Using Explainable Boosting Machine to Compare Idiographic and Nomothetic Approaches for Ecological Momentary Assessment Data

TL;DR

This study compares linear and non-linear machine learning models, especially explainable boosting machines, for classifying ecological momentary assessment data, highlighting the benefits of group-level and knowledge distillation approaches.

Contribution

The paper introduces the use of explainable boosting machines for EMA data classification and compares nomothetic and idiographic approaches, demonstrating improved performance with non-linear models and knowledge distillation.

Findings

Non-linear models outperform linear models in EMA classification.

Group-level models can enhance predictive performance.

Knowledge distillation improves AUC scores in real-world datasets.

Abstract

Previous research on EMA data of mental disorders was mainly focused on multivariate regression-based approaches modeling each individual separately. This paper goes a step further towards exploring the use of non-linear interpretable machine learning (ML) models in classification problems. ML models can enhance the ability to accurately predict the occurrence of different behaviors by recognizing complicated patterns between variables in data. To evaluate this, the performance of various ensembles of trees are compared to linear models using imbalanced synthetic and real-world datasets. After examining the distributions of AUC scores in all cases, non-linear models appear to be superior to baseline linear models. Moreover, apart from personalized approaches, group-level prediction models are also likely to offer an enhanced performance. According to this, two different nomothetic approaches to integrate data of more than one individuals are examined, one using directly all data during training and one based on knowledge distillation. Interestingly, it is observed that in one of the two real-world datasets, knowledge distillation method achieves improved AUC scores (mean relative change of +17\% compared to personalized) showing how it can benefit EMA data classification and performance.