Developing electronic health record algorithms that accurately identify patients with juvenile idiopathic arthritis
Authors' conclusion
We developed and validated JIA EHR algorithms with ICD-9 and ICD-10-CM codes to accurately identify a JIA cohort.
Study context
- Population
- Patients in a de-identified electronic health record (EHR) with ≥1 occurrence of a juvenile idiopathic arthritis (JIA) ICD-9 or ICD-10-CM code; case status by rheumatology clinic note documenting JIA diagnosis before age 20training set
- Participants
- 200 patients
- Outcome
- PPV, sensitivity and F-measure of EHR algorithms for identifying JIA
Methodological detailsalgorithm development and validation, de-identified EHR, training set randomly selected
- Algorithm development and validation
- De-identified EHR
- Training set randomly selected
Performance
As reported in the abstract
Performance of highest-PPV algorithm in training set (of 103 algorithms developed)
| Test or model | PPV | F-measure |
|---|---|---|
| Highest-PPV algorithm | 97% | 87% |
Highest-PPV algorithm
PPV97%
F-measure87%
- JIA cases returned by this algorithm
- 1,131
Further findings
| Outcome | Values |
|---|---|
| Validation in a separate cohort from the training set | Highest-PPV algorithm PPV 92% · F-measure 75% |
Original publication
Developing electronic health record algorithms that accurately identify patients with juvenile idiopathic arthritis. Semin Arthritis Rheum. Published 18 January 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →