Systemic sclerosis & Raynaud's

Evaluating unsupervised and rule-based phenotyping methods versus administrative code counts for systemic sclerosis identification

Semin Arthritis RheumPublished Diagnostic accuracy study

Authors' conclusion

M34 code counts achieved reasonable performance for SSc identification and comparable to those of LPC and PheRS. However, both LPC and PheRS demonstrated better performance for predicting mortality compared with M34 code counts in patients with SSc.

Study context

Population
Patients with at least one M34 code in the electronic health record (EHR) of a single centre; rheumatologist-diagnosed systemic sclerosis (SSc) as reference547 (84%) with rheumatologist-diagnosed SSc
Participants
653 patients
Comparison
LPC vs phenotype risk score (PheRS) vs M34 International Classification of Disease (ICD) code counts for identifying SSc and predicting mortality from EHR
Outcome
Identification of rheumatologist-diagnosed SSc and prediction of mortality
Methodological detailssingle-centre, retrospective
  • Single-centre
  • Retrospective

Performance

As reported in the abstract

Distinguishing rheumatologist-diagnosed SSc from M34 non-SSc controls (individuals with ≥1 M34 code)
Test or modelAUROC
LPC0.72
PheRS0.70
M34 ICD code counts0.70

AUROC

LPC0.72
PheRS0.70
M34 ICD code counts0.70

Further findings

OutcomeLPCPheRSM34 code counts
Distinguishing rheumatologist-diagnosed SSc from M34 non-SSc controls, among individuals with ≥1 M34 code (AUROC)
AUROC0.720.700.70
Predicting mortality in patients with SSc (AUROC)
AUROC0.740.720.63

Distinguishing rheumatologist-diagnosed SSc from M34 non-SSc controls, among individuals with ≥1 M34 code (AUROC)

LPC only marginally superior to PheRS and M34 code counts

Identifying SSc using ≥2 M34 codes

Sensitivity of ≥2 M34 codes
87.8%
PPV of ≥2 M34 codes
87.0%

Original publication

Evaluating unsupervised and rule-based phenotyping methods versus administrative code counts for systemic sclerosis identification. Semin Arthritis Rheum. Published 29 June 2026. doi:10.1016/j.semarthrit.2026.153033

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.