法的必要性。这些初步研究结果表明，成功实施用于心理健康的被动传感技术将需要考虑用户的独特特征。需要进一步开展更大样本量的研究，以优化模型、解决数据异质性问题，并开发用于个性化心理健康干预的可扩展系统。
