Using Data‐Driven Approaches to Classify and Predict Health Care Spending in Patients With Gout Using Urate‐Lowering Therapy
Authors' conclusion
We identified distinct long-term health care spending patterns in patients with gout using ULT with high accuracy.
Study context
- Population
- US patients aged ≥40 years with gout treated with urate-lowering therapy (ULT), insurance claims 2017–2019mean age 71.0
- Participants
- 57,980 patients
- Exposure
- Minimal spending vs Moderate spending vs High spending
- Outcome
- Total health care spending trajectory groups and prediction of group membership (C statistics)
- Follow-up
- 2 years
Methodological detailsinsurance claims data, group-based trajectory modeling, logistic and generalized boosted regression with split-sample validation
- Insurance claims data
- Group-based trajectory modeling
- Logistic and generalized boosted regression with split-sample validation
Main finding
As reported in the abstract
Spending trajectory group membership and prediction (boosted C statistic, all predictors)
| Group | Value | C statistic |
|---|---|---|
| Minimal spending | 13.2% | 0.89 |
| Moderate spending | 37.4% | 0.78 |
| High spending | 49.4% | 0.90 |
Value
Minimal spending13.2%
Moderate spending37.4%
High spending49.4%
C statistic
Minimal spending0.89
Moderate spending0.78
High spending0.90
Observational data: associations, not effects.
Further findings
Most influential predictors of high spending
- Greater gout medication adherence and diabetes mellitus diagnosis
- Average adherence relatively high in the population
Original publication
Using Data‐Driven Approaches to Classify and Predict Health Care Spending in Patients With Gout Using Urate‐Lowering Therapy. Arthritis Care Res (Hoboken). Published 18 January 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →