JMIR Publications

ABSTRACT

Background:

Investigations into person-specific predictors of stress have typically taken either a population-level nomothetic approach, or an individualized ideographic approach. Nomothetic approaches can quickly identify predictors but can be hindered by heterogeneity of these predictors across individuals and across time. Ideographic approaches may result in more predictive models at the individual-level, but require a longer period of data collection to identify robust predictors.

Objective:

Our objectives were to compare predictors of stress identified through nomothetic and ideographic models and to assess whether sequentially combining nomothetic and ideographic models could yield more accurate and actionable predictions of stress than relying on either model, alone. At the same time, we sought to maintain the interpretability necessary to retrieve individual predictors of stress despite using nomothetic models.

Methods:

Data collected in a 1-year observational study of 79 low-exercising participants were used. Physical activity was continuously and objectively monitored by actigraphy. Perceived stress was recorded by participants via daily ecological momentary assessments on a mobile application. Environmental variables including daylight time, temperature, and precipitation were retrieved from public archives. Using these environmental, actigraphy, and mobile assessment data, we built machine learning models predicting individual stress ratings using linear, decision tree, and neural network techniques employing nomothetic and ideographic approaches. The accuracy of approaches for predicting individual stress ratings was compared based on classification errors.

Results:

Across the group of patients, the nomothetic recurrent neural network model most heavily weighted an individual’s recent history of stress ratings in predicting a future stress rating, whereas the ideographic models more heavily weighted environmental factors such as temperature and daylight, as well as duration and frequency of bouts of exercise. The nomothetic recurrent neural network model was the highest performing nomothetic model, and yielded 72% accuracy for an 80%/20% train/test split. Using the same 80/20 split, the ideographic models yielded 75% accuracy. However, restricting ideographic models to participants with greater than 50 valid days in the training set, with the same 80/20 split, yielded 85% accuracy.

Conclusions:

We conclude that for some applications, nomothetic models may be useful for yielding higher initial performance while still surfacing personalized predictors of stress, before switching to ideographic models upon sufficient data collection.