Fibromyalgia & musculoskeletal pain
Machine learning identifies risk factors associated with long-term opioid use in fibromyalgia patients newly initiated on an opioid
Authors' conclusion
High dose of initial opioid prescription, a history of self-harm, obesity, high deprivation, substance use disorder and age were associated with long-term opioid use.
Study context
- Population
- FM patients without prior cancer newly initiated on opioids, nationally representative UK primary care dataset (Clinical Research Practice Datalink)
- Participants
- 28,552 patients
- Outcome
- Long-term opioid use
Methodological detailsmachine learning, logistic regression, random forest, Boruta feature selection
- Machine learning
- Logistic regression
- Random forest
- Boruta feature selection
Main finding
As reported in the abstract
Factors most strongly associated with long-term opioid use
- Long-term opioid use
- 7369 (26%)
- High initial opioid dose, aOR
- 31.96
- High initial opioid dose, mean decrease accuracy (MDA)
- 135
- History of self-harm, aOR
- 2.01
- History of self-harm, MDA
- 44
- Obesity, aOR
- 2.43
- Obesity, MDA
- 36
- High deprivation, aOR
- 2.00
- High deprivation, MDA
- 31
- Substance use disorder, aOR
- 2.08
- Substance use disorder, MDA
- 25
Observational data: associations, not effects.
Original publication
Machine learning identifies risk factors associated with long-term opioid use in fibromyalgia patients newly initiated on an opioid. RMD Open. Published 20 May 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →