Predictors of participation in online self-management programs: A longitudinal observational study.
Elena D Staguhn, Tricia Kirkhart, Lauren Allen and 3 others
PMID 37956087WHAT IT FOUND
Older age and high confidence predicted full completion of online pain programs, while prior online shopping predicted partial engagement.
However, the overall model failed to accurately predict who would drop out, with poor statistical power. Clinicians cannot yet reliably identify non-compliant patients based on these baseline factors.
Key findings
01Participants who had high confidence in completing the program or were 60 years or older had significantly higher odds of completing all modules.
02Participants aged 50 and up or those who had previously ordered something online had significantly higher odds of at least partially completing the lessons.
03The predictive power of the logistic regression models was marginal, with area under the curve scores of 0.65 and 0.66, failing to reach the commonly used threshold of 0.70.
STILL TO COME
How it was doneWhat they found
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The sample size was modest, which prevented the use of continuous data for many variables and required categorization. There was no independent validation dataset; all data was used to build the model, increasing the risk of overfitting. The study was a secondary analysis and not pre-registered. The predictive models failed to reach statistical thresholds for accuracy (AUC < 0.70), meaning they cannot reliably predict individual patient engagement.
Declared interests
Not reported
The easy way to misread this
Do not use these findings to screen or exclude patients from online therapy based on age or computer literacy. The predictive model failed to reach the threshold for adequate accuracy, so these factors are not reliable enough to determine who will succeed or fail in a self-management program.