Leveraging Language Embeddings from EMA Surveys to Predict Perceived Social Isolation among Stroke Survivors
Preprint
Abstract
Perceived social isolation (PSI) significantly affects the emotional well-being of stroke survivors, necessitating effective monitoring and prediction for timely, targeted interventions. While Ecological Momentary Assessment (EMA) has been increasingly used to identify precursor characteristics of PSI, existing prediction methods rely on handcrafted features, which often fail to capture the semantic richness and contextual relationships among survey questions. In this study, we propose a novel approach to predict PSI by processing structured EMA data with language embeddings. A total of 11,802 EMA surveys were collected from 218 stroke survivors, the largest dataset of its kind in social isolation research for this population. Language embeddings were extracted from the structured EMA surveys using a pre-trained language model. These embeddings were then processed by training an autoencoder to generate compact latent representations, which were used for the downstream PSI prediction. Our findings show that the proposed approach achieves accurate PSI prediction, with a weighted F 1 score of 0.84 and a weighted AUPRC of 0.92, outperforming traditional handcrafted features. Furthermore, by leveraging only three carefully selected questions, our method can optimize a trade-off between validity and usability. This study demonstrates an efficient method for real-time monitoring of psychosocial outcomes in stroke survivors, with potential implications for early intervention and personalized care.Keywords
This publication has 42 references indexed in Scilit:
- Dynamics of Perceived Social Isolation, Secondary Conditions, and Daily Activity Patterns Among Individuals With Stroke: A Network Analysis of Ecological Momentary Assessment DataArchives of Physical Medicine and Rehabilitation, 2024
- Ecological Momentary Assessment and Machine Learning for Predicting Suicidal Ideation Among Sexual and Gender Minority IndividualsJAMA Network Open, 2023
- Ecological Momentary Assessment of Real-World Functional Behaviors in Individuals With Stroke: A Longitudinal Observational StudyArchives of Physical Medicine and Rehabilitation, 2022
- Ecological Momentary Assessment of Social Interactions: Associations With Depression, Anxiety, Pain, and Fatigue in Individuals With Mild StrokeArchives of Physical Medicine and Rehabilitation, 2021
- Digital phenotyping of suicidal thoughtsDepression and Anxiety, 2018
- Feasibility and Acceptability of Ecological Momentary Assessment of Daily Functioning Among Older Adults with HIVThe American Journal of Geriatric Psychiatry, 2017
- Sensor-Driven Detection of Social Isolation in Community-Dwelling Elderly2017
- Role of social factors on cell death, cerebral plasticity and recovery after strokeMetabolic Brain Disease, 2014
- Social isolation after stroke leads to depressive-like behavior and decreased BDNF levels in miceBehavioural Brain Research, 2014
- The continuum of connectedness and social isolation during post stroke recoveryJournal of Aging Studies, 2008